summaryrefslogtreecommitdiff
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rwxr-xr-xtools/testing/ktest/ktest.pl2
-rw-r--r--tools/testing/kunit/kunit_kernel.py24
-rw-r--r--tools/testing/kunit/kunit_parser.py7
-rw-r--r--tools/testing/nvdimm/test/nfit.c103
-rw-r--r--tools/testing/scatterlist/main.c66
-rw-r--r--tools/testing/selftests/Makefile6
-rw-r--r--tools/testing/selftests/android/Makefile39
-rw-r--r--tools/testing/selftests/android/config5
-rw-r--r--tools/testing/selftests/android/ion/Makefile20
-rw-r--r--tools/testing/selftests/android/ion/README101
-rw-r--r--tools/testing/selftests/android/ion/ion.h134
-rwxr-xr-xtools/testing/selftests/android/ion/ion_test.sh58
-rw-r--r--tools/testing/selftests/android/ion/ionapp_export.c127
-rw-r--r--tools/testing/selftests/android/ion/ionapp_import.c79
-rw-r--r--tools/testing/selftests/android/ion/ionmap_test.c136
-rw-r--r--tools/testing/selftests/android/ion/ionutils.c253
-rw-r--r--tools/testing/selftests/android/ion/ionutils.h55
-rw-r--r--tools/testing/selftests/android/ion/ipcsocket.c227
-rw-r--r--tools/testing/selftests/android/ion/ipcsocket.h35
-rwxr-xr-xtools/testing/selftests/android/run.sh3
-rw-r--r--tools/testing/selftests/bpf/.gitignore3
-rw-r--r--tools/testing/selftests/bpf/Makefile73
-rw-r--r--tools/testing/selftests/bpf/README.rst33
-rw-r--r--tools/testing/selftests/bpf/bpf_tcp_helpers.h1
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/.gitignore6
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/Makefile20
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h36
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c52
-rw-r--r--tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h14
-rw-r--r--tools/testing/selftests/bpf/btf_helpers.c259
-rw-r--r--tools/testing/selftests/bpf/btf_helpers.h19
-rw-r--r--tools/testing/selftests/bpf/config5
-rwxr-xr-xtools/testing/selftests/bpf/ima_setup.sh123
-rw-r--r--tools/testing/selftests/bpf/prog_tests/align.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/bpf_iter.c118
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf.c40
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c325
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_split.c99
-rw-r--r--tools/testing/selftests/bpf/prog_tests/btf_write.c43
-rw-r--r--tools/testing/selftests/bpf/prog_tests/core_reloc.c80
-rw-r--r--tools/testing/selftests/bpf/prog_tests/hash_large_key.c43
-rw-r--r--tools/testing/selftests/bpf/prog_tests/module_attach.c62
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf.c8
-rw-r--r--tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c2
-rw-r--r--tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c135
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c12
-rw-r--r--tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c145
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c116
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_ima.c74
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_local_storage.c212
-rw-r--r--tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c41
-rw-r--r--tools/testing/selftests/bpf/progs/bind4_prog.c102
-rw-r--r--tools/testing/selftests/bpf/progs/bind6_prog.c119
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_flow.c2
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c2
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c65
-rw-r--r--tools/testing/selftests/bpf/progs/bpf_iter_task.c3
-rw-r--r--tools/testing/selftests/bpf/progs/bprm_opts.c34
-rw-r--r--tools/testing/selftests/bpf/progs/core_reloc_types.h17
-rw-r--r--tools/testing/selftests/bpf/progs/ima.c28
-rw-r--r--tools/testing/selftests/bpf/progs/local_storage.c103
-rw-r--r--tools/testing/selftests/bpf/progs/map_ptr_kern.c7
-rw-r--r--tools/testing/selftests/bpf/progs/profiler.inc.h2
-rw-r--r--tools/testing/selftests/bpf/progs/skb_pkt_end.c54
-rw-r--r--tools/testing/selftests/bpf/progs/test_core_reloc_module.c104
-rw-r--r--tools/testing/selftests/bpf/progs/test_hash_large_key.c44
-rw-r--r--tools/testing/selftests/bpf/progs/test_module_attach.c77
-rw-r--r--tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c29
-rw-r--r--tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c95
-rw-r--r--tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c117
-rw-r--r--tools/testing/selftests/bpf/progs/test_tunnel_kern.c42
-rwxr-xr-xtools/testing/selftests/bpf/tcp_client.py50
-rwxr-xr-xtools/testing/selftests/bpf/tcp_server.py80
-rw-r--r--tools/testing/selftests/bpf/test_maps.c3
-rwxr-xr-xtools/testing/selftests/bpf/test_offload.py53
-rw-r--r--tools/testing/selftests/bpf/test_progs.c75
-rw-r--r--tools/testing/selftests/bpf/test_progs.h12
-rw-r--r--tools/testing/selftests/bpf/test_sock_addr.c196
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c36
-rw-r--r--tools/testing/selftests/bpf/test_tcpbpf.h4
-rw-r--r--tools/testing/selftests/bpf/test_tcpbpf_user.c165
-rwxr-xr-xtools/testing/selftests/bpf/test_tunnel.sh43
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c44
-rwxr-xr-xtools/testing/selftests/bpf/test_xsk.sh259
-rw-r--r--tools/testing/selftests/bpf/verifier/array_access.c2
-rw-r--r--tools/testing/selftests/bpf/verifier/bounds.c41
-rw-r--r--tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c7
-rw-r--r--tools/testing/selftests/bpf/verifier/ctx_skb.c42
-rw-r--r--tools/testing/selftests/bpf/verifier/direct_value_access.c3
-rw-r--r--tools/testing/selftests/bpf/verifier/map_ptr.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/raw_tp_writable.c1
-rw-r--r--tools/testing/selftests/bpf/verifier/ref_tracking.c4
-rw-r--r--tools/testing/selftests/bpf/verifier/regalloc.c8
-rw-r--r--tools/testing/selftests/bpf/verifier/unpriv.c5
-rw-r--r--tools/testing/selftests/bpf/verifier/wide_access.c46
-rw-r--r--tools/testing/selftests/bpf/xdpxceiver.c1074
-rw-r--r--tools/testing/selftests/bpf/xdpxceiver.h160
-rwxr-xr-xtools/testing/selftests/bpf/xsk_prereqs.sh135
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.c4
-rw-r--r--tools/testing/selftests/clone3/Makefile2
-rw-r--r--tools/testing/selftests/core/close_range_test.c74
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh36
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh296
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh251
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh77
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh66
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/ethtool-coalesce.sh132
-rw-r--r--tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh53
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh63
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh85
-rwxr-xr-xtools/testing/selftests/drivers/net/netdevsim/nexthop.sh436
-rw-r--r--tools/testing/selftests/gpio/Makefile25
-rw-r--r--tools/testing/selftests/intel_pstate/aperf.c22
-rw-r--r--tools/testing/selftests/kvm/set_memory_region_test.c17
-rw-r--r--tools/testing/selftests/lkdtm/tests.txt1
-rw-r--r--tools/testing/selftests/memfd/fuse_test.c2
-rw-r--r--tools/testing/selftests/memfd/memfd_test.c2
-rw-r--r--tools/testing/selftests/net/Makefile1
-rwxr-xr-xtools/testing/selftests/net/bareudp.sh546
-rw-r--r--tools/testing/selftests/net/config7
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh95
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile1
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_igmp.sh485
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_mld.sh558
-rw-r--r--tools/testing/selftests/net/forwarding/config3
-rwxr-xr-xtools/testing/selftests/net/forwarding/gre_multipath_nh.sh356
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh107
-rwxr-xr-xtools/testing/selftests/net/forwarding/q_in_vni.sh347
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_mpath_nh.sh70
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_nh.sh160
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_mpls_l2vpn.sh192
-rw-r--r--tools/testing/selftests/net/mptcp/config10
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh292
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh79
-rw-r--r--tools/testing/selftests/net/psock_fanout.c72
-rwxr-xr-xtools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh494
-rwxr-xr-xtools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh502
-rwxr-xr-xtools/testing/selftests/net/test_vxlan_under_vrf.sh2
-rw-r--r--tools/testing/selftests/net/timestamping.c47
-rw-r--r--tools/testing/selftests/net/tls.c40
-rw-r--r--tools/testing/selftests/net/udpgso_bench_rx.c3
-rw-r--r--tools/testing/selftests/openat2/openat2_test.c8
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/console-badness.sh3
-rw-r--r--tools/testing/selftests/rcutorture/bin/functions.sh1
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-check-branches.sh5
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh19
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh29
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-t3
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-u3
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE016
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE026
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon3
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TRACE0115
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01.boot1
-rw-r--r--tools/testing/selftests/rseq/param_test.c4
-rwxr-xr-xtools/testing/selftests/run_kselftest.sh2
-rw-r--r--tools/testing/selftests/seccomp/config1
-rw-r--r--tools/testing/selftests/seccomp/seccomp_benchmark.c151
-rw-r--r--tools/testing/selftests/seccomp/settings2
-rw-r--r--tools/testing/selftests/sgx/.gitignore2
-rw-r--r--tools/testing/selftests/sgx/Makefile57
-rw-r--r--tools/testing/selftests/sgx/call.S44
-rw-r--r--tools/testing/selftests/sgx/defines.h21
-rw-r--r--tools/testing/selftests/sgx/load.c277
-rw-r--r--tools/testing/selftests/sgx/main.c246
-rw-r--r--tools/testing/selftests/sgx/main.h41
-rw-r--r--tools/testing/selftests/sgx/sign_key.S12
-rw-r--r--tools/testing/selftests/sgx/sign_key.pem39
-rw-r--r--tools/testing/selftests/sgx/sigstruct.c381
-rw-r--r--tools/testing/selftests/sgx/test_encl.c20
-rw-r--r--tools/testing/selftests/sgx/test_encl.lds40
-rw-r--r--tools/testing/selftests/sgx/test_encl_bootstrap.S89
-rw-r--r--tools/testing/selftests/syscall_user_dispatch/.gitignore (renamed from tools/testing/selftests/android/ion/.gitignore)5
-rw-r--r--tools/testing/selftests/syscall_user_dispatch/Makefile9
-rw-r--r--tools/testing/selftests/syscall_user_dispatch/config1
-rw-r--r--tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c200
-rw-r--r--tools/testing/selftests/syscall_user_dispatch/sud_test.c310
-rw-r--r--tools/testing/selftests/tc-testing/config1
-rw-r--r--tools/testing/selftests/timens/procfs.c58
-rw-r--r--tools/testing/selftests/vDSO/Makefile16
-rw-r--r--tools/testing/selftests/vDSO/vdso_config.h92
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_abi.c244
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_clock_getres.c124
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_correctness.c (renamed from tools/testing/selftests/x86/test_vdso.c)115
-rw-r--r--tools/testing/selftests/vm/.gitignore4
-rw-r--r--tools/testing/selftests/vm/Makefile43
-rw-r--r--tools/testing/selftests/vm/check_config.sh31
-rw-r--r--tools/testing/selftests/vm/config2
-rw-r--r--tools/testing/selftests/vm/gup_benchmark.c143
-rw-r--r--tools/testing/selftests/vm/gup_test.c194
-rw-r--r--tools/testing/selftests/vm/hmm-tests.c10
-rw-r--r--tools/testing/selftests/vm/mremap_test.c344
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests43
-rw-r--r--tools/testing/selftests/vm/userfaultfd.c123
-rw-r--r--tools/testing/selftests/x86/Makefile2
-rw-r--r--tools/testing/selftests/x86/fsgsbase.c12
-rw-r--r--tools/testing/selftests/x86/raw_syscall_helper_32.S2
-rw-r--r--tools/testing/selftests/x86/thunks.S2
201 files changed, 14307 insertions, 2755 deletions
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index cb16d2aac51c..54188ee16c48 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -2040,7 +2040,7 @@ sub reboot_to {
if ($reboot_type eq "grub") {
run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch)'";
- } elsif ($reboot_type eq "grub2") {
+ } elsif (($reboot_type eq "grub2") or ($reboot_type eq "grub2bls")) {
run_ssh "$grub_reboot $grub_number";
} elsif ($reboot_type eq "syslinux") {
run_ssh "$syslinux --once \\\"$syslinux_label\\\" $syslinux_path";
diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py
index 2e3cc0fac726..57c1724b7e5d 100644
--- a/tools/testing/kunit/kunit_kernel.py
+++ b/tools/testing/kunit/kunit_kernel.py
@@ -23,6 +23,11 @@ DEFAULT_KUNITCONFIG_PATH = 'arch/um/configs/kunit_defconfig'
BROKEN_ALLCONFIG_PATH = 'tools/testing/kunit/configs/broken_on_uml.config'
OUTFILE_PATH = 'test.log'
+def get_file_path(build_dir, default):
+ if build_dir:
+ default = os.path.join(build_dir, default)
+ return default
+
class ConfigError(Exception):
"""Represents an error trying to configure the Linux kernel."""
@@ -97,9 +102,7 @@ class LinuxSourceTreeOperations(object):
def linux_bin(self, params, timeout, build_dir):
"""Runs the Linux UML binary. Must be named 'linux'."""
- linux_bin = './linux'
- if build_dir:
- linux_bin = os.path.join(build_dir, 'linux')
+ linux_bin = get_file_path(build_dir, 'linux')
outfile = get_outfile_path(build_dir)
with open(outfile, 'w') as output:
process = subprocess.Popen([linux_bin] + params,
@@ -108,22 +111,13 @@ class LinuxSourceTreeOperations(object):
process.wait(timeout)
def get_kconfig_path(build_dir):
- kconfig_path = KCONFIG_PATH
- if build_dir:
- kconfig_path = os.path.join(build_dir, KCONFIG_PATH)
- return kconfig_path
+ return get_file_path(build_dir, KCONFIG_PATH)
def get_kunitconfig_path(build_dir):
- kunitconfig_path = KUNITCONFIG_PATH
- if build_dir:
- kunitconfig_path = os.path.join(build_dir, KUNITCONFIG_PATH)
- return kunitconfig_path
+ return get_file_path(build_dir, KUNITCONFIG_PATH)
def get_outfile_path(build_dir):
- outfile_path = OUTFILE_PATH
- if build_dir:
- outfile_path = os.path.join(build_dir, OUTFILE_PATH)
- return outfile_path
+ return get_file_path(build_dir, OUTFILE_PATH)
class LinuxSourceTree(object):
"""Represents a Linux kernel source tree with KUnit tests."""
diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py
index bbfe1b4e4c1c..6614ec4d0898 100644
--- a/tools/testing/kunit/kunit_parser.py
+++ b/tools/testing/kunit/kunit_parser.py
@@ -135,8 +135,8 @@ def parse_ok_not_ok_test_case(lines: List[str], test_case: TestCase) -> bool:
else:
return False
-SUBTEST_DIAGNOSTIC = re.compile(r'^[\s]+# .*?: (.*)$')
-DIAGNOSTIC_CRASH_MESSAGE = 'kunit test case crashed!'
+SUBTEST_DIAGNOSTIC = re.compile(r'^[\s]+# (.*)$')
+DIAGNOSTIC_CRASH_MESSAGE = re.compile(r'^[\s]+# .*?: kunit test case crashed!$')
def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool:
save_non_diagnositic(lines, test_case)
@@ -146,7 +146,8 @@ def parse_diagnostic(lines: List[str], test_case: TestCase) -> bool:
match = SUBTEST_DIAGNOSTIC.match(line)
if match:
test_case.log.append(lines.pop(0))
- if match.group(1) == DIAGNOSTIC_CRASH_MESSAGE:
+ crash_match = DIAGNOSTIC_CRASH_MESSAGE.match(line)
+ if crash_match:
test_case.status = TestStatus.TEST_CRASHED
return True
else:
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 2ac0fff6dad8..9b185bf82da8 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -23,7 +23,6 @@
#include "nfit_test.h"
#include "../watermark.h"
-#include <asm/copy_mc_test.h>
#include <asm/mce.h>
/*
@@ -3284,107 +3283,6 @@ static struct platform_driver nfit_test_driver = {
.id_table = nfit_test_id,
};
-static char copy_mc_buf[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
-
-enum INJECT {
- INJECT_NONE,
- INJECT_SRC,
- INJECT_DST,
-};
-
-static void copy_mc_test_init(char *dst, char *src, size_t size)
-{
- size_t i;
-
- memset(dst, 0xff, size);
- for (i = 0; i < size; i++)
- src[i] = (char) i;
-}
-
-static bool copy_mc_test_validate(unsigned char *dst, unsigned char *src,
- size_t size, unsigned long rem)
-{
- size_t i;
-
- for (i = 0; i < size - rem; i++)
- if (dst[i] != (unsigned char) i) {
- pr_info_once("%s:%d: offset: %zd got: %#x expect: %#x\n",
- __func__, __LINE__, i, dst[i],
- (unsigned char) i);
- return false;
- }
- for (i = size - rem; i < size; i++)
- if (dst[i] != 0xffU) {
- pr_info_once("%s:%d: offset: %zd got: %#x expect: 0xff\n",
- __func__, __LINE__, i, dst[i]);
- return false;
- }
- return true;
-}
-
-void copy_mc_test(void)
-{
- char *inject_desc[] = { "none", "source", "destination" };
- enum INJECT inj;
-
- if (IS_ENABLED(CONFIG_COPY_MC_TEST)) {
- pr_info("%s: run...\n", __func__);
- } else {
- pr_info("%s: disabled, skip.\n", __func__);
- return;
- }
-
- for (inj = INJECT_NONE; inj <= INJECT_DST; inj++) {
- int i;
-
- pr_info("%s: inject: %s\n", __func__, inject_desc[inj]);
- for (i = 0; i < 512; i++) {
- unsigned long expect, rem;
- void *src, *dst;
- bool valid;
-
- switch (inj) {
- case INJECT_NONE:
- copy_mc_inject_src(NULL);
- copy_mc_inject_dst(NULL);
- dst = &copy_mc_buf[2048];
- src = &copy_mc_buf[1024 - i];
- expect = 0;
- break;
- case INJECT_SRC:
- copy_mc_inject_src(&copy_mc_buf[1024]);
- copy_mc_inject_dst(NULL);
- dst = &copy_mc_buf[2048];
- src = &copy_mc_buf[1024 - i];
- expect = 512 - i;
- break;
- case INJECT_DST:
- copy_mc_inject_src(NULL);
- copy_mc_inject_dst(&copy_mc_buf[2048]);
- dst = &copy_mc_buf[2048 - i];
- src = &copy_mc_buf[1024];
- expect = 512 - i;
- break;
- }
-
- copy_mc_test_init(dst, src, 512);
- rem = copy_mc_fragile(dst, src, 512);
- valid = copy_mc_test_validate(dst, src, 512, expect);
- if (rem == expect && valid)
- continue;
- pr_info("%s: copy(%#lx, %#lx, %d) off: %d rem: %ld %s expect: %ld\n",
- __func__,
- ((unsigned long) dst) & ~PAGE_MASK,
- ((unsigned long ) src) & ~PAGE_MASK,
- 512, i, rem, valid ? "valid" : "bad",
- expect);
- }
- }
-
- copy_mc_inject_src(NULL);
- copy_mc_inject_dst(NULL);
-}
-
static __init int nfit_test_init(void)
{
int rc, i;
@@ -3393,7 +3291,6 @@ static __init int nfit_test_init(void)
libnvdimm_test();
acpi_nfit_test();
device_dax_test();
- copy_mc_test();
dax_pmem_test();
dax_pmem_core_test();
#ifdef CONFIG_DEV_DAX_PMEM_COMPAT
diff --git a/tools/testing/scatterlist/main.c b/tools/testing/scatterlist/main.c
index f561aed7c657..71c960dcd8a4 100644
--- a/tools/testing/scatterlist/main.c
+++ b/tools/testing/scatterlist/main.c
@@ -9,6 +9,7 @@ struct test {
int alloc_ret;
unsigned num_pages;
unsigned *pfn;
+ unsigned *pfn_app;
unsigned size;
unsigned int max_seg;
unsigned int expected_segments;
@@ -50,33 +51,41 @@ static void fail(struct test *test, struct sg_table *st, const char *cond)
int main(void)
{
- const unsigned int sgmax = SCATTERLIST_MAX_SEGMENT;
+ const unsigned int sgmax = UINT_MAX;
struct test *test, tests[] = {
- { -EINVAL, 1, pfn(0), PAGE_SIZE, 0, 1 },
- { 0, 1, pfn(0), PAGE_SIZE, PAGE_SIZE + 1, 1 },
- { 0, 1, pfn(0), PAGE_SIZE, sgmax + 1, 1 },
- { 0, 1, pfn(0), PAGE_SIZE, sgmax, 1 },
- { 0, 1, pfn(0), 1, sgmax, 1 },
- { 0, 2, pfn(0, 1), 2 * PAGE_SIZE, sgmax, 1 },
- { 0, 2, pfn(1, 0), 2 * PAGE_SIZE, sgmax, 2 },
- { 0, 3, pfn(0, 1, 2), 3 * PAGE_SIZE, sgmax, 1 },
- { 0, 3, pfn(0, 2, 1), 3 * PAGE_SIZE, sgmax, 3 },
- { 0, 3, pfn(0, 1, 3), 3 * PAGE_SIZE, sgmax, 2 },
- { 0, 3, pfn(1, 2, 4), 3 * PAGE_SIZE, sgmax, 2 },
- { 0, 3, pfn(1, 3, 4), 3 * PAGE_SIZE, sgmax, 2 },
- { 0, 4, pfn(0, 1, 3, 4), 4 * PAGE_SIZE, sgmax, 2 },
- { 0, 5, pfn(0, 1, 3, 4, 5), 5 * PAGE_SIZE, sgmax, 2 },
- { 0, 5, pfn(0, 1, 3, 4, 6), 5 * PAGE_SIZE, sgmax, 3 },
- { 0, 5, pfn(0, 1, 2, 3, 4), 5 * PAGE_SIZE, sgmax, 1 },
- { 0, 5, pfn(0, 1, 2, 3, 4), 5 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
- { 0, 6, pfn(0, 1, 2, 3, 4, 5), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
- { 0, 6, pfn(0, 2, 3, 4, 5, 6), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 4 },
- { 0, 6, pfn(0, 1, 3, 4, 5, 6), 6 * PAGE_SIZE, 2 * PAGE_SIZE, 3 },
- { 0, 0, NULL, 0, 0, 0 },
+ { -EINVAL, 1, pfn(0), NULL, PAGE_SIZE, 0, 1 },
+ { 0, 1, pfn(0), NULL, PAGE_SIZE, PAGE_SIZE + 1, 1 },
+ { 0, 1, pfn(0), NULL, PAGE_SIZE, sgmax + 1, 1 },
+ { 0, 1, pfn(0), NULL, PAGE_SIZE, sgmax, 1 },
+ { 0, 1, pfn(0), NULL, 1, sgmax, 1 },
+ { 0, 2, pfn(0, 1), NULL, 2 * PAGE_SIZE, sgmax, 1 },
+ { 0, 2, pfn(1, 0), NULL, 2 * PAGE_SIZE, sgmax, 2 },
+ { 0, 3, pfn(0, 1, 2), NULL, 3 * PAGE_SIZE, sgmax, 1 },
+ { 0, 3, pfn(0, 1, 2), NULL, 3 * PAGE_SIZE, sgmax, 1 },
+ { 0, 3, pfn(0, 1, 2), pfn(3, 4, 5), 3 * PAGE_SIZE, sgmax, 1 },
+ { 0, 3, pfn(0, 1, 2), pfn(4, 5, 6), 3 * PAGE_SIZE, sgmax, 2 },
+ { 0, 3, pfn(0, 2, 1), NULL, 3 * PAGE_SIZE, sgmax, 3 },
+ { 0, 3, pfn(0, 1, 3), NULL, 3 * PAGE_SIZE, sgmax, 2 },
+ { 0, 3, pfn(1, 2, 4), NULL, 3 * PAGE_SIZE, sgmax, 2 },
+ { 0, 3, pfn(1, 3, 4), NULL, 3 * PAGE_SIZE, sgmax, 2 },
+ { 0, 4, pfn(0, 1, 3, 4), NULL, 4 * PAGE_SIZE, sgmax, 2 },
+ { 0, 5, pfn(0, 1, 3, 4, 5), NULL, 5 * PAGE_SIZE, sgmax, 2 },
+ { 0, 5, pfn(0, 1, 3, 4, 6), NULL, 5 * PAGE_SIZE, sgmax, 3 },
+ { 0, 5, pfn(0, 1, 2, 3, 4), NULL, 5 * PAGE_SIZE, sgmax, 1 },
+ { 0, 5, pfn(0, 1, 2, 3, 4), NULL, 5 * PAGE_SIZE, 2 * PAGE_SIZE,
+ 3 },
+ { 0, 6, pfn(0, 1, 2, 3, 4, 5), NULL, 6 * PAGE_SIZE,
+ 2 * PAGE_SIZE, 3 },
+ { 0, 6, pfn(0, 2, 3, 4, 5, 6), NULL, 6 * PAGE_SIZE,
+ 2 * PAGE_SIZE, 4 },
+ { 0, 6, pfn(0, 1, 3, 4, 5, 6), pfn(7, 8, 9, 10, 11, 12),
+ 6 * PAGE_SIZE, 12 * PAGE_SIZE, 2 },
+ { 0, 0, NULL, NULL, 0, 0, 0 },
};
unsigned int i;
for (i = 0, test = tests; test->expected_segments; test++, i++) {
+ int left_pages = test->pfn_app ? test->num_pages : 0;
struct page *pages[MAX_PAGES];
struct sg_table st;
struct scatterlist *sg;
@@ -84,14 +93,23 @@ int main(void)
set_pages(pages, test->pfn, test->num_pages);
sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0,
- test->size, test->max_seg, NULL, 0, GFP_KERNEL);
+ test->size, test->max_seg, NULL, left_pages, GFP_KERNEL);
assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret);
if (test->alloc_ret)
continue;
+ if (test->pfn_app) {
+ set_pages(pages, test->pfn_app, test->num_pages);
+ sg = __sg_alloc_table_from_pages(&st, pages, test->num_pages, 0,
+ test->size, test->max_seg, sg, 0, GFP_KERNEL);
+
+ assert(PTR_ERR_OR_ZERO(sg) == test->alloc_ret);
+ }
+
VALIDATE(st.nents == test->expected_segments, &st, test);
- VALIDATE(st.orig_nents == test->expected_segments, &st, test);
+ if (!test->pfn_app)
+ VALIDATE(st.orig_nents == test->expected_segments, &st, test);
sg_free_table(&st);
}
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index d9c283503159..afbab4aeef3c 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -1,6 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-TARGETS = android
-TARGETS += arm64
+TARGETS = arm64
TARGETS += bpf
TARGETS += breakpoints
TARGETS += capabilities
@@ -50,12 +49,14 @@ TARGETS += openat2
TARGETS += rseq
TARGETS += rtc
TARGETS += seccomp
+TARGETS += sgx
TARGETS += sigaltstack
TARGETS += size
TARGETS += sparc64
TARGETS += splice
TARGETS += static_keys
TARGETS += sync
+TARGETS += syscall_user_dispatch
TARGETS += sysctl
TARGETS += tc-testing
TARGETS += timens
@@ -65,6 +66,7 @@ endif
TARGETS += tmpfs
TARGETS += tpm2
TARGETS += user
+TARGETS += vDSO
TARGETS += vm
TARGETS += x86
TARGETS += zram
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
deleted file mode 100644
index 9258306cafe9..000000000000
--- a/tools/testing/selftests/android/Makefile
+++ /dev/null
@@ -1,39 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-SUBDIRS := ion
-
-TEST_PROGS := run.sh
-
-.PHONY: all clean
-
-include ../lib.mk
-
-all:
- @for DIR in $(SUBDIRS); do \
- BUILD_TARGET=$(OUTPUT)/$$DIR; \
- mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
- #SUBDIR test prog name should be in the form: SUBDIR_test.sh \
- TEST=$$DIR"_test.sh"; \
- if [ -e $$DIR/$$TEST ]; then \
- rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \
- fi \
- done
-
-override define INSTALL_RULE
- mkdir -p $(INSTALL_PATH)
-install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
-
- @for SUBDIR in $(SUBDIRS); do \
- BUILD_TARGET=$(OUTPUT)/$$SUBDIR; \
- mkdir $$BUILD_TARGET -p; \
- $(MAKE) OUTPUT=$$BUILD_TARGET -C $$SUBDIR INSTALL_PATH=$(INSTALL_PATH)/$$SUBDIR install; \
- done;
-endef
-
-override define CLEAN
- @for DIR in $(SUBDIRS); do \
- BUILD_TARGET=$(OUTPUT)/$$DIR; \
- mkdir $$BUILD_TARGET -p; \
- make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
- done
-endef
diff --git a/tools/testing/selftests/android/config b/tools/testing/selftests/android/config
deleted file mode 100644
index b4ad748a9dd9..000000000000
--- a/tools/testing/selftests/android/config
+++ /dev/null
@@ -1,5 +0,0 @@
-CONFIG_ANDROID=y
-CONFIG_STAGING=y
-CONFIG_ION=y
-CONFIG_ION_SYSTEM_HEAP=y
-CONFIG_DRM_VGEM=y
diff --git a/tools/testing/selftests/android/ion/Makefile b/tools/testing/selftests/android/ion/Makefile
deleted file mode 100644
index 42b71f005332..000000000000
--- a/tools/testing/selftests/android/ion/Makefile
+++ /dev/null
@@ -1,20 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-
-INCLUDEDIR := -I. -I../../../../../drivers/staging/android/uapi/ -I../../../../../usr/include/
-CFLAGS := $(CFLAGS) $(INCLUDEDIR) -Wall -O2 -g
-
-TEST_GEN_FILES := ionapp_export ionapp_import ionmap_test
-
-all: $(TEST_GEN_FILES)
-
-$(TEST_GEN_FILES): ipcsocket.c ionutils.c
-
-TEST_PROGS := ion_test.sh
-
-KSFT_KHDR_INSTALL := 1
-top_srcdir = ../../../../..
