summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rwxr-xr-xtools/testing/kunit/kunit.py2
-rw-r--r--tools/testing/kunit/kunit_kernel.py6
-rw-r--r--tools/testing/kunit/kunit_parser.py6
-rwxr-xr-xtools/testing/kunit/kunit_tool_test.py16
-rw-r--r--tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log (renamed from tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log)0
-rw-r--r--tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log2
-rw-r--r--tools/testing/nvdimm/test/nfit.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tailcalls.c36
-rw-r--r--tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c18
-rw-r--r--tools/testing/selftests/bpf/verifier/dead_code.c12
-rw-r--r--tools/testing/selftests/bpf/verifier/value_ptr_arith.c229
-rw-r--r--tools/testing/selftests/kvm/.gitignore1
-rw-r--r--tools/testing/selftests/kvm/Makefile1
-rw-r--r--tools/testing/selftests/kvm/aarch64/get-reg-list.c3
-rw-r--r--tools/testing/selftests/kvm/access_tracking_perf_test.c429
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c1
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h3
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/hyperv.h5
-rw-r--r--tools/testing/selftests/kvm/lib/aarch64/processor.c2
-rw-r--r--tools/testing/selftests/kvm/lib/guest_modes.c16
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c5
-rw-r--r--tools/testing/selftests/kvm/set_memory_region_test.c3
-rw-r--r--tools/testing/selftests/kvm/steal_time.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_clock.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/hyperv_features.c43
-rw-r--r--tools/testing/selftests/kvm/x86_64/mmu_role_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c70
-rwxr-xr-xtools/testing/selftests/memory-hotplug/mem-on-off-test.sh4
-rwxr-xr-xtools/testing/selftests/net/icmp_redirect.sh5
-rw-r--r--tools/testing/selftests/net/ipsec.c165
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh2
-rw-r--r--tools/testing/selftests/net/nettest.c55
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh212
-rw-r--r--tools/testing/selftests/net/timestamping.c55
-rw-r--r--tools/testing/selftests/netfilter/Makefile2
-rwxr-xr-xtools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh167
-rw-r--r--tools/testing/selftests/sgx/sigstruct.c41
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c6
38 files changed, 1537 insertions, 94 deletions
diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py
index be8d8d4a4e08..6276ce0c0196 100755
--- a/tools/testing/kunit/kunit.py
+++ b/tools/testing/kunit/kunit.py
@@ -12,6 +12,8 @@ import sys
import os
import time
+assert sys.version_info >= (3, 7), "Python version is too old"
+
from collections import namedtuple
from enum import Enum, auto
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 90bc007f1f93..2c6f916ccbaf 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -6,15 +6,13 @@
# Author: Felix Guo <felixguoxiuping@gmail.com>
# Author: Brendan Higgins <brendanhiggins@google.com>
-from __future__ import annotations
import importlib.util
import logging
import subprocess
import os
import shutil
import signal
-from typing import Iterator
-from typing import Optional
+from typing import Iterator, Optional, Tuple
from contextlib import ExitStack
@@ -208,7 +206,7 @@ def get_source_tree_ops(arch: str, cross_compile: Optional[str]) -> LinuxSourceT
raise ConfigError(arch + ' is not a valid arch')
def get_source_tree_ops_from_qemu_config(config_path: str,
- cross_compile: Optional[str]) -> tuple[
+ cross_compile: Optional[str]) -> Tuple[
str, LinuxSourceTreeOperations]:
# The module name/path has very little to do with where the actual file
# exists (I learned this through experimentation and could not find it
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index c3c524b79db8..b88db3f51dc5 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -338,9 +338,11 @@ def bubble_up_suite_errors(test_suites: Iterable[TestSuite]) -> TestStatus:
def parse_test_result(lines: LineStream) -> TestResult:
consume_non_diagnostic(lines)
if not lines or not parse_tap_header(lines):
- return TestResult(TestStatus.NO_TESTS, [], lines)
+ return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines)
expected_test_suite_num = parse_test_plan(lines)
- if not expected_test_suite_num:
+ if expected_test_suite_num == 0:
+ return TestResult(TestStatus.NO_TESTS, [], lines)
+ elif expected_test_suite_num is None:
return TestResult(TestStatus.FAILURE_TO_PARSE_TESTS, [], lines)
test_suites = []
for i in range(1, expected_test_suite_num + 1):
diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py
index bdae0e5f6197..75045aa0f8a1 100755
--- a/tools/testing/kunit/kunit_tool_test.py
+++ b/tools/testing/kunit/kunit_tool_test.py
@@ -157,8 +157,18 @@ class KUnitParserTest(unittest.TestCase):
kunit_parser.TestStatus.FAILURE,
result.status)
+ def test_no_header(self):
+ empty_log = test_data_path('test_is_test_passed-no_tests_run_no_header.log')
+ with open(empty_log) as file:
+ result = kunit_parser.parse_run_tests(
+ kunit_parser.extract_tap_lines(file.readlines()))
+ self.assertEqual(0, len(result.suites))
+ self.assertEqual(
+ kunit_parser.TestStatus.FAILURE_TO_PARSE_TESTS,
+ result.status)
+
def test_no_tests(self):
- empty_log = test_data_path('test_is_test_passed-no_tests_run.log')
+ empty_log = test_data_path('test_is_test_passed-no_tests_run_with_header.log')
with open(empty_log) as file:
result = kunit_parser.parse_run_tests(
kunit_parser.extract_tap_lines(file.readlines()))
@@ -173,7 +183,7 @@ class KUnitParserTest(unittest.TestCase):
with open(crash_log) as file:
result = kunit_parser.parse_run_tests(
kunit_parser.extract_tap_lines(file.readlines()))
- print_mock.assert_any_call(StrContains('no tests run!'))
+ print_mock.assert_any_call(StrContains('could not parse test results!'))
print_mock.stop()
file.close()
@@ -309,7 +319,7 @@ class KUnitJsonTest(unittest.TestCase):
result["sub_groups"][1]["test_cases"][0])
def test_no_tests_json(self):
- result = self._json_for('test_is_test_passed-no_tests_run.log')
+ result = self._json_for('test_is_test_passed-no_tests_run_with_header.log')
self.assertEqual(0, len(result['sub_groups']))
class StrContains(str):
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log
index ba69f5c94b75..ba69f5c94b75 100644
--- a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run.log
+++ b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_no_header.log
diff --git a/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log
new file mode 100644
index 000000000000..5f48ee659d40
--- /dev/null
+++ b/tools/testing/kunit/test_data/test_is_test_passed-no_tests_run_with_header.log
@@ -0,0 +1,2 @@
+TAP version 14
+1..0
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 54f367cbadae..b1bff5fb0f65 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -434,7 +434,7 @@ static int nd_intel_test_finish_query(struct nfit_test *t,
dev_dbg(dev, "%s: transition out verify\n", __func__);
fw->state = FW_STATE_UPDATED;
fw->missed_activate = false;
- /* fall through */
+ fallthrough;
case FW_STATE_UPDATED:
nd_cmd->status = 0;
/* bogus test version */
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index ee27d68d2a1c..b5940e6ca67c 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -715,6 +715,8 @@ out:
bpf_object__close(obj);
}
+#include "tailcall_bpf2bpf4.skel.h"
+
/* test_tailcall_bpf2bpf_4 checks that tailcall counter is correctly preserved
* across tailcalls combined with bpf2bpf calls. for making sure that tailcall
* counter behaves correctly, bpf program will go through following flow:
@@ -727,10 +729,15 @@ out:
* the loop begins. At the end of the test make sure that the global counter is
* equal to 31, because tailcall counter includes the first two tailcalls
* whereas global counter is incremented only on loop presented on flow above.
+ *
+ * The noise parameter is used to insert bpf_map_update calls into the logic
+ * to force verifier to patch instructions. This allows us to ensure jump
+ * logic remains correct with instruction movement.