-include ../../lib.mk
-
-$(OUTPUT)/ionapp_export: ionapp_export.c ipcsocket.c ionutils.c
-$(OUTPUT)/ionapp_import: ionapp_import.c ipcsocket.c ionutils.c
-$(OUTPUT)/ionmap_test: ionmap_test.c ionutils.c ipcsocket.c
diff --git a/tools/testing/selftests/android/ion/README b/tools/testing/selftests/android/ion/README
deleted file mode 100644
index 21783e9c451e..000000000000
--- a/tools/testing/selftests/android/ion/README
+++ /dev/null
@@ -1,101 +0,0 @@
-ION BUFFER SHARING UTILITY
-==========================
-File: ion_test.sh : Utility to test ION driver buffer sharing mechanism.
-Author: Pintu Kumar <pintu.ping@gmail.com>
-
-Introduction:
--------------
-This is a test utility to verify ION buffer sharing in user space
-between 2 independent processes.
-It uses unix domain socket (with SCM_RIGHTS) as IPC to transfer an FD to
-another process to share the same buffer.
-This utility demonstrates how ION buffer sharing can be implemented between
-two user space processes, using various heap types.
-The following heap types are supported by ION driver.
-ION_HEAP_TYPE_SYSTEM (0)
-ION_HEAP_TYPE_SYSTEM_CONTIG (1)
-ION_HEAP_TYPE_CARVEOUT (2)
-ION_HEAP_TYPE_CHUNK (3)
-ION_HEAP_TYPE_DMA (4)
-
-By default only the SYSTEM and SYSTEM_CONTIG heaps are supported.
-Each heap is associated with the respective heap id.
-This utility is designed in the form of client/server program.
-The server part (ionapp_export) is the exporter of the buffer.
-It is responsible for creating an ION client, allocating the buffer based on
-the heap id, writing some data to this buffer and then exporting the FD
-(associated with this buffer) to another process using socket IPC.
-This FD is called as buffer FD (which is different than the ION client FD).
-
-The client part (ionapp_import) is the importer of the buffer.
-It retrives the FD from the socket data and installs into its address space.
-This new FD internally points to the same kernel buffer.
-So first it reads the data that is stored in this buffer and prints it.
-Then it writes the different size of data (it could be different data) to the
-same buffer.
-Finally the buffer FD must be closed by both the exporter and importer.
-Thus the same kernel buffer is shared among two user space processes using
-ION driver and only one time allocation.
-
-Prerequisite:
--------------
-This utility works only if /dev/ion interface is present.
-The following configs needs to be enabled in kernel to include ion driver.
-CONFIG_ANDROID=y
-CONFIG_STAGING=y
-CONFIG_ION=y
-CONFIG_ION_SYSTEM_HEAP=y
-
-This utility requires to be run as root user.
-
-
-Compile and test:
------------------
-This utility is made to be run as part of kselftest framework in kernel.
-To compile and run using kselftest you can simply do the following from the
-kernel top directory.
-linux$ make TARGETS=android kselftest
-Or you can also use:
-linux$ make -C tools/testing/selftests TARGETS=android run_tests
-Using the selftest it can directly execute the ion_test.sh script to test the
-buffer sharing using ion system heap.
-Currently the heap size is hard coded as just 10 bytes inside this script.
-You need to be a root user to run under selftest.
-
-You can also compile and test manually using the following steps:
-ion$ make
-These will generate 2 executable: ionapp_export, ionapp_import
-Now you can run the export and import manually by specifying the heap type
-and the heap size.
-You can also directly execute the shell script to run the test automatically.
-Simply use the following command to run the test.
-ion$ sudo ./ion_test.sh
-
-Test Results:
--------------
-The utility is verified on Ubuntu-32 bit system with Linux Kernel 4.14.
-Here is the snapshot of the test result using kselftest.
-
-linux# make TARGETS=android kselftest
-heap_type: 0, heap_size: 10
---------------------------------------
-heap type: 0
- heap id: 1
-heap name: ion_system_heap
---------------------------------------
-Fill buffer content:
-0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
-Sharing fd: 6, Client fd: 5
-<ion_close_buffer_fd>: buffer release successfully....
-Received buffer fd: 4
-Read buffer content:
-0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0x0 0x0 0x0 0x0 0x0 0x0
-0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0 0x0
-Fill buffer content:
-0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
-0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd 0xfd
-0xfd 0xfd
-<ion_close_buffer_fd>: buffer release successfully....
-ion_test.sh: heap_type: 0 - [PASS]
-
-ion_test.sh: done
diff --git a/tools/testing/selftests/android/ion/ion.h b/tools/testing/selftests/android/ion/ion.h
deleted file mode 100644
index 33db23018abf..000000000000
--- a/tools/testing/selftests/android/ion/ion.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * ion.h
- *
- * Copyright (C) 2011 Google, Inc.
- */
-
-/* This file is copied from drivers/staging/android/uapi/ion.h
- * This local copy is required for the selftest to pass, when build
- * outside the kernel source tree.
- * Please keep this file in sync with its original file until the
- * ion driver is moved outside the staging tree.
- */
-
-#ifndef _UAPI_LINUX_ION_H
-#define _UAPI_LINUX_ION_H
-
-#include <linux/ioctl.h>
-#include <linux/types.h>
-
-/**
- * enum ion_heap_types - list of all possible types of heaps
- * @ION_HEAP_TYPE_SYSTEM: memory allocated via vmalloc
- * @ION_HEAP_TYPE_SYSTEM_CONTIG: memory allocated via kmalloc
- * @ION_HEAP_TYPE_CARVEOUT: memory allocated from a prereserved
- * carveout heap, allocations are physically
- * contiguous
- * @ION_HEAP_TYPE_DMA: memory allocated via DMA API
- * @ION_NUM_HEAPS: helper for iterating over heaps, a bit mask
- * is used to identify the heaps, so only 32
- * total heap types are supported
- */
-enum ion_heap_type {
- ION_HEAP_TYPE_SYSTEM,
- ION_HEAP_TYPE_SYSTEM_CONTIG,
- ION_HEAP_TYPE_CARVEOUT,
- ION_HEAP_TYPE_CHUNK,
- ION_HEAP_TYPE_DMA,
- ION_HEAP_TYPE_CUSTOM, /*
- * must be last so device specific heaps always
- * are at the end of this enum
- */
-};
-
-#define ION_NUM_HEAP_IDS (sizeof(unsigned int) * 8)
-
-/**
- * allocation flags - the lower 16 bits are used by core ion, the upper 16
- * bits are reserved for use by the heaps themselves.
- */
-
-/*
- * mappings of this buffer should be cached, ion will do cache maintenance
- * when the buffer is mapped for dma
- */
-#define ION_FLAG_CACHED 1
-
-/**
- * DOC: Ion Userspace API
- *
- * create a client by opening /dev/ion
- * most operations handled via following ioctls
- *
- */
-
-/**
- * struct ion_allocation_data - metadata passed from userspace for allocations
- * @len: size of the allocation
- * @heap_id_mask: mask of heap ids to allocate from
- * @flags: flags passed to heap
- * @handle: pointer that will be populated with a cookie to use to
- * refer to this allocation
- *
- * Provided by userspace as an argument to the ioctl
- */
-struct ion_allocation_data {
- __u64 len;
- __u32 heap_id_mask;
- __u32 flags;
- __u32 fd;
- __u32 unused;
-};
-
-#define MAX_HEAP_NAME 32
-
-/**
- * struct ion_heap_data - data about a heap
- * @name - first 32 characters of the heap name
- * @type - heap type
- * @heap_id - heap id for the heap
- */
-struct ion_heap_data {
- char name[MAX_HEAP_NAME];
- __u32 type;
- __u32 heap_id;
- __u32 reserved0;
- __u32 reserved1;
- __u32 reserved2;
-};
-
-/**
- * struct ion_heap_query - collection of data about all heaps
- * @cnt - total number of heaps to be copied
- * @heaps - buffer to copy heap data
- */
-struct ion_heap_query {
- __u32 cnt; /* Total number of heaps to be copied */
- __u32 reserved0; /* align to 64bits */
- __u64 heaps; /* buffer to be populated */
- __u32 reserved1;
- __u32 reserved2;
-};
-
-#define ION_IOC_MAGIC 'I'
-
-/**
- * DOC: ION_IOC_ALLOC - allocate memory
- *
- * Takes an ion_allocation_data struct and returns it with the handle field
- * populated with the opaque handle for the allocation.
- */
-#define ION_IOC_ALLOC _IOWR(ION_IOC_MAGIC, 0, \
- struct ion_allocation_data)
-
-/**
- * DOC: ION_IOC_HEAP_QUERY - information about available heaps
- *
- * Takes an ion_heap_query structure and populates information about
- * available Ion heaps.
- */
-#define ION_IOC_HEAP_QUERY _IOWR(ION_IOC_MAGIC, 8, \
- struct ion_heap_query)
-
-#endif /* _UAPI_LINUX_ION_H */
diff --git a/tools/testing/selftests/android/ion/ion_test.sh b/tools/testing/selftests/android/ion/ion_test.sh
deleted file mode 100755
index 69e676cfc94e..000000000000
--- a/tools/testing/selftests/android/ion/ion_test.sh
+++ /dev/null
@@ -1,58 +0,0 @@
-#!/bin/bash
-
-heapsize=4096
-TCID="ion_test.sh"
-errcode=0
-
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
-
-run_test()
-{
- heaptype=$1
- ./ionapp_export -i $heaptype -s $heapsize &
- sleep 1
- ./ionapp_import
- if [ $? -ne 0 ]; then
- echo "$TCID: heap_type: $heaptype - [FAIL]"
- errcode=1
- else
- echo "$TCID: heap_type: $heaptype - [PASS]"
- fi
- sleep 1
- echo ""
-}
-
-check_root()
-{
- uid=$(id -u)
- if [ $uid -ne 0 ]; then
- echo $TCID: must be run as root >&2
- exit $ksft_skip
- fi
-}
-
-check_device()
-{
- DEVICE=/dev/ion
- if [ ! -e $DEVICE ]; then
- echo $TCID: No $DEVICE device found >&2
- echo $TCID: May be CONFIG_ION is not set >&2
- exit $ksft_skip
- fi
-}
-
-main_function()
-{
- check_device
- check_root
-
- # ION_SYSTEM_HEAP TEST
- run_test 0
- # ION_SYSTEM_CONTIG_HEAP TEST
- run_test 1
-}
-
-main_function
-echo "$TCID: done"
-exit $errcode
diff --git a/tools/testing/selftests/android/ion/ionapp_export.c b/tools/testing/selftests/android/ion/ionapp_export.c
deleted file mode 100644
index 063b7830d1bd..000000000000
--- a/tools/testing/selftests/android/ion/ionapp_export.c
+++ /dev/null
@@ -1,127 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ionapp_export.c
- *
- * It is a user space utility to create and export android
- * ion memory buffer fd to another process using unix domain socket as IPC.
- * This acts like a server for ionapp_import(client).
- * So, this server has to be started first before the client.
- *
- * Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <errno.h>
-#include <sys/time.h>
-#include "ionutils.h"
-#include "ipcsocket.h"
-
-
-void print_usage(int argc, char *argv[])
-{
- printf("Usage: %s [-h <help>] [-i <heap id>] [-s <size in bytes>]\n",
- argv[0]);
-}
-
-int main(int argc, char *argv[])
-{
- int opt, ret, status, heapid;
- int sockfd, client_fd, shared_fd;
- unsigned char *map_buf;
- unsigned long map_len, heap_type, heap_size, flags;
- struct ion_buffer_info info;
- struct socket_info skinfo;
-
- if (argc < 2) {
- print_usage(argc, argv);
- return -1;
- }
-
- heap_size = 0;
- flags = 0;
- heap_type = ION_HEAP_TYPE_SYSTEM;
-
- while ((opt = getopt(argc, argv, "hi:s:")) != -1) {
- switch (opt) {
- case 'h':
- print_usage(argc, argv);
- exit(0);
- break;
- case 'i':
- heapid = atoi(optarg);
- switch (heapid) {
- case 0:
- heap_type = ION_HEAP_TYPE_SYSTEM;
- break;
- case 1:
- heap_type = ION_HEAP_TYPE_SYSTEM_CONTIG;
- break;
- default:
- printf("ERROR: heap type not supported\n");
- exit(1);
- }
- break;
- case 's':
- heap_size = atoi(optarg);
- break;
- default:
- print_usage(argc, argv);
- exit(1);
- break;
- }
- }
-
- if (heap_size <= 0) {
- printf("heap_size cannot be 0\n");
- print_usage(argc, argv);
- exit(1);
- }
-
- printf("heap_type: %ld, heap_size: %ld\n", heap_type, heap_size);
- info.heap_type = heap_type;
- info.heap_size = heap_size;
- info.flag_type = flags;
-
- /* This is server: open the socket connection first */
- /* Here; 1 indicates server or exporter */
- status = opensocket(&sockfd, SOCKET_NAME, 1);
- if (status < 0) {
- fprintf(stderr, "<%s>: Failed opensocket.\n", __func__);
- goto err_socket;
- }
- skinfo.sockfd = sockfd;
-
- ret = ion_export_buffer_fd(&info);
- if (ret < 0) {
- fprintf(stderr, "FAILED: ion_get_buffer_fd\n");
- goto err_export;
- }
- client_fd = info.ionfd;
- shared_fd = info.buffd;
- map_buf = info.buffer;
- map_len = info.buflen;
- write_buffer(map_buf, map_len);
-
- /* share ion buf fd with other user process */
- printf("Sharing fd: %d, Client fd: %d\n", shared_fd, client_fd);
- skinfo.datafd = shared_fd;
- skinfo.buflen = map_len;
-
- ret = socket_send_fd(&skinfo);
- if (ret < 0) {
- fprintf(stderr, "FAILED: socket_send_fd\n");
- goto err_send;
- }
-
-err_send:
-err_export:
- ion_close_buffer_fd(&info);
-
-err_socket:
- closesocket(sockfd, SOCKET_NAME);
-
- return 0;
-}
diff --git a/tools/testing/selftests/android/ion/ionapp_import.c b/tools/testing/selftests/android/ion/ionapp_import.c
deleted file mode 100644
index 54b580cb04f6..000000000000
--- a/tools/testing/selftests/android/ion/ionapp_import.c
+++ /dev/null
@@ -1,79 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * ionapp_import.c
- *
- * It is a user space utility to receive android ion memory buffer fd
- * over unix domain socket IPC that can be exported by ionapp_export.
- * This acts like a client for ionapp_export.
- *
- * Copyright (C) 2017 Pintu Kumar <pintu.ping@gmail.com>
- */
-
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <string.h>
-#include "ionutils.h"
-#include "ipcsocket.h"
-
-
-int main(void)
-{
- int ret, status;
- int sockfd, shared_fd;
- unsigned char *map_buf;
- unsigned long map_len;
- struct ion_buffer_info info;
- struct socket_info skinfo;
-
- /* This is the client part. Here 0 means client or importer */
- status = opensocket(&sockfd, SOCKET_NAME, 0);
- if (status < 0) {
- fprintf(stderr, "No exporter exists...\n");
- ret = status;
- goto err_socket;
- }
-
- skinfo.sockfd = sockfd;
-
- ret = socket_receive_fd(&skinfo);
- if (ret < 0) {
- fprintf(stderr, "Failed: socket_receive_fd\n");
- goto err_recv;
- }
-
- shared_fd = skinfo.datafd;
- printf("Received buffer fd: %d\n", shared_fd);
- if (shared_fd <= 0) {
- fprintf(stderr, "ERROR: improper buf fd\n");
- ret = -1;
- goto err_fd;
- }
-
- memset(&info, 0, sizeof(info));
- info.buffd = shared_fd;
- info.buflen = ION_BUFFER_LEN;
-
- ret = ion_import_buffer_fd(&info);
- if (ret < 0) {
- fprintf(stderr, "Failed: ion_use_buffer_fd\n");
- goto err_import;
- }
-
- map_buf = info.buffer;
- map_len = info.buflen;
- read_buffer(map_buf, map_len);
-
- /* Write probably new data to the same buffer again */
- map_len = ION_BUFFER_LEN;
- write_buffer(map_buf, map_len);
-
-err_import:
- ion_close_buffer_fd(&info);
-err_fd:
-err_recv:
-err_socket:
- closesocket(sockfd, SOCKET_NAME);
-
- return ret;
-}
diff --git a/tools/testing/selftests/android/ion/ionmap_test.c b/tools/testing/selftests/android/ion/ionmap_test.c
deleted file mode 100644
index dab36b06b37d..000000000000
--- a/tools/testing/selftests/android/ion/ionmap_test.c
+++ /dev/null
@@ -1,136 +0,0 @@
-#include <errno.h>
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdint.h>
-#include <string.h>
-#include <unistd.h>
-
-#include <sys/ioctl.h>
-#include <sys/types.h>
-#include <sys/stat.h>
-
-#include <linux/dma-buf.h>
-
-#include <drm/drm.h>
-
-#include "ion.h"
-#include "ionutils.h"
-
-int check_vgem(int fd)
-{
- drm_version_t version = { 0 };
- char name[5];
- int ret;
-
- version.name_len = 4;
- version.name = name;
-
- ret = ioctl(fd, DRM_IOCTL_VERSION, &version);
- if (ret)
- return 1;
-
- return strcmp(name, "vgem");
-}
-
-int open_vgem(void)
-{
- int i, fd;
- const char *drmstr = "/dev/dri/card";
-
- fd = -1;
- for (i = 0; i < 16; i++) {
- char name[80];
-
- sprintf(name, "%s%u", drmstr, i);
-
- fd = open(name, O_RDWR);
- if (fd < 0)
- continue;
-
- if (check_vgem(fd)) {
- close(fd);
- continue;
- } else {
- break;
- }
-
- }
- return fd;
-}
-
-int import_vgem_fd(int vgem_fd, int dma_buf_fd, uint32_t *handle)
-{
- struct drm_prime_handle import_handle = { 0 };
- int ret;
-
- import_handle.fd = dma_buf_fd;
- import_handle.flags = 0;
- import_handle.handle = 0;
-
- ret = ioctl(vgem_fd, DRM_IOCTL_PRIME_FD_TO_HANDLE, &import_handle);
- if (ret == 0)
- *handle = import_handle.handle;
- return ret;
-}
-
-void close_handle(int vgem_fd, uint32_t handle)
-{
- struct drm_gem_close close = { 0 };
-
- close.handle = handle;
- ioctl(vgem_fd, DRM_IOCTL_GEM_CLOSE, &close);
-}
-
-int main()
-{
- int ret, vgem_fd;
- struct ion_buffer_info info;
- uint32_t handle = 0;
- struct dma_buf_sync sync = { 0 };
-
- info.heap_type = ION_HEAP_TYPE_SYSTEM;
- info.heap_size = 4096;
- info.flag_type = ION_FLAG_CACHED;
-
- ret = ion_export_buffer_fd(&info);
- if (ret < 0) {
- printf("ion buffer alloc failed\n");
- return -1;
- }
-
- vgem_fd = open_vgem();
- if (vgem_fd < 0) {
- ret = vgem_fd;
- printf("Failed to open vgem\n");
- goto out_ion;
- }
-
- ret = import_vgem_fd(vgem_fd, info.buffd, &handle);
-
- if (ret < 0) {
- printf("Failed to import buffer\n");
- goto out_vgem;
- }
-
- sync.flags = DMA_BUF_SYNC_START | DMA_BUF_SYNC_RW;
- ret = ioctl(info.buffd, DMA_BUF_IOCTL_SYNC, &sync);
- if (ret)
- printf("sync start failed %d\n", errno);
-
- memset(info.buffer, 0xff, 4096);
-
- sync.flags = DMA_BUF_SYNC_END | DMA_BUF_SYNC_RW;
- ret = ioctl(info.buffd, DMA_BUF_IOCTL_SYNC, &sync);
- if (ret)
- printf("sync end failed %d\n", errno);
-
- close_handle(vgem_fd, handle);
- ret = 0;
-
-out_vgem:
- close(vgem_fd);
-out_ion:
- ion_close_buffer_fd(&info);
- printf("done.\n");
- return ret;
-}
diff --git a/tools/testing/selftests/android/ion/ionutils.c b/tools/testing/selftests/android/ion/ionutils.c
deleted file mode 100644
index 7d1d37c4ef6a..000000000000
--- a/tools/testing/selftests/android/ion/ionutils.c
+++ /dev/null
@@ -1,253 +0,0 @@
-#include <stdio.h>
-#include <string.h>
-#include <unistd.h>
-#include <fcntl.h>
-#include <errno.h>
-//#include <stdint.h>
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include "ionutils.h"
-#include "ipcsocket.h"
-
-
-void write_buffer(void *buffer, unsigned long len)
-{
- int i;
- unsigned char *ptr = (unsigned char *)buffer;
-
- if (!ptr) {
- fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
- return;
- }
-
- printf("Fill buffer content:\n");
- memset(ptr, 0xfd, len);
- for (i = 0; i < len; i++)
- printf("0x%x ", ptr[i]);
- printf("\n");
-}
-
-void read_buffer(void *buffer, unsigned long len)
-{
- int i;
- unsigned char *ptr = (unsigned char *)buffer;
-
- if (!ptr) {
- fprintf(stderr, "<%s>: Invalid buffer...\n", __func__);
- return;
- }
-
- printf("Read buffer content:\n");
- for (i = 0; i < len; i++)
- printf("0x%x ", ptr[i]);
- printf("\n");
-}
-
-int ion_export_buffer_fd(struct ion_buffer_info *ion_info)
-{
- int i, ret, ionfd, buffer_fd;
- unsigned int heap_id;
- unsigned long maplen;
- unsigned char *map_buffer;
- struct ion_allocation_data alloc_data;
- struct ion_heap_query query;
- struct ion_heap_data heap_data[MAX_HEAP_COUNT];
-
- if (!ion_info) {
- fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
- return -1;
- }
-
- /* Create an ION client */
- ionfd = open(ION_DEVICE, O_RDWR);
- if (ionfd < 0) {
- fprintf(stderr, "<%s>: Failed to open ion client: %s\n",
- __func__, strerror(errno));
- return -1;
- }
-
- memset(&query, 0, sizeof(query));
- query.cnt = MAX_HEAP_COUNT;
- query.heaps = (unsigned long int)&heap_data[0];
- /* Query ION heap_id_mask from ION heap */
- ret = ioctl(ionfd, ION_IOC_HEAP_QUERY, &query);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed: ION_IOC_HEAP_QUERY: %s\n",
- __func__, strerror(errno));
- goto err_query;
- }
-
- heap_id = MAX_HEAP_COUNT + 1;
- for (i = 0; i < query.cnt; i++) {
- if (heap_data[i].type == ion_info->heap_type) {
- heap_id = heap_data[i].heap_id;
- break;
- }
- }
-
- if (heap_id > MAX_HEAP_COUNT) {
- fprintf(stderr, "<%s>: ERROR: heap type does not exists\n",
- __func__);
- goto err_heap;
- }
-
- alloc_data.len = ion_info->heap_size;
- alloc_data.heap_id_mask = 1 << heap_id;
- alloc_data.flags = ion_info->flag_type;
-
- /* Allocate memory for this ION client as per heap_type */
- ret = ioctl(ionfd, ION_IOC_ALLOC, &alloc_data);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed: ION_IOC_ALLOC: %s\n",
- __func__, strerror(errno));
- goto err_alloc;
- }
-
- /* This will return a valid buffer fd */
- buffer_fd = alloc_data.fd;
- maplen = alloc_data.len;
-
- if (buffer_fd < 0 || maplen <= 0) {
- fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
- __func__, buffer_fd, maplen);
- goto err_fd_data;
- }
-
- /* Create memory mapped buffer for the buffer fd */
- map_buffer = (unsigned char *)mmap(NULL, maplen, PROT_READ|PROT_WRITE,
- MAP_SHARED, buffer_fd, 0);
- if (map_buffer == MAP_FAILED) {
- fprintf(stderr, "<%s>: Failed: mmap: %s\n",
- __func__, strerror(errno));
- goto err_mmap;
- }
-
- ion_info->ionfd = ionfd;
- ion_info->buffd = buffer_fd;
- ion_info->buffer = map_buffer;
- ion_info->buflen = maplen;
-
- return 0;
-
- munmap(map_buffer, maplen);
-
-err_fd_data:
-err_mmap:
- /* in case of error: close the buffer fd */
- if (buffer_fd)
- close(buffer_fd);
-
-err_query:
-err_heap:
-err_alloc:
- /* In case of error: close the ion client fd */
- if (ionfd)
- close(ionfd);
-
- return -1;
-}
-
-int ion_import_buffer_fd(struct ion_buffer_info *ion_info)
-{
- int buffd;
- unsigned char *map_buf;
- unsigned long map_len;
-
- if (!ion_info) {
- fprintf(stderr, "<%s>: Invalid ion info\n", __func__);
- return -1;
- }
-
- map_len = ion_info->buflen;
- buffd = ion_info->buffd;
-
- if (buffd < 0 || map_len <= 0) {
- fprintf(stderr, "<%s>: Invalid map data, fd: %d, len: %ld\n",
- __func__, buffd, map_len);
- goto err_buffd;
- }
-
- map_buf = (unsigned char *)mmap(NULL, map_len, PROT_READ|PROT_WRITE,
- MAP_SHARED, buffd, 0);
- if (map_buf == MAP_FAILED) {
- printf("<%s>: Failed - mmap: %s\n",
- __func__, strerror(errno));
- goto err_mmap;
- }
-
- ion_info->buffer = map_buf;
- ion_info->buflen = map_len;
-
- return 0;
-
-err_mmap:
- if (buffd)
- close(buffd);
-
-err_buffd:
- return -1;
-}
-
-void ion_close_buffer_fd(struct ion_buffer_info *ion_info)
-{
- if (ion_info) {
- /* unmap the buffer properly in the end */
- munmap(ion_info->buffer, ion_info->buflen);
- /* close the buffer fd */
- if (ion_info->buffd > 0)
- close(ion_info->buffd);
- /* Finally, close the client fd */
- if (ion_info->ionfd > 0)
- close(ion_info->ionfd);
- }
-}
-
-int socket_send_fd(struct socket_info *info)
-{
- int status;
- int fd, sockfd;
- struct socketdata skdata;
-
- if (!info) {
- fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
- return -1;
- }
-
- sockfd = info->sockfd;
- fd = info->datafd;
- memset(&skdata, 0, sizeof(skdata));
- skdata.data = fd;
- skdata.len = sizeof(skdata.data);
- status = sendtosocket(sockfd, &skdata);
- if (status < 0) {
- fprintf(stderr, "<%s>: Failed: sendtosocket\n", __func__);
- return -1;
- }
-
- return 0;
-}
-
-int socket_receive_fd(struct socket_info *info)
-{
- int status;
- int fd, sockfd;
- struct socketdata skdata;
-
- if (!info) {
- fprintf(stderr, "<%s>: Invalid socket info\n", __func__);
- return -1;
- }
-
- sockfd = info->sockfd;
- memset(&skdata, 0, sizeof(skdata));
- status = receivefromsocket(sockfd, &skdata);
- if (status < 0) {
- fprintf(stderr, "<%s>: Failed: receivefromsocket\n", __func__);
- return -1;
- }
-
- fd = (int)skdata.data;
- info->datafd = fd;
-
- return status;
-}
diff --git a/tools/testing/selftests/android/ion/ionutils.h b/tools/testing/selftests/android/ion/ionutils.h
deleted file mode 100644
index 9941eb858576..000000000000
--- a/tools/testing/selftests/android/ion/ionutils.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef __ION_UTILS_H
-#define __ION_UTILS_H
-
-#include "ion.h"
-
-#define SOCKET_NAME "ion_socket"
-#define ION_DEVICE "/dev/ion"
-
-#define ION_BUFFER_LEN 4096
-#define MAX_HEAP_COUNT ION_HEAP_TYPE_CUSTOM
-
-struct socket_info {
- int sockfd;
- int datafd;
- unsigned long buflen;
-};
-
-struct ion_buffer_info {
- int ionfd;
- int buffd;
- unsigned int heap_type;
- unsigned int flag_type;
- unsigned long heap_size;
- unsigned long buflen;
- unsigned char *buffer;
-};
-
-
-/* This is used to fill the data into the mapped buffer */
-void write_buffer(void *buffer, unsigned long len);
-
-/* This is used to read the data from the exported buffer */
-void read_buffer(void *buffer, unsigned long len);
-
-/* This is used to create an ION buffer FD for the kernel buffer
- * So you can export this same buffer to others in the form of FD
- */
-int ion_export_buffer_fd(struct ion_buffer_info *ion_info);
-
-/* This is used to import or map an exported FD.