*/
-static void test_tailcall_bpf2bpf_4(void)
+static void test_tailcall_bpf2bpf_4(bool noise)
{
- int err, map_fd, prog_fd, main_fd, data_fd, i, val;
+ int err, map_fd, prog_fd, main_fd, data_fd, i;
+ struct tailcall_bpf2bpf4__bss val;
struct bpf_map *prog_array, *data_map;
struct bpf_program *prog;
struct bpf_object *obj;
@@ -774,11 +781,6 @@ static void test_tailcall_bpf2bpf_4(void)
goto out;
}
- err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
- &duration, &retval, NULL);
- CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
- err, errno, retval);
-
data_map = bpf_object__find_map_by_name(obj, "tailcall.bss");
if (CHECK_FAIL(!data_map || !bpf_map__is_internal(data_map)))
return;
@@ -788,9 +790,21 @@ static void test_tailcall_bpf2bpf_4(void)
return;
i = 0;
+ val.noise = noise;
+ val.count = 0;
+ err = bpf_map_update_elem(data_fd, &i, &val, BPF_ANY);
+ if (CHECK_FAIL(err))
+ goto out;
+
+ err = bpf_prog_test_run(main_fd, 1, &pkt_v4, sizeof(pkt_v4), 0,
+ &duration, &retval, NULL);
+ CHECK(err || retval != sizeof(pkt_v4) * 3, "tailcall", "err %d errno %d retval %d\n",
+ err, errno, retval);
+
+ i = 0;
err = bpf_map_lookup_elem(data_fd, &i, &val);
- CHECK(err || val != 31, "tailcall count", "err %d errno %d count %d\n",
- err, errno, val);
+ CHECK(err || val.count != 31, "tailcall count", "err %d errno %d count %d\n",
+ err, errno, val.count);
out:
bpf_object__close(obj);
@@ -815,5 +829,7 @@ void test_tailcalls(void)
if (test__start_subtest("tailcall_bpf2bpf_3"))
test_tailcall_bpf2bpf_3();
if (test__start_subtest("tailcall_bpf2bpf_4"))
- test_tailcall_bpf2bpf_4();
+ test_tailcall_bpf2bpf_4(false);
+ if (test__start_subtest("tailcall_bpf2bpf_5"))
+ test_tailcall_bpf2bpf_4(true);
}
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
index 77df6d4db895..e89368a50b97 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
@@ -3,6 +3,13 @@
#include <bpf/bpf_helpers.h>
struct {
+ __uint(type, BPF_MAP_TYPE_ARRAY);
+ __uint(max_entries, 1);
+ __uint(key_size, sizeof(__u32));
+ __uint(value_size, sizeof(__u32));
+} nop_table SEC(".maps");
+
+struct {
__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
__uint(max_entries, 3);
__uint(key_size, sizeof(__u32));
@@ -10,10 +17,21 @@ struct {
} jmp_table SEC(".maps");
int count = 0;
+int noise = 0;
+
+__always_inline int subprog_noise(void)
+{
+ __u32 key = 0;
+
+ bpf_map_lookup_elem(&nop_table, &key);
+ return 0;
+}
__noinline
int subprog_tail_2(struct __sk_buff *skb)
{
+ if (noise)
+ subprog_noise();
bpf_tail_call_static(skb, &jmp_table, 2);
return skb->len * 3;
}
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index 2c8935b3e65d..ee454327e5c6 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -159,3 +159,15 @@
.result = ACCEPT,
.retval = 2,
},
+{
+ "dead code: zero extension",
+ .insns = {
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4),
+ BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 0, 1),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -4),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .retval = 0,
+},
diff --git a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
index a3e593ddfafc..2debba4e8a3a 100644
--- a/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/verifier/value_ptr_arith.c
@@ -1,4 +1,233 @@
{
+ "map access: known scalar += value_ptr unknown vs const",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs unknown",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 9),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (ne)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr const vs const (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_1, 5),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (eq)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (lt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
+ "map access: known scalar += value_ptr unknown vs unknown (gt)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct __sk_buff, len)),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 1, 3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ BPF_LDX_MEM(BPF_B, BPF_REG_4, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_4, 1, 4),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x7),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 6),
+ BPF_ALU64_IMM(BPF_NEG, BPF_REG_1, 0),
+ BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x3),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_0),
+ BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_16b = { 5 },
+ .fixup_map_array_48b = { 8 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "R1 tried to add from different maps, paths or scalars",
+ .result = ACCEPT,
+ .retval = 1,
+},
+{
"map access: known scalar += value_ptr from different maps",
.insns = {
BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index 06a351b4f93b..0709af0144c8 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -38,6 +38,7 @@
/x86_64/xen_vmcall_test
/x86_64/xss_msr_test
/x86_64/vmx_pmu_msrs_test
+/access_tracking_perf_test
/demand_paging_test
/dirty_log_test
/dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index b853be2ae3c6..5832f510a16c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -71,6 +71,7 @@ TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_msrs_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test
TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test
+TEST_GEN_PROGS_x86_64 += access_tracking_perf_test
TEST_GEN_PROGS_x86_64 += demand_paging_test
TEST_GEN_PROGS_x86_64 += dirty_log_test
TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index a16c8f05366c..cc898181faab 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -1019,7 +1019,8 @@ static __u64 sve_rejects_set[] = {
#define VREGS_SUBLIST \
{ "vregs", .regs = vregs, .regs_n = ARRAY_SIZE(vregs), }
#define PMU_SUBLIST \
- { "pmu", .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
+ { "pmu", .capability = KVM_CAP_ARM_PMU_V3, .feature = KVM_ARM_VCPU_PMU_V3, \
+ .regs = pmu_regs, .regs_n = ARRAY_SIZE(pmu_regs), }
#define SVE_SUBLIST \
{ "sve", .capability = KVM_CAP_ARM_SVE, .feature = KVM_ARM_VCPU_SVE, .finalize = true, \
.regs = sve_regs, .regs_n = ARRAY_SIZE(sve_regs), \
diff --git a/tools/testing/selftests/kvm/access_tracking_perf_test.c b/tools/testing/selftests/kvm/access_tracking_perf_test.c
new file mode 100644
index 000000000000..e2baa187a21e
--- /dev/null
+++ b/tools/testing/selftests/kvm/access_tracking_perf_test.c
@@ -0,0 +1,429 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * access_tracking_perf_test
+ *
+ * Copyright (C) 2021, Google, Inc.
+ *
+ * This test measures the performance effects of KVM's access tracking.
+ * Access tracking is driven by the MMU notifiers test_young, clear_young, and
+ * clear_flush_young. These notifiers do not have a direct userspace API,
+ * however the clear_young notifier can be triggered by marking a pages as idle
+ * in /sys/kernel/mm/page_idle/bitmap. This test leverages that mechanism to
+ * enable access tracking on guest memory.
+ *
+ * To measure performance this test runs a VM with a configurable number of
+ * vCPUs that each touch every page in disjoint regions of memory. Performance
+ * is measured in the time it takes all vCPUs to finish touching their
+ * predefined region.
+ *
+ * Note that a deterministic correctness test of access tracking is not possible
+ * by using page_idle as it exists today. This is for a few reasons:
+ *
+ * 1. page_idle only issues clear_young notifiers, which lack a TLB flush. This
+ * means subsequent guest accesses are not guaranteed to see page table
+ * updates made by KVM until some time in the future.
+ *
+ * 2. page_idle only operates on LRU pages. Newly allocated pages are not
+ * immediately allocated to LRU lists. Instead they are held in a "pagevec",
+ * which is drained to LRU lists some time in the future. There is no
+ * userspace API to force this drain to occur.
+ *
+ * These limitations are worked around in this test by using a large enough
+ * region of memory for each vCPU such that the number of translations cached in
+ * the TLB and the number of pages held in pagevecs are a small fraction of the
+ * overall workload. And if either of those conditions are not true this test
+ * will fail rather than silently passing.
+ */
+#include <inttypes.h>
+#include <limits.h>
+#include <pthread.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include "kvm_util.h"
+#include "test_util.h"
+#include "perf_test_util.h"
+#include "guest_modes.h"
+
+/* Global variable used to synchronize all of the vCPU threads. */
+static int iteration = -1;
+
+/* Defines what vCPU threads should do during a given iteration. */
+static enum {
+ /* Run the vCPU to access all its memory. */
+ ITERATION_ACCESS_MEMORY,
+ /* Mark the vCPU's memory idle in page_idle. */
+ ITERATION_MARK_IDLE,
+} iteration_work;
+
+/* Set to true when vCPU threads should exit. */
+static bool done;
+
+/* The iteration that was last completed by each vCPU. */
+static int vcpu_last_completed_iteration[KVM_MAX_VCPUS];
+
+/* Whether to overlap the regions of memory vCPUs access. */
+static bool overlap_memory_access;
+
+struct test_params {
+ /* The backing source for the region of memory. */
+ enum vm_mem_backing_src_type backing_src;
+
+ /* The amount of memory to allocate for each vCPU. */
+ uint64_t vcpu_memory_bytes;
+
+ /* The number of vCPUs to create in the VM. */
+ int vcpus;
+};
+
+static uint64_t pread_uint64(int fd, const char *filename, uint64_t index)
+{
+ uint64_t value;
+ off_t offset = index * sizeof(value);
+
+ TEST_ASSERT(pread(fd, &value, sizeof(value), offset) == sizeof(value),
+ "pread from %s offset 0x%" PRIx64 " failed!",
+ filename, offset);
+
+ return value;
+
+}
+
+#define PAGEMAP_PRESENT (1ULL << 63)
+#define PAGEMAP_PFN_MASK ((1ULL << 55) - 1)
+
+static uint64_t lookup_pfn(int pagemap_fd, struct kvm_vm *vm, uint64_t gva)
+{
+ uint64_t hva = (uint64_t) addr_gva2hva(vm, gva);
+ uint64_t entry;
+ uint64_t pfn;
+
+ entry = pread_uint64(pagemap_fd, "pagemap", hva / getpagesize());
+ if (!(entry & PAGEMAP_PRESENT))
+ return 0;
+
+ pfn = entry & PAGEMAP_PFN_MASK;
+ if (!pfn) {
+ print_skip("Looking up PFNs requires CAP_SYS_ADMIN");
+ exit(KSFT_SKIP);
+ }
+
+ return pfn;
+}
+
+static bool is_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = pread_uint64(page_idle_fd, "page_idle", pfn / 64);
+
+ return !!((bits >> (pfn % 64)) & 1);
+}
+
+static void mark_page_idle(int page_idle_fd, uint64_t pfn)
+{
+ uint64_t bits = 1ULL << (pfn % 64);
+
+ TEST_ASSERT(pwrite(page_idle_fd, &bits, 8, 8 * (pfn / 64)) == 8,
+ "Set page_idle bits for PFN 0x%" PRIx64, pfn);
+}
+
+static void mark_vcpu_memory_idle(struct kvm_vm *vm, int vcpu_id)
+{
+ uint64_t base_gva = perf_test_args.vcpu_args[vcpu_id].gva;
+ uint64_t pages = perf_test_args.vcpu_args[vcpu_id].pages;
+ uint64_t page;
+ uint64_t still_idle = 0;
+ uint64_t no_pfn = 0;
+ int page_idle_fd;
+ int pagemap_fd;
+
+ /* If vCPUs are using an overlapping region, let vCPU 0 mark it idle. */
+ if (overlap_memory_access && vcpu_id)
+ return;
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ TEST_ASSERT(page_idle_fd > 0, "Failed to open page_idle.");
+
+ pagemap_fd = open("/proc/self/pagemap", O_RDONLY);
+ TEST_ASSERT(pagemap_fd > 0, "Failed to open pagemap.");
+
+ for (page = 0; page < pages; page++) {
+ uint64_t gva = base_gva + page * perf_test_args.guest_page_size;
+ uint64_t pfn = lookup_pfn(pagemap_fd, vm, gva);
+
+ if (!pfn) {
+ no_pfn++;
+ continue;
+ }
+
+ if (is_page_idle(page_idle_fd, pfn)) {
+ still_idle++;
+ continue;
+ }
+
+ mark_page_idle(page_idle_fd, pfn);
+ }
+
+ /*
+ * Assumption: Less than 1% of pages are going to be swapped out from
+ * under us during this test.