- * So we point to same buffer without making a copy. Hence zero-copy.
- */
-int ion_import_buffer_fd(struct ion_buffer_info *ion_info);
-
-/* This is used to close all references for the ION client */
-void ion_close_buffer_fd(struct ion_buffer_info *ion_info);
-
-/* This is used to send FD to another process using socket IPC */
-int socket_send_fd(struct socket_info *skinfo);
-
-/* This is used to receive FD from another process using socket IPC */
-int socket_receive_fd(struct socket_info *skinfo);
-
-
-#endif
diff --git a/tools/testing/selftests/android/ion/ipcsocket.c b/tools/testing/selftests/android/ion/ipcsocket.c
deleted file mode 100644
index 7dc521002095..000000000000
--- a/tools/testing/selftests/android/ion/ipcsocket.c
+++ /dev/null
@@ -1,227 +0,0 @@
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <sys/types.h>
-#include <sys/socket.h>
-#include <sys/time.h>
-#include <sys/un.h>
-#include <errno.h>
-
-#include "ipcsocket.h"
-
-
-int opensocket(int *sockfd, const char *name, int connecttype)
-{
- int ret, temp = 1;
-
- if (!name || strlen(name) > MAX_SOCK_NAME_LEN) {
- fprintf(stderr, "<%s>: Invalid socket name.\n", __func__);
- return -1;
- }
-
- ret = socket(PF_LOCAL, SOCK_STREAM, 0);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed socket: <%s>\n",
- __func__, strerror(errno));
- return ret;
- }
-
- *sockfd = ret;
- if (setsockopt(*sockfd, SOL_SOCKET, SO_REUSEADDR,
- (char *)&temp, sizeof(int)) < 0) {
- fprintf(stderr, "<%s>: Failed setsockopt: <%s>\n",
- __func__, strerror(errno));
- goto err;
- }
-
- sprintf(sock_name, "/tmp/%s", name);
-
- if (connecttype == 1) {
- /* This is for Server connection */
- struct sockaddr_un skaddr;
- int clientfd;
- socklen_t sklen;
-
- unlink(sock_name);
- memset(&skaddr, 0, sizeof(skaddr));
- skaddr.sun_family = AF_LOCAL;
- strcpy(skaddr.sun_path, sock_name);
-
- ret = bind(*sockfd, (struct sockaddr *)&skaddr,
- SUN_LEN(&skaddr));
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed bind: <%s>\n",
- __func__, strerror(errno));
- goto err;
- }
-
- ret = listen(*sockfd, 5);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed listen: <%s>\n",
- __func__, strerror(errno));
- goto err;
- }
-
- memset(&skaddr, 0, sizeof(skaddr));
- sklen = sizeof(skaddr);
-
- ret = accept(*sockfd, (struct sockaddr *)&skaddr,
- (socklen_t *)&sklen);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed accept: <%s>\n",
- __func__, strerror(errno));
- goto err;
- }
-
- clientfd = ret;
- *sockfd = clientfd;
- } else {
- /* This is for client connection */
- struct sockaddr_un skaddr;
-
- memset(&skaddr, 0, sizeof(skaddr));
- skaddr.sun_family = AF_LOCAL;
- strcpy(skaddr.sun_path, sock_name);
-
- ret = connect(*sockfd, (struct sockaddr *)&skaddr,
- SUN_LEN(&skaddr));
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed connect: <%s>\n",
- __func__, strerror(errno));
- goto err;
- }
- }
-
- return 0;
-
-err:
- if (*sockfd)
- close(*sockfd);
-
- return ret;
-}
-
-int sendtosocket(int sockfd, struct socketdata *skdata)
-{
- int ret, buffd;
- unsigned int len;
- char cmsg_b[CMSG_SPACE(sizeof(int))];
- struct cmsghdr *cmsg;
- struct msghdr msgh;
- struct iovec iov;
- struct timeval timeout;
- fd_set selFDs;
-
- if (!skdata) {
- fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
- return -1;
- }
-
- FD_ZERO(&selFDs);
- FD_SET(0, &selFDs);
- FD_SET(sockfd, &selFDs);
- timeout.tv_sec = 20;
- timeout.tv_usec = 0;
-
- ret = select(sockfd+1, NULL, &selFDs, NULL, &timeout);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed select: <%s>\n",
- __func__, strerror(errno));
- return -1;
- }
-
- if (FD_ISSET(sockfd, &selFDs)) {
- buffd = skdata->data;
- len = skdata->len;
- memset(&msgh, 0, sizeof(msgh));
- msgh.msg_control = &cmsg_b;
- msgh.msg_controllen = CMSG_LEN(len);
- iov.iov_base = "OK";
- iov.iov_len = 2;
- msgh.msg_iov = &iov;
- msgh.msg_iovlen = 1;
- cmsg = CMSG_FIRSTHDR(&msgh);
- cmsg->cmsg_level = SOL_SOCKET;
- cmsg->cmsg_type = SCM_RIGHTS;
- cmsg->cmsg_len = CMSG_LEN(len);
- memcpy(CMSG_DATA(cmsg), &buffd, len);
-
- ret = sendmsg(sockfd, &msgh, MSG_DONTWAIT);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed sendmsg: <%s>\n",
- __func__, strerror(errno));
- return -1;
- }
- }
-
- return 0;
-}
-
-int receivefromsocket(int sockfd, struct socketdata *skdata)
-{
- int ret, buffd;
- unsigned int len = 0;
- char cmsg_b[CMSG_SPACE(sizeof(int))];
- struct cmsghdr *cmsg;
- struct msghdr msgh;
- struct iovec iov;
- fd_set recvFDs;
- char data[32];
-
- if (!skdata) {
- fprintf(stderr, "<%s>: socketdata is NULL\n", __func__);
- return -1;
- }
-
- FD_ZERO(&recvFDs);
- FD_SET(0, &recvFDs);
- FD_SET(sockfd, &recvFDs);
-
- ret = select(sockfd+1, &recvFDs, NULL, NULL, NULL);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed select: <%s>\n",
- __func__, strerror(errno));
- return -1;
- }
-
- if (FD_ISSET(sockfd, &recvFDs)) {
- len = sizeof(buffd);
- memset(&msgh, 0, sizeof(msgh));
- msgh.msg_control = &cmsg_b;
- msgh.msg_controllen = CMSG_LEN(len);
- iov.iov_base = data;
- iov.iov_len = sizeof(data)-1;
- msgh.msg_iov = &iov;
- msgh.msg_iovlen = 1;
- cmsg = CMSG_FIRSTHDR(&msgh);
- cmsg->cmsg_level = SOL_SOCKET;
- cmsg->cmsg_type = SCM_RIGHTS;
- cmsg->cmsg_len = CMSG_LEN(len);
-
- ret = recvmsg(sockfd, &msgh, MSG_DONTWAIT);
- if (ret < 0) {
- fprintf(stderr, "<%s>: Failed recvmsg: <%s>\n",
- __func__, strerror(errno));
- return -1;
- }
-
- memcpy(&buffd, CMSG_DATA(cmsg), len);
- skdata->data = buffd;
- skdata->len = len;
- }
- return 0;
-}
-
-int closesocket(int sockfd, char *name)
-{
- char sockname[MAX_SOCK_NAME_LEN];
-
- if (sockfd)
- close(sockfd);
- sprintf(sockname, "/tmp/%s", name);
- unlink(sockname);
- shutdown(sockfd, 2);
-
- return 0;
-}
diff --git a/tools/testing/selftests/android/ion/ipcsocket.h b/tools/testing/selftests/android/ion/ipcsocket.h
deleted file mode 100644
index b3e84498a8a1..000000000000
--- a/tools/testing/selftests/android/ion/ipcsocket.h
+++ /dev/null
@@ -1,35 +0,0 @@
-
-#ifndef _IPCSOCKET_H
-#define _IPCSOCKET_H
-
-
-#define MAX_SOCK_NAME_LEN 64
-
-char sock_name[MAX_SOCK_NAME_LEN];
-
-/* This structure is responsible for holding the IPC data
- * data: hold the buffer fd
- * len: just the length of 32-bit integer fd
- */
-struct socketdata {
- int data;
- unsigned int len;
-};
-
-/* This API is used to open the IPC socket connection
- * name: implies a unique socket name in the system
- * connecttype: implies server(0) or client(1)
- */
-int opensocket(int *sockfd, const char *name, int connecttype);
-
-/* This is the API to send socket data over IPC socket */
-int sendtosocket(int sockfd, struct socketdata *data);
-
-/* This is the API to receive socket data over IPC socket */
-int receivefromsocket(int sockfd, struct socketdata *data);
-
-/* This is the API to close the socket connection */
-int closesocket(int sockfd, char *name);
-
-
-#endif
diff --git a/tools/testing/selftests/android/run.sh b/tools/testing/selftests/android/run.sh
deleted file mode 100755
index dd8edf291454..000000000000
--- a/tools/testing/selftests/android/run.sh
+++ /dev/null
@@ -1,3 +0,0 @@
-#!/bin/sh
-
-(cd ion; ./ion_test.sh)
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 3ab1200e172f..f5b7ef93618c 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -8,7 +8,6 @@ FEATURE-DUMP.libbpf
fixdep
test_dev_cgroup
/test_progs*
-test_tcpbpf_user
test_verifier_log
feature
test_sock
@@ -36,3 +35,5 @@ test_cpp
/tools
/runqslower
/bench
+*.ko
+xdpxceiver
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 542768f5195b..8c33e999319a 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -19,7 +19,6 @@ ifneq ($(wildcard $(GENHDR)),)
endif
CLANG ?= clang
-LLC ?= llc
LLVM_OBJCOPY ?= llvm-objcopy
BPF_GCC ?= $(shell command -v bpf-gcc;)
SAN_CFLAGS ?=
@@ -32,7 +31,7 @@ LDLIBS += -lcap -lelf -lz -lrt -lpthread
# Order correspond to 'make run_tests' order
TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
- test_verifier_log test_dev_cgroup test_tcpbpf_user \
+ test_verifier_log test_dev_cgroup \
test_sock test_sockmap get_cgroup_id_user test_socket_cookie \
test_cgroup_storage \
test_netcnt test_tcpnotify_user test_sysctl \
@@ -46,7 +45,8 @@ endif
TEST_GEN_FILES =
TEST_FILES = test_lwt_ip_encap.o \
- test_tc_edt.o
+ test_tc_edt.o \
+ xsk_prereqs.sh
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@@ -70,17 +70,17 @@ TEST_PROGS := test_kmod.sh \
test_bpftool_build.sh \
test_bpftool.sh \
test_bpftool_metadata.sh \
+ test_xsk.sh
TEST_PROGS_EXTENDED := with_addr.sh \
with_tunnels.sh \
- tcp_client.py \
- tcp_server.py \
test_xdp_vlan.sh
# Compile but not part of 'make run_tests'
TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \
flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \
- test_lirc_mode2_user xdping test_cpp runqslower bench
+ test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko \
+ xdpxceiver
TEST_CUSTOM_PROGS = urandom_read
@@ -104,6 +104,7 @@ OVERRIDE_TARGETS := 1
override define CLEAN
$(call msg,CLEAN)
$(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN)
+ $(Q)$(MAKE) -C bpf_testmod clean
endef
include ../lib.mk
@@ -114,6 +115,13 @@ INCLUDE_DIR := $(SCRATCH_DIR)/include
BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
RESOLVE_BTFIDS := $(BUILD_DIR)/resolve_btfids/resolve_btfids
+VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
+ $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
+ ../../../../vmlinux \
+ /sys/kernel/btf/vmlinux \
+ /boot/vmlinux-$(shell uname -r)
+VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
+
# Define simple and short `make test_progs`, `make test_sysctl`, etc targets
# to build individual tests.
# NOTE: Semicolon at the end is critical to override lib.mk's default static
@@ -136,17 +144,16 @@ $(OUTPUT)/urandom_read: urandom_read.c
$(call msg,BINARY,,$@)
$(Q)$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id=sha1
+$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
+ $(call msg,MOD,,$@)
+ $(Q)$(RM) bpf_testmod/bpf_testmod.ko # force re-compilation
+ $(Q)$(MAKE) $(submake_extras) -C bpf_testmod
+ $(Q)cp bpf_testmod/bpf_testmod.ko $@
+
$(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
$(call msg,CC,,$@)
$(Q)$(CC) -c $(CFLAGS) -o $@ $<
-VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux) \
- $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux) \
- ../../../../vmlinux \
- /sys/kernel/btf/vmlinux \
- /boot/vmlinux-$(shell uname -r)
-VMLINUX_BTF ?= $(abspath $(firstword $(wildcard $(VMLINUX_BTF_PATHS))))
-
DEFAULT_BPFTOOL := $(SCRATCH_DIR)/sbin/bpftool
$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
@@ -163,7 +170,6 @@ $(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
$(OUTPUT)/test_sockmap: cgroup_helpers.c
-$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
$(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
@@ -220,7 +226,8 @@ $(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids \
# build would have failed anyways.
define get_sys_includes
$(shell $(1) -v -E - </dev/null 2>&1 \
- | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \
+$(shell $(1) -dM -E - </dev/null | grep '#define __riscv_xlen ' | sed 's/#define /-D/' | sed 's/ /=/')
endef
# Determine target endianness.
@@ -245,31 +252,19 @@ $(OUTPUT)/flow_dissector_load.o: flow_dissector_load.h
# $1 - input .c file
# $2 - output .o file
# $3 - CFLAGS
-# $4 - LDFLAGS
define CLANG_BPF_BUILD_RULE
- $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
- $(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm \
- -c $1 -o - || echo "BPF obj compilation failed") | \
- $(LLC) -mattr=dwarfris -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
+ $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
+ $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -o $2 -mcpu=v3
endef
# Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
define CLANG_NOALU32_BPF_BUILD_RULE
- $(call msg,CLNG-LLC,$(TRUNNER_BINARY),$2)
- $(Q)($(CLANG) $3 -O2 -target bpf -emit-llvm \
- -c $1 -o - || echo "BPF obj compilation failed") | \
- $(LLC) -march=bpf -mcpu=v2 $4 -filetype=obj -o $2
-endef
-# Similar to CLANG_BPF_BUILD_RULE, but using native Clang and bpf LLC
-define CLANG_NATIVE_BPF_BUILD_RULE
$(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
- $(Q)($(CLANG) $3 -O2 -emit-llvm \
- -c $1 -o - || echo "BPF obj compilation failed") | \
- $(LLC) -march=bpf -mcpu=v3 $4 -filetype=obj -o $2
+ $(Q)$(CLANG) $3 -O2 -target bpf -c $1 -o $2 -mcpu=v2
endef
# Build BPF object using GCC
define GCC_BPF_BUILD_RULE
$(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
- $(Q)$(BPF_GCC) $3 $4 -O2 -c $1 -o $2
+ $(Q)$(BPF_GCC) $3 -O2 -c $1 -o $2
endef
SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
@@ -324,8 +319,7 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o: \
$$(INCLUDE_DIR)/vmlinux.h \
$(wildcard $(BPFDIR)/bpf_*.h) | $(TRUNNER_OUTPUT)
$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
- $(TRUNNER_BPF_CFLAGS), \
- $(TRUNNER_BPF_LDFLAGS))
+ $(TRUNNER_BPF_CFLAGS))
$(TRUNNER_BPF_SKELS): $(TRUNNER_OUTPUT)/%.skel.h: \
$(TRUNNER_OUTPUT)/%.o \
@@ -378,7 +372,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \
| $(TRUNNER_BINARY)-extras
$$(call msg,BINARY,,$$@)
$(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@
- $(Q)$(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@
+ $(Q)$(RESOLVE_BTFIDS) --no-fail --btf $(TRUNNER_OUTPUT)/btf_data.o $$@
endef
@@ -387,24 +381,22 @@ TRUNNER_TESTS_DIR := prog_tests
TRUNNER_BPF_PROGS_DIR := progs
TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \
network_helpers.c testing_helpers.c \
- flow_dissector_load.h
-TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \
+ btf_helpers.c flow_dissector_load.h
+TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \
+ ima_setup.sh \
$(wildcard progs/btf_dump_test_case_*.c)
TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS)
-TRUNNER_BPF_LDFLAGS := -mattr=+alu32
$(eval $(call DEFINE_TEST_RUNNER,test_progs))
# Define test_progs-no_alu32 test runner.
TRUNNER_BPF_BUILD_RULE := CLANG_NOALU32_BPF_BUILD_RULE
-TRUNNER_BPF_LDFLAGS :=
$(eval $(call DEFINE_TEST_RUNNER,test_progs,no_alu32))
# Define test_progs BPF-GCC-flavored test runner.
ifneq ($(BPF_GCC),)
TRUNNER_BPF_BUILD_RULE := GCC_BPF_BUILD_RULE
TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(call get_sys_includes,gcc)
-TRUNNER_BPF_LDFLAGS :=
$(eval $(call DEFINE_TEST_RUNNER,test_progs,bpf_gcc))
endif
@@ -415,7 +407,6 @@ TRUNNER_EXTRA_SOURCES := test_maps.c
TRUNNER_EXTRA_FILES :=
TRUNNER_BPF_BUILD_RULE := $$(error no BPF objects should be built)
TRUNNER_BPF_CFLAGS :=
-TRUNNER_BPF_LDFLAGS :=
$(eval $(call DEFINE_TEST_RUNNER,test_maps))
# Define test_verifier test runner.
@@ -459,4 +450,4 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \
prog_tests/tests.h map_tests/tests.h verifier/tests.h \
feature \
- $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc)
+ $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko)
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index ac9eda830187..ca064180d4d0 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -2,7 +2,10 @@
BPF Selftest Notes
==================
General instructions on running selftests can be found in
-`Documentation/bpf/bpf_devel_QA.rst`_.
+`Documentation/bpf/bpf_devel_QA.rst`__.
+
+__ /Documentation/bpf/bpf_devel_QA.rst#q-how-to-run-bpf-selftests
+
Additional information about selftest failures are
documented here.
@@ -30,11 +33,12 @@ The verifier will reject such code with above error.
At insn 18 the r7 is indeed unbounded. The later insn 19 checks the bounds and
the insn 20 undoes map_value addition. It is currently impossible for the
verifier to understand such speculative pointer arithmetic.
-Hence
- https://reviews.llvm.org/D85570
-addresses it on the compiler side. It was committed on llvm 12.
+Hence `this patch`__ addresses it on the compiler side. It was committed on llvm 12.
+
+__ https://reviews.llvm.org/D85570
The corresponding C code
+
.. code-block:: c
for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) {
@@ -77,10 +81,11 @@ The symptom for ``bpf_iter/netlink`` looks like
17: (7b) *(u64 *)(r7 +0) = r2
only read is supported
-This is due to a llvm BPF backend bug. The fix
- https://reviews.llvm.org/D78466
+This is due to a llvm BPF backend bug. `The fix`__
has been pushed to llvm 10.x release branch and will be
-available in 10.0.1. The fix is available in llvm 11.0.0 trunk.
+available in 10.0.1. The patch is available in llvm 11.0.0 trunk.
+
+__ https://reviews.llvm.org/D78466
BPF CO-RE-based tests and Clang version
=======================================
@@ -94,11 +99,11 @@ them to Clang/LLVM. These sub-tests are going to be skipped if Clang is too
old to support them, they shouldn't cause build failures or runtime test
failures:
- - __builtin_btf_type_id() ([0], [1], [2]);
- - __builtin_preserve_type_info(), __builtin_preserve_enum_value() ([3], [4]).
+- __builtin_btf_type_id() [0_, 1_, 2_];
+- __builtin_preserve_type_info(), __builtin_preserve_enum_value() [3_, 4_].
- [0] https://reviews.llvm.org/D74572
- [1] https://reviews.llvm.org/D74668
- [2] https://reviews.llvm.org/D85174
- [3] https://reviews.llvm.org/D83878
- [4] https://reviews.llvm.org/D83242
+.. _0: https://reviews.llvm.org/D74572
+.. _1: https://reviews.llvm.org/D74668
+.. _2: https://reviews.llvm.org/D85174
+.. _3: https://reviews.llvm.org/D83878
+.. _4: https://reviews.llvm.org/D83242
diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 2915664c335d..6a9053162cf2 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -56,6 +56,7 @@ struct tcp_sock {
__u32 rcv_nxt;
__u32 snd_nxt;
__u32 snd_una;
+ __u32 window_clamp;
__u8 ecn_flags;
__u32 delivered;
__u32 delivered_ce;
diff --git a/tools/testing/selftests/bpf/bpf_testmod/.gitignore b/tools/testing/selftests/bpf/bpf_testmod/.gitignore
new file mode 100644
index 000000000000..ded513777281
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/.gitignore
@@ -0,0 +1,6 @@
+*.mod
+*.mod.c
+*.o
+.ko
+/Module.symvers
+/modules.order
diff --git a/tools/testing/selftests/bpf/bpf_testmod/Makefile b/tools/testing/selftests/bpf/bpf_testmod/Makefile
new file mode 100644
index 000000000000..15cb36c4483a
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/Makefile
@@ -0,0 +1,20 @@
+BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..)