+ */
+ TEST_ASSERT(no_pfn < pages / 100,
+ "vCPU %d: No PFN for %" PRIu64 " out of %" PRIu64 " pages.",
+ vcpu_id, no_pfn, pages);
+
+ /*
+ * Test that at least 90% of memory has been marked idle (the rest might
+ * not be marked idle because the pages have not yet made it to an LRU
+ * list or the translations are still cached in the TLB). 90% is
+ * arbitrary; high enough that we ensure most memory access went through
+ * access tracking but low enough as to not make the test too brittle
+ * over time and across architectures.
+ */
+ TEST_ASSERT(still_idle < pages / 10,
+ "vCPU%d: Too many pages still idle (%"PRIu64 " out of %"
+ PRIu64 ").\n",
+ vcpu_id, still_idle, pages);
+
+ close(page_idle_fd);
+ close(pagemap_fd);
+}
+
+static void assert_ucall(struct kvm_vm *vm, uint32_t vcpu_id,
+ uint64_t expected_ucall)
+{
+ struct ucall uc;
+ uint64_t actual_ucall = get_ucall(vm, vcpu_id, &uc);
+
+ TEST_ASSERT(expected_ucall == actual_ucall,
+ "Guest exited unexpectedly (expected ucall %" PRIu64
+ ", got %" PRIu64 ")",
+ expected_ucall, actual_ucall);
+}
+
+static bool spin_wait_for_next_iteration(int *current_iteration)
+{
+ int last_iteration = *current_iteration;
+
+ do {
+ if (READ_ONCE(done))
+ return false;
+
+ *current_iteration = READ_ONCE(iteration);
+ } while (last_iteration == *current_iteration);
+
+ return true;
+}
+
+static void *vcpu_thread_main(void *arg)
+{
+ struct perf_test_vcpu_args *vcpu_args = arg;
+ struct kvm_vm *vm = perf_test_args.vm;
+ int vcpu_id = vcpu_args->vcpu_id;
+ int current_iteration = -1;
+
+ vcpu_args_set(vm, vcpu_id, 1, vcpu_id);
+
+ while (spin_wait_for_next_iteration(&current_iteration)) {
+ switch (READ_ONCE(iteration_work)) {
+ case ITERATION_ACCESS_MEMORY:
+ vcpu_run(vm, vcpu_id);
+ assert_ucall(vm, vcpu_id, UCALL_SYNC);
+ break;
+ case ITERATION_MARK_IDLE:
+ mark_vcpu_memory_idle(vm, vcpu_id);
+ break;
+ };
+
+ vcpu_last_completed_iteration[vcpu_id] = current_iteration;
+ }
+
+ return NULL;
+}
+
+static void spin_wait_for_vcpu(int vcpu_id, int target_iteration)
+{
+ while (READ_ONCE(vcpu_last_completed_iteration[vcpu_id]) !=
+ target_iteration) {
+ continue;
+ }
+}
+
+/* The type of memory accesses to perform in the VM. */
+enum access_type {
+ ACCESS_READ,
+ ACCESS_WRITE,
+};
+
+static void run_iteration(struct kvm_vm *vm, int vcpus, const char *description)
+{
+ struct timespec ts_start;
+ struct timespec ts_elapsed;
+ int next_iteration;
+ int vcpu_id;
+
+ /* Kick off the vCPUs by incrementing iteration. */
+ next_iteration = ++iteration;
+
+ clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+ /* Wait for all vCPUs to finish the iteration. */
+ for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++)
+ spin_wait_for_vcpu(vcpu_id, next_iteration);
+
+ ts_elapsed = timespec_elapsed(ts_start);
+ pr_info("%-30s: %ld.%09lds\n",
+ description, ts_elapsed.tv_sec, ts_elapsed.tv_nsec);
+}
+
+static void access_memory(struct kvm_vm *vm, int vcpus, enum access_type access,
+ const char *description)
+{
+ perf_test_args.wr_fract = (access == ACCESS_READ) ? INT_MAX : 1;
+ sync_global_to_guest(vm, perf_test_args);
+ iteration_work = ITERATION_ACCESS_MEMORY;
+ run_iteration(vm, vcpus, description);
+}
+
+static void mark_memory_idle(struct kvm_vm *vm, int vcpus)
+{
+ /*
+ * Even though this parallelizes the work across vCPUs, this is still a
+ * very slow operation because page_idle forces the test to mark one pfn
+ * at a time and the clear_young notifier serializes on the KVM MMU
+ * lock.
+ */
+ pr_debug("Marking VM memory idle (slow)...\n");
+ iteration_work = ITERATION_MARK_IDLE;
+ run_iteration(vm, vcpus, "Mark memory idle");
+}
+
+static pthread_t *create_vcpu_threads(int vcpus)
+{
+ pthread_t *vcpu_threads;
+ int i;
+
+ vcpu_threads = malloc(vcpus * sizeof(vcpu_threads[0]));
+ TEST_ASSERT(vcpu_threads, "Failed to allocate vcpu_threads.");
+
+ for (i = 0; i < vcpus; i++) {
+ vcpu_last_completed_iteration[i] = iteration;
+ pthread_create(&vcpu_threads[i], NULL, vcpu_thread_main,
+ &perf_test_args.vcpu_args[i]);
+ }
+
+ return vcpu_threads;
+}
+
+static void terminate_vcpu_threads(pthread_t *vcpu_threads, int vcpus)
+{
+ int i;
+
+ /* Set done to signal the vCPU threads to exit */
+ done = true;
+
+ for (i = 0; i < vcpus; i++)
+ pthread_join(vcpu_threads[i], NULL);
+}
+
+static void run_test(enum vm_guest_mode mode, void *arg)
+{
+ struct test_params *params = arg;
+ struct kvm_vm *vm;
+ pthread_t *vcpu_threads;
+ int vcpus = params->vcpus;
+
+ vm = perf_test_create_vm(mode, vcpus, params->vcpu_memory_bytes,
+ params->backing_src);
+
+ perf_test_setup_vcpus(vm, vcpus, params->vcpu_memory_bytes,
+ !overlap_memory_access);
+
+ vcpu_threads = create_vcpu_threads(vcpus);
+
+ pr_info("\n");
+ access_memory(vm, vcpus, ACCESS_WRITE, "Populating memory");
+
+ /* As a control, read and write to the populated memory first. */
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to populated memory");
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from populated memory");
+
+ /* Repeat on memory that has been marked as idle. */
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_WRITE, "Writing to idle memory");
+ mark_memory_idle(vm, vcpus);
+ access_memory(vm, vcpus, ACCESS_READ, "Reading from idle memory");
+
+ terminate_vcpu_threads(vcpu_threads, vcpus);
+ free(vcpu_threads);
+ perf_test_destroy_vm(vm);
+}
+
+static void help(char *name)
+{
+ puts("");
+ printf("usage: %s [-h] [-m mode] [-b vcpu_bytes] [-v vcpus] [-o] [-s mem_type]\n",
+ name);
+ puts("");
+ printf(" -h: Display this help message.");
+ guest_modes_help();
+ printf(" -b: specify the size of the memory region which should be\n"
+ " dirtied by each vCPU. e.g. 10M or 3G.\n"
+ " (default: 1G)\n");
+ printf(" -v: specify the number of vCPUs to run.\n");
+ printf(" -o: Overlap guest memory accesses instead of partitioning\n"
+ " them into a separate region of memory for each vCPU.\n");
+ printf(" -s: specify the type of memory that should be used to\n"
+ " back the guest data region.\n\n");
+ backing_src_help();
+ puts("");
+ exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct test_params params = {
+ .backing_src = VM_MEM_SRC_ANONYMOUS,
+ .vcpu_memory_bytes = DEFAULT_PER_VCPU_MEM_SIZE,
+ .vcpus = 1,
+ };
+ int page_idle_fd;
+ int opt;
+
+ guest_modes_append_default();
+
+ while ((opt = getopt(argc, argv, "hm:b:v:os:")) != -1) {
+ switch (opt) {
+ case 'm':
+ guest_modes_cmdline(optarg);
+ break;
+ case 'b':
+ params.vcpu_memory_bytes = parse_size(optarg);
+ break;
+ case 'v':
+ params.vcpus = atoi(optarg);
+ break;
+ case 'o':
+ overlap_memory_access = true;
+ break;
+ case 's':
+ params.backing_src = parse_backing_src_type(optarg);
+ break;
+ case 'h':
+ default:
+ help(argv[0]);
+ break;
+ }
+ }
+
+ page_idle_fd = open("/sys/kernel/mm/page_idle/bitmap", O_RDWR);
+ if (page_idle_fd < 0) {
+ print_skip("CONFIG_IDLE_PAGE_TRACKING is not enabled");
+ exit(KSFT_SKIP);
+ }
+ close(page_idle_fd);
+
+ for_each_guest_mode(run_test, &params);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index 04a2641261be..80cbd3a748c0 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -312,6 +312,7 @@ int main(int argc, char *argv[])
break;
case 'o':
p.partition_vcpu_memory_access = false;
+ break;
case 's':
p.backing_src = parse_backing_src_type(optarg);
break;
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
index 615ab254899d..010b59b13917 100644
--- a/tools/testing/selftests/kvm/include/kvm_util.h
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -45,6 +45,7 @@ enum vm_guest_mode {
VM_MODE_P40V48_64K,
VM_MODE_PXXV48_4K, /* For 48bits VA but ANY bits PA */
VM_MODE_P47V64_4K,
+ VM_MODE_P44V64_4K,
NUM_VM_MODES,
};
@@ -62,7 +63,7 @@ enum vm_guest_mode {
#elif defined(__s390x__)
-#define VM_MODE_DEFAULT VM_MODE_P47V64_4K
+#define VM_MODE_DEFAULT VM_MODE_P44V64_4K
#define MIN_PAGE_SHIFT 12U
#define ptes_per_page(page_size) ((page_size) / 16)
diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
index 412eaee7884a..b66910702c0a 100644
--- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h
+++ b/tools/testing/selftests/kvm/include/x86_64/hyperv.h
@@ -117,7 +117,7 @@
#define HV_X64_GUEST_DEBUGGING_AVAILABLE BIT(1)
#define HV_X64_PERF_MONITOR_AVAILABLE BIT(2)
#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE BIT(3)
-#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE BIT(4)
+#define HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE BIT(4)
#define HV_X64_GUEST_IDLE_STATE_AVAILABLE BIT(5)
#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8)
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
@@ -182,4 +182,7 @@
#define HV_STATUS_INVALID_CONNECTION_ID 18
#define HV_STATUS_INSUFFICIENT_BUFFERS 19
+/* hypercall options */
+#define HV_HYPERCALL_FAST_BIT BIT(16)
+
#endif /* !SELFTEST_KVM_HYPERV_H */
diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/aarch64/processor.c
index 9f49f6caafe5..632b74d6b3ca 100644
--- a/tools/testing/selftests/kvm/lib/aarch64/processor.c
+++ b/tools/testing/selftests/kvm/lib/aarch64/processor.c
@@ -401,7 +401,7 @@ unexpected_exception:
void vm_init_descriptor_tables(struct kvm_vm *vm)
{
vm->handlers = vm_vaddr_alloc(vm, sizeof(struct handlers),
- vm->page_size, 0, 0);
+ vm->page_size);
*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
}
diff --git a/tools/testing/selftests/kvm/lib/guest_modes.c b/tools/testing/selftests/kvm/lib/guest_modes.c
index 25bff307c71f..c330f414ef96 100644
--- a/tools/testing/selftests/kvm/lib/guest_modes.c
+++ b/tools/testing/selftests/kvm/lib/guest_modes.c
@@ -22,6 +22,22 @@ void guest_modes_append_default(void)
}
}
#endif
+#ifdef __s390x__
+ {
+ int kvm_fd, vm_fd;
+ struct kvm_s390_vm_cpu_processor info;
+
+ kvm_fd = open_kvm_dev_path_or_exit();
+ vm_fd = ioctl(kvm_fd, KVM_CREATE_VM, 0);
+ kvm_device_access(vm_fd, KVM_S390_VM_CPU_MODEL,
+ KVM_S390_VM_CPU_PROCESSOR, &info, false);
+ close(vm_fd);
+ close(kvm_fd);
+ /* Starting with z13 we have 47bits of physical address */
+ if (info.ibc >= 0x30)
+ guest_mode_append(VM_MODE_P47V64_4K, true, true);
+ }
+#endif
}
void for_each_guest_mode(void (*func)(enum vm_guest_mode, void *), void *arg)
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
index 5b56b57b3c20..10a8ed691c66 100644
--- a/tools/testing/selftests/kvm/lib/kvm_util.c
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -176,6 +176,7 @@ const char *vm_guest_mode_string(uint32_t i)
[VM_MODE_P40V48_64K] = "PA-bits:40, VA-bits:48, 64K pages",
[VM_MODE_PXXV48_4K] = "PA-bits:ANY, VA-bits:48, 4K pages",
[VM_MODE_P47V64_4K] = "PA-bits:47, VA-bits:64, 4K pages",
+ [VM_MODE_P44V64_4K] = "PA-bits:44, VA-bits:64, 4K pages",
};
_Static_assert(sizeof(strings)/sizeof(char *) == NUM_VM_MODES,
"Missing new mode strings?");
@@ -194,6 +195,7 @@ const struct vm_guest_mode_params vm_guest_mode_params[] = {
{ 40, 48, 0x10000, 16 },
{ 0, 0, 0x1000, 12 },
{ 47, 64, 0x1000, 12 },
+ { 44, 64, 0x1000, 12 },
};
_Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params) == NUM_VM_MODES,
"Missing new mode params?");
@@ -282,6 +284,9 @@ struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
case VM_MODE_P47V64_4K:
vm->pgtable_levels = 5;
break;
+ case VM_MODE_P44V64_4K:
+ vm->pgtable_levels = 5;
+ break;
default:
TEST_FAIL("Unknown guest mode, mode: 0x%x", mode);
}
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index 85b18bb8f762..72a1c9b4882c 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -377,7 +377,8 @@ static void test_add_max_memory_regions(void)
(max_mem_slots - 1), MEM_REGION_SIZE >> 10);
mem = mmap(NULL, (size_t)max_mem_slots * MEM_REGION_SIZE + alignment,
- PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
TEST_ASSERT(mem != MAP_FAILED, "Failed to mmap() host");
mem_aligned = (void *)(((size_t) mem + alignment - 1) & ~(alignment - 1));
diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c
index b0031f2d38fd..ecec30865a74 100644
--- a/tools/testing/selftests/kvm/steal_time.c
+++ b/tools/testing/selftests/kvm/steal_time.c
@@ -320,7 +320,7 @@ int main(int ac, char **av)
run_delay = get_run_delay();
pthread_create(&thread, &attr, do_steal_time, NULL);
do
- pthread_yield();
+ sched_yield();
while (get_run_delay() - run_delay < MIN_RUN_DELAY_NS);
pthread_join(thread, NULL);
run_delay = get_run_delay() - run_delay;
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
index bab10ae787b6..e0b2bb1339b1 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_clock.c
@@ -215,7 +215,7 @@ int main(void)
vcpu_set_hv_cpuid(vm, VCPU_ID);
tsc_page_gva = vm_vaddr_alloc_page(vm);
- memset(addr_gpa2hva(vm, tsc_page_gva), 0x0, getpagesize());
+ memset(addr_gva2hva(vm, tsc_page_gva), 0x0, getpagesize());
TEST_ASSERT((addr_gva2gpa(vm, tsc_page_gva) & (getpagesize() - 1)) == 0,
"TSC page has to be page aligned\n");
vcpu_args_set(vm, VCPU_ID, 2, tsc_page_gva, addr_gva2gpa(vm, tsc_page_gva));
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
index 42bd658f52a8..91d88aaa9899 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_features.c
@@ -47,6 +47,7 @@ static void do_wrmsr(u32 idx, u64 val)
}
static int nr_gp;
+static int nr_ud;
static inline u64 hypercall(u64 control, vm_vaddr_t input_address,
vm_vaddr_t output_address)
@@ -80,6 +81,12 @@ static void guest_gp_handler(struct ex_regs *regs)
regs->rip = (uint64_t)&wrmsr_end;
}
+static void guest_ud_handler(struct ex_regs *regs)
+{
+ nr_ud++;
+ regs->rip += 3;
+}
+
struct msr_data {
uint32_t idx;
bool available;
@@ -90,6 +97,7 @@ struct msr_data {
struct hcall_data {
uint64_t control;
uint64_t expect;
+ bool ud_expected;
};
static void guest_msr(struct msr_data *msr)
@@ -117,13 +125,26 @@ static void guest_msr(struct msr_data *msr)
static void guest_hcall(vm_vaddr_t pgs_gpa, struct hcall_data *hcall)
{
int i = 0;
+ u64 res, input, output;
wrmsr(HV_X64_MSR_GUEST_OS_ID, LINUX_OS_ID);
wrmsr(HV_X64_MSR_HYPERCALL, pgs_gpa);
while (hcall->control) {
- GUEST_ASSERT(hypercall(hcall->control, pgs_gpa,
- pgs_gpa + 4096) == hcall->expect);
+ nr_ud = 0;
+ if (!(hcall->control & HV_HYPERCALL_FAST_BIT)) {
+ input = pgs_gpa;
+ output = pgs_gpa + 4096;
+ } else {
+ input = output = 0;
+ }
+
+ res = hypercall(hcall->control, input, output);
+ if (hcall->ud_expected)
+ GUEST_ASSERT(nr_ud == 1);
+ else
+ GUEST_ASSERT(res == hcall->expect);
+
GUEST_SYNC(i++);
}
@@ -552,8 +573,18 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
recomm.ebx = 0xfff;
hcall->expect = HV_STATUS_SUCCESS;
break;
-
case 17:
+ /* XMM fast hypercall */
+ hcall->control = HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE | HV_HYPERCALL_FAST_BIT;
+ hcall->ud_expected = true;
+ break;
+ case 18:
+ feat.edx |= HV_X64_HYPERCALL_XMM_INPUT_AVAILABLE;
+ hcall->ud_expected = false;
+ hcall->expect = HV_STATUS_SUCCESS;
+ break;
+
+ case 19:
/* END */
hcall->control = 0;
break;
@@ -615,7 +646,7 @@ int main(void)
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
- vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+ vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
pr_info("Testing access to Hyper-V specific MSRs\n");
guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
@@ -625,6 +656,10 @@ int main(void)
/* Test hypercalls */
vm = vm_create_default(VCPU_ID, 0, guest_hcall);
+ vm_init_descriptor_tables(vm);
+ vcpu_init_descriptor_tables(vm, VCPU_ID);
+ vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
/* Hypercall input/output */
hcall_page = vm_vaddr_alloc_pages(vm, 2);
memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
diff --git a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
index 523371cf8e8f..da2325fcad87 100644
--- a/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
+++ b/tools/testing/selftests/kvm/x86_64/mmu_role_test.c
@@ -71,7 +71,7 @@ static void mmu_role_test(u32 *cpuid_reg, u32 evil_cpuid_val)
/* Set up a #PF handler to eat the RSVD #PF and signal all done! */
vm_init_descriptor_tables(vm);
vcpu_init_descriptor_tables(vm, VCPU_ID);
- vm_handle_exception(vm, PF_VECTOR, guest_pf_handler);
+ vm_install_exception_handler(vm, PF_VECTOR, guest_pf_handler);
r = _vcpu_run(vm, VCPU_ID);
TEST_ASSERT(r == 0, "vcpu_run failed: %d\n", r);
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index c1f831803ad2..d0fe2fdce58c 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -53,15 +53,28 @@ static inline void sync_with_host(uint64_t phase)
: "+a" (phase));
}
-void self_smi(void)
+static void self_smi(void)
{
x2apic_write_reg(APIC_ICR,
APIC_DEST_SELF | APIC_INT_ASSERT | APIC_DM_SMI);
}
-void guest_code(void *arg)
+static void l2_guest_code(void)
{
+ sync_with_host(8);
+
+ sync_with_host(10);
+
+ vmcall();
+}
+
+static void guest_code(void *arg)
+{
+ #define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
uint64_t apicbase = rdmsr(MSR_IA32_APICBASE);
+ struct svm_test_data *svm = arg;
+ struct vmx_pages *vmx_pages = arg;
sync_with_host(1);
@@ -74,21 +87,50 @@ void guest_code(void *arg)
sync_with_host(4);
if (arg) {
- if (cpu_has_svm())
- generic_svm_setup(arg, NULL, NULL);
- else
- GUEST_ASSERT(prepare_for_vmx_operation(arg));
+ if (cpu_has_svm()) {
+ generic_svm_setup(svm, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ } else {
+ GUEST_ASSERT(prepare_for_vmx_operation(vmx_pages));
+ GUEST_ASSERT(load_vmcs(vmx_pages));
+ prepare_vmcs(vmx_pages, l2_guest_code,
+ &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ }
sync_with_host(5);
self_smi();
sync_with_host(7);
+
+ if (cpu_has_svm()) {
+ run_guest(svm->vmcb, svm->vmcb_gpa);
+ svm->vmcb->save.rip += 3;
+ run_guest(svm->vmcb, svm->vmcb_gpa);
+ } else {
+ vmlaunch();
+ vmresume();
+ }
+
+ /* Stages 8-11 are eaten by SMM (SMRAM_STAGE reported instead) */
+ sync_with_host(12);
}
sync_with_host(DONE);
}
+void inject_smi(struct kvm_vm *vm)
+{
+ struct kvm_vcpu_events events;
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+
+ events.smi.pending = 1;
+ events.flags |= KVM_VCPUEVENT_VALID_SMM;
+
+ vcpu_events_set(vm, VCPU_ID, &events);
+}
+
int main(int argc, char *argv[])
{
vm_vaddr_t nested_gva = 0;
@@ -147,6 +189,22 @@ int main(int argc, char *argv[])
"Unexpected stage: #%x, got %x",
stage, stage_reported);
+ /*
+ * Enter SMM during L2 execution and check that we correctly
+ * return from it. Do not perform save/restore while in SMM yet.