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+MODULES = bpf_testmod.ko
+
+obj-m += bpf_testmod.o
+CFLAGS_bpf_testmod.o = -I$(src)
+
+all:
+ +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules
+
+clean:
+ +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean
+
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
new file mode 100644
index 000000000000..b83ea448bc79
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bpf_testmod
+
+#if !defined(_BPF_TESTMOD_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _BPF_TESTMOD_EVENTS_H
+
+#include <linux/tracepoint.h>
+#include "bpf_testmod.h"
+
+TRACE_EVENT(bpf_testmod_test_read,
+ TP_PROTO(struct task_struct *task, struct bpf_testmod_test_read_ctx *ctx),
+ TP_ARGS(task, ctx),
+ TP_STRUCT__entry(
+ __field(pid_t, pid)
+ __array(char, comm, TASK_COMM_LEN)
+ __field(loff_t, off)
+ __field(size_t, len)
+ ),
+ TP_fast_assign(
+ __entry->pid = task->pid;
+ memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
+ __entry->off = ctx->off;
+ __entry->len = ctx->len;
+ ),
+ TP_printk("pid=%d comm=%s off=%llu len=%zu",
+ __entry->pid, __entry->comm, __entry->off, __entry->len)
+);
+
+#endif /* _BPF_TESTMOD_EVENTS_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE bpf_testmod-events
+#include <trace/define_trace.h>
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
new file mode 100644
index 000000000000..2df19d73ca49
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <linux/error-injection.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sysfs.h>
+#include <linux/tracepoint.h>
+#include "bpf_testmod.h"
+
+#define CREATE_TRACE_POINTS
+#include "bpf_testmod-events.h"
+
+noinline ssize_t
+bpf_testmod_test_read(struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buf, loff_t off, size_t len)
+{
+ struct bpf_testmod_test_read_ctx ctx = {
+ .buf = buf,
+ .off = off,
+ .len = len,
+ };
+
+ trace_bpf_testmod_test_read(current, &ctx);
+
+ return -EIO; /* always fail */
+}
+EXPORT_SYMBOL(bpf_testmod_test_read);
+ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO);
+
+static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
+ .attr = { .name = "bpf_testmod", .mode = 0444, },
+ .read = bpf_testmod_test_read,
+};
+
+static int bpf_testmod_init(void)
+{
+ return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+}
+
+static void bpf_testmod_exit(void)
+{
+ return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+}
+
+module_init(bpf_testmod_init);
+module_exit(bpf_testmod_exit);
+
+MODULE_AUTHOR("Andrii Nakryiko");
+MODULE_DESCRIPTION("BPF selftests module");
+MODULE_LICENSE("Dual BSD/GPL");
+
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
new file mode 100644
index 000000000000..b81adfedb4f6
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef _BPF_TESTMOD_H
+#define _BPF_TESTMOD_H
+
+#include <linux/types.h>
+
+struct bpf_testmod_test_read_ctx {
+ char *buf;
+ loff_t off;
+ size_t len;
+};
+
+#endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
new file mode 100644
index 000000000000..48f90490f922
--- /dev/null
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <stdio.h>
+#include <errno.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+
+static const char * const btf_kind_str_mapping[] = {
+ [BTF_KIND_UNKN] = "UNKNOWN",
+ [BTF_KIND_INT] = "INT",
+ [BTF_KIND_PTR] = "PTR",
+ [BTF_KIND_ARRAY] = "ARRAY",
+ [BTF_KIND_STRUCT] = "STRUCT",
+ [BTF_KIND_UNION] = "UNION",
+ [BTF_KIND_ENUM] = "ENUM",
+ [BTF_KIND_FWD] = "FWD",
+ [BTF_KIND_TYPEDEF] = "TYPEDEF",
+ [BTF_KIND_VOLATILE] = "VOLATILE",
+ [BTF_KIND_CONST] = "CONST",
+ [BTF_KIND_RESTRICT] = "RESTRICT",
+ [BTF_KIND_FUNC] = "FUNC",
+ [BTF_KIND_FUNC_PROTO] = "FUNC_PROTO",
+ [BTF_KIND_VAR] = "VAR",
+ [BTF_KIND_DATASEC] = "DATASEC",
+};
+
+static const char *btf_kind_str(__u16 kind)
+{
+ if (kind > BTF_KIND_DATASEC)
+ return "UNKNOWN";
+ return btf_kind_str_mapping[kind];
+}
+
+static const char *btf_int_enc_str(__u8 encoding)
+{
+ switch (encoding) {
+ case 0:
+ return "(none)";
+ case BTF_INT_SIGNED:
+ return "SIGNED";
+ case BTF_INT_CHAR:
+ return "CHAR";
+ case BTF_INT_BOOL:
+ return "BOOL";
+ default:
+ return "UNKN";
+ }
+}
+
+static const char *btf_var_linkage_str(__u32 linkage)
+{
+ switch (linkage) {
+ case BTF_VAR_STATIC:
+ return "static";
+ case BTF_VAR_GLOBAL_ALLOCATED:
+ return "global-alloc";
+ default:
+ return "(unknown)";
+ }
+}
+
+static const char *btf_func_linkage_str(const struct btf_type *t)
+{
+ switch (btf_vlen(t)) {
+ case BTF_FUNC_STATIC:
+ return "static";
+ case BTF_FUNC_GLOBAL:
+ return "global";
+ case BTF_FUNC_EXTERN:
+ return "extern";
+ default:
+ return "(unknown)";
+ }
+}
+
+static const char *btf_str(const struct btf *btf, __u32 off)
+{
+ if (!off)
+ return "(anon)";
+ return btf__str_by_offset(btf, off) ?: "(invalid)";
+}
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
+{
+ const struct btf_type *t;
+ int kind, i;
+ __u32 vlen;
+
+ t = btf__type_by_id(btf, id);
+ if (!t)
+ return -EINVAL;
+
+ vlen = btf_vlen(t);
+ kind = btf_kind(t);
+
+ fprintf(out, "[%u] %s '%s'", id, btf_kind_str(kind), btf_str(btf, t->name_off));
+
+ switch (kind) {
+ case BTF_KIND_INT:
+ fprintf(out, " size=%u bits_offset=%u nr_bits=%u encoding=%s",
+ t->size, btf_int_offset(t), btf_int_bits(t),
+ btf_int_enc_str(btf_int_encoding(t)));
+ break;
+ case BTF_KIND_PTR:
+ case BTF_KIND_CONST:
+ case BTF_KIND_VOLATILE:
+ case BTF_KIND_RESTRICT:
+ case BTF_KIND_TYPEDEF:
+ fprintf(out, " type_id=%u", t->type);
+ break;
+ case BTF_KIND_ARRAY: {
+ const struct btf_array *arr = btf_array(t);
+
+ fprintf(out, " type_id=%u index_type_id=%u nr_elems=%u",
+ arr->type, arr->index_type, arr->nelems);
+ break;
+ }
+ case BTF_KIND_STRUCT:
+ case BTF_KIND_UNION: {
+ const struct btf_member *m = btf_members(t);
+
+ fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ for (i = 0; i < vlen; i++, m++) {
+ __u32 bit_off, bit_sz;
+
+ bit_off = btf_member_bit_offset(t, i);
+ bit_sz = btf_member_bitfield_size(t, i);
+ fprintf(out, "\n\t'%s' type_id=%u bits_offset=%u",
+ btf_str(btf, m->name_off), m->type, bit_off);
+ if (bit_sz)
+ fprintf(out, " bitfield_size=%u", bit_sz);
+ }
+ break;
+ }
+ case BTF_KIND_ENUM: {
+ const struct btf_enum *v = btf_enum(t);
+
+ fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ for (i = 0; i < vlen; i++, v++) {
+ fprintf(out, "\n\t'%s' val=%u",
+ btf_str(btf, v->name_off), v->val);
+ }
+ break;
+ }
+ case BTF_KIND_FWD:
+ fprintf(out, " fwd_kind=%s", btf_kflag(t) ? "union" : "struct");
+ break;
+ case BTF_KIND_FUNC:
+ fprintf(out, " type_id=%u linkage=%s", t->type, btf_func_linkage_str(t));
+ break;
+ case BTF_KIND_FUNC_PROTO: {
+ const struct btf_param *p = btf_params(t);
+
+ fprintf(out, " ret_type_id=%u vlen=%u", t->type, vlen);
+ for (i = 0; i < vlen; i++, p++) {
+ fprintf(out, "\n\t'%s' type_id=%u",
+ btf_str(btf, p->name_off), p->type);
+ }
+ break;
+ }
+ case BTF_KIND_VAR:
+ fprintf(out, " type_id=%u, linkage=%s",
+ t->type, btf_var_linkage_str(btf_var(t)->linkage));
+ break;
+ case BTF_KIND_DATASEC: {
+ const struct btf_var_secinfo *v = btf_var_secinfos(t);
+
+ fprintf(out, " size=%u vlen=%u", t->size, vlen);
+ for (i = 0; i < vlen; i++, v++) {
+ fprintf(out, "\n\ttype_id=%u offset=%u size=%u",
+ v->type, v->offset, v->size);
+ }
+ break;
+ }
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+/* Print raw BTF type dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_raw_dump(const struct btf *btf, int type_id)
+{
+ static char buf[16 * 1024];
+ FILE *buf_file;
+
+ buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+ if (!buf_file) {
+ fprintf(stderr, "Failed to open memstream: %d\n", errno);
+ return NULL;
+ }
+
+ fprintf_btf_type_raw(buf_file, btf, type_id);
+ fflush(buf_file);
+ fclose(buf_file);
+
+ return buf;
+}
+
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[])
+{
+ int i;
+ bool ok = true;
+
+ ASSERT_EQ(btf__get_nr_types(btf), nr_types, "btf_nr_types");
+
+ for (i = 1; i <= nr_types; i++) {
+ if (!ASSERT_STREQ(btf_type_raw_dump(btf, i), exp_types[i - 1], "raw_dump"))
+ ok = false;
+ }
+
+ return ok;
+}
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+ vfprintf(ctx, fmt, args);
+}
+
+/* Print BTF-to-C dump into a local buffer and return string pointer back.
+ * Buffer *will* be overwritten by subsequent btf_type_raw_dump() calls
+ */
+const char *btf_type_c_dump(const struct btf *btf)
+{
+ static char buf[16 * 1024];
+ FILE *buf_file;
+ struct btf_dump *d = NULL;
+ struct btf_dump_opts opts = {};
+ int err, i;
+
+ buf_file = fmemopen(buf, sizeof(buf) - 1, "w");
+ if (!buf_file) {
+ fprintf(stderr, "Failed to open memstream: %d\n", errno);
+ return NULL;
+ }
+
+ opts.ctx = buf_file;
+ d = btf_dump__new(btf, NULL, &opts, btf_dump_printf);
+ if (libbpf_get_error(d)) {
+ fprintf(stderr, "Failed to create btf_dump instance: %ld\n", libbpf_get_error(d));
+ return NULL;
+ }
+
+ for (i = 1; i <= btf__get_nr_types(btf); i++) {
+ err = btf_dump__dump_type(d, i);
+ if (err) {
+ fprintf(stderr, "Failed to dump type [%d]: %d\n", i, err);
+ return NULL;
+ }
+ }
+
+ fflush(buf_file);
+ fclose(buf_file);
+ return buf;
+}
diff --git a/tools/testing/selftests/bpf/btf_helpers.h b/tools/testing/selftests/bpf/btf_helpers.h
new file mode 100644
index 000000000000..295c0137d9bd
--- /dev/null
+++ b/tools/testing/selftests/bpf/btf_helpers.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2020 Facebook */
+#ifndef __BTF_HELPERS_H
+#define __BTF_HELPERS_H
+
+#include <stdio.h>
+#include <bpf/btf.h>
+
+int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id);
+const char *btf_type_raw_dump(const struct btf *btf, int type_id);
+int btf_validate_raw(struct btf *btf, int nr_types, const char *exp_types[]);
+
+#define VALIDATE_RAW_BTF(btf, raw_types...) \
+ btf_validate_raw(btf, \
+ sizeof((const char *[]){raw_types})/sizeof(void *),\
+ (const char *[]){raw_types})
+
+const char *btf_type_c_dump(const struct btf *btf);
+#endif
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 2118e23ac07a..37e1f303fc11 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -39,3 +39,8 @@ CONFIG_BPF_JIT=y
CONFIG_BPF_LSM=y
CONFIG_SECURITY=y
CONFIG_LIRC=y
+CONFIG_IMA=y
+CONFIG_SECURITYFS=y
+CONFIG_IMA_WRITE_POLICY=y
+CONFIG_IMA_READ_POLICY=y
+CONFIG_BLK_DEV_LOOP=y
diff --git a/tools/testing/selftests/bpf/ima_setup.sh b/tools/testing/selftests/bpf/ima_setup.sh
new file mode 100755
index 000000000000..8e62581113a3
--- /dev/null
+++ b/tools/testing/selftests/bpf/ima_setup.sh
@@ -0,0 +1,123 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+set -u
+set -o pipefail
+
+IMA_POLICY_FILE="/sys/kernel/security/ima/policy"
+TEST_BINARY="/bin/true"
+VERBOSE="${SELFTESTS_VERBOSE:=0}"
+LOG_FILE="$(mktemp /tmp/ima_setup.XXXX.log)"
+
+usage()
+{
+ echo "Usage: $0 <setup|cleanup|run> <existing_tmp_dir>"
+ exit 1
+}
+
+ensure_mount_securityfs()
+{
+ local securityfs_dir=$(grep "securityfs" /proc/mounts | awk '{print $2}')
+
+ if [ -z "${securityfs_dir}" ]; then
+ securityfs_dir=/sys/kernel/security
+ mount -t securityfs security "${securityfs_dir}"
+ fi
+
+ if [ ! -d "${securityfs_dir}" ]; then
+ echo "${securityfs_dir}: securityfs is not mounted" && exit 1
+ fi
+}
+
+setup()
+{
+ local tmp_dir="$1"
+ local mount_img="${tmp_dir}/test.img"
+ local mount_dir="${tmp_dir}/mnt"
+ local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})"
+ mkdir -p ${mount_dir}
+
+ dd if=/dev/zero of="${mount_img}" bs=1M count=10
+
+ losetup -f "${mount_img}"
+ local loop_device=$(losetup -a | grep ${mount_img:?} | cut -d ":" -f1)
+
+ mkfs.ext2 "${loop_device:?}"
+ mount "${loop_device}" "${mount_dir}"
+
+ cp "${TEST_BINARY}" "${mount_dir}"
+ local mount_uuid="$(blkid ${loop_device} | sed 's/.*UUID="\([^"]*\)".*/\1/')"
+
+ ensure_mount_securityfs
+ echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${IMA_POLICY_FILE}
+}
+
+cleanup() {
+ local tmp_dir="$1"
+ local mount_img="${tmp_dir}/test.img"
+ local mount_dir="${tmp_dir}/mnt"
+
+ local loop_devices=$(losetup -a | grep ${mount_img:?} | cut -d ":" -f1)
+
+ for loop_dev in "${loop_devices}"; do
+ losetup -d $loop_dev
+ done
+
+ umount ${mount_dir}
+ rm -rf ${tmp_dir}
+}
+
+run()
+{
+ local tmp_dir="$1"
+ local mount_dir="${tmp_dir}/mnt"
+ local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})"
+
+ exec "${copied_bin_path}"
+}
+
+catch()
+{
+ local exit_code="$1"
+ local log_file="$2"
+
+ if [[ "${exit_code}" -ne 0 ]]; then
+ cat "${log_file}" >&3
+ fi
+
+ rm -f "${log_file}"
+ exit ${exit_code}
+}
+
+main()
+{
+ [[ $# -ne 2 ]] && usage
+
+ local action="$1"
+ local tmp_dir="$2"
+
+ [[ ! -d "${tmp_dir}" ]] && echo "Directory ${tmp_dir} doesn't exist" && exit 1
+
+ if [[ "${action}" == "setup" ]]; then
+ setup "${tmp_dir}"
+ elif [[ "${action}" == "cleanup" ]]; then
+ cleanup "${tmp_dir}"
+ elif [[ "${action}" == "run" ]]; then
+ run "${tmp_dir}"
+ else
+ echo "Unknown action: ${action}"
+ exit 1
+ fi
+}
+
+trap 'catch "$?" "${LOG_FILE}"' EXIT
+
+if [[ "${VERBOSE}" -eq 0 ]]; then
+ # Save the stderr to 3 so that we can output back to
+ # it incase of an error.
+ exec 3>&2 1>"${LOG_FILE}" 2>&1
+fi
+
+main "$@"
+rm -f "${LOG_FILE}"
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 52414058a627..5861446d0777 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -456,10 +456,10 @@ static struct bpf_align_test tests[] = {
*/
{7, "R5_w=inv(id=0,smin_value=-9223372036854775806,smax_value=9223372036854775806,umin_value=2,umax_value=18446744073709551614,var_off=(0x2; 0xfffffffffffffffc)"},
/* Checked s>=0 */
- {9, "R5=inv(id=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+ {9, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
/* packet pointer + nonnegative (4n+2) */
- {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
- {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+ {11, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
+ {13, "R4_w=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
/* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine.
* We checked the bounds, but it might have been able
* to overflow if the packet pointer started in the
@@ -467,7 +467,7 @@ static struct bpf_align_test tests[] = {
* So we did not get a 'range' on R6, and the access
* attempt will fail.
*/
- {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372034707292158,var_off=(0x2; 0x7fffffff7ffffffc)"},
+ {15, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc)"},
}
},
{
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 448885b95eed..0e586368948d 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -20,6 +20,7 @@
#include "bpf_iter_bpf_percpu_hash_map.skel.h"
#include "bpf_iter_bpf_array_map.skel.h"
#include "bpf_iter_bpf_percpu_array_map.skel.h"
+#include "bpf_iter_bpf_sk_storage_helpers.skel.h"
#include "bpf_iter_bpf_sk_storage_map.skel.h"
#include "bpf_iter_test_kern5.skel.h"
#include "bpf_iter_test_kern6.skel.h"
@@ -913,6 +914,119 @@ out:
bpf_iter_bpf_percpu_array_map__destroy(skel);
}
+/* An iterator program deletes all local storage in a map. */
+static void test_bpf_sk_storage_delete(void)
+{
+ DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+ struct bpf_iter_bpf_sk_storage_helpers *skel;
+ union bpf_iter_link_info linfo;
+ int err, len, map_fd, iter_fd;
+ struct bpf_link *link;
+ int sock_fd = -1;
+ __u32 val = 42;
+ char buf[64];
+
+ skel = bpf_iter_bpf_sk_storage_helpers__open_and_load();
+ if (CHECK(!skel, "bpf_iter_bpf_sk_storage_helpers__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ map_fd = bpf_map__fd(skel->maps.sk_stg_map);
+
+ sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(sock_fd < 0, "socket", "errno: %d\n", errno))
+ goto out;
+ err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
+ if (CHECK(err, "map_update", "map_update failed\n"))
+ goto out;
+
+ memset(&linfo, 0, sizeof(linfo));
+ linfo.map.map_fd = map_fd;
+ opts.link_info = &linfo;
+ opts.link_info_len = sizeof(linfo);
+ link = bpf_program__attach_iter(skel->progs.delete_bpf_sk_storage_map,
+ &opts);
+ if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+ goto out;
+
+ iter_fd = bpf_iter_create(bpf_link__fd(link));
+ if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+ goto free_link;
+
+ /* do some tests */
+ while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+ ;
+ if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+ goto close_iter;
+
+ /* test results */
+ err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
+ if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+ "map value wasn't deleted (err=%d, errno=%d)\n", err, errno))
+ goto close_iter;
+
+close_iter:
+ close(iter_fd);
+free_link:
+ bpf_link__destroy(link);
+out:
+ if (sock_fd >= 0)
+ close(sock_fd);
+ bpf_iter_bpf_sk_storage_helpers__destroy(skel);
+}
+
+/* This creates a socket and its local storage. It then runs a task_iter BPF
+ * program that replaces the existing socket local storage with the tgid of the
+ * only task owning a file descriptor to this socket, this process, prog_tests.
+ * It then runs a tcp socket iterator that negates the value in the existing
+ * socket local storage, the test verifies that the resulting value is -pid.
+ */
+static void test_bpf_sk_storage_get(void)
+{
+ struct bpf_iter_bpf_sk_storage_helpers *skel;
+ int err, map_fd, val = -1;
+ int sock_fd = -1;
+
+ skel = bpf_iter_bpf_sk_storage_helpers__open_and_load();
+ if (CHECK(!skel, "bpf_iter_bpf_sk_storage_helpers__open_and_load",
+ "skeleton open_and_load failed\n"))
+ return;
+
+ sock_fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (CHECK(sock_fd < 0, "socket", "errno: %d\n", errno))
+ goto out;
+
+ err = listen(sock_fd, 1);
+ if (CHECK(err != 0, "listen", "errno: %d\n", errno))
+ goto close_socket;
+
+ map_fd = bpf_map__fd(skel->maps.sk_stg_map);
+
+ err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST);
+ if (CHECK(err, "bpf_map_update_elem", "map_update_failed\n"))
+ goto close_socket;
+
+ do_dummy_read(skel->progs.fill_socket_owner);
+
+ err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
+ if (CHECK(err || val != getpid(), "bpf_map_lookup_elem",
+ "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
+ getpid(), val, err))
+ goto close_socket;
+
+ do_dummy_read(skel->progs.negate_socket_local_storage);
+
+ err = bpf_map_lookup_elem(map_fd, &sock_fd, &val);
+ CHECK(err || val != -getpid(), "bpf_map_lookup_elem",
+ "map value wasn't set correctly (expected %d, got %d, err=%d)\n",
+ -getpid(), val, err);
+
+close_socket:
+ close(sock_fd);
+out:
+ bpf_iter_bpf_sk_storage_helpers__destroy(skel);
+}
+
static void test_bpf_sk_storage_map(void)
{
DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
@@ -1067,6 +1181,10 @@ void test_bpf_iter(void)
test_bpf_percpu_array_map();
if (test__start_subtest("bpf_sk_storage_map"))
test_bpf_sk_storage_map();
+ if (test__start_subtest("bpf_sk_storage_delete"))
+ test_bpf_sk_storage_delete();
+ if (test__start_subtest("bpf_sk_storage_get"))
+ test_bpf_sk_storage_get();
if (test__start_subtest("rdonly-buf-out-of-bound"))
test_rdonly_buf_out_of_bound();
if (test__start_subtest("buf-neg-offset"))
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 93162484c2ca..8ae97e2a4b9d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -6652,7 +6652,7 @@ static void do_test_dedup(unsigned int test_num)
const void *test_btf_data, *expect_btf_data;
const char *ret_test_next_str, *ret_expect_next_str;
const char *test_strs, *expect_strs;
- const char *test_str_cur, *test_str_end;
+ const char *test_str_cur;
const char *expect_str_cur, *expect_str_end;
unsigned int raw_btf_size;
void *raw_btf;
@@ -6719,12 +6719,18 @@ static void do_test_dedup(unsigned int test_num)
goto done;
}
- test_str_cur = test_strs;
- test_str_end = test_strs + test_hdr->str_len;
expect_str_cur = expect_strs;
expect_str_end = expect_strs + expect_hdr->str_len;
- while (test_str_cur < test_str_end && expect_str_cur < expect_str_end) {
+ while (expect_str_cur < expect_str_end) {
size_t test_len, expect_len;
+ int off;
+
+ off = btf__find_str(test_btf, expect_str_cur);
+ if (CHECK(off < 0, "exp str '%s' not found: %d\n", expect_str_cur, off)) {
+ err = -1;
+ goto done;
+ }
+ test_str_cur = btf__str_by_offset(test_btf, off);
test_len = strlen(test_str_cur);
expect_len = strlen(expect_str_cur);
@@ -6741,15 +6747,8 @@ static void do_test_dedup(unsigned int test_num)
err = -1;
goto done;
}
- test_str_cur += test_len + 1;
expect_str_cur += expect_len + 1;
}
- if (CHECK(test_str_cur != test_str_end,
- "test_str_cur:%p != test_str_end:%p",
- test_str_cur, test_str_end)) {
- err = -1;
- goto done;
- }
test_nr_types = btf__get_nr_types(test_btf);
expect_nr_types = btf__get_nr_types(expect_btf);
@@ -6775,10 +6774,21 @@ static void do_test_dedup(unsigned int test_num)
err = -1;
goto done;
}
- if (CHECK(memcmp((void *)test_type,
- (void *)expect_type,
- test_size),
- "type #%d: contents differ", i)) {
+ if (CHECK(btf_kind(test_type) != btf_kind(expect_type),
+ "type %d kind: exp %d != got %u\n",
+ i, btf_kind(expect_type), btf_kind(test_type))) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(test_type->info != expect_type->info,
+ "type %d info: exp %d != got %u\n",
+ i, expect_type->info, test_type->info)) {
+ err = -1;
+ goto done;
+ }
+ if (CHECK(test_type->size != expect_type->size,
+ "type %d size/type: exp %d != got %u\n",
+ i, expect_type->size, test_type->size)) {
err = -1;
goto done;
}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
new file mode 100644
index 000000000000..64554fd33547
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dedup_split.c
@@ -0,0 +1,325 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "btf_helpers.h"
+
+static void test_split_simple() {
+ const struct btf_type *t;
+ struct btf *btf1, *btf2;
+ int str_off, err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 1); /* [2] ptr to int */
+ btf__add_struct(btf1, "s1", 4); /* [3] struct s1 { */
+ btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf1,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=1",
+ "[3] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0");
+
+ ASSERT_STREQ(btf_type_c_dump(btf1), "\
+struct s1 {\n\
+ int f1;\n\
+};\n\n", "c_dump");
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ /* pointer size should be "inherited" from main BTF */
+ ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+ str_off = btf__find_str(btf2, "int");
+ ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+ t = btf__type_by_id(btf2, 1);
+ if (!ASSERT_OK_PTR(t, "int_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_int(t), true, "int_kind");
+ ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+ btf__add_struct(btf2, "s2", 16); /* [4] struct s2 { */
+ btf__add_field(btf2, "f1", 6, 0, 0); /* struct s1 f1; */
+ btf__add_field(btf2, "f2", 5, 32, 0); /* int f2; */
+ btf__add_field(btf2, "f3", 2, 64, 0); /* int *f3; */
+ /* } */
+
+ /* duplicated int */
+ btf__add_int(btf2, "int", 4, BTF_INT_SIGNED); /* [5] int */
+
+ /* duplicated struct s1 */
+ btf__add_struct(btf2, "s1", 4); /* [6] struct s1 { */
+ btf__add_field(btf2, "f1", 5, 0, 0); /* int f1; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=1",
+ "[3] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0",
+ "[4] STRUCT 's2' size=16 vlen=3\n"
+ "\t'f1' type_id=6 bits_offset=0\n"
+ "\t'f2' type_id=5 bits_offset=32\n"
+ "\t'f3' type_id=2 bits_offset=64",
+ "[5] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[6] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=5 bits_offset=0");
+
+ ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+ int f1;\n\
+};\n\
+\n\
+struct s1___2 {\n\
+ int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+ struct s1___2 f1;\n\
+ int f2;\n\
+ int *f3;\n\
+};\n\n", "c_dump");
+
+ err = btf__dedup(btf2, NULL, NULL);
+ if (!ASSERT_OK(err, "btf_dedup"))
+ goto cleanup;
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=1",
+ "[3] STRUCT 's1' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0",
+ "[4] STRUCT 's2' size=16 vlen=3\n"
+ "\t'f1' type_id=3 bits_offset=0\n"
+ "\t'f2' type_id=1 bits_offset=32\n"
+ "\t'f3' type_id=2 bits_offset=64");
+
+ ASSERT_STREQ(btf_type_c_dump(btf2), "\
+struct s1 {\n\
+ int f1;\n\
+};\n\
+\n\
+struct s2 {\n\
+ struct s1 f1;\n\
+ int f2;\n\
+ int *f3;\n\
+};\n\n", "c_dump");
+
+cleanup:
+ btf__free(btf2);
+ btf__free(btf1);
+}
+
+static void test_split_fwd_resolve() {
+ struct btf *btf1, *btf2;
+ int err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 4); /* [2] ptr to struct s1 */
+ btf__add_ptr(btf1, 5); /* [3] ptr to struct s2 */
+ btf__add_struct(btf1, "s1", 16); /* [4] struct s1 { */
+ btf__add_field(btf1, "f1", 2, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf1, "f2", 3, 64, 0); /* struct s2 *f2; */
+ /* } */
+ btf__add_struct(btf1, "s2", 4); /* [5] struct s2 { */
+ btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf1,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=4",
+ "[3] PTR '(anon)' type_id=5",
+ "[4] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=3 bits_offset=64",
+ "[5] STRUCT 's2' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0");
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ btf__add_int(btf2, "int", 4, BTF_INT_SIGNED); /* [6] int */
+ btf__add_ptr(btf2, 10); /* [7] ptr to struct s1 */
+ btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT); /* [8] fwd for struct s2 */
+ btf__add_ptr(btf2, 8); /* [9] ptr to fwd struct s2 */
+ btf__add_struct(btf2, "s1", 16); /* [10] struct s1 { */
+ btf__add_field(btf2, "f1", 7, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf2, "f2", 9, 64, 0); /* struct s2 *f2; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=4",
+ "[3] PTR '(anon)' type_id=5",
+ "[4] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=3 bits_offset=64",
+ "[5] STRUCT 's2' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0",
+ "[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[7] PTR '(anon)' type_id=10",
+ "[8] FWD 's2' fwd_kind=struct",
+ "[9] PTR '(anon)' type_id=8",
+ "[10] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=7 bits_offset=0\n"
+ "\t'f2' type_id=9 bits_offset=64");
+
+ err = btf__dedup(btf2, NULL, NULL);
+ if (!ASSERT_OK(err, "btf_dedup"))
+ goto cleanup;
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=4",
+ "[3] PTR '(anon)' type_id=5",
+ "[4] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=3 bits_offset=64",
+ "[5] STRUCT 's2' size=4 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0");
+
+cleanup:
+ btf__free(btf2);
+ btf__free(btf1);
+}
+
+static void test_split_struct_duped() {
+ struct btf *btf1, *btf2;
+ int err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 5); /* [2] ptr to struct s1 */
+ btf__add_fwd(btf1, "s2", BTF_FWD_STRUCT); /* [3] fwd for struct s2 */
+ btf__add_ptr(btf1, 3); /* [4] ptr to fwd struct s2 */
+ btf__add_struct(btf1, "s1", 16); /* [5] struct s1 { */
+ btf__add_field(btf1, "f1", 2, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf1, "f2", 4, 64, 0); /* struct s2 *f2; */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf1,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=5",
+ "[3] FWD 's2' fwd_kind=struct",
+ "[4] PTR '(anon)' type_id=3",
+ "[5] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=4 bits_offset=64");
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ btf__add_int(btf2, "int", 4, BTF_INT_SIGNED); /* [6] int */
+ btf__add_ptr(btf2, 10); /* [7] ptr to struct s1 */
+ btf__add_fwd(btf2, "s2", BTF_FWD_STRUCT); /* [8] fwd for struct s2 */
+ btf__add_ptr(btf2, 11); /* [9] ptr to struct s2 */
+ btf__add_struct(btf2, "s1", 16); /* [10] struct s1 { */
+ btf__add_field(btf2, "f1", 7, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf2, "f2", 9, 64, 0); /* struct s2 *f2; */
+ /* } */
+ btf__add_struct(btf2, "s2", 40); /* [11] struct s2 { */
+ btf__add_field(btf2, "f1", 7, 0, 0); /* struct s1 *f1; */
+ btf__add_field(btf2, "f2", 9, 64, 0); /* struct s2 *f2; */
+ btf__add_field(btf2, "f3", 6, 128, 0); /* int f3; */
+ btf__add_field(btf2, "f4", 10, 192, 0); /* struct s1 f4; */
+ /* } */
+ btf__add_ptr(btf2, 8); /* [12] ptr to fwd struct s2 */
+ btf__add_struct(btf2, "s3", 8); /* [13] struct s3 { */
+ btf__add_field(btf2, "f1", 12, 0, 0); /* struct s2 *f1; (fwd) */
+ /* } */