+ */
+ if (stage == 8) {
+ inject_smi(vm);
+ continue;
+ }
+
+ /*
+ * Perform save/restore while the guest is in SMM triggered
+ * during L2 execution.
+ */
+ if (stage == 10)
+ inject_smi(vm);
+
state = vcpu_save_state(vm, VCPU_ID);
kvm_vm_release(vm);
kvm_vm_restart(vm, O_RDWR);
diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
index b37585e6aa38..46a97f318f58 100755
--- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
+++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
@@ -282,7 +282,9 @@ done
#
echo $error > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
for memory in `hotpluggable_online_memory`; do
- offline_memory_expect_fail $memory
+ if [ $((RANDOM % 100)) -lt $ratio ]; then
+ offline_memory_expect_fail $memory
+ fi
done
echo 0 > $NOTIFIER_ERR_INJECT_DIR/actions/MEM_GOING_OFFLINE/error
diff --git a/tools/testing/selftests/net/icmp_redirect.sh b/tools/testing/selftests/net/icmp_redirect.sh
index c19ecc6a8614..ecbf57f264ed 100755
--- a/tools/testing/selftests/net/icmp_redirect.sh
+++ b/tools/testing/selftests/net/icmp_redirect.sh
@@ -313,9 +313,10 @@ check_exception()
fi
log_test $? 0 "IPv4: ${desc}"
- if [ "$with_redirect" = "yes" ]; then
+ # No PMTU info for test "redirect" and "mtu exception plus redirect"
+ if [ "$with_redirect" = "yes" ] && [ "$desc" != "redirect exception plus mtu" ]; then
ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
- grep -q "${H2_N2_IP6} from :: via ${R2_LLADDR} dev br0.*${mtu}"
+ grep -v "mtu" | grep -q "${H2_N2_IP6} .*via ${R2_LLADDR} dev br0"
elif [ -n "${mtu}" ]; then
ip -netns h1 -6 ro get ${H1_VRF_ARG} ${H2_N2_IP6} | \
grep -q "${mtu}"
diff --git a/tools/testing/selftests/net/ipsec.c b/tools/testing/selftests/net/ipsec.c
index f23438d512c5..3d7dde2c321b 100644
--- a/tools/testing/selftests/net/ipsec.c
+++ b/tools/testing/selftests/net/ipsec.c
@@ -484,13 +484,16 @@ enum desc_type {
MONITOR_ACQUIRE,
EXPIRE_STATE,
EXPIRE_POLICY,
+ SPDINFO_ATTRS,
};
const char *desc_name[] = {
"create tunnel",
"alloc spi",
"monitor acquire",
"expire state",
- "expire policy"
+ "expire policy",
+ "spdinfo attributes",
+ ""
};
struct xfrm_desc {
enum desc_type type;
@@ -1593,6 +1596,155 @@ out_close:
return ret;
}
+static int xfrm_spdinfo_set_thresh(int xfrm_sock, uint32_t *seq,
+ unsigned thresh4_l, unsigned thresh4_r,
+ unsigned thresh6_l, unsigned thresh6_r,
+ bool add_bad_attr)
+
+{
+ struct {
+ struct nlmsghdr nh;
+ union {
+ uint32_t unused;
+ int error;
+ };
+ char attrbuf[MAX_PAYLOAD];
+ } req;
+ struct xfrmu_spdhthresh thresh;
+
+ memset(&req, 0, sizeof(req));
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused));
+ req.nh.nlmsg_type = XFRM_MSG_NEWSPDINFO;
+ req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+ req.nh.nlmsg_seq = (*seq)++;
+
+ thresh.lbits = thresh4_l;
+ thresh.rbits = thresh4_r;
+ if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV4_HTHRESH, &thresh, sizeof(thresh)))
+ return -1;
+
+ thresh.lbits = thresh6_l;
+ thresh.rbits = thresh6_r;
+ if (rtattr_pack(&req.nh, sizeof(req), XFRMA_SPD_IPV6_HTHRESH, &thresh, sizeof(thresh)))
+ return -1;
+
+ if (add_bad_attr) {
+ BUILD_BUG_ON(XFRMA_IF_ID <= XFRMA_SPD_MAX + 1);
+ if (rtattr_pack(&req.nh, sizeof(req), XFRMA_IF_ID, NULL, 0)) {
+ pr_err("adding attribute failed: no space");
+ return -1;
+ }
+ }
+
+ if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ pr_err("send()");
+ return -1;
+ }
+
+ if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+ pr_err("recv()");
+ return -1;
+ } else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+ printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+ return -1;
+ }
+
+ if (req.error) {
+ printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+ return -1;
+ }
+
+ return 0;
+}
+
+static int xfrm_spdinfo_attrs(int xfrm_sock, uint32_t *seq)
+{
+ struct {
+ struct nlmsghdr nh;
+ union {
+ uint32_t unused;
+ int error;
+ };
+ char attrbuf[MAX_PAYLOAD];
+ } req;
+
+ if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 31, 120, 16, false)) {
+ pr_err("Can't set SPD HTHRESH");
+ return KSFT_FAIL;
+ }
+
+ memset(&req, 0, sizeof(req));
+
+ req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(req.unused));
+ req.nh.nlmsg_type = XFRM_MSG_GETSPDINFO;
+ req.nh.nlmsg_flags = NLM_F_REQUEST;
+ req.nh.nlmsg_seq = (*seq)++;
+ if (send(xfrm_sock, &req, req.nh.nlmsg_len, 0) < 0) {
+ pr_err("send()");
+ return KSFT_FAIL;
+ }
+
+ if (recv(xfrm_sock, &req, sizeof(req), 0) < 0) {
+ pr_err("recv()");
+ return KSFT_FAIL;
+ } else if (req.nh.nlmsg_type == XFRM_MSG_NEWSPDINFO) {
+ size_t len = NLMSG_PAYLOAD(&req.nh, sizeof(req.unused));
+ struct rtattr *attr = (void *)req.attrbuf;
+ int got_thresh = 0;
+
+ for (; RTA_OK(attr, len); attr = RTA_NEXT(attr, len)) {
+ if (attr->rta_type == XFRMA_SPD_IPV4_HTHRESH) {
+ struct xfrmu_spdhthresh *t = RTA_DATA(attr);
+
+ got_thresh++;
+ if (t->lbits != 32 || t->rbits != 31) {
+ pr_err("thresh differ: %u, %u",
+ t->lbits, t->rbits);
+ return KSFT_FAIL;
+ }
+ }
+ if (attr->rta_type == XFRMA_SPD_IPV6_HTHRESH) {
+ struct xfrmu_spdhthresh *t = RTA_DATA(attr);
+
+ got_thresh++;
+ if (t->lbits != 120 || t->rbits != 16) {
+ pr_err("thresh differ: %u, %u",
+ t->lbits, t->rbits);
+ return KSFT_FAIL;
+ }
+ }
+ }
+ if (got_thresh != 2) {
+ pr_err("only %d thresh returned by XFRM_MSG_GETSPDINFO", got_thresh);
+ return KSFT_FAIL;
+ }
+ } else if (req.nh.nlmsg_type != NLMSG_ERROR) {
+ printk("expected NLMSG_ERROR, got %d", (int)req.nh.nlmsg_type);
+ return KSFT_FAIL;
+ } else {
+ printk("NLMSG_ERROR: %d: %s", req.error, strerror(-req.error));
+ return -1;
+ }
+
+ /* Restore the default */
+ if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, false)) {
+ pr_err("Can't restore SPD HTHRESH");
+ return KSFT_FAIL;
+ }
+
+ /*
+ * At this moment xfrm uses nlmsg_parse_deprecated(), which
+ * implies NL_VALIDATE_LIBERAL - ignoring attributes with
+ * (type > maxtype). nla_parse_depricated_strict() would enforce
+ * it. Or even stricter nla_parse().
+ * Right now it's not expected to fail, but to be ignored.
+ */
+ if (xfrm_spdinfo_set_thresh(xfrm_sock, seq, 32, 32, 128, 128, true))
+ return KSFT_PASS;
+
+ return KSFT_PASS;
+}
+
static int child_serv(int xfrm_sock, uint32_t *seq,
unsigned int nr, int cmd_fd, void *buf, struct xfrm_desc *desc)
{
@@ -1717,6 +1869,9 @@ static int child_f(unsigned int nr, int test_desc_fd, int cmd_fd, void *buf)
case EXPIRE_POLICY:
ret = xfrm_expire_policy(xfrm_sock, &seq, nr, &desc);
break;
+ case SPDINFO_ATTRS:
+ ret = xfrm_spdinfo_attrs(xfrm_sock, &seq);
+ break;
default:
printk("Unknown desc type %d", desc.type);
exit(KSFT_FAIL);
@@ -1994,8 +2149,10 @@ static int write_proto_plan(int fd, int proto)
* sizeof(xfrm_user_polexpire) = 168 | sizeof(xfrm_user_polexpire) = 176
*
* Check the affected by the UABI difference structures.