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=5",
+ "[3] FWD 's2' fwd_kind=struct",
+ "[4] PTR '(anon)' type_id=3",
+ "[5] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=4 bits_offset=64",
+ "[6] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[7] PTR '(anon)' type_id=10",
+ "[8] FWD 's2' fwd_kind=struct",
+ "[9] PTR '(anon)' type_id=11",
+ "[10] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=7 bits_offset=0\n"
+ "\t'f2' type_id=9 bits_offset=64",
+ "[11] STRUCT 's2' size=40 vlen=4\n"
+ "\t'f1' type_id=7 bits_offset=0\n"
+ "\t'f2' type_id=9 bits_offset=64\n"
+ "\t'f3' type_id=6 bits_offset=128\n"
+ "\t'f4' type_id=10 bits_offset=192",
+ "[12] PTR '(anon)' type_id=8",
+ "[13] STRUCT 's3' size=8 vlen=1\n"
+ "\t'f1' type_id=12 bits_offset=0");
+
+ err = btf__dedup(btf2, NULL, NULL);
+ if (!ASSERT_OK(err, "btf_dedup"))
+ goto cleanup;
+
+ VALIDATE_RAW_BTF(
+ btf2,
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+ "[2] PTR '(anon)' type_id=5",
+ "[3] FWD 's2' fwd_kind=struct",
+ "[4] PTR '(anon)' type_id=3",
+ "[5] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=2 bits_offset=0\n"
+ "\t'f2' type_id=4 bits_offset=64",
+ "[6] PTR '(anon)' type_id=8",
+ "[7] PTR '(anon)' type_id=9",
+ "[8] STRUCT 's1' size=16 vlen=2\n"
+ "\t'f1' type_id=6 bits_offset=0\n"
+ "\t'f2' type_id=7 bits_offset=64",
+ "[9] STRUCT 's2' size=40 vlen=4\n"
+ "\t'f1' type_id=6 bits_offset=0\n"
+ "\t'f2' type_id=7 bits_offset=64\n"
+ "\t'f3' type_id=1 bits_offset=128\n"
+ "\t'f4' type_id=8 bits_offset=192",
+ "[10] STRUCT 's3' size=8 vlen=1\n"
+ "\t'f1' type_id=7 bits_offset=0");
+
+cleanup:
+ btf__free(btf2);
+ btf__free(btf1);
+}
+
+void test_btf_dedup_split()
+{
+ if (test__start_subtest("split_simple"))
+ test_split_simple();
+ if (test__start_subtest("split_struct_duped"))
+ test_split_struct_duped();
+ if (test__start_subtest("split_fwd_resolve"))
+ test_split_fwd_resolve();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
index 86ccf37e26b3..762f6a9da8b5 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_skc_cls_ingress.c
@@ -17,7 +17,7 @@
#include "test_btf_skc_cls_ingress.skel.h"
static struct test_btf_skc_cls_ingress *skel;
-struct sockaddr_in6 srv_sa6;
+static struct sockaddr_in6 srv_sa6;
static __u32 duration;
#define PROG_PIN_FILE "/sys/fs/bpf/btf_skc_cls_ingress"
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c
new file mode 100644
index 000000000000..ca7c2a91610a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <bpf/btf.h>
+
+static char *dump_buf;
+static size_t dump_buf_sz;
+static FILE *dump_buf_file;
+
+static void btf_dump_printf(void *ctx, const char *fmt, va_list args)
+{
+ vfprintf(ctx, fmt, args);
+}
+
+void test_btf_split() {
+ struct btf_dump_opts opts;
+ struct btf_dump *d = NULL;
+ const struct btf_type *t;
+ struct btf *btf1, *btf2;
+ int str_off, i, err;
+
+ btf1 = btf__new_empty();
+ if (!ASSERT_OK_PTR(btf1, "empty_main_btf"))
+ return;
+
+ btf__set_pointer_size(btf1, 8); /* enforce 64-bit arch */
+
+ btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */
+ btf__add_ptr(btf1, 1); /* [2] ptr to int */
+
+ btf__add_struct(btf1, "s1", 4); /* [3] struct s1 { */
+ btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */
+ /* } */
+
+ btf2 = btf__new_empty_split(btf1);
+ if (!ASSERT_OK_PTR(btf2, "empty_split_btf"))
+ goto cleanup;
+
+ /* pointer size should be "inherited" from main BTF */
+ ASSERT_EQ(btf__pointer_size(btf2), 8, "inherit_ptr_sz");
+
+ str_off = btf__find_str(btf2, "int");
+ ASSERT_NEQ(str_off, -ENOENT, "str_int_missing");
+
+ t = btf__type_by_id(btf2, 1);
+ if (!ASSERT_OK_PTR(t, "int_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_int(t), true, "int_kind");
+ ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "int", "int_name");
+
+ btf__add_struct(btf2, "s2", 16); /* [4] struct s2 { */
+ btf__add_field(btf2, "f1", 3, 0, 0); /* struct s1 f1; */
+ btf__add_field(btf2, "f2", 1, 32, 0); /* int f2; */
+ btf__add_field(btf2, "f3", 2, 64, 0); /* int *f3; */
+ /* } */
+
+ t = btf__type_by_id(btf1, 4);
+ ASSERT_NULL(t, "split_type_in_main");
+
+ t = btf__type_by_id(btf2, 4);
+ if (!ASSERT_OK_PTR(t, "split_struct_type"))
+ goto cleanup;
+ ASSERT_EQ(btf_is_struct(t), true, "split_struct_kind");
+ ASSERT_EQ(btf_vlen(t), 3, "split_struct_vlen");
+ ASSERT_STREQ(btf__str_by_offset(btf2, t->name_off), "s2", "split_struct_name");
+
+ /* BTF-to-C dump of split BTF */
+ dump_buf_file = open_memstream(&dump_buf, &dump_buf_sz);
+ if (!ASSERT_OK_PTR(dump_buf_file, "dump_memstream"))
+ return;
+ opts.ctx = dump_buf_file;
+ d = btf_dump__new(btf2, NULL, &opts, btf_dump_printf);
+ if (!ASSERT_OK_PTR(d, "btf_dump__new"))
+ goto cleanup;
+ for (i = 1; i <= btf__get_nr_types(btf2); i++) {
+ err = btf_dump__dump_type(d, i);
+ ASSERT_OK(err, "dump_type_ok");
+ }
+ fflush(dump_buf_file);
+ dump_buf[dump_buf_sz] = 0; /* some libc implementations don't do this */
+ ASSERT_STREQ(dump_buf,
+"struct s1 {\n"
+" int f1;\n"
+"};\n"
+"\n"
+"struct s2 {\n"
+" struct s1 f1;\n"
+" int f2;\n"
+" int *f3;\n"
+"};\n\n", "c_dump");
+
+cleanup:
+ if (dump_buf_file)
+ fclose(dump_buf_file);
+ free(dump_buf);
+ btf_dump__free(d);
+ btf__free(btf1);
+ btf__free(btf2);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index 314e1e7c36df..f36da15b134f 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -2,6 +2,7 @@
/* Copyright (c) 2020 Facebook */
#include <test_progs.h>
#include <bpf/btf.h>
+#include "btf_helpers.h"
static int duration = 0;
@@ -39,6 +40,8 @@ void test_btf_write() {
ASSERT_EQ(t->size, 4, "int_sz");
ASSERT_EQ(btf_int_encoding(t), BTF_INT_SIGNED, "int_enc");
ASSERT_EQ(btf_int_bits(t), 32, "int_bits");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 1),
+ "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", "raw_dump");
/* invalid int size */
id = btf__add_int(btf, "bad sz int", 7, 0);
@@ -59,24 +62,32 @@ void test_btf_write() {
t = btf__type_by_id(btf, 2);
ASSERT_EQ(btf_kind(t), BTF_KIND_PTR, "ptr_kind");
ASSERT_EQ(t->type, 1, "ptr_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 2),
+ "[2] PTR '(anon)' type_id=1", "raw_dump");
id = btf__add_const(btf, 5); /* points forward to restrict */
ASSERT_EQ(id, 3, "const_id");
t = btf__type_by_id(btf, 3);
ASSERT_EQ(btf_kind(t), BTF_KIND_CONST, "const_kind");
ASSERT_EQ(t->type, 5, "const_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 3),
+ "[3] CONST '(anon)' type_id=5", "raw_dump");
id = btf__add_volatile(btf, 3);
ASSERT_EQ(id, 4, "volatile_id");
t = btf__type_by_id(btf, 4);
ASSERT_EQ(btf_kind(t), BTF_KIND_VOLATILE, "volatile_kind");
ASSERT_EQ(t->type, 3, "volatile_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 4),
+ "[4] VOLATILE '(anon)' type_id=3", "raw_dump");
id = btf__add_restrict(btf, 4);
ASSERT_EQ(id, 5, "restrict_id");
t = btf__type_by_id(btf, 5);
ASSERT_EQ(btf_kind(t), BTF_KIND_RESTRICT, "restrict_kind");
ASSERT_EQ(t->type, 4, "restrict_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 5),
+ "[5] RESTRICT '(anon)' type_id=4", "raw_dump");
/* ARRAY */
id = btf__add_array(btf, 1, 2, 10); /* int *[10] */
@@ -86,6 +97,8 @@ void test_btf_write() {
ASSERT_EQ(btf_array(t)->index_type, 1, "array_index_type");
ASSERT_EQ(btf_array(t)->type, 2, "array_elem_type");
ASSERT_EQ(btf_array(t)->nelems, 10, "array_nelems");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 6),
+ "[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10", "raw_dump");
/* STRUCT */
err = btf__add_field(btf, "field", 1, 0, 0);
@@ -113,6 +126,10 @@ void test_btf_write() {
ASSERT_EQ(m->type, 1, "f2_type");
ASSERT_EQ(btf_member_bit_offset(t, 1), 32, "f2_bit_off");
ASSERT_EQ(btf_member_bitfield_size(t, 1), 16, "f2_bit_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 7),
+ "[7] STRUCT 's1' size=8 vlen=2\n"
+ "\t'f1' type_id=1 bits_offset=0\n"
+ "\t'f2' type_id=1 bits_offset=32 bitfield_size=16", "raw_dump");
/* UNION */
id = btf__add_union(btf, "u1", 8);
@@ -136,6 +153,9 @@ void test_btf_write() {
ASSERT_EQ(m->type, 1, "f1_type");
ASSERT_EQ(btf_member_bit_offset(t, 0), 0, "f1_bit_off");
ASSERT_EQ(btf_member_bitfield_size(t, 0), 16, "f1_bit_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 8),
+ "[8] UNION 'u1' size=8 vlen=1\n"
+ "\t'f1' type_id=1 bits_offset=0 bitfield_size=16", "raw_dump");
/* ENUM */
id = btf__add_enum(btf, "e1", 4);
@@ -156,6 +176,10 @@ void test_btf_write() {
v = btf_enum(t) + 1;
ASSERT_STREQ(btf__str_by_offset(btf, v->name_off), "v2", "v2_name");
ASSERT_EQ(v->val, 2, "v2_val");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 9),
+ "[9] ENUM 'e1' size=4 vlen=2\n"
+ "\t'v1' val=1\n"
+ "\t'v2' val=2", "raw_dump");
/* FWDs */
id = btf__add_fwd(btf, "struct_fwd", BTF_FWD_STRUCT);
@@ -164,6 +188,8 @@ void test_btf_write() {
ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "struct_fwd", "fwd_name");
ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
ASSERT_EQ(btf_kflag(t), 0, "fwd_kflag");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 10),
+ "[10] FWD 'struct_fwd' fwd_kind=struct", "raw_dump");
id = btf__add_fwd(btf, "union_fwd", BTF_FWD_UNION);
ASSERT_EQ(id, 11, "union_fwd_id");
@@ -171,6 +197,8 @@ void test_btf_write() {
ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "union_fwd", "fwd_name");
ASSERT_EQ(btf_kind(t), BTF_KIND_FWD, "fwd_kind");
ASSERT_EQ(btf_kflag(t), 1, "fwd_kflag");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 11),
+ "[11] FWD 'union_fwd' fwd_kind=union", "raw_dump");
id = btf__add_fwd(btf, "enum_fwd", BTF_FWD_ENUM);
ASSERT_EQ(id, 12, "enum_fwd_id");
@@ -179,6 +207,8 @@ void test_btf_write() {
ASSERT_EQ(btf_kind(t), BTF_KIND_ENUM, "enum_fwd_kind");
ASSERT_EQ(btf_vlen(t), 0, "enum_fwd_kind");
ASSERT_EQ(t->size, 4, "enum_fwd_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 12),
+ "[12] ENUM 'enum_fwd' size=4 vlen=0", "raw_dump");
/* TYPEDEF */
id = btf__add_typedef(btf, "typedef1", 1);
@@ -187,6 +217,8 @@ void test_btf_write() {
ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "typedef1", "typedef_name");
ASSERT_EQ(btf_kind(t), BTF_KIND_TYPEDEF, "typedef_kind");
ASSERT_EQ(t->type, 1, "typedef_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 13),
+ "[13] TYPEDEF 'typedef1' type_id=1", "raw_dump");
/* FUNC & FUNC_PROTO */
id = btf__add_func(btf, "func1", BTF_FUNC_GLOBAL, 15);
@@ -196,6 +228,8 @@ void test_btf_write() {
ASSERT_EQ(t->type, 15, "func_type");
ASSERT_EQ(btf_kind(t), BTF_KIND_FUNC, "func_kind");
ASSERT_EQ(btf_vlen(t), BTF_FUNC_GLOBAL, "func_vlen");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 14),
+ "[14] FUNC 'func1' type_id=15 linkage=global", "raw_dump");
id = btf__add_func_proto(btf, 1);
ASSERT_EQ(id, 15, "func_proto_id");
@@ -214,6 +248,10 @@ void test_btf_write() {
p = btf_params(t) + 1;
ASSERT_STREQ(btf__str_by_offset(btf, p->name_off), "p2", "p2_name");
ASSERT_EQ(p->type, 2, "p2_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 15),
+ "[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+ "\t'p1' type_id=1\n"
+ "\t'p2' type_id=2", "raw_dump");
/* VAR */
id = btf__add_var(btf, "var1", BTF_VAR_GLOBAL_ALLOCATED, 1);
@@ -223,6 +261,8 @@ void test_btf_write() {
ASSERT_EQ(btf_kind(t), BTF_KIND_VAR, "var_kind");
ASSERT_EQ(t->type, 1, "var_type");
ASSERT_EQ(btf_var(t)->linkage, BTF_VAR_GLOBAL_ALLOCATED, "var_type");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 16),
+ "[16] VAR 'var1' type_id=1, linkage=global-alloc", "raw_dump");
/* DATASECT */
id = btf__add_datasec(btf, "datasec1", 12);
@@ -239,6 +279,9 @@ void test_btf_write() {
ASSERT_EQ(vi->type, 1, "v1_type");
ASSERT_EQ(vi->offset, 4, "v1_off");
ASSERT_EQ(vi->size, 8, "v1_sz");
+ ASSERT_STREQ(btf_type_raw_dump(btf, 17),
+ "[17] DATASEC 'datasec1' size=12 vlen=1\n"
+ "\ttype_id=1 offset=4 size=8", "raw_dump");
btf__free(btf);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 30e40ff4b0d8..06eb956ff7bb 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <test_progs.h>
#include "progs/core_reloc_types.h"
+#include "bpf_testmod/bpf_testmod.h"
#include <sys/mman.h>
#include <sys/syscall.h>
#include <bpf/btf.h>
@@ -9,6 +10,30 @@ static int duration = 0;
#define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name)
+#define MODULES_CASE(name, sec_name, tp_name) { \
+ .case_name = name, \
+ .bpf_obj_file = "test_core_reloc_module.o", \
+ .btf_src_file = NULL, /* find in kernel module BTFs */ \
+ .input = "", \
+ .input_len = 0, \
+ .output = STRUCT_TO_CHAR_PTR(core_reloc_module_output) { \
+ .read_ctx_sz = sizeof(struct bpf_testmod_test_read_ctx),\
+ .read_ctx_exists = true, \
+ .buf_exists = true, \
+ .len_exists = true, \
+ .off_exists = true, \
+ .len = 123, \
+ .off = 0, \
+ .comm = "test_progs", \
+ .comm_len = sizeof("test_progs"), \
+ }, \
+ .output_len = sizeof(struct core_reloc_module_output), \
+ .prog_sec_name = sec_name, \
+ .raw_tp_name = tp_name, \
+ .trigger = trigger_module_test_read, \
+ .needs_testmod = true, \
+}
+
#define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \
.a = 42, \
.b = 0xc001, \
@@ -211,7 +236,7 @@ static int duration = 0;
.output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output) \
__VA_ARGS__, \
.output_len = sizeof(struct core_reloc_bitfields_output), \
- .direct_raw_tp = true, \
+ .prog_sec_name = "tp_btf/sys_enter", \
}
@@ -222,7 +247,7 @@ static int duration = 0;
}, { \
BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \
"direct:", name), \
- .direct_raw_tp = true, \
+ .prog_sec_name = "tp_btf/sys_enter", \
.fails = true, \
}
@@ -309,6 +334,7 @@ static int duration = 0;
struct core_reloc_test_case;
typedef int (*setup_test_fn)(struct core_reloc_test_case *test);
+typedef int (*trigger_test_fn)(const struct core_reloc_test_case *test);
struct core_reloc_test_case {
const char *case_name;
@@ -319,9 +345,12 @@ struct core_reloc_test_case {
const char *output;
int output_len;
bool fails;
+ bool needs_testmod;
bool relaxed_core_relocs;
- bool direct_raw_tp;
+ const char *prog_sec_name;
+ const char *raw_tp_name;
setup_test_fn setup;
+ trigger_test_fn trigger;
};
static int find_btf_type(const struct btf *btf, const char *name, __u32 kind)
@@ -451,6 +480,23 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test)
return 0;
}
+static int trigger_module_test_read(const struct core_reloc_test_case *test)
+{
+ struct core_reloc_module_output *exp = (void *)test->output;
+ int fd, err;
+
+ fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+ err = -errno;
+ if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err))
+ return err;
+
+ read(fd, NULL, exp->len); /* request expected number of bytes */
+ close(fd);
+
+ return 0;
+}
+
+
static struct core_reloc_test_case test_cases[] = {
/* validate we can find kernel image and use its BTF for relocs */
{
@@ -467,6 +513,10 @@ static struct core_reloc_test_case test_cases[] = {
.output_len = sizeof(struct core_reloc_kernel_output),
},
+ /* validate we can find kernel module BTF types for relocs/attach */
+ MODULES_CASE("module_probed", "raw_tp/bpf_testmod_test_read", "bpf_testmod_test_read"),
+ MODULES_CASE("module_direct", "tp_btf/bpf_testmod_test_read", NULL),
+
/* validate BPF program can use multiple flavors to match against
* single target BTF type
*/
@@ -779,6 +829,11 @@ void test_core_reloc(void)
if (!test__start_subtest(test_case->case_name))
continue;
+ if (test_case->needs_testmod && !env.has_testmod) {
+ test__skip();
+ continue;
+ }
+
if (test_case->setup) {
err = test_case->setup(test_case);
if (CHECK(err, "test_setup", "test #%d setup failed: %d\n", i, err))
@@ -790,13 +845,11 @@ void test_core_reloc(void)
test_case->bpf_obj_file, PTR_ERR(obj)))
continue;
- /* for typed raw tracepoints, NULL should be specified */
- if (test_case->direct_raw_tp) {
- probe_name = "tp_btf/sys_enter";
- tp_name = NULL;
- } else {
- probe_name = "raw_tracepoint/sys_enter";
- tp_name = "sys_enter";
+ probe_name = "raw_tracepoint/sys_enter";
+ tp_name = "sys_enter";
+ if (test_case->prog_sec_name) {
+ probe_name = test_case->prog_sec_name;
+ tp_name = test_case->raw_tp_name; /* NULL for tp_btf */
}
prog = bpf_object__find_program_by_title(obj, probe_name);
@@ -837,7 +890,12 @@ void test_core_reloc(void)
goto cleanup;
/* trigger test run */
- usleep(1);
+ if (test_case->trigger) {
+ if (!ASSERT_OK(test_case->trigger(test_case), "test_trigger"))
+ goto cleanup;
+ } else {
+ usleep(1);
+ }
if (data->skip) {
test__skip();
diff --git a/tools/testing/selftests/bpf/prog_tests/hash_large_key.c b/tools/testing/selftests/bpf/prog_tests/hash_large_key.c
new file mode 100644
index 000000000000..34684c0fc76d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/hash_large_key.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include "test_hash_large_key.skel.h"
+
+void test_hash_large_key(void)
+{
+ int err, value = 21, duration = 0, hash_map_fd;
+ struct test_hash_large_key *skel;
+
+ struct bigelement {
+ int a;
+ char b[4096];
+ long long c;
+ } key;
+ bzero(&key, sizeof(key));
+
+ skel = test_hash_large_key__open_and_load();
+ if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
+ return;
+
+ hash_map_fd = bpf_map__fd(skel->maps.hash_map);
+ if (CHECK(hash_map_fd < 0, "bpf_map__fd", "failed\n"))
+ goto cleanup;
+
+ err = test_hash_large_key__attach(skel);
+ if (CHECK(err, "attach_raw_tp", "err %d\n", err))
+ goto cleanup;
+
+ err = bpf_map_update_elem(hash_map_fd, &key, &value, BPF_ANY);
+ if (CHECK(err, "bpf_map_update_elem", "errno=%d\n", errno))
+ goto cleanup;
+
+ key.c = 1;
+ err = bpf_map_lookup_elem(hash_map_fd, &key, &value);
+ if (CHECK(err, "bpf_map_lookup_elem", "errno=%d\n", errno))
+ goto cleanup;
+
+ CHECK_FAIL(value != 42);
+
+cleanup:
+ test_hash_large_key__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
new file mode 100644
index 000000000000..50796b651f72
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <test_progs.h>
+#include "test_module_attach.skel.h"
+
+static int duration;
+
+static int trigger_module_test_read(int read_sz)
+{
+ int fd, err;
+
+ fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+ err = -errno;
+ if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err))
+ return err;
+
+ read(fd, NULL, read_sz);
+ close(fd);
+
+ return 0;
+}
+
+void test_module_attach(void)
+{
+ const int READ_SZ = 456;
+ struct test_module_attach* skel;
+ struct test_module_attach__bss *bss;
+ int err;
+
+ skel = test_module_attach__open();
+ if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+ return;
+
+ err = bpf_program__set_attach_target(skel->progs.handle_fentry_manual,
+ 0, "bpf_testmod_test_read");
+ ASSERT_OK(err, "set_attach_target");
+
+ err = test_module_attach__load(skel);
+ if (CHECK(err, "skel_load", "failed to load skeleton\n"))
+ return;
+
+ bss = skel->bss;
+
+ err = test_module_attach__attach(skel);
+ if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+ goto cleanup;
+
+ /* trigger tracepoint */
+ ASSERT_OK(trigger_module_test_read(READ_SZ), "trigger_read");
+
+ ASSERT_EQ(bss->raw_tp_read_sz, READ_SZ, "raw_tp");
+ ASSERT_EQ(bss->tp_btf_read_sz, READ_SZ, "tp_btf");
+ ASSERT_EQ(bss->fentry_read_sz, READ_SZ, "fentry");
+ ASSERT_EQ(bss->fentry_manual_read_sz, READ_SZ, "fentry_manual");
+ ASSERT_EQ(bss->fexit_read_sz, READ_SZ, "fexit");
+ ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
+ ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
+
+cleanup:
+ test_module_attach__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index c1650548433c..fddbc5db5d6a 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -217,9 +217,15 @@ void test_ringbuf(void)
if (CHECK(err, "join_bg", "err %d\n", err))
goto cleanup;
- if (CHECK(bg_ret != 1, "bg_ret", "epoll_wait result: %ld", bg_ret))
+ if (CHECK(bg_ret <= 0, "bg_ret", "epoll_wait result: %ld", bg_ret))
goto cleanup;
+ /* due to timing variations, there could still be non-notified
+ * samples, so consume them here to collect all the samples
+ */
+ err = ring_buffer__consume(ringbuf);
+ CHECK(err < 0, "rb_consume", "failed: %d\b", err);
+
/* 3 rounds, 2 samples each */
cnt = atomic_xchg(&sample_cnt, 0);
CHECK(cnt != 6, "cnt", "exp %d samples, got %d\n", 6, cnt);
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
index 78e450609803..d37161e59bb2 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf_multi.c
@@ -81,7 +81,7 @@ void test_ringbuf_multi(void)
/* poll for samples, should get 2 ringbufs back */
err = ring_buffer__poll(ringbuf, -1);
- if (CHECK(err != 4, "poll_res", "expected 4 records, got %d\n", err))
+ if (CHECK(err != 2, "poll_res", "expected 2 records, got %d\n", err))
goto cleanup;
/* expect extra polling to return nothing */
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
new file mode 100644
index 000000000000..2b392590e8ca
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <sys/types.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "test_sk_storage_trace_itself.skel.h"
+#include "test_sk_storage_tracing.skel.h"
+
+#define LO_ADDR6 "::1"
+#define TEST_COMM "test_progs"
+
+struct sk_stg {
+ __u32 pid;
+ __u32 last_notclose_state;
+ char comm[16];
+};
+
+static struct test_sk_storage_tracing *skel;
+static __u32 duration;
+static pid_t my_pid;
+
+static int check_sk_stg(int sk_fd, __u32 expected_state)
+{
+ struct sk_stg sk_stg;
+ int err;
+
+ err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.sk_stg_map), &sk_fd,
+ &sk_stg);
+ if (!ASSERT_OK(err, "map_lookup(sk_stg_map)"))
+ return -1;
+
+ if (!ASSERT_EQ(sk_stg.last_notclose_state, expected_state,
+ "last_notclose_state"))
+ return -1;
+
+ if (!ASSERT_EQ(sk_stg.pid, my_pid, "pid"))
+ return -1;
+
+ if (!ASSERT_STREQ(sk_stg.comm, skel->bss->task_comm, "task_comm"))
+ return -1;
+
+ return 0;
+}
+
+static void do_test(void)
+{
+ int listen_fd = -1, passive_fd = -1, active_fd = -1, value = 1, err;
+ char abyte;
+
+ listen_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+ if (CHECK(listen_fd == -1, "start_server",
+ "listen_fd:%d errno:%d\n", listen_fd, errno))
+ return;
+
+ active_fd = connect_to_fd(listen_fd, 0);
+ if (CHECK(active_fd == -1, "connect_to_fd", "active_fd:%d errno:%d\n",
+ active_fd, errno))
+ goto out;
+
+ err = bpf_map_update_elem(bpf_map__fd(skel->maps.del_sk_stg_map),
+ &active_fd, &value, 0);
+ if (!ASSERT_OK(err, "map_update(del_sk_stg_map)"))
+ goto out;
+
+ passive_fd = accept(listen_fd, NULL, 0);
+ if (CHECK(passive_fd == -1, "accept", "passive_fd:%d errno:%d\n",
+ passive_fd, errno))
+ goto out;
+
+ shutdown(active_fd, SHUT_WR);
+ err = read(passive_fd, &abyte, 1);
+ if (!ASSERT_OK(err, "read(passive_fd)"))
+ goto out;
+
+ shutdown(passive_fd, SHUT_WR);
+ err = read(active_fd, &abyte, 1);
+ if (!ASSERT_OK(err, "read(active_fd)"))
+ goto out;
+
+ err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.del_sk_stg_map),
+ &active_fd, &value);
+ if (!ASSERT_ERR(err, "map_lookup(del_sk_stg_map)"))
+ goto out;
+
+ err = check_sk_stg(listen_fd, BPF_TCP_LISTEN);
+ if (!ASSERT_OK(err, "listen_fd sk_stg"))
+ goto out;
+
+ err = check_sk_stg(active_fd, BPF_TCP_FIN_WAIT2);
+ if (!ASSERT_OK(err, "active_fd sk_stg"))
+ goto out;
+
+ err = check_sk_stg(passive_fd, BPF_TCP_LAST_ACK);
+ ASSERT_OK(err, "passive_fd sk_stg");
+
+out:
+ if (active_fd != -1)
+ close(active_fd);
+ if (passive_fd != -1)
+ close(passive_fd);
+ if (listen_fd != -1)
+ close(listen_fd);
+}
+
+void test_sk_storage_tracing(void)
+{
+ struct test_sk_storage_trace_itself *skel_itself;
+ int err;
+
+ my_pid = getpid();
+
+ skel_itself = test_sk_storage_trace_itself__open_and_load();
+
+ if (!ASSERT_NULL(skel_itself, "test_sk_storage_trace_itself")) {
+ test_sk_storage_trace_itself__destroy(skel_itself);
+ return;
+ }
+
+ skel = test_sk_storage_tracing__open_and_load();
+ if (!ASSERT_OK_PTR(skel, "test_sk_storage_tracing"))
+ return;
+
+ err = test_sk_storage_tracing__attach(skel);
+ if (!ASSERT_OK(err, "test_sk_storage_tracing__attach")) {
+ test_sk_storage_tracing__destroy(skel);
+ return;
+ }
+
+ do_test();
+
+ test_sk_storage_tracing__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
index c85174cdcb77..08d19cafd5e8 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_hdr_options.c
@@ -18,12 +18,12 @@
#define LO_ADDR6 "::1"
#define CG_NAME "/tcpbpf-hdr-opt-test"
-struct bpf_test_option exp_passive_estab_in;
-struct bpf_test_option exp_active_estab_in;
-struct bpf_test_option exp_passive_fin_in;
-struct bpf_test_option exp_active_fin_in;
-struct hdr_stg exp_passive_hdr_stg;
-struct hdr_stg exp_active_hdr_stg = { .active = true, };
+static struct bpf_test_option exp_passive_estab_in;
+static struct bpf_test_option exp_active_estab_in;
+static struct bpf_test_option exp_passive_fin_in;
+static struct bpf_test_option exp_active_fin_in;
+static struct hdr_stg exp_passive_hdr_stg;
+static struct hdr_stg exp_active_hdr_stg = { .active = true, };
static struct test_misc_tcp_hdr_options *misc_skel;
static struct test_tcp_hdr_options *skel;
diff --git a/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c b/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c
new file mode 100644
index 000000000000..87923d2865b7
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+
+#include "test_tcpbpf.h"
+#include "test_tcpbpf_kern.skel.h"
+
+#define LO_ADDR6 "::1"
+#define CG_NAME "/tcpbpf-user-test"
+
+static __u32 duration;
+
+static void verify_result(struct tcpbpf_globals *result)
+{
+ __u32 expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+ (1 << BPF_SOCK_OPS_RWND_INIT) |
+ (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+ (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+ (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+ (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+ (1 << BPF_SOCK_OPS_STATE_CB) |
+ (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
+
+ /* check global map */
+ CHECK(expected_events != result->event_map, "event_map",
+ "unexpected event_map: actual 0x%08x != expected 0x%08x\n",
+ result->event_map, expected_events);
+
+ ASSERT_EQ(result->bytes_received, 501, "bytes_received");
+ ASSERT_EQ(result->bytes_acked, 1002, "bytes_acked");
+ ASSERT_EQ(result->data_segs_in, 1, "data_segs_in");
+ ASSERT_EQ(result->data_segs_out, 1, "data_segs_out");
+ ASSERT_EQ(result->bad_cb_test_rv, 0x80, "bad_cb_test_rv");
+ ASSERT_EQ(result->good_cb_test_rv, 0, "good_cb_test_rv");
+ ASSERT_EQ(result->num_listen, 1, "num_listen");
+
+ /* 3 comes from one listening socket + both ends of the connection */
+ ASSERT_EQ(result->num_close_events, 3, "num_close_events");
+
+ /* check setsockopt for SAVE_SYN */
+ ASSERT_EQ(result->tcp_save_syn, 0, "tcp_save_syn");
+
+ /* check getsockopt for SAVED_SYN */
+ ASSERT_EQ(result->tcp_saved_syn, 1, "tcp_saved_syn");
+
+ /* check getsockopt for window_clamp */
+ ASSERT_EQ(result->window_clamp_client, 9216, "window_clamp_client");
+ ASSERT_EQ(result->window_clamp_server, 9216, "window_clamp_server");
+}
+
+static void run_test(struct tcpbpf_globals *result)
+{
+ int listen_fd = -1, cli_fd = -1, accept_fd = -1;
+ char buf[1000];
+ int err = -1;
+ int i, rv;
+
+ listen_fd = start_server(AF_INET6, SOCK_STREAM, LO_ADDR6, 0, 0);
+ if (CHECK(listen_fd == -1, "start_server", "listen_fd:%d errno:%d\n",
+ listen_fd, errno))
+ goto done;
+
+ cli_fd = connect_to_fd(listen_fd, 0);
+ if (CHECK(cli_fd == -1, "connect_to_fd(listen_fd)",
+ "cli_fd:%d errno:%d\n", cli_fd, errno))
+ goto done;
+
+ accept_fd = accept(listen_fd, NULL, NULL);
+ if (CHECK(accept_fd == -1, "accept(listen_fd)",
+ "accept_fd:%d errno:%d\n", accept_fd, errno))
+ goto done;
+
+ /* Send 1000B of '+'s from cli_fd -> accept_fd */
+ for (i = 0; i < 1000; i++)
+ buf[i] = '+';
+
+ rv = send(cli_fd, buf, 1000, 0);
+ if (CHECK(rv != 1000, "send(cli_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ rv = recv(accept_fd, buf, 1000, 0);
+ if (CHECK(rv != 1000, "recv(accept_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ /* Send 500B of '.'s from accept_fd ->cli_fd */
+ for (i = 0; i < 500; i++)
+ buf[i] = '.';
+
+ rv = send(accept_fd, buf, 500, 0);
+ if (CHECK(rv != 500, "send(accept_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ rv = recv(cli_fd, buf, 500, 0);
+ if (CHECK(rv != 500, "recv(cli_fd)", "rv:%d errno:%d\n", rv, errno))
+ goto done;
+
+ /*
+ * shutdown accept first to guarantee correct ordering for
+ * bytes_received and bytes_acked when we go to verify the results.