+ * Also, check translation for xfrm_set_spdinfo: it has it's own attributes
+ * which needs to be correctly copied, but not translated.
*/
-const unsigned int compat_plan = 4;
+const unsigned int compat_plan = 5;
static int write_compat_struct_tests(int test_desc_fd)
{
struct xfrm_desc desc = {};
@@ -2019,6 +2176,10 @@ static int write_compat_struct_tests(int test_desc_fd)
if (__write_desc(test_desc_fd, &desc))
return -1;
+ desc.type = SPDINFO_ATTRS;
+ if (__write_desc(test_desc_fd, &desc))
+ return -1;
+
return 0;
}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 9a191c1a5de8..f02f4de2f3a0 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1409,7 +1409,7 @@ syncookies_tests()
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
run_tests $ns1 $ns2 10.0.1.1
- chk_join_nr "subflows limited by server w cookies" 2 2 1
+ chk_join_nr "subflows limited by server w cookies" 2 1 1
# test signal address with cookies
reset_with_cookies
diff --git a/tools/testing/selftests/net/nettest.c b/tools/testing/selftests/net/nettest.c
index 6365c7fd1262..bd6288302094 100644
--- a/tools/testing/selftests/net/nettest.c
+++ b/tools/testing/selftests/net/nettest.c
@@ -11,9 +11,11 @@
#include <sys/socket.h>
#include <sys/wait.h>
#include <linux/tcp.h>
+#include <linux/udp.h>
#include <arpa/inet.h>
#include <net/if.h>
#include <netinet/in.h>
+#include <netinet/ip.h>
#include <netdb.h>
#include <fcntl.h>
#include <libgen.h>
@@ -27,6 +29,10 @@
#include <time.h>
#include <errno.h>
+#include <linux/xfrm.h>
+#include <linux/ipsec.h>
+#include <linux/pfkeyv2.h>
+
#ifndef IPV6_UNICAST_IF
#define IPV6_UNICAST_IF 76
#endif
@@ -114,6 +120,9 @@ struct sock_args {
struct in_addr in;
struct in6_addr in6;
} expected_raddr;
+
+ /* ESP in UDP encap test */
+ int use_xfrm;
};
static int server_mode;
@@ -1346,6 +1355,41 @@ static int bind_socket(int sd, struct sock_args *args)
return 0;
}
+static int config_xfrm_policy(int sd, struct sock_args *args)
+{
+ struct xfrm_userpolicy_info policy = {};
+ int type = UDP_ENCAP_ESPINUDP;
+ int xfrm_af = IP_XFRM_POLICY;
+ int level = SOL_IP;
+
+ if (args->type != SOCK_DGRAM) {
+ log_error("Invalid socket type. Only DGRAM could be used for XFRM\n");
+ return 1;
+ }
+
+ policy.action = XFRM_POLICY_ALLOW;
+ policy.sel.family = args->version;
+ if (args->version == AF_INET6) {
+ xfrm_af = IPV6_XFRM_POLICY;
+ level = SOL_IPV6;
+ }
+
+ policy.dir = XFRM_POLICY_OUT;
+ if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+ return 1;
+
+ policy.dir = XFRM_POLICY_IN;
+ if (setsockopt(sd, level, xfrm_af, &policy, sizeof(policy)) < 0)
+ return 1;
+
+ if (setsockopt(sd, IPPROTO_UDP, UDP_ENCAP, &type, sizeof(type)) < 0) {
+ log_err_errno("Failed to set xfrm encap");
+ return 1;
+ }
+
+ return 0;
+}
+
static int lsock_init(struct sock_args *args)
{
long flags;
@@ -1389,6 +1433,11 @@ static int lsock_init(struct sock_args *args)
if (fcntl(sd, F_SETFD, FD_CLOEXEC) < 0)
log_err_errno("Failed to set close-on-exec flag");
+ if (args->use_xfrm && config_xfrm_policy(sd, args)) {
+ log_err_errno("Failed to set xfrm policy");
+ goto err;
+ }
+
out:
return sd;
@@ -1772,7 +1821,7 @@ static int ipc_parent(int cpid, int fd, struct sock_args *args)
return client_status;
}
-#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6L:0:1:2:3:Fbq"
+#define GETOPT_STR "sr:l:c:p:t:g:P:DRn:M:X:m:d:I:BN:O:SCi6xL:0:1:2:3:Fbq"
static void print_usage(char *prog)
{
@@ -1795,6 +1844,7 @@ static void print_usage(char *prog)
" -D|R datagram (D) / raw (R) socket (default stream)\n"
" -l addr local address to bind to in server mode\n"
" -c addr local address to bind to in client mode\n"
+ " -x configure XFRM policy on socket\n"
"\n"
" -d dev bind socket to given device name\n"
" -I dev bind socket to given device name - server mode\n"
@@ -1966,6 +2016,9 @@ int main(int argc, char *argv[])
case 'q':
quiet = 1;
break;
+ case 'x':
+ args.use_xfrm = 1;
+ break;
default:
print_usage(argv[0]);
return 1;
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 64cd2e23c568..543ad7513a8e 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -118,6 +118,16 @@
# below for IPv6 doesn't apply here, because, on IPv4, administrative MTU
# changes alone won't affect PMTU
#
+# - pmtu_vti4_udp_exception
+# Same as pmtu_vti4_exception, but using ESP-in-UDP
+#
+# - pmtu_vti4_udp_routed_exception
+# Set up vti tunnel on top of veth connected through routing namespace and
+# add xfrm states and policies with ESP-in-UDP encapsulation. Check that
+# route exception is not created if link layer MTU is not exceeded, then
+# lower MTU on second part of routed environment and check that exception
+# is created with the expected PMTU.
+#
# - pmtu_vti6_exception
# Set up vti6 tunnel on top of veth, with xfrm states and policies, in two
# namespaces with matching endpoints. Check that route exception is
@@ -125,6 +135,13 @@
# decrease and increase MTU of tunnel, checking that route exception PMTU
# changes accordingly
#
+# - pmtu_vti6_udp_exception
+# Same as pmtu_vti6_exception, but using ESP-in-UDP
+#
+# - pmtu_vti6_udp_routed_exception
+# Same as pmtu_vti6_udp_routed_exception but with routing between vti
+# endpoints
+#
# - pmtu_vti4_default_mtu
# Set up vti4 tunnel on top of veth, in two namespaces with matching
# endpoints. Check that MTU assigned to vti interface is the MTU of the
@@ -224,6 +241,10 @@ tests="
pmtu_ipv6_ipv6_exception IPv6 over IPv6: PMTU exceptions 1
pmtu_vti6_exception vti6: PMTU exceptions 0
pmtu_vti4_exception vti4: PMTU exceptions 0
+ pmtu_vti6_udp_exception vti6: PMTU exceptions (ESP-in-UDP) 0
+ pmtu_vti4_udp_exception vti4: PMTU exceptions (ESP-in-UDP) 0
+ pmtu_vti6_udp_routed_exception vti6: PMTU exceptions, routed (ESP-in-UDP) 0
+ pmtu_vti4_udp_routed_exception vti4: PMTU exceptions, routed (ESP-in-UDP) 0
pmtu_vti4_default_mtu vti4: default MTU assignment 0
pmtu_vti6_default_mtu vti6: default MTU assignment 0
pmtu_vti4_link_add_mtu vti4: MTU setting on link creation 0
@@ -246,7 +267,6 @@ ns_b="ip netns exec ${NS_B}"
ns_c="ip netns exec ${NS_C}"
ns_r1="ip netns exec ${NS_R1}"
ns_r2="ip netns exec ${NS_R2}"
-
# Addressing and routing for tests with routers: four network segments, with
# index SEGMENT between 1 and 4, a common prefix (PREFIX4 or PREFIX6) and an
# identifier ID, which is 1 for hosts (A and B), 2 for routers (R1 and R2).
@@ -279,7 +299,6 @@ routes="
A ${prefix6}:${b_r2}::1 ${prefix6}:${a_r2}::2
B default ${prefix6}:${b_r1}::2
"
-
USE_NH="no"
# ns family nh id destination gateway
nexthops="
@@ -326,6 +345,7 @@ dummy6_mask="64"
err_buf=
tcpdump_pids=
+nettest_pids=
err() {
err_buf="${err_buf}${1}
@@ -548,6 +568,14 @@ setup_vti6() {
setup_vti 6 ${veth6_a_addr} ${veth6_b_addr} ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
}
+setup_vti4routed() {
+ setup_vti 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 ${tunnel4_a_addr} ${tunnel4_b_addr} ${tunnel4_mask}
+}
+
+setup_vti6routed() {
+ setup_vti 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 ${tunnel6_a_addr} ${tunnel6_b_addr} ${tunnel6_mask}
+}
+
setup_vxlan_or_geneve() {
type="${1}"
a_addr="${2}"
@@ -619,18 +647,36 @@ setup_xfrm() {
proto=${1}
veth_a_addr="${2}"
veth_b_addr="${3}"
+ encap=${4}
- run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel || return 1
- run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+ run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap} || return 1
+ run_cmd ${ns_a} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
run_cmd ${ns_a} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
run_cmd ${ns_a} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
- run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
- run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel
+ run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_a_addr} dst ${veth_b_addr} spi 0x1000 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
+ run_cmd ${ns_b} ip -${proto} xfrm state add src ${veth_b_addr} dst ${veth_a_addr} spi 0x1001 proto esp aead 'rfc4106(gcm(aes))' 0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f 128 mode tunnel ${encap}
run_cmd ${ns_b} ip -${proto} xfrm policy add dir out mark 10 tmpl src ${veth_b_addr} dst ${veth_a_addr} proto esp mode tunnel
run_cmd ${ns_b} ip -${proto} xfrm policy add dir in mark 10 tmpl src ${veth_a_addr} dst ${veth_b_addr} proto esp mode tunnel
}
+setup_nettest_xfrm() {
+ which nettest >/dev/null
+ if [ $? -ne 0 ]; then
+ echo "'nettest' command not found; skipping tests"
+ return 1
+ fi
+
+ [ ${1} -eq 6 ] && proto="-6" || proto=""
+ port=${2}
+
+ run_cmd ${ns_a} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ nettest_pids="${nettest_pids} $!"