+ */
+ shutdown(accept_fd, SHUT_WR);
+ err = recv(cli_fd, buf, 1, 0);
+ if (CHECK(err, "recv(cli_fd) for fin", "err:%d errno:%d\n", err, errno))
+ goto done;
+
+ shutdown(cli_fd, SHUT_WR);
+ err = recv(accept_fd, buf, 1, 0);
+ CHECK(err, "recv(accept_fd) for fin", "err:%d errno:%d\n", err, errno);
+done:
+ if (accept_fd != -1)
+ close(accept_fd);
+ if (cli_fd != -1)
+ close(cli_fd);
+ if (listen_fd != -1)
+ close(listen_fd);
+
+ if (!err)
+ verify_result(result);
+}
+
+void test_tcpbpf_user(void)
+{
+ struct test_tcpbpf_kern *skel;
+ int cg_fd = -1;
+
+ skel = test_tcpbpf_kern__open_and_load();
+ if (CHECK(!skel, "open and load skel", "failed"))
+ return;
+
+ cg_fd = test__join_cgroup(CG_NAME);
+ if (CHECK(cg_fd < 0, "test__join_cgroup(" CG_NAME ")",
+ "cg_fd:%d errno:%d", cg_fd, errno))
+ goto err;
+
+ skel->links.bpf_testcb = bpf_program__attach_cgroup(skel->progs.bpf_testcb, cg_fd);
+ if (!ASSERT_OK_PTR(skel->links.bpf_testcb, "attach_cgroup(bpf_testcb)"))
+ goto err;
+
+ run_test(&skel->bss->global);
+
+err:
+ if (cg_fd != -1)
+ close(cg_fd);
+ test_tcpbpf_kern__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
new file mode 100644
index 000000000000..2559bb775762
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <linux/limits.h>
+
+#include "bprm_opts.skel.h"
+#include "network_helpers.h"
+
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open 434
+#endif
+
+static const char * const bash_envp[] = { "TMPDIR=shouldnotbeset", NULL };
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+ return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static int update_storage(int map_fd, int secureexec)
+{
+ int task_fd, ret = 0;
+
+ task_fd = sys_pidfd_open(getpid(), 0);
+ if (task_fd < 0)
+ return errno;
+
+ ret = bpf_map_update_elem(map_fd, &task_fd, &secureexec, BPF_NOEXIST);
+ if (ret)
+ ret = errno;
+
+ close(task_fd);
+ return ret;
+}
+
+static int run_set_secureexec(int map_fd, int secureexec)
+{
+ int child_pid, child_status, ret, null_fd;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ null_fd = open("/dev/null", O_WRONLY);
+ if (null_fd == -1)
+ exit(errno);
+ dup2(null_fd, STDOUT_FILENO);
+ dup2(null_fd, STDERR_FILENO);
+ close(null_fd);
+
+ /* Ensure that all executions from hereon are
+ * secure by setting a local storage which is read by
+ * the bprm_creds_for_exec hook and sets bprm->secureexec.
+ */
+ ret = update_storage(map_fd, secureexec);
+ if (ret)
+ exit(ret);
+
+ /* If the binary is executed with securexec=1, the dynamic
+ * loader ingores and unsets certain variables like LD_PRELOAD,
+ * TMPDIR etc. TMPDIR is used here to simplify the example, as
+ * LD_PRELOAD requires a real .so file.
+ *
+ * If the value of TMPDIR is set, the bash command returns 10
+ * and if the value is unset, it returns 20.
+ */
+ execle("/bin/bash", "bash", "-c",
+ "[[ -z \"${TMPDIR}\" ]] || exit 10 && exit 20", NULL,
+ bash_envp);
+ exit(errno);
+ } else if (child_pid > 0) {
+ waitpid(child_pid, &child_status, 0);
+ ret = WEXITSTATUS(child_status);
+
+ /* If a secureexec occurred, the exit status should be 20 */
+ if (secureexec && ret == 20)
+ return 0;
+
+ /* If normal execution happened, the exit code should be 10 */
+ if (!secureexec && ret == 10)
+ return 0;
+ }
+
+ return -EINVAL;
+}
+
+void test_test_bprm_opts(void)
+{
+ int err, duration = 0;
+ struct bprm_opts *skel = NULL;
+
+ skel = bprm_opts__open_and_load();
+ if (CHECK(!skel, "skel_load", "skeleton failed\n"))
+ goto close_prog;
+
+ err = bprm_opts__attach(skel);
+ if (CHECK(err, "attach", "attach failed: %d\n", err))
+ goto close_prog;
+
+ /* Run the test with the secureexec bit unset */
+ err = run_set_secureexec(bpf_map__fd(skel->maps.secure_exec_task_map),
+ 0 /* secureexec */);
+ if (CHECK(err, "run_set_secureexec:0", "err = %d\n", err))
+ goto close_prog;
+
+ /* Run the test with the secureexec bit set */
+ err = run_set_secureexec(bpf_map__fd(skel->maps.secure_exec_task_map),
+ 1 /* secureexec */);
+ if (CHECK(err, "run_set_secureexec:1", "err = %d\n", err))
+ goto close_prog;
+
+close_prog:
+ bprm_opts__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
new file mode 100644
index 000000000000..61fca681d524
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/wait.h>
+#include <test_progs.h>
+
+#include "ima.skel.h"
+
+static int run_measured_process(const char *measured_dir, u32 *monitored_pid)
+{
+ int child_pid, child_status;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ *monitored_pid = getpid();
+ execlp("./ima_setup.sh", "./ima_setup.sh", "run", measured_dir,
+ NULL);
+ exit(errno);
+
+ } else if (child_pid > 0) {
+ waitpid(child_pid, &child_status, 0);
+ return WEXITSTATUS(child_status);
+ }
+
+ return -EINVAL;
+}
+
+void test_test_ima(void)
+{
+ char measured_dir_template[] = "/tmp/ima_measuredXXXXXX";
+ const char *measured_dir;
+ char cmd[256];
+
+ int err, duration = 0;
+ struct ima *skel = NULL;
+
+ skel = ima__open_and_load();
+ if (CHECK(!skel, "skel_load", "skeleton failed\n"))
+ goto close_prog;
+
+ err = ima__attach(skel);
+ if (CHECK(err, "attach", "attach failed: %d\n", err))
+ goto close_prog;
+
+ measured_dir = mkdtemp(measured_dir_template);
+ if (CHECK(measured_dir == NULL, "mkdtemp", "err %d\n", errno))
+ goto close_prog;
+
+ snprintf(cmd, sizeof(cmd), "./ima_setup.sh setup %s", measured_dir);
+ if (CHECK_FAIL(system(cmd)))
+ goto close_clean;
+
+ err = run_measured_process(measured_dir, &skel->bss->monitored_pid);
+ if (CHECK(err, "run_measured_process", "err = %d\n", err))
+ goto close_clean;
+
+ CHECK(skel->data->ima_hash_ret < 0, "ima_hash_ret",
+ "ima_hash_ret = %ld\n", skel->data->ima_hash_ret);
+
+ CHECK(skel->bss->ima_hash == 0, "ima_hash",
+ "ima_hash = %lu\n", skel->bss->ima_hash);
+
+close_clean:
+ snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir);
+ CHECK_FAIL(system(cmd));
+close_prog:
+ ima__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
index 91cd6f357246..c0fe73a17ed1 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c
@@ -4,30 +4,173 @@
* Copyright (C) 2020 Google LLC.
*/
+#include <asm-generic/errno-base.h>
+#include <sys/stat.h>
#include <test_progs.h>
#include <linux/limits.h>
#include "local_storage.skel.h"
#include "network_helpers.h"
-int create_and_unlink_file(void)
+#ifndef __NR_pidfd_open
+#define __NR_pidfd_open 434
+#endif
+
+static inline int sys_pidfd_open(pid_t pid, unsigned int flags)
+{
+ return syscall(__NR_pidfd_open, pid, flags);
+}
+
+static unsigned int duration;
+
+#define TEST_STORAGE_VALUE 0xbeefdead
+
+struct storage {
+ void *inode;
+ unsigned int value;
+ /* Lock ensures that spin locked versions of local stoage operations
+ * also work, most operations in this tests are still single threaded
+ */
+ struct bpf_spin_lock lock;
+};
+
+/* Copies an rm binary to a temp file. dest is a mkstemp template */
+static int copy_rm(char *dest)
{
- char fname[PATH_MAX] = "/tmp/fileXXXXXX";
- int fd;
+ int fd_in, fd_out = -1, ret = 0;
+ struct stat stat;
+ char *buf = NULL;
+
+ fd_in = open("/bin/rm", O_RDONLY);
+ if (fd_in < 0)
+ return -errno;
+
+ fd_out = mkstemp(dest);
+ if (fd_out < 0) {
+ ret = -errno;
+ goto out;
+ }
+
+ ret = fstat(fd_in, &stat);
+ if (ret == -1) {
+ ret = -errno;
+ goto out;
+ }
+
+ buf = malloc(stat.st_blksize);
+ if (!buf) {
+ ret = -errno;
+ goto out;
+ }
+
+ while (ret = read(fd_in, buf, stat.st_blksize), ret > 0) {
+ ret = write(fd_out, buf, ret);
+ if (ret < 0) {
+ ret = -errno;
+ goto out;
+
+ }
+ }
+ if (ret < 0) {
+ ret = -errno;
+ goto out;
+
+ }
+
+ /* Set executable permission on the copied file */
+ ret = chmod(dest, 0100);
+ if (ret == -1)
+ ret = -errno;
+
+out:
+ free(buf);
+ close(fd_in);
+ close(fd_out);
+ return ret;
+}
- fd = mkstemp(fname);
- if (fd < 0)
- return fd;
+/* Fork and exec the provided rm binary and return the exit code of the
+ * forked process and its pid.
+ */
+static int run_self_unlink(int *monitored_pid, const char *rm_path)
+{
+ int child_pid, child_status, ret;
+ int null_fd;
+
+ child_pid = fork();
+ if (child_pid == 0) {
+ null_fd = open("/dev/null", O_WRONLY);
+ dup2(null_fd, STDOUT_FILENO);
+ dup2(null_fd, STDERR_FILENO);
+ close(null_fd);
+
+ *monitored_pid = getpid();
+ /* Use the copied /usr/bin/rm to delete itself
+ * /tmp/copy_of_rm /tmp/copy_of_rm.
+ */
+ ret = execlp(rm_path, rm_path, rm_path, NULL);
+ if (ret)
+ exit(errno);
+ } else if (child_pid > 0) {
+ waitpid(child_pid, &child_status, 0);
+ return WEXITSTATUS(child_status);
+ }
+
+ return -EINVAL;
+}
- close(fd);
- unlink(fname);
- return 0;
+static bool check_syscall_operations(int map_fd, int obj_fd)
+{
+ struct storage val = { .value = TEST_STORAGE_VALUE, .lock = { 0 } },
+ lookup_val = { .value = 0, .lock = { 0 } };
+ int err;
+
+ /* Looking up an existing element should fail initially */
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+ BPF_F_LOCK);
+ if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+ "err:%d errno:%d\n", err, errno))
+ return false;
+
+ /* Create a new element */
+ err = bpf_map_update_elem(map_fd, &obj_fd, &val,
+ BPF_NOEXIST | BPF_F_LOCK);
+ if (CHECK(err < 0, "bpf_map_update_elem", "err:%d errno:%d\n", err,
+ errno))
+ return false;
+
+ /* Lookup the newly created element */
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+ BPF_F_LOCK);
+ if (CHECK(err < 0, "bpf_map_lookup_elem", "err:%d errno:%d", err,
+ errno))
+ return false;
+
+ /* Check the value of the newly created element */
+ if (CHECK(lookup_val.value != val.value, "bpf_map_lookup_elem",
+ "value got = %x errno:%d", lookup_val.value, val.value))
+ return false;
+
+ err = bpf_map_delete_elem(map_fd, &obj_fd);
+ if (CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n", err,
+ errno))
+ return false;
+
+ /* The lookup should fail, now that the element has been deleted */
+ err = bpf_map_lookup_elem_flags(map_fd, &obj_fd, &lookup_val,
+ BPF_F_LOCK);
+ if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem",
+ "err:%d errno:%d\n", err, errno))
+ return false;
+
+ return true;
}
void test_test_local_storage(void)
{
+ char tmp_exec_path[PATH_MAX] = "/tmp/copy_of_rmXXXXXX";
+ int err, serv_sk = -1, task_fd = -1, rm_fd = -1;
struct local_storage *skel = NULL;
- int err, duration = 0, serv_sk = -1;
skel = local_storage__open_and_load();
if (CHECK(!skel, "skel_load", "lsm skeleton failed\n"))
@@ -37,12 +180,46 @@ void test_test_local_storage(void)
if (CHECK(err, "attach", "lsm attach failed: %d\n", err))
goto close_prog;
- skel->bss->monitored_pid = getpid();
+ task_fd = sys_pidfd_open(getpid(), 0);
+ if (CHECK(task_fd < 0, "pidfd_open",
+ "failed to get pidfd err:%d, errno:%d", task_fd, errno))
+ goto close_prog;
- err = create_and_unlink_file();
- if (CHECK(err < 0, "exec_cmd", "err %d errno %d\n", err, errno))
+ if (!check_syscall_operations(bpf_map__fd(skel->maps.task_storage_map),
+ task_fd))
goto close_prog;
+ err = copy_rm(tmp_exec_path);
+ if (CHECK(err < 0, "copy_rm", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ rm_fd = open(tmp_exec_path, O_RDONLY);
+ if (CHECK(rm_fd < 0, "open", "failed to open %s err:%d, errno:%d",
+ tmp_exec_path, rm_fd, errno))
+ goto close_prog;
+
+ if (!check_syscall_operations(bpf_map__fd(skel->maps.inode_storage_map),
+ rm_fd))
+ goto close_prog;
+
+ /* Sets skel->bss->monitored_pid to the pid of the forked child
+ * forks a child process that executes tmp_exec_path and tries to
+ * unlink its executable. This operation should be denied by the loaded
+ * LSM program.
+ */
+ err = run_self_unlink(&skel->bss->monitored_pid, tmp_exec_path);
+ if (CHECK(err != EPERM, "run_self_unlink", "err %d want EPERM\n", err))
+ goto close_prog_unlink;
+
+ /* Set the process being monitored to be the current process */
+ skel->bss->monitored_pid = getpid();
+
+ /* Remove the temporary created executable */
+ err = unlink(tmp_exec_path);
+ if (CHECK(err != 0, "unlink", "unable to unlink %s: %d", tmp_exec_path,
+ errno))
+ goto close_prog_unlink;
+
CHECK(skel->data->inode_storage_result != 0, "inode_storage_result",
"inode_local_storage not set\n");
@@ -53,8 +230,15 @@ void test_test_local_storage(void)
CHECK(skel->data->sk_storage_result != 0, "sk_storage_result",
"sk_local_storage not set\n");
- close(serv_sk);
+ if (!check_syscall_operations(bpf_map__fd(skel->maps.sk_storage_map),
+ serv_sk))
+ goto close_prog;
+close_prog_unlink:
+ unlink(tmp_exec_path);
close_prog:
+ close(serv_sk);
+ close(rm_fd);
+ close(task_fd);
local_storage__destroy(skel);
}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
new file mode 100644
index 000000000000..cf1215531920
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_skb_pkt_end.c
@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "skb_pkt_end.skel.h"
+
+static int sanity_run(struct bpf_program *prog)
+{
+ __u32 duration, retval;
+ int err, prog_fd;
+
+ prog_fd = bpf_program__fd(prog);
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ NULL, NULL, &retval, &duration);
+ if (CHECK(err || retval != 123, "test_run",
+ "err %d errno %d retval %d duration %d\n",
+ err, errno, retval, duration))
+ return -1;
+ return 0;
+}
+
+void test_test_skb_pkt_end(void)
+{
+ struct skb_pkt_end *skb_pkt_end_skel = NULL;
+ __u32 duration = 0;
+ int err;
+
+ skb_pkt_end_skel = skb_pkt_end__open_and_load();
+ if (CHECK(!skb_pkt_end_skel, "skb_pkt_end_skel_load", "skb_pkt_end skeleton failed\n"))
+ goto cleanup;
+
+ err = skb_pkt_end__attach(skb_pkt_end_skel);
+ if (CHECK(err, "skb_pkt_end_attach", "skb_pkt_end attach failed: %d\n", err))
+ goto cleanup;
+
+ if (sanity_run(skb_pkt_end_skel->progs.main_prog))
+ goto cleanup;
+
+cleanup:
+ skb_pkt_end__destroy(skb_pkt_end_skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c
new file mode 100644
index 000000000000..c6520f21f5f5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bind4_prog.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <linux/if.h>
+#include <errno.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define SERV4_IP 0xc0a801feU /* 192.168.1.254 */
+#define SERV4_PORT 4040
+#define SERV4_REWRITE_IP 0x7f000001U /* 127.0.0.1 */
+#define SERV4_REWRITE_PORT 4444
+
+#ifndef IFNAMSIZ
+#define IFNAMSIZ 16
+#endif
+
+static __inline int bind_to_device(struct bpf_sock_addr *ctx)
+{
+ char veth1[IFNAMSIZ] = "test_sock_addr1";
+ char veth2[IFNAMSIZ] = "test_sock_addr2";
+ char missing[IFNAMSIZ] = "nonexistent_dev";
+ char del_bind[IFNAMSIZ] = "";
+
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &veth1, sizeof(veth1)))
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &veth2, sizeof(veth2)))
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &missing, sizeof(missing)) != -ENODEV)
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &del_bind, sizeof(del_bind)))
+ return 1;
+
+ return 0;
+}
+
+SEC("cgroup/bind4")
+int bind_v4_prog(struct bpf_sock_addr *ctx)
+{
+ struct bpf_sock *sk;
+ __u32 user_ip4;
+ __u16 user_port;
+
+ sk = ctx->sk;
+ if (!sk)
+ return 0;
+
+ if (sk->family != AF_INET)
+ return 0;
+
+ if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+ return 0;
+
+ if (ctx->user_ip4 != bpf_htonl(SERV4_IP) ||
+ ctx->user_port != bpf_htons(SERV4_PORT))
+ return 0;
+
+ // u8 narrow loads:
+ user_ip4 = 0;
+ user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[0] << 0;
+ user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[1] << 8;
+ user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[2] << 16;
+ user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[3] << 24;
+ if (ctx->user_ip4 != user_ip4)
+ return 0;
+
+ user_port = 0;
+ user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0;
+ user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8;
+ if (ctx->user_port != user_port)
+ return 0;
+
+ // u16 narrow loads:
+ user_ip4 = 0;
+ user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[0] << 0;
+ user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[1] << 16;
+ if (ctx->user_ip4 != user_ip4)
+ return 0;
+
+ /* Bind to device and unbind it. */
+ if (bind_to_device(ctx))
+ return 0;
+
+ ctx->user_ip4 = bpf_htonl(SERV4_REWRITE_IP);
+ ctx->user_port = bpf_htons(SERV4_REWRITE_PORT);
+
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c
new file mode 100644
index 000000000000..4358e44dcf47
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bind6_prog.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <sys/socket.h>
+#include <netinet/tcp.h>
+#include <linux/if.h>
+#include <errno.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define SERV6_IP_0 0xfaceb00c /* face:b00c:1234:5678::abcd */
+#define SERV6_IP_1 0x12345678
+#define SERV6_IP_2 0x00000000
+#define SERV6_IP_3 0x0000abcd
+#define SERV6_PORT 6060
+#define SERV6_REWRITE_IP_0 0x00000000
+#define SERV6_REWRITE_IP_1 0x00000000
+#define SERV6_REWRITE_IP_2 0x00000000
+#define SERV6_REWRITE_IP_3 0x00000001
+#define SERV6_REWRITE_PORT 6666
+
+#ifndef IFNAMSIZ
+#define IFNAMSIZ 16
+#endif
+
+static __inline int bind_to_device(struct bpf_sock_addr *ctx)
+{
+ char veth1[IFNAMSIZ] = "test_sock_addr1";
+ char veth2[IFNAMSIZ] = "test_sock_addr2";
+ char missing[IFNAMSIZ] = "nonexistent_dev";
+ char del_bind[IFNAMSIZ] = "";
+
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &veth1, sizeof(veth1)))
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &veth2, sizeof(veth2)))
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &missing, sizeof(missing)) != -ENODEV)
+ return 1;
+ if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE,
+ &del_bind, sizeof(del_bind)))
+ return 1;
+
+ return 0;
+}
+
+SEC("cgroup/bind6")
+int bind_v6_prog(struct bpf_sock_addr *ctx)
+{
+ struct bpf_sock *sk;
+ __u32 user_ip6;
+ __u16 user_port;
+ int i;
+
+ sk = ctx->sk;
+ if (!sk)
+ return 0;
+
+ if (sk->family != AF_INET6)
+ return 0;
+
+ if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM)
+ return 0;
+
+ if (ctx->user_ip6[0] != bpf_htonl(SERV6_IP_0) ||
+ ctx->user_ip6[1] != bpf_htonl(SERV6_IP_1) ||
+ ctx->user_ip6[2] != bpf_htonl(SERV6_IP_2) ||
+ ctx->user_ip6[3] != bpf_htonl(SERV6_IP_3) ||
+ ctx->user_port != bpf_htons(SERV6_PORT))
+ return 0;
+
+ // u8 narrow loads:
+ for (i = 0; i < 4; i++) {
+ user_ip6 = 0;
+ user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[0] << 0;
+ user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[1] << 8;
+ user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[2] << 16;
+ user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[3] << 24;
+ if (ctx->user_ip6[i] != user_ip6)
+ return 0;
+ }
+
+ user_port = 0;
+ user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0;
+ user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8;
+ if (ctx->user_port != user_port)
+ return 0;
+
+ // u16 narrow loads:
+ for (i = 0; i < 4; i++) {
+ user_ip6 = 0;
+ user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[0] << 0;
+ user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[1] << 16;
+ if (ctx->user_ip6[i] != user_ip6)
+ return 0;
+ }
+
+ /* Bind to device and unbind it. */
+ if (bind_to_device(ctx))
+ return 0;
+
+ ctx->user_ip6[0] = bpf_htonl(SERV6_REWRITE_IP_0);
+ ctx->user_ip6[1] = bpf_htonl(SERV6_REWRITE_IP_1);
+ ctx->user_ip6[2] = bpf_htonl(SERV6_REWRITE_IP_2);
+ ctx->user_ip6[3] = bpf_htonl(SERV6_REWRITE_IP_3);
+ ctx->user_port = bpf_htons(SERV6_REWRITE_PORT);
+
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 5a65f6b51377..95a5a0778ed7 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -368,6 +368,8 @@ PROG(IPV6FR)(struct __sk_buff *skb)
*/
if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG))
return export_flow_keys(keys, BPF_OK);
+ } else {
+ return export_flow_keys(keys, BPF_OK);
}
return parse_ipv6_proto(skb, fragh->nexthdr);
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
index 08651b23edba..b83b5d2e17dc 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c
@@ -23,6 +23,6 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx)
BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter,
map->usercnt.counter,
- map->memory.user->locked_vm.counter);
+ 0LLU);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
new file mode 100644
index 000000000000..6cecab2b32ba
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_sk_storage_helpers.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Google LLC. */
+#include "bpf_iter.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} sk_stg_map SEC(".maps");
+
+SEC("iter/bpf_sk_storage_map")
+int delete_bpf_sk_storage_map(struct bpf_iter__bpf_sk_storage_map *ctx)
+{
+ if (ctx->sk)
+ bpf_sk_storage_delete(&sk_stg_map, ctx->sk);
+
+ return 0;
+}
+
+SEC("iter/task_file")
+int fill_socket_owner(struct bpf_iter__task_file *ctx)
+{
+ struct task_struct *task = ctx->task;
+ struct file *file = ctx->file;
+ struct socket *sock;
+ int *sock_tgid;
+
+ if (!task || !file)
+ return 0;
+
+ sock = bpf_sock_from_file(file);
+ if (!sock)
+ return 0;
+
+ sock_tgid = bpf_sk_storage_get(&sk_stg_map, sock->sk, 0, 0);
+ if (!sock_tgid)
+ return 0;
+
+ *sock_tgid = task->tgid;
+
+ return 0;
+}
+
+SEC("iter/tcp")
+int negate_socket_local_storage(struct bpf_iter__tcp *ctx)
+{
+ struct sock_common *sk_common = ctx->sk_common;
+ int *sock_tgid;
+
+ if (!sk_common)
+ return 0;
+
+ sock_tgid = bpf_sk_storage_get(&sk_stg_map, sk_common, 0, 0);
+ if (!sock_tgid)
+ return 0;
+
+ *sock_tgid = -*sock_tgid;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
index 4983087852a0..b7f32c160f4e 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_task.c
@@ -11,9 +11,10 @@ int dump_task(struct bpf_iter__task *ctx)
{
struct seq_file *seq = ctx->meta->seq;
struct task_struct *task = ctx->task;
+ static char info[] = " === END ===";
if (task == (void *)0) {
- BPF_SEQ_PRINTF(seq, " === END ===\n");
+ BPF_SEQ_PRINTF(seq, "%s\n", info);
return 0;
}
diff --git a/tools/testing/selftests/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c
new file mode 100644
index 000000000000..5bfef2887e70
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bprm_opts.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} secure_exec_task_map SEC(".maps");
+
+SEC("lsm/bprm_creds_for_exec")
+int BPF_PROG(secure_exec, struct linux_binprm *bprm)
+{
+ int *secureexec;
+
+ secureexec = bpf_task_storage_get(&secure_exec_task_map,
+ bpf_get_current_task_btf(), 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+
+ if (secureexec && *secureexec)
+ bpf_bprm_opts_set(bprm, BPF_F_BPRM_SECUREEXEC);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h
index e6e616cb7bc9..9a2850850121 100644
--- a/tools/testing/selftests/bpf/progs/core_reloc_types.h
+++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h
@@ -16,6 +16,23 @@ struct core_reloc_kernel_output {
};
/*
+ * MODULE
+ */
+
+struct core_reloc_module_output {
+ long long len;
+ long long off;
+ int read_ctx_sz;
+ bool read_ctx_exists;
+ bool buf_exists;
+ bool len_exists;
+ bool off_exists;
+ /* we have test_progs[-flavor], so cut flavor part */
+ char comm[sizeof("test_progs")];
+ int comm_len;
+};
+
+/*
* FLAVORS
*/
struct core_reloc_flavors {
diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c
new file mode 100644
index 000000000000..86b21aff4bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/ima.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include "vmlinux.h"
+#include <errno.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+long ima_hash_ret = -1;
+u64 ima_hash = 0;
+u32 monitored_pid = 0;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("lsm.s/bprm_committed_creds")
+int BPF_PROG(ima, struct linux_binprm *bprm)
+{
+ u32 pid = bpf_get_current_pid_tgid() >> 32;
+
+ if (pid == monitored_pid)
+ ima_hash_ret = bpf_ima_inode_hash(bprm->file->f_inode,
+ &ima_hash, sizeof(ima_hash));
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/local_storage.c b/tools/testing/selftests/bpf/progs/local_storage.c
index 0758ba229ae0..3e3de130f28f 100644
--- a/tools/testing/selftests/bpf/progs/local_storage.c
+++ b/tools/testing/selftests/bpf/progs/local_storage.c
@@ -4,9 +4,8 @@
* Copyright 2020 Google LLC.
*/
+#include "vmlinux.h"
#include <errno.h>
-#include <linux/bpf.h>
-#include <stdbool.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
@@ -18,60 +17,68 @@ int monitored_pid = 0;
int inode_storage_result = -1;
int sk_storage_result = -1;
-struct dummy_storage {
+struct local_storage {
+ struct inode *exec_inode;
__u32 value;
+ struct bpf_spin_lock lock;
};
struct {
__uint(type, BPF_MAP_TYPE_INODE_STORAGE);
__uint(map_flags, BPF_F_NO_PREALLOC);
__type(key, int);
- __type(value, struct dummy_storage);
+ __type(value, struct local_storage);
} inode_storage_map SEC(".maps");
struct {
__uint(type, BPF_MAP_TYPE_SK_STORAGE);
__uint(map_flags, BPF_F_NO_PREALLOC | BPF_F_CLONE);
__type(key, int);
- __type(value, struct dummy_storage);
+ __type(value, struct local_storage);
} sk_storage_map SEC(".maps");
-/* TODO Use vmlinux.h once BTF pruning for embedded types is fixed.
- */
-struct sock {} __attribute__((preserve_access_index));
-struct sockaddr {} __attribute__((preserve_access_index));
-struct socket {
- struct sock *sk;
-} __attribute__((preserve_access_index));
-
-struct inode {} __attribute__((preserve_access_index));
-struct dentry {
- struct inode *d_inode;
-} __attribute__((preserve_access_index));
-struct file {
- struct inode *f_inode;
-} __attribute__((preserve_access_index));
-
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct local_storage);
+} task_storage_map SEC(".maps");
SEC("lsm/inode_unlink")
int BPF_PROG(unlink_hook, struct inode *dir, struct dentry *victim)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
+ bool is_self_unlink;
+ int err;
if (pid != monitored_pid)
return 0;
+ storage = bpf_task_storage_get(&task_storage_map,
+ bpf_get_current_task_btf(), 0, 0);
+ if (storage) {
+ /* Don't let an executable delete itself */
+ bpf_spin_lock(&storage->lock);
+ is_self_unlink = storage->exec_inode == victim->d_inode;
+ bpf_spin_unlock(&storage->lock);
+ if (is_self_unlink)
+ return -EPERM;
+ }
+
storage = bpf_inode_storage_get(&inode_storage_map, victim->d_inode, 0,
- BPF_SK_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
- if (storage->value == DUMMY_STORAGE_VALUE)
+ bpf_spin_lock(&storage->lock);
+ if (storage->value != DUMMY_STORAGE_VALUE)
inode_storage_result = -1;
+ bpf_spin_unlock(&storage->lock);
- inode_storage_result =
- bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+ err = bpf_inode_storage_delete(&inode_storage_map, victim->d_inode);
+ if (!err)
+ inode_storage_result = err;
return 0;
}
@@ -81,20 +88,26 @@ int BPF_PROG(socket_bind, struct socket *sock, struct sockaddr *address,
int addrlen)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
+ int err;
if (pid != monitored_pid)
return 0;
storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
- BPF_SK_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
- if (storage->value == DUMMY_STORAGE_VALUE)
+ bpf_spin_lock(&storage->lock);
+ if (storage->value != DUMMY_STORAGE_VALUE)
sk_storage_result = -1;
+ bpf_spin_unlock(&storage->lock);
+
+ err = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
+ if (!err)
+ sk_storage_result = err;
- sk_storage_result = bpf_sk_storage_delete(&sk_storage_map, sock->sk);
return 0;
}
@@ -103,17 +116,19 @@ int BPF_PROG(socket_post_create, struct socket *sock, int family, int type,
int protocol, int kern)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
if (pid != monitored_pid)
return 0;
storage = bpf_sk_storage_get(&sk_storage_map, sock->sk, 0,
- BPF_SK_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
+ bpf_spin_lock(&storage->lock);
storage->value = DUMMY_STORAGE_VALUE;
+ bpf_spin_unlock(&storage->lock);
return 0;
}
@@ -122,7 +137,7 @@ SEC("lsm/file_open")
int BPF_PROG(file_open, struct file *file)
{
__u32 pid = bpf_get_current_pid_tgid() >> 32;
- struct dummy_storage *storage;
+ struct local_storage *storage;
if (pid != monitored_pid)
return 0;
@@ -131,10 +146,30 @@ int BPF_PROG(file_open, struct file *file)
return 0;
storage = bpf_inode_storage_get(&inode_storage_map, file->f_inode, 0,
- BPF_LOCAL_STORAGE_GET_F_CREATE);
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
if (!storage)
return 0;
+ bpf_spin_lock(&storage->lock);
storage->value = DUMMY_STORAGE_VALUE;
+ bpf_spin_unlock(&storage->lock);
return 0;
}
+
+/* This uses the local storage to remember the inode of the binary that a
+ * process was originally executing.
+ */
+SEC("lsm/bprm_committed_creds")
+void BPF_PROG(exec, struct linux_binprm *bprm)
+{
+ struct local_storage *storage;
+
+ storage = bpf_task_storage_get(&task_storage_map,
+ bpf_get_current_task_btf(), 0,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (storage) {
+ bpf_spin_lock(&storage->lock);
+ storage->exec_inode = bprm->file->f_inode;
+ bpf_spin_unlock(&storage->lock);
+ }
+}
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index c325405751e2..d8850bc6a9f1 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -26,17 +26,12 @@ __u32 g_line = 0;
return 0; \
})
-struct bpf_map_memory {
- __u32 pages;
-} __attribute__((preserve_access_index));
-
struct bpf_map {
enum bpf_map_type map_type;
__u32 key_size;
__u32 value_size;
__u32 max_entries;
__u32 id;
- struct bpf_map_memory memory;
} __attribute__((preserve_access_index));
static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
@@ -47,7 +42,6 @@ static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size,
VERIFY(map->value_size == value_size);
VERIFY(map->max_entries == max_entries);
VERIFY(map->id > 0);
- VERIFY(map->memory.pages > 0);
return 1;
}
@@ -60,7 +54,6 @@ static inline int check_bpf_map_ptr(struct bpf_map *indirect,
VERIFY(indirect->value_size == direct->value_size);
VERIFY(indirect->max_entries == direct->max_entries);
VERIFY(indirect->id == direct->id);
- VERIFY(indirect->memory.pages == direct->memory.pages);
return 1;
}
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 30982a7e4d0f..4896fdf816f7 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -256,6 +256,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn);
struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn);
+#if __has_builtin(__builtin_preserve_enum_value)
if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) {
int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local,
pids_cgrp_id___local);
@@ -275,6 +276,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data,
}
}
}
+#endif
cgroup_data->cgroup_root_inode = get_inode_from_kernfs(root_kernfs);
cgroup_data->cgroup_proc_inode = get_inode_from_kernfs(proc_kernfs);
diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
new file mode 100644
index 000000000000..cf6823f42e80
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_PRESERVE_ACCESS_INDEX
+#include <vmlinux.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+#define NULL 0
+#define INLINE __always_inline
+
+#define skb_shorter(skb, len) ((void *)(long)(skb)->data + (len) > (void *)(long)skb->data_end)
+
+#define ETH_IPV4_TCP_SIZE (14 + sizeof(struct iphdr) + sizeof(struct tcphdr))
+
+static INLINE struct iphdr *get_iphdr(struct __sk_buff *skb)
+{
+ struct iphdr *ip = NULL;
+ struct ethhdr *eth;
+
+ if (skb_shorter(skb, ETH_IPV4_TCP_SIZE))
+ goto out;
+
+ eth = (void *)(long)skb->data;
+ ip = (void *)(eth + 1);
+
+out:
+ return ip;
+}
+
+SEC("classifier/cls")
+int main_prog(struct __sk_buff *skb)
+{
+ struct iphdr *ip = NULL;
+ struct tcphdr *tcp;
+ __u8 proto = 0;
+
+ if (!(ip = get_iphdr(skb)))
+ goto out;
+
+ proto = ip->protocol;
+
+ if (proto != IPPROTO_TCP)
+ goto out;
+
+ tcp = (void*)(ip + 1);
+ if (tcp->dest != 0)
+ goto out;
+ if (!tcp)
+ goto out;
+
+ return tcp->urg_ptr;
+out:
+ return -1;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
new file mode 100644
index 000000000000..f59f175c7baf
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_testmod_test_read_ctx {
+ /* field order is mixed up */
+ size_t len;
+ char *buf;
+ loff_t off;
+} __attribute__((preserve_access_index));
+
+struct {
+ char in[256];
+ char out[256];
+ bool skip;
+ uint64_t my_pid_tgid;
+} data = {};
+
+struct core_reloc_module_output {
+ long long len;
+ long long off;
+ int read_ctx_sz;
+ bool read_ctx_exists;
+ bool buf_exists;
+ bool len_exists;
+ bool off_exists;
+ /* we have test_progs[-flavor], so cut flavor part */
+ char comm[sizeof("test_progs")];
+ int comm_len;
+};
+
+SEC("raw_tp/bpf_testmod_test_read")
+int BPF_PROG(test_core_module_probed,
+ struct task_struct *task,
+ struct bpf_testmod_test_read_ctx *read_ctx)
+{
+#if __has_builtin(__builtin_preserve_enum_value)
+ struct core_reloc_module_output *out = (void *)&data.out;
+ __u64 pid_tgid = bpf_get_current_pid_tgid();
+ __u32 real_tgid = (__u32)(pid_tgid >> 32);
+ __u32 real_pid = (__u32)pid_tgid;
+
+ if (data.my_pid_tgid != pid_tgid)
+ return 0;
+
+ if (BPF_CORE_READ(task, pid) != real_pid || BPF_CORE_READ(task, tgid) != real_tgid)
+ return 0;
+
+ out->len = BPF_CORE_READ(read_ctx, len);
+ out->off = BPF_CORE_READ(read_ctx, off);
+
+ out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx);
+ out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx);
+ out->buf_exists = bpf_core_field_exists(read_ctx->buf);
+ out->off_exists = bpf_core_field_exists(read_ctx->off);
+ out->len_exists = bpf_core_field_exists(read_ctx->len);
+
+ out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm);
+#else
+ data.skip = true;
+#endif
+
+ return 0;
+}
+
+SEC("tp_btf/bpf_testmod_test_read")
+int BPF_PROG(test_core_module_direct,
+ struct task_struct *task,
+ struct bpf_testmod_test_read_ctx *read_ctx)
+{
+#if __has_builtin(__builtin_preserve_enum_value)
+ struct core_reloc_module_output *out = (void *)&data.out;
+ __u64 pid_tgid = bpf_get_current_pid_tgid();
+ __u32 real_tgid = (__u32)(pid_tgid >> 32);
+ __u32 real_pid = (__u32)pid_tgid;
+
+ if (data.my_pid_tgid != pid_tgid)
+ return 0;
+
+ if (task->pid != real_pid || task->tgid != real_tgid)
+ return 0;
+
+ out->len = read_ctx->len;
+ out->off = read_ctx->off;
+
+ out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx);
+ out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx);
+ out->buf_exists = bpf_core_field_exists(read_ctx->buf);
+ out->off_exists = bpf_core_field_exists(read_ctx->off);
+ out->len_exists = bpf_core_field_exists(read_ctx->len);
+
+ out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm);
+#else
+ data.skip = true;
+#endif
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_hash_large_key.c b/tools/testing/selftests/bpf/progs/test_hash_large_key.c
new file mode 100644
index 000000000000..473a22794a62
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_hash_large_key.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_HASH);
+ __uint(max_entries, 2);
+ __type(key, struct bigelement);
+ __type(value, __u32);
+} hash_map SEC(".maps");
+
+struct {
+ __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
+ __uint(max_entries, 1);
+ __type(key, __u32);
+ __type(value, struct bigelement);
+} key_map SEC(".maps");
+
+struct bigelement {
+ int a;
+ char b[4096];
+ long long c;
+};
+
+SEC("raw_tracepoint/sys_enter")
+int bpf_hash_large_key_test(void *ctx)
+{
+ int zero = 0, err = 1, value = 42;
+ struct bigelement *key;
+
+ key = bpf_map_lookup_elem(&key_map, &zero);
+ if (!key)
+ return 0;
+
+ key->c = 1;
+ if (bpf_map_update_elem(&hash_map, key, &value, BPF_ANY))
+ return 0;
+
+ return 0;
+}
+
diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
new file mode 100644
index 000000000000..efd1e287ac17
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include "../bpf_testmod/bpf_testmod.h"
+
+__u32 raw_tp_read_sz = 0;
+
+SEC("raw_tp/bpf_testmod_test_read")
+int BPF_PROG(handle_raw_tp,
+ struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx)
+{
+ raw_tp_read_sz = BPF_CORE_READ(read_ctx, len);
+ return 0;
+}
+
+__u32 tp_btf_read_sz = 0;
+
+SEC("tp_btf/bpf_testmod_test_read")
+int BPF_PROG(handle_tp_btf,
+ struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx)
+{
+ tp_btf_read_sz = read_ctx->len;
+ return 0;
+}
+
+__u32 fentry_read_sz = 0;
+
+SEC("fentry/bpf_testmod_test_read")
+int BPF_PROG(handle_fentry,
+ struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+ fentry_read_sz = len;
+ return 0;
+}
+
+__u32 fentry_manual_read_sz = 0;
+
+SEC("fentry/placeholder")
+int BPF_PROG(handle_fentry_manual,
+ struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+ fentry_manual_read_sz = len;
+ return 0;
+}
+
+__u32 fexit_read_sz = 0;
+int fexit_ret = 0;
+
+SEC("fexit/bpf_testmod_test_read")
+int BPF_PROG(handle_fexit,
+ struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len,
+ int ret)
+{
+ fexit_read_sz = len;
+ fexit_ret = ret;
+ return 0;
+}
+
+__u32 fmod_ret_read_sz = 0;
+
+SEC("fmod_ret/bpf_testmod_test_read")
+int BPF_PROG(handle_fmod_ret,
+ struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len)
+{
+ fmod_ret_read_sz = len;
+ return 0; /* don't override the exit code */
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c b/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c
new file mode 100644
index 000000000000..59ef72d02a61
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_storage_trace_itself.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} sk_stg_map SEC(".maps");
+
+SEC("fentry/bpf_sk_storage_free")
+int BPF_PROG(trace_bpf_sk_storage_free, struct sock *sk)
+{
+ int *value;
+
+ value = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+
+ if (value)
+ *value = 1;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
new file mode 100644
index 000000000000..8e94e5c080aa
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_sk_storage_tracing.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+
+#include <vmlinux.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+
+struct sk_stg {
+ __u32 pid;
+ __u32 last_notclose_state;
+ char comm[16];
+};
+
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, struct sk_stg);
+} sk_stg_map SEC(".maps");
+
+/* Testing delete */
+struct {
+ __uint(type, BPF_MAP_TYPE_SK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, int);
+} del_sk_stg_map SEC(".maps");
+
+char task_comm[16] = "";
+
+SEC("tp_btf/inet_sock_set_state")
+int BPF_PROG(trace_inet_sock_set_state, struct sock *sk, int oldstate,
+ int newstate)
+{
+ struct sk_stg *stg;
+
+ if (newstate == BPF_TCP_CLOSE)
+ return 0;
+
+ stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!stg)
+ return 0;
+
+ stg->last_notclose_state = newstate;
+
+ bpf_sk_storage_delete(&del_sk_stg_map, sk);
+
+ return 0;
+}
+
+static void set_task_info(struct sock *sk)
+{
+ struct task_struct *task;
+ struct sk_stg *stg;
+
+ stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+ BPF_SK_STORAGE_GET_F_CREATE);
+ if (!stg)
+ return;
+
+ stg->pid = bpf_get_current_pid_tgid();
+
+ task = (struct task_struct *)bpf_get_current_task();
+ bpf_core_read_str(&stg->comm, sizeof(stg->comm), &task->comm);
+ bpf_core_read_str(&task_comm, sizeof(task_comm), &task->comm);
+}
+
+SEC("fentry/inet_csk_listen_start")
+int BPF_PROG(trace_inet_csk_listen_start, struct sock *sk, int backlog)
+{
+ set_task_info(sk);
+
+ return 0;
+}
+
+SEC("fentry/tcp_connect")
+int BPF_PROG(trace_tcp_connect, struct sock *sk)
+{
+ set_task_info(sk);
+
+ return 0;
+}
+
+SEC("fexit/inet_csk_accept")
+int BPF_PROG(inet_csk_accept, struct sock *sk, int flags, int *err, bool kern,
+ struct sock *accepted_sk)
+{
+ set_task_info(accepted_sk);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 3e6912e4df3d..94f50f7e94d6 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -12,50 +12,41 @@
#include <linux/tcp.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_endian.h>
+#include "bpf_tcp_helpers.h"
#include "test_tcpbpf.h"
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 4);
- __type(key, __u32);
- __type(value, struct tcpbpf_globals);
-} global_map SEC(".maps");
-
-struct {
- __uint(type, BPF_MAP_TYPE_ARRAY);
- __uint(max_entries, 2);
- __type(key, __u32);
- __type(value, int);
-} sockopt_results SEC(".maps");
-
-static inline void update_event_map(int event)
+struct tcpbpf_globals global = {};
+int _version SEC("version") = 1;
+
+/**
+ * SOL_TCP is defined in <netinet/tcp.h> while
+ * TCP_SAVED_SYN is defined in already included <linux/tcp.h>
+ */
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
+static __always_inline int get_tp_window_clamp(struct bpf_sock_ops *skops)
{
- __u32 key = 0;
- struct tcpbpf_globals g, *gp;
-
- gp = bpf_map_lookup_elem(&global_map, &key);
- if (gp == NULL) {
- struct tcpbpf_globals g = {0};
-
- g.event_map |= (1 << event);
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
- } else {
- g = *gp;
- g.event_map |= (1 << event);
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
- }
+ struct bpf_sock *sk;
+ struct tcp_sock *tp;
+
+ sk = skops->sk;
+ if (!sk)
+ return -1;
+ tp = bpf_skc_to_tcp_sock(sk);
+ if (!tp)
+ return -1;
+ return tp->window_clamp;
}
-int _version SEC("version") = 1;
-
SEC("sockops")
int bpf_testcb(struct bpf_sock_ops *skops)
{
char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
struct bpf_sock_ops *reuse = skops;
struct tcphdr *thdr;
+ int window_clamp = 9216;
int good_call_rv = 0;
int bad_call_rv = 0;
int save_syn = 1;
@@ -105,29 +96,20 @@ int bpf_testcb(struct bpf_sock_ops *skops)
op = (int) skops->op;
- update_event_map(op);
+ global.event_map |= (1 << op);
switch (op) {
+ case BPF_SOCK_OPS_TCP_CONNECT_CB:
+ rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP,
+ &window_clamp, sizeof(window_clamp));
+ global.window_clamp_client = get_tp_window_clamp(skops);
+ break;
case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
/* Test failure to set largest cb flag (assumes not defined) */
- bad_call_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
+ global.bad_cb_test_rv = bpf_sock_ops_cb_flags_set(skops, 0x80);
/* Set callback */
- good_call_rv = bpf_sock_ops_cb_flags_set(skops,
+ global.good_cb_test_rv = bpf_sock_ops_cb_flags_set(skops,
BPF_SOCK_OPS_STATE_CB_FLAG);
- /* Update results */
- {
- __u32 key = 0;
- struct tcpbpf_globals g, *gp;
-
- gp = bpf_map_lookup_elem(&global_map, &key);
- if (!gp)
- break;
- g = *gp;
- g.bad_cb_test_rv = bad_call_rv;
- g.good_cb_test_rv = good_call_rv;
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
- }
break;
case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
skops->sk_txhash = 0x12345f;
@@ -143,12 +125,14 @@ int bpf_testcb(struct bpf_sock_ops *skops)
thdr = (struct tcphdr *)(header + offset);
v = thdr->syn;
- __u32 key = 1;
- bpf_map_update_elem(&sockopt_results, &key, &v,
- BPF_ANY);
+ global.tcp_saved_syn = v;
}
}
+ rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP,
+ &window_clamp, sizeof(window_clamp));
+
+ global.window_clamp_server = get_tp_window_clamp(skops);
break;
case BPF_SOCK_OPS_RTO_CB:
break;
@@ -156,25 +140,16 @@ int bpf_testcb(struct bpf_sock_ops *skops)
break;
case BPF_SOCK_OPS_STATE_CB:
if (skops->args[1] == BPF_TCP_CLOSE) {
- __u32 key = 0;
- struct tcpbpf_globals g, *gp;
-
- gp = bpf_map_lookup_elem(&global_map, &key);
- if (!gp)
- break;
- g = *gp;
if (skops->args[0] == BPF_TCP_LISTEN) {
- g.num_listen++;
+ global.num_listen++;
} else {
- g.total_retrans = skops->total_retrans;
- g.data_segs_in = skops->data_segs_in;
- g.data_segs_out = skops->data_segs_out;
- g.bytes_received = skops->bytes_received;
- g.bytes_acked = skops->bytes_acked;
+ global.total_retrans = skops->total_retrans;
+ global.data_segs_in = skops->data_segs_in;
+ global.data_segs_out = skops->data_segs_out;
+ global.bytes_received = skops->bytes_received;
+ global.bytes_acked = skops->bytes_acked;
}
- g.num_close_events++;
- bpf_map_update_elem(&global_map, &key, &g,
- BPF_ANY);
+ global.num_close_events++;
}
break;
case BPF_SOCK_OPS_TCP_LISTEN_CB:
@@ -182,9 +157,7 @@ int bpf_testcb(struct bpf_sock_ops *skops)
v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN,
&save_syn, sizeof(save_syn));
/* Update global map w/ result of setsock opt */
- __u32 key = 0;
-
- bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY);
+ global.tcp_save_syn = v;
break;
default:
rv = -1;
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index f48dbfe24ddc..a621b58ab079 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -15,7 +15,6 @@
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/types.h>
-#include <linux/tcp.h>
#include <linux/socket.h>
#include <linux/pkt_cls.h>
#include <linux/erspan.h>
@@ -528,12 +527,11 @@ int _ipip_set_tunnel(struct __sk_buff *skb)
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ if (data + sizeof(*iph) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
@@ -541,16 +539,6 @@ int _ipip_set_tunnel(struct __sk_buff *skb)
key.tunnel_ttl = 64;
if (iph->protocol == IPPROTO_ICMP) {
key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- } else {
- if (iph->protocol != IPPROTO_TCP || iph->ihl != 5)
- return TC_ACT_SHOT;
-
- if (tcp->dest == bpf_htons(5200))
- key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
- else if (tcp->dest == bpf_htons(5201))
- key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */
- else
- return TC_ACT_SHOT;
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0);
@@ -585,19 +573,20 @@ int _ipip6_set_tunnel(struct __sk_buff *skb)
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct iphdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ if (data + sizeof(*iph) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
__builtin_memset(&key, 0x0, sizeof(key));
- key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
key.tunnel_ttl = 64;
+ if (iph->protocol == IPPROTO_ICMP) {
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ }
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
BPF_F_TUNINFO_IPV6);
@@ -634,35 +623,18 @@ int _ip6ip6_set_tunnel(struct __sk_buff *skb)
struct bpf_tunnel_key key = {};
void *data = (void *)(long)skb->data;
struct ipv6hdr *iph = data;
- struct tcphdr *tcp = data + sizeof(*iph);
void *data_end = (void *)(long)skb->data_end;
int ret;
/* single length check */
- if (data + sizeof(*iph) + sizeof(*tcp) > data_end) {
+ if (data + sizeof(*iph) > data_end) {
ERROR(1);
return TC_ACT_SHOT;
}
- key.remote_ipv6[0] = bpf_htonl(0x2401db00);
key.tunnel_ttl = 64;
-
if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) {
- key.remote_ipv6[3] = bpf_htonl(1);
- } else {
- if (iph->nexthdr != 6 /* NEXTHDR_TCP */) {
- ERROR(iph->nexthdr);
- return TC_ACT_SHOT;
- }
-
- if (tcp->dest == bpf_htons(5200)) {
- key.remote_ipv6[3] = bpf_htonl(1);
- } else if (tcp->dest == bpf_htons(5201)) {
- key.remote_ipv6[3] = bpf_htonl(2);
- } else {
- ERROR(tcp->dest);
- return TC_ACT_SHOT;
- }
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
}
ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
deleted file mode 100755
index bfff82be3fc1..000000000000
--- a/tools/testing/selftests/bpf/tcp_client.py
+++ /dev/null
@@ -1,50 +0,0 @@
-#!/usr/bin/env python3
-#
-# SPDX-License-Identifier: GPL-2.0
-#
-
-import sys, os, os.path, getopt
-import socket, time
-import subprocess
-import select
-
-def read(sock, n):
- buf = b''
- while len(buf) < n:
- rem = n - len(buf)
- try: s = sock.recv(rem)
- except (socket.error) as e: return b''
- buf += s
- return buf
-
-def send(sock, s):
- total = len(s)
- count = 0
- while count < total:
- try: n = sock.send(s)
- except (socket.error) as e: n = 0
- if n == 0:
- return count;
- count += n
- return count
-
-
-serverPort = int(sys.argv[1])
-
-# create active socket
-sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-try:
- sock.connect(('::1', serverPort))
-except socket.error as e:
- sys.exit(1)
-
-buf = b''
-n = 0
-while n < 1000:
- buf += b'+'
- n += 1
-
-sock.settimeout(1);
-n = send(sock, buf)
-n = read(sock, 500)
-sys.exit(0)
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
deleted file mode 100755
index 42ab8882f00f..000000000000
--- a/tools/testing/selftests/bpf/tcp_server.py
+++ /dev/null
@@ -1,80 +0,0 @@
-#!/usr/bin/env python3
-#
-# SPDX-License-Identifier: GPL-2.0
-#
-
-import sys, os, os.path, getopt
-import socket, time
-import subprocess
-import select
-
-def read(sock, n):
- buf = b''
- while len(buf) < n:
- rem = n - len(buf)
- try: s = sock.recv(rem)
- except (socket.error) as e: return b''
- buf += s
- return buf
-
-def send(sock, s):
- total = len(s)
- count = 0
- while count < total:
- try: n = sock.send(s)
- except (socket.error) as e: n = 0
- if n == 0:
- return count;
- count += n
- return count
-
-
-SERVER_PORT = 12877
-MAX_PORTS = 2
-
-serverPort = SERVER_PORT
-serverSocket = None
-
-# create passive socket
-serverSocket = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
-
-try: serverSocket.bind(('::1', 0))
-except socket.error as msg:
- print('bind fails: ' + str(msg))
-
-sn = serverSocket.getsockname()
-serverPort = sn[1]
-
-cmdStr = ("./tcp_client.py %d &") % (serverPort)
-os.system(cmdStr)
-
-buf = b''
-n = 0
-while n < 500:
- buf += b'.'