+
+ run_cmd ${ns_b} nettest ${proto} -q -D -s -x -p ${port} -t 5 &
+ nettest_pids="${nettest_pids} $!"
+}
+
setup_xfrm4() {
setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr}
}
@@ -639,6 +685,26 @@ setup_xfrm6() {
setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr}
}
+setup_xfrm4udp() {
+ setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udp() {
+ setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 6 4500
+}
+
+setup_xfrm4udprouted() {
+ setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 4 4500
+}
+
+setup_xfrm6udprouted() {
+ setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
+ setup_nettest_xfrm 6 4500
+}
+
setup_routing_old() {
for i in ${routes}; do
[ "${ns}" = "" ] && ns="${i}" && continue
@@ -823,6 +889,11 @@ cleanup() {
done
tcpdump_pids=
+ for pid in ${nettest_pids}; do
+ kill ${pid}
+ done
+ nettest_pids=
+
for n in ${NS_A} ${NS_B} ${NS_C} ${NS_R1} ${NS_R2}; do
ip netns del ${n} 2> /dev/null
done
@@ -1432,6 +1503,135 @@ test_pmtu_vti6_exception() {
return ${fail}
}
+test_pmtu_vti4_udp_exception() {
+ setup namespaces veth vti4 xfrm4udp || return $ksft_skip
+ trace "${ns_a}" veth_a "${ns_b}" veth_b \
+ "${ns_a}" vti4_a "${ns_b}" vti4_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 20))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 28))
+
+ mtu "${ns_a}" veth_a ${veth_mtu}
+ mtu "${ns_b}" veth_b ${veth_mtu}
+ mtu "${ns_a}" vti4_a ${vti_mtu}
+ mtu "${ns_b}" vti4_b ${vti_mtu}
+
+ # Send DF packet without exceeding link layer MTU, check that no
+ # exception is created
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now exceed link layer MTU by one byte, check that exception is created
+ # with the right PMTU value
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload + 1)) ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "${esp_payload_rfc4106}" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106 + 1)))"
+}
+
+test_pmtu_vti6_udp_exception() {
+ setup namespaces veth vti6 xfrm6udp || return $ksft_skip
+ trace "${ns_a}" veth_a "${ns_b}" veth_b \
+ "${ns_a}" vti6_a "${ns_b}" vti6_b
+ fail=0
+
+ # Create route exception by exceeding link layer MTU
+ mtu "${ns_a}" veth_a 4000
+ mtu "${ns_b}" veth_b 4000
+ mtu "${ns_a}" vti6_a 5000
+ mtu "${ns_b}" vti6_b 5000
+ run_cmd ${ns_a} ${ping6} -q -i 0.1 -w 1 -s 60000 ${tunnel6_b_addr}
+
+ # Check that exception was created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value any "${pmtu}" "creating tunnel exceeding link layer MTU" || return 1
+
+ # Decrease tunnel MTU, check for PMTU decrease in route exception
+ mtu "${ns_a}" vti6_a 3000
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "3000" "${pmtu}" "decreasing tunnel MTU" || fail=1
+
+ # Increase tunnel MTU, check for PMTU increase in route exception
+ mtu "${ns_a}" vti6_a 9000
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "9000" "${pmtu}" "increasing tunnel MTU" || fail=1
+
+ return ${fail}
+}
+
+test_pmtu_vti4_udp_routed_exception() {
+ setup namespaces routing vti4routed xfrm4udprouted || return $ksft_skip
+ trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \
+ "${ns_a}" vti4_a "${ns_b}" vti4_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 20))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 28))
+
+ mtu "${ns_a}" veth_A-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+ mtu "${ns_b}" veth_B-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+ mtu "${ns_a}" vti4_a ${vti_mtu}
+ mtu "${ns_b}" vti4_b ${vti_mtu}
+
+ # Send DF packet without exceeding link layer MTU, check that no
+ # exception is created
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+ # with the right PMTU value
+ mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+ run_cmd ${ns_a} ping -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel4_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel4_b_addr})"
+ check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+}
+
+test_pmtu_vti6_udp_routed_exception() {
+ setup namespaces routing vti6routed xfrm6udprouted || return $ksft_skip
+ trace "${ns_a}" veth_A-R1 "${ns_b}" veth_B-R1 \
+ "${ns_a}" vti6_a "${ns_b}" vti6_b
+
+ veth_mtu=1500
+ vti_mtu=$((veth_mtu - 40))
+
+ # UDP SPI SN IV ICV pad length next header
+ esp_payload_rfc4106=$((vti_mtu - 8 - 4 - 4 - 8 - 16 - 1 - 1))
+ ping_payload=$((esp_payload_rfc4106 - 48))
+
+ mtu "${ns_a}" veth_A-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-A ${veth_mtu}
+ mtu "${ns_b}" veth_B-R1 ${veth_mtu}
+ mtu "${ns_r1}" veth_R1-B ${veth_mtu}
+
+ # mtu "${ns_a}" vti6_a ${vti_mtu}
+ # mtu "${ns_b}" vti6_b ${vti_mtu}
+
+ run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s ${ping_payload} ${tunnel6_b_addr}
+
+ # Check that exception was not created
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "" "${pmtu}" "sending packet smaller than PMTU (IP payload length ${esp_payload_rfc4106})" || return 1
+
+ # Now decrease link layer MTU by 8 bytes on R1, check that exception is created
+ # with the right PMTU value
+ mtu "${ns_r1}" veth_R1-B $((veth_mtu - 8))
+ run_cmd ${ns_a} ${ping6} -q -M want -i 0.1 -w 1 -s $((ping_payload)) ${tunnel6_b_addr}
+ pmtu="$(route_get_dst_pmtu_from_exception "${ns_a}" ${tunnel6_b_addr})"
+ check_pmtu_value "$((esp_payload_rfc4106 - 8))" "${pmtu}" "exceeding PMTU (IP payload length $((esp_payload_rfc4106)))"
+
+}
+
test_pmtu_vti4_default_mtu() {
setup namespaces veth vti4 || return $ksft_skip
diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c
index 21091be70688..aee631c5284e 100644
--- a/tools/testing/selftests/net/timestamping.c
+++ b/tools/testing/selftests/net/timestamping.c
@@ -47,7 +47,7 @@ static void usage(const char *error)
{
if (error)
printf("invalid option: %s\n", error);
- printf("timestamping interface option*\n\n"
+ printf("timestamping <interface> [bind_phc_index] [option]*\n\n"
"Options:\n"
" IP_MULTICAST_LOOP - looping outgoing multicasts\n"
" SO_TIMESTAMP - normal software time stamping, ms resolution\n"
@@ -58,6 +58,7 @@ static void usage(const char *error)
" SOF_TIMESTAMPING_RX_SOFTWARE - software fallback for incoming packets\n"
" SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
" SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
+ " SOF_TIMESTAMPING_BIND_PHC - request to bind a PHC of PTP vclock\n"
" SIOCGSTAMP - check last socket time stamp\n"
" SIOCGSTAMPNS - more accurate socket time stamp\n"
" PTPV2 - use PTPv2 messages\n");
@@ -311,7 +312,6 @@ static void recvpacket(int sock, int recvmsg_flags,
int main(int argc, char **argv)
{
- int so_timestamping_flags = 0;
int so_timestamp = 0;
int so_timestampns = 0;
int siocgstamp = 0;
@@ -325,6 +325,8 @@ int main(int argc, char **argv)
struct ifreq device;
struct ifreq hwtstamp;
struct hwtstamp_config hwconfig, hwconfig_requested;
+ struct so_timestamping so_timestamping_get = { 0, -1 };
+ struct so_timestamping so_timestamping = { 0, -1 };
struct sockaddr_in addr;
struct ip_mreq imr;
struct in_addr iaddr;
@@ -342,7 +344,12 @@ int main(int argc, char **argv)
exit(1);
}
- for (i = 2; i < argc; i++) {
+ if (argc >= 3 && sscanf(argv[2], "%d", &so_timestamping.bind_phc) == 1)
+ val = 3;
+ else
+ val = 2;
+
+ for (i = val; i < argc; i++) {
if (!strcasecmp(argv[i], "SO_TIMESTAMP"))
so_timestamp = 1;
else if (!strcasecmp(argv[i], "SO_TIMESTAMPNS"))
@@ -356,17 +363,19 @@ int main(int argc, char **argv)
else if (!strcasecmp(argv[i], "PTPV2"))
ptpv2 = 1;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_TX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_TX_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RX_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RX_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RX_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_SOFTWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_SOFTWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_SOFTWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_RAW_HARDWARE"))
- so_timestamping_flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ so_timestamping.flags |= SOF_TIMESTAMPING_RAW_HARDWARE;
+ else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_BIND_PHC"))
+ so_timestamping.flags |= SOF_TIMESTAMPING_BIND_PHC;
else
usage(argv[i]);
}
@@ -385,10 +394,10 @@ int main(int argc, char **argv)
hwtstamp.ifr_data = (void *)&hwconfig;
memset(&hwconfig, 0, sizeof(hwconfig));
hwconfig.tx_type =
- (so_timestamping_flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
+ (so_timestamping.flags & SOF_TIMESTAMPING_TX_HARDWARE) ?
HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
hwconfig.rx_filter =
- (so_timestamping_flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
+ (so_timestamping.flags & SOF_TIMESTAMPING_RX_HARDWARE) ?
ptpv2 ? HWTSTAMP_FILTER_PTP_V2_L4_SYNC :
HWTSTAMP_FILTER_PTP_V1_L4_SYNC : HWTSTAMP_FILTER_NONE;
hwconfig_requested = hwconfig;
@@ -413,6 +422,9 @@ int main(int argc, char **argv)
sizeof(struct sockaddr_in)) < 0)
bail("bind");
+ if (setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, interface, if_len))
+ bail("bind device");
+
/* set multicast group for outgoing packets */
inet_aton("224.0.1.130", &iaddr); /* alternate PTP domain 1 */
addr.sin_addr = iaddr;
@@ -444,10 +456,9 @@ int main(int argc, char **argv)
&enabled, sizeof(enabled)) < 0)
bail("setsockopt SO_TIMESTAMPNS");
- if (so_timestamping_flags &&
- setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING,
- &so_timestamping_flags,
- sizeof(so_timestamping_flags)) < 0)
+ if (so_timestamping.flags &&
+ setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping,
+ sizeof(so_timestamping)) < 0)
bail("setsockopt SO_TIMESTAMPING");
/* request IP_PKTINFO for debugging purposes */
@@ -468,14 +479,18 @@ int main(int argc, char **argv)
else
printf("SO_TIMESTAMPNS %d\n", val);
- if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &val, &len) < 0) {
+ len = sizeof(so_timestamping_get);
+ if (getsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &so_timestamping_get,
+ &len) < 0) {
printf("%s: %s\n", "getsockopt SO_TIMESTAMPING",
strerror(errno));
} else {
- printf("SO_TIMESTAMPING %d\n", val);
- if (val != so_timestamping_flags)
- printf(" not the expected value %d\n",
- so_timestamping_flags);
+ printf("SO_TIMESTAMPING flags %d, bind phc %d\n",
+ so_timestamping_get.flags, so_timestamping_get.bind_phc);
+ if (so_timestamping_get.flags != so_timestamping.flags ||
+ so_timestamping_get.bind_phc != so_timestamping.bind_phc)
+ printf(" not expected, flags %d, bind phc %d\n",
+ so_timestamping.flags, so_timestamping.bind_phc);
}
/* send packets forever every five seconds */
diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile
index cd6430b39982..8748199ac109 100644
--- a/tools/testing/selftests/netfilter/Makefile
+++ b/tools/testing/selftests/netfilter/Makefile
@@ -5,7 +5,7 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \
conntrack_icmp_related.sh nft_flowtable.sh ipvs.sh \
nft_concat_range.sh nft_conntrack_helper.sh \
nft_queue.sh nft_meta.sh nf_nat_edemux.sh \
- ipip-conntrack-mtu.sh
+ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh
LDLIBS = -lmnl
TEST_GEN_FILES = nf-queue
diff --git a/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh b/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh
new file mode 100755
index 000000000000..e7d7bf13cff5
--- /dev/null
+++ b/tools/testing/selftests/netfilter/conntrack_tcp_unreplied.sh
@@ -0,0 +1,167 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check that UNREPLIED tcp conntrack will eventually timeout.
+#
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+ret=0
+
+waittime=20
+sfx=$(mktemp -u "XXXXXXXX")
+ns1="ns1-$sfx"
+ns2="ns2-$sfx"
+
+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() {
+ ip netns pids $ns1 | xargs kill 2>/dev/null
+ ip netns pids $ns2 | xargs kill 2>/dev/null
+
+ ip netns del $ns1
+ ip netns del $ns2
+}
+
+ipv4() {
+ echo -n 192.168.$1.2
+}
+
+check_counter()
+{
+ ns=$1
+ name=$2
+ expect=$3
+ local lret=0
+
+ cnt=$(ip netns exec $ns2 nft list counter inet filter "$name" | grep -q "$expect")
+ if [ $? -ne 0 ]; then
+ echo "ERROR: counter $name in $ns2 has unexpected value (expected $expect)" 1>&2
+ ip netns exec $ns2 nft list counter inet filter "$name" 1>&2
+ lret=1
+ fi
+
+ return $lret
+}
+
+# Create test namespaces
+ip netns add $ns1 || exit 1
+
+trap cleanup EXIT
+
+ip netns add $ns2 || exit 1
+
+# Connect the namespace to the host using a veth pair
+ip -net $ns1 link add name veth1 type veth peer name veth2
+ip -net $ns1 link set netns $ns2 dev veth2
+
+ip -net $ns1 link set up dev lo
+ip -net $ns2 link set up dev lo
+ip -net $ns1 link set up dev veth1
+ip -net $ns2 link set up dev veth2
+
+ip -net $ns2 addr add 10.11.11.2/24 dev veth2
+ip -net $ns2 route add default via 10.11.11.1
+
+ip netns exec $ns2 sysctl -q net.ipv4.conf.veth2.forwarding=1
+
+# add a rule inside NS so we enable conntrack
+ip netns exec $ns1 iptables -A INPUT -m state --state established,related -j ACCEPT
+
+ip -net $ns1 addr add 10.11.11.1/24 dev veth1
+ip -net $ns1 route add 10.99.99.99 via 10.11.11.2
+
+# Check connectivity works
+ip netns exec $ns1 ping -q -c 2 10.11.11.2 >/dev/null || exit 1
+
+ip netns exec $ns2 nc -l -p 8080 < /dev/null &
+
+# however, conntrack entries are there
+
+ip netns exec $ns2 nft -f - <<EOF
+table inet filter {
+ counter connreq { }
+ counter redir { }
+ chain input {
+ type filter hook input priority 0; policy accept;
+ ct state new tcp flags syn ip daddr 10.99.99.99 tcp dport 80 counter name "connreq" accept
+ ct state new ct status dnat tcp dport 8080 counter name "redir" accept
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not load nft rules"
+ exit 1
+fi
+
+ip netns exec $ns2 sysctl -q net.netfilter.nf_conntrack_tcp_timeout_syn_sent=10
+
+echo "INFO: connect $ns1 -> $ns2 to the virtual ip"
+ip netns exec $ns1 bash -c 'while true ; do
+ nc -p 60000 10.99.99.99 80
+ sleep 1
+ done' &
+
+sleep 1
+
+ip netns exec $ns2 nft -f - <<EOF
+table inet nat {
+ chain prerouting {
+ type nat hook prerouting priority 0; policy accept;
+ ip daddr 10.99.99.99 tcp dport 80 redirect to :8080
+ }
+}
+EOF
+if [ $? -ne 0 ]; then
+ echo "ERROR: Could not load nat redirect"
+ exit 1
+fi
+
+count=$(ip netns exec $ns2 conntrack -L -p tcp --dport 80 2>/dev/null | wc -l)
+if [ $count -eq 0 ]; then
+ echo "ERROR: $ns2 did not pick up tcp connection from peer"
+ exit 1
+fi
+
+echo "INFO: NAT redirect added in ns $ns2, waiting for $waittime seconds for nat to take effect"
+for i in $(seq 1 $waittime); do
+ echo -n "."
+
+ sleep 1
+
+ count=$(ip netns exec $ns2 conntrack -L -p tcp --reply-port-src 8080 2>/dev/null | wc -l)
+ if [ $count -gt 0 ]; then
+ echo
+ echo "PASS: redirection took effect after $i seconds"
+ break
+ fi
+
+ m=$((i%20))
+ if [ $m -eq 0 ]; then
+ echo " waited for $i seconds"
+ fi
+done
+
+expect="packets 1 bytes 60"
+check_counter "$ns2" "redir" "$expect"
+if [ $? -ne 0 ]; then
+ ret=1
+fi
+
+if [ $ret -eq 0 ];then
+ echo "PASS: redirection counter has expected values"
+else
+ echo "ERROR: no tcp connection was redirected"
+fi
+
+exit $ret
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
index dee7a3d6c5a5..92bbc5a15c39 100644
--- a/tools/testing/selftests/sgx/sigstruct.c
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -55,10 +55,27 @@ static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m,
return true;
}
+static void reverse_bytes(void *data, int length)
+{
+ int i = 0;
+ int j = length - 1;
+ uint8_t temp;
+ uint8_t *ptr = data;
+
+ while (i < j) {
+ temp = ptr[i];
+ ptr[i] = ptr[j];
+ ptr[j] = temp;
+ i++;
+ j--;
+ }
+}
+
static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1,
uint8_t *q2)
{
struct q1q2_ctx ctx;
+ int len;
if (!alloc_q1q2_ctx(s, m, &ctx)) {
fprintf(stderr, "Not enough memory for Q1Q2 calculation\n");
@@ -89,8 +106,10 @@ static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1,
goto out;
}
- BN_bn2bin(ctx.q1, q1);
- BN_bn2bin(ctx.q2, q2);
+ len = BN_bn2bin(ctx.q1, q1);
+ reverse_bytes(q1, len);
+ len = BN_bn2bin(ctx.q2, q2);
+ reverse_bytes(q2, len);
free_q1q2_ctx(&ctx);
return true;
@@ -152,22 +171,6 @@ static RSA *gen_sign_key(void)
return key;
}
-static void reverse_bytes(void *data, int length)
-{
- int i = 0;
- int j = length - 1;
- uint8_t temp;
- uint8_t *ptr = data;
-
- while (i < j) {
- temp = ptr[i];
- ptr[i] = ptr[j];
- ptr[j] = temp;
- i++;
- j--;
- }
-}
-
enum mrtags {
MRECREATE = 0x0045544145524345,
MREADD = 0x0000000044444145,
@@ -367,8 +370,6 @@ bool encl_measure(struct encl *encl)
/* BE -> LE */
reverse_bytes(sigstruct->signature, SGX_MODULUS_SIZE);
reverse_bytes(sigstruct->modulus, SGX_MODULUS_SIZE);
- reverse_bytes(sigstruct->q1, SGX_MODULUS_SIZE);
- reverse_bytes(sigstruct->q2, SGX_MODULUS_SIZE);
EVP_MD_CTX_destroy(ctx);
RSA_free(key);
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index e363bdaff59d..2ea438e6b8b1 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -210,8 +210,10 @@ static void anon_release_pages(char *rel_area)
static void anon_allocate_area(void **alloc_area)
{
- if (posix_memalign(alloc_area, page_size, nr_pages * page_size))
- err("posix_memalign() failed");
+ *alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
+ MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (*alloc_area == MAP_FAILED)
+ err("mmap of anonymous memory failed");
}
static void noop_alias_mapping(__u64 *start, size_t len, unsigned long offset)