- n += 1
-
-serverSocket.listen(MAX_PORTS)
-readList = [serverSocket]
-
-while True:
- readyRead, readyWrite, inError = \
- select.select(readList, [], [], 2)
-
- if len(readyRead) > 0:
- waitCount = 0
- for sock in readyRead:
- if sock == serverSocket:
- (clientSocket, address) = serverSocket.accept()
- address = str(address[0])
- readList.append(clientSocket)
- else:
- sock.settimeout(1);
- s = read(sock, 1000)
- n = send(sock, buf)
- sock.close()
- serverSocket.close()
- sys.exit(0)
- else:
- print('Select timeout!')
- sys.exit(1)
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 0d92ebcb335d..0ad3e6305ff0 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1223,9 +1223,10 @@ out_map_in_map:
static void test_map_large(void)
{
+
struct bigkey {
int a;
- char b[116];
+ char b[4096];
long long c;
} key;
int fd, i, value;
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 43c9cda199b8..b99bb8ed3ed4 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -184,9 +184,7 @@ def bpftool_prog_list(expected=None, ns=""):
def bpftool_map_list(expected=None, ns=""):
_, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
# Remove the base maps
- for m in base_maps:
- if m in maps:
- maps.remove(m)
+ maps = [m for m in maps if m not in base_maps and m.get('name') not in base_map_names]
if expected is not None:
if len(maps) != expected:
fail(True, "%d BPF maps loaded, expected %d" %
@@ -716,13 +714,11 @@ def test_multi_prog(simdev, sim, obj, modename, modeid):
fail(ret == 0, "Replaced one of programs without -force")
check_extack(err, "XDP program already attached.", args)
- if modename == "" or modename == "drv":
- othermode = "" if modename == "drv" else "drv"
- start_test("Test multi-attachment XDP - detach...")
- ret, _, err = sim.unset_xdp(othermode, force=True,
- fail=False, include_stderr=True)
- fail(ret == 0, "Removed program with a bad mode")
- check_extack(err, "program loaded with different flags.", args)
+ start_test("Test multi-attachment XDP - remove without mode...")
+ ret, _, err = sim.unset_xdp("", force=True,
+ fail=False, include_stderr=True)
+ fail(ret == 0, "Removed program without a mode flag")
+ check_extack(err, "More than one program loaded, unset mode is ambiguous.", args)
sim.unset_xdp("offload")
xdp = sim.ip_link_show(xdp=True)["xdp"]
@@ -772,6 +768,9 @@ ret, progs = bpftool("prog", fail=False)
skip(ret != 0, "bpftool not installed")
base_progs = progs
_, base_maps = bpftool("map")
+base_map_names = [
+ 'pid_iter.rodata' # created on each bpftool invocation
+]
# Check netdevsim
ret, out = cmd("modprobe netdevsim", fail=False)
@@ -913,11 +912,18 @@ try:
sim.tc_flush_filters()
+ start_test("Test TC offloads failure...")
+ sim.dfs["dev/bpf_bind_verifier_accept"] = 0
+ ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True,
+ fail=False, include_stderr=True)
+ fail(ret == 0, "TC filter did not reject with TC offloads enabled")
+ check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
+ sim.dfs["dev/bpf_bind_verifier_accept"] = 1
+
start_test("Test TC offloads work...")
ret, _, err = sim.cls_bpf_add_filter(obj, verbose=True, skip_sw=True,
fail=False, include_stderr=True)
fail(ret != 0, "TC filter did not load with TC offloads enabled")
- check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
start_test("Test TC offload basics...")
dfs = simdev.dfs_get_bound_progs(expected=1)
@@ -941,6 +947,7 @@ try:
start_test("Test disabling TC offloads is rejected while filters installed...")
ret, _ = sim.set_ethtool_tc_offloads(False, fail=False)
fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...")
+ sim.set_ethtool_tc_offloads(True)
start_test("Test qdisc removal frees things...")
sim.tc_flush_filters()
@@ -999,18 +1006,8 @@ try:
fail=False, include_stderr=True)
fail(ret == 0, "Replaced XDP program with a program in different mode")
check_extack(err,
- "native and generic XDP can't be active at the same time.",
+ "Native and generic XDP can't be active at the same time.",
args)
- ret, _, err = sim.set_xdp(obj, "", force=True,
- fail=False, include_stderr=True)
- fail(ret == 0, "Replaced XDP program with a program in different mode")
- check_extack(err, "program loaded with different flags.", args)
-
- start_test("Test XDP prog remove with bad flags...")
- ret, _, err = sim.unset_xdp("", force=True,
- fail=False, include_stderr=True)
- fail(ret == 0, "Removed program with a bad mode")
- check_extack(err, "program loaded with different flags.", args)
start_test("Test MTU restrictions...")
ret, _ = sim.set_mtu(9000, fail=False)
@@ -1040,10 +1037,19 @@ try:
offload = bpf_pinned("/sys/fs/bpf/offload")
ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True)
fail(ret == 0, "attached offloaded XDP program to drv")
- check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args)
+ check_extack(err, "Using device-bound program without HW_MODE flag is not supported.", args)
rm("/sys/fs/bpf/offload")
sim.wait_for_flush()
+ start_test("Test XDP load failure...")
+ sim.dfs["dev/bpf_bind_verifier_accept"] = 0
+ ret, _, err = bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload",
+ dev=sim['ifname'], fail=False, include_stderr=True)
+ fail(ret == 0, "verifier should fail on load")
+ check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
+ sim.dfs["dev/bpf_bind_verifier_accept"] = 1
+ sim.wait_for_flush()
+
start_test("Test XDP offload...")
_, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True)
ipl = sim.ip_link_show(xdp=True)
@@ -1051,7 +1057,6 @@ try:
progs = bpftool_prog_list(expected=1)
prog = progs[0]
fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID")
- check_verifier_log(err, "[netdevsim] Hello from netdevsim!")
start_test("Test XDP offload is device bound...")
dfs = simdev.dfs_get_bound_progs(expected=1)
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 22943b58d752..7d077d48cadd 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -149,15 +149,15 @@ void test__end_subtest()
if (sub_error_cnt)
env.fail_cnt++;
- else
+ else if (test->skip_cnt == 0)
env.sub_succ_cnt++;
skip_account();
dump_test_log(test, sub_error_cnt);
fprintf(env.stdout, "#%d/%d %s:%s\n",
- test->test_num, test->subtest_num,
- test->subtest_name, sub_error_cnt ? "FAIL" : "OK");
+ test->test_num, test->subtest_num, test->subtest_name,
+ sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
free(test->subtest_name);
test->subtest_name = NULL;
@@ -360,6 +360,58 @@ err:
return -1;
}
+static int finit_module(int fd, const char *param_values, int flags)
+{
+ return syscall(__NR_finit_module, fd, param_values, flags);
+}
+
+static int delete_module(const char *name, int flags)
+{
+ return syscall(__NR_delete_module, name, flags);
+}
+
+static void unload_bpf_testmod(void)
+{
+ if (delete_module("bpf_testmod", 0)) {
+ if (errno == ENOENT) {
+ if (env.verbosity > VERBOSE_NONE)
+ fprintf(stdout, "bpf_testmod.ko is already unloaded.\n");
+ return;
+ }
+ fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno);
+ exit(1);
+ }
+ if (env.verbosity > VERBOSE_NONE)
+ fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n");
+}
+
+static int load_bpf_testmod(void)
+{
+ int fd;
+
+ /* ensure previous instance of the module is unloaded */
+ unload_bpf_testmod();
+
+ if (env.verbosity > VERBOSE_NONE)
+ fprintf(stdout, "Loading bpf_testmod.ko...\n");
+
+ fd = open("bpf_testmod.ko", O_RDONLY);
+ if (fd < 0) {
+ fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno);
+ return -ENOENT;
+ }
+ if (finit_module(fd, "", 0)) {
+ fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno);
+ close(fd);
+ return -EINVAL;
+ }
+ close(fd);
+
+ if (env.verbosity > VERBOSE_NONE)
+ fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n");
+ return 0;
+}
+
/* extern declarations for test funcs */
#define DEFINE_TEST(name) extern void test_##name(void);
#include <prog_tests/tests.h>
@@ -535,6 +587,16 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
return -EINVAL;
}
}
+
+ if (env->verbosity > VERBOSE_NONE) {
+ if (setenv("SELFTESTS_VERBOSE", "1", 1) == -1) {
+ fprintf(stderr,
+ "Unable to setenv SELFTESTS_VERBOSE=1 (errno=%d)",
+ errno);
+ return -1;
+ }
+ }
+
break;
case ARG_GET_TEST_CNT:
env->get_test_cnt = true;
@@ -678,6 +740,11 @@ int main(int argc, char **argv)
save_netns();
stdio_hijack();
+ env.has_testmod = true;
+ if (load_bpf_testmod()) {
+ fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
+ env.has_testmod = false;
+ }
for (i = 0; i < prog_test_cnt; i++) {
struct prog_test_def *test = &prog_test_defs[i];
@@ -722,6 +789,8 @@ int main(int argc, char **argv)
if (test->need_cgroup_cleanup)
cleanup_cgroup_environment();
}
+ if (env.has_testmod)
+ unload_bpf_testmod();
stdio_restore();
if (env.get_test_cnt) {
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 238f5f61189e..115953243f62 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -66,6 +66,7 @@ struct test_env {
enum verbosity verbosity;
bool jit_enabled;
+ bool has_testmod;
bool get_test_cnt;
bool list_test_names;
@@ -141,6 +142,17 @@ extern int test__join_cgroup(const char *path);
___ok; \
})
+#define ASSERT_NEQ(actual, expected, name) ({ \
+ static int duration = 0; \
+ typeof(actual) ___act = (actual); \
+ typeof(expected) ___exp = (expected); \
+ bool ___ok = ___act != ___exp; \
+ CHECK(!___ok, (name), \
+ "unexpected %s: actual %lld == expected %lld\n", \
+ (name), (long long)(___act), (long long)(___exp)); \
+ ___ok; \
+})
+
#define ASSERT_STREQ(actual, expected, name) ({ \
static int duration = 0; \
const char *___act = actual; \
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index b8c72c1d9cf7..dcb83ab02919 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -31,6 +31,8 @@
#define CONNECT6_PROG_PATH "./connect6_prog.o"
#define SENDMSG4_PROG_PATH "./sendmsg4_prog.o"
#define SENDMSG6_PROG_PATH "./sendmsg6_prog.o"
+#define BIND4_PROG_PATH "./bind4_prog.o"
+#define BIND6_PROG_PATH "./bind6_prog.o"
#define SERV4_IP "192.168.1.254"
#define SERV4_REWRITE_IP "127.0.0.1"
@@ -660,190 +662,6 @@ static int load_insns(const struct sock_addr_test *test,
return ret;
}
-/* [1] These testing programs try to read different context fields, including
- * narrow loads of different sizes from user_ip4 and user_ip6, and write to
- * those allowed to be overridden.
- *
- * [2] BPF_LD_IMM64 & BPF_JMP_REG are used below whenever there is a need to
- * compare a register with unsigned 32bit integer. BPF_JMP_IMM can't be used
- * in such cases since it accepts only _signed_ 32bit integer as IMM
- * argument. Also note that BPF_LD_IMM64 contains 2 instructions what matters
- * to count jumps properly.
- */
-
-static int bind4_prog_load(const struct sock_addr_test *test)
-{
- union {
- uint8_t u4_addr8[4];
- uint16_t u4_addr16[2];
- uint32_t u4_addr32;
- } ip4, port;
- struct sockaddr_in addr4_rw;
-
- if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) {
- log_err("Invalid IPv4: %s", SERV4_IP);
- return -1;
- }
-
- port.u4_addr32 = htons(SERV4_PORT);
-
- if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
- (struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1)
- return -1;
-
- /* See [1]. */
- struct bpf_insn insns[] = {
- BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-
- /* if (sk.family == AF_INET && */
- BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, family)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 32),
-
- /* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */
- BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, type)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1),
- BPF_JMP_A(1),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 28),
-
- /* 1st_byte_of_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 26),
-
- /* 2nd_byte_of_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4) + 1),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 24),
-
- /* 3rd_byte_of_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4) + 2),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 22),
-
- /* 4th_byte_of_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4) + 3),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 20),
-
- /* 1st_half_of_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 18),
-
- /* 2nd_half_of_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4) + 2),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 16),
-
- /* whole_user_ip4 == expected && */
- BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip4)),
- BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */
- BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 12),
-
- /* 1st_byte_of_user_port == expected && */
- BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_port)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr8[0], 10),
-
- /* 1st_half_of_user_port == expected && */
- BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_port)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr16[0], 8),
-
- /* user_port == expected) { */
- BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_port)),
- BPF_LD_IMM64(BPF_REG_8, port.u4_addr32), /* See [2]. */
- BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4),
-
- /* user_ip4 = addr4_rw.sin_addr */
- BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_addr.s_addr),
- BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
- offsetof(struct bpf_sock_addr, user_ip4)),
-
- /* user_port = addr4_rw.sin_port */
- BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_port),
- BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
- offsetof(struct bpf_sock_addr, user_port)),
- /* } */
-
- /* return 1 */
- BPF_MOV64_IMM(BPF_REG_0, 1),
- BPF_EXIT_INSN(),
- };
-
- return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
-}
-
-static int bind6_prog_load(const struct sock_addr_test *test)
-{
- struct sockaddr_in6 addr6_rw;
- struct in6_addr ip6;
-
- if (inet_pton(AF_INET6, SERV6_IP, (void *)&ip6) != 1) {
- log_err("Invalid IPv6: %s", SERV6_IP);
- return -1;
- }
-
- if (mk_sockaddr(AF_INET6, SERV6_REWRITE_IP, SERV6_REWRITE_PORT,
- (struct sockaddr *)&addr6_rw, sizeof(addr6_rw)) == -1)
- return -1;
-
- /* See [1]. */
- struct bpf_insn insns[] = {
- BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-
- /* if (sk.family == AF_INET6 && */
- BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, family)),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18),
-
- /* 5th_byte_of_user_ip6 == expected && */
- BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip6[1])),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr[4], 16),
-
- /* 3rd_half_of_user_ip6 == expected && */
- BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip6[1])),
- BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr16[2], 14),
-
- /* last_word_of_user_ip6 == expected) { */
- BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6,
- offsetof(struct bpf_sock_addr, user_ip6[3])),
- BPF_LD_IMM64(BPF_REG_8, ip6.s6_addr32[3]), /* See [2]. */
- BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 10),
-
-
-#define STORE_IPV6_WORD(N) \
- BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_addr.s6_addr32[N]), \
- BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \
- offsetof(struct bpf_sock_addr, user_ip6[N]))
-
- /* user_ip6 = addr6_rw.sin6_addr */
- STORE_IPV6_WORD(0),
- STORE_IPV6_WORD(1),
- STORE_IPV6_WORD(2),
- STORE_IPV6_WORD(3),
-
- /* user_port = addr6_rw.sin6_port */
- BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_port),
- BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
- offsetof(struct bpf_sock_addr, user_port)),
-
- /* } */
-
- /* return 1 */
- BPF_MOV64_IMM(BPF_REG_0, 1),
- BPF_EXIT_INSN(),
- };
-
- return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
-}
-
static int load_path(const struct sock_addr_test *test, const char *path)
{
struct bpf_prog_load_attr attr;
@@ -865,6 +683,16 @@ static int load_path(const struct sock_addr_test *test, const char *path)
return prog_fd;
}
+static int bind4_prog_load(const struct sock_addr_test *test)
+{
+ return load_path(test, BIND4_PROG_PATH);
+}
+
+static int bind6_prog_load(const struct sock_addr_test *test)
+{
+ return load_path(test, BIND6_PROG_PATH);
+}
+
static int connect4_prog_load(const struct sock_addr_test *test)
{
return load_path(test, CONNECT4_PROG_PATH);
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 0fa1e421c3d7..427ca00a3217 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1273,6 +1273,16 @@ static char *test_to_str(int test)
return "unknown";
}
+static void append_str(char *dst, const char *src, size_t dst_cap)
+{
+ size_t avail = dst_cap - strlen(dst);
+
+ if (avail <= 1) /* just zero byte could be written */
+ return;
+
+ strncat(dst, src, avail - 1); /* strncat() adds + 1 for zero byte */
+}
+
#define OPTSTRING 60
static void test_options(char *options)
{
@@ -1281,42 +1291,42 @@ static void test_options(char *options)
memset(options, 0, OPTSTRING);
if (txmsg_pass)
- strncat(options, "pass,", OPTSTRING);
+ append_str(options, "pass,", OPTSTRING);
if (txmsg_redir)
- strncat(options, "redir,", OPTSTRING);
+ append_str(options, "redir,", OPTSTRING);
if (txmsg_drop)
- strncat(options, "drop,", OPTSTRING);
+ append_str(options, "drop,", OPTSTRING);
if (txmsg_apply) {
snprintf(tstr, OPTSTRING, "apply %d,", txmsg_apply);
- strncat(options, tstr, OPTSTRING);
+ append_str(options, tstr, OPTSTRING);
}
if (txmsg_cork) {
snprintf(tstr, OPTSTRING, "cork %d,", txmsg_cork);
- strncat(options, tstr, OPTSTRING);
+ append_str(options, tstr, OPTSTRING);
}
if (txmsg_start) {
snprintf(tstr, OPTSTRING, "start %d,", txmsg_start);
- strncat(options, tstr, OPTSTRING);
+ append_str(options, tstr, OPTSTRING);
}
if (txmsg_end) {
snprintf(tstr, OPTSTRING, "end %d,", txmsg_end);
- strncat(options, tstr, OPTSTRING);
+ append_str(options, tstr, OPTSTRING);
}
if (txmsg_start_pop) {
snprintf(tstr, OPTSTRING, "pop (%d,%d),",
txmsg_start_pop, txmsg_start_pop + txmsg_pop);
- strncat(options, tstr, OPTSTRING);
+ append_str(options, tstr, OPTSTRING);
}
if (txmsg_ingress)
- strncat(options, "ingress,", OPTSTRING);
+ append_str(options, "ingress,", OPTSTRING);
if (txmsg_redir_skb)
- strncat(options, "redir_skb,", OPTSTRING);
+ append_str(options, "redir_skb,", OPTSTRING);
if (txmsg_ktls_skb)
- strncat(options, "ktls_skb,", OPTSTRING);
+ append_str(options, "ktls_skb,", OPTSTRING);
if (ktls)
- strncat(options, "ktls,", OPTSTRING);
+ append_str(options, "ktls,", OPTSTRING);
if (peek_flag)
- strncat(options, "peek,", OPTSTRING);
+ append_str(options, "peek,", OPTSTRING);
}
static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
index 6220b95cbd02..9dd9b5590f9d 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf.h
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -14,5 +14,9 @@ struct tcpbpf_globals {
__u64 bytes_acked;
__u32 num_listen;
__u32 num_close_events;
+ __u32 tcp_save_syn;
+ __u32 tcp_saved_syn;
+ __u32 window_clamp_client;
+ __u32 window_clamp_server;
};
#endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
deleted file mode 100644
index 74a9e49988b6..000000000000
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ /dev/null
@@ -1,165 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <inttypes.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-#include <errno.h>
-#include <string.h>
-#include <linux/bpf.h>
-#include <sys/types.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "bpf_rlimit.h"
-#include "bpf_util.h"
-#include "cgroup_helpers.h"
-
-#include "test_tcpbpf.h"
-
-/* 3 comes from one listening socket + both ends of the connection */
-#define EXPECTED_CLOSE_EVENTS 3
-
-#define EXPECT_EQ(expected, actual, fmt) \
- do { \
- if ((expected) != (actual)) { \
- printf(" Value of: " #actual "\n" \
- " Actual: %" fmt "\n" \
- " Expected: %" fmt "\n", \
- (actual), (expected)); \
- ret--; \
- } \
- } while (0)
-
-int verify_result(const struct tcpbpf_globals *result)
-{
- __u32 expected_events;
- int ret = 0;
-
- expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
- (1 << BPF_SOCK_OPS_RWND_INIT) |
- (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
- (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
- (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
- (1 << BPF_SOCK_OPS_NEEDS_ECN) |
- (1 << BPF_SOCK_OPS_STATE_CB) |
- (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
-
- EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
- EXPECT_EQ(501ULL, result->bytes_received, "llu");
- EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
- EXPECT_EQ(1, result->data_segs_in, PRIu32);
- EXPECT_EQ(1, result->data_segs_out, PRIu32);
- EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
- EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
- EXPECT_EQ(1, result->num_listen, PRIu32);
- EXPECT_EQ(EXPECTED_CLOSE_EVENTS, result->num_close_events, PRIu32);
-
- return ret;
-}
-
-int verify_sockopt_result(int sock_map_fd)
-{
- __u32 key = 0;
- int ret = 0;
- int res;
- int rv;
-
- /* check setsockopt for SAVE_SYN */
- rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
- EXPECT_EQ(0, rv, "d");
- EXPECT_EQ(0, res, "d");
- key = 1;
- /* check getsockopt for SAVED_SYN */
- rv = bpf_map_lookup_elem(sock_map_fd, &key, &res);
- EXPECT_EQ(0, rv, "d");
- EXPECT_EQ(1, res, "d");
- return ret;
-}
-
-static int bpf_find_map(const char *test, struct bpf_object *obj,
- const char *name)
-{
- struct bpf_map *map;
-
- map = bpf_object__find_map_by_name(obj, name);
- if (!map) {
- printf("%s:FAIL:map '%s' not found\n", test, name);
- return -1;
- }
- return bpf_map__fd(map);
-}
-
-int main(int argc, char **argv)
-{
- const char *file = "test_tcpbpf_kern.o";
- int prog_fd, map_fd, sock_map_fd;
- struct tcpbpf_globals g = {0};
- const char *cg_path = "/foo";
- int error = EXIT_FAILURE;
- struct bpf_object *obj;
- int cg_fd = -1;
- int retry = 10;
- __u32 key = 0;
- int rv;
-
- cg_fd = cgroup_setup_and_join(cg_path);
- if (cg_fd < 0)
- goto err;
-
- if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
- printf("FAILED: load_bpf_file failed for: %s\n", file);
- goto err;
- }
-
- rv = bpf_prog_attach(prog_fd, cg_fd, BPF_CGROUP_SOCK_OPS, 0);
- if (rv) {
- printf("FAILED: bpf_prog_attach: %d (%s)\n",
- error, strerror(errno));
- goto err;
- }
-
- if (system("./tcp_server.py")) {
- printf("FAILED: TCP server\n");
- goto err;
- }
-
- map_fd = bpf_find_map(__func__, obj, "global_map");
- if (map_fd < 0)
- goto err;
-
- sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results");
- if (sock_map_fd < 0)
- goto err;
-
-retry_lookup:
- rv = bpf_map_lookup_elem(map_fd, &key, &g);
- if (rv != 0) {
- printf("FAILED: bpf_map_lookup_elem returns %d\n", rv);
- goto err;
- }
-
- if (g.num_close_events != EXPECTED_CLOSE_EVENTS && retry--) {
- printf("Unexpected number of close events (%d), retrying!\n",
- g.num_close_events);
- usleep(100);
- goto retry_lookup;
- }
-
- if (verify_result(&g)) {
- printf("FAILED: Wrong stats\n");
- goto err;
- }
-
- if (verify_sockopt_result(sock_map_fd)) {
- printf("FAILED: Wrong sockopt stats\n");
- goto err;
- }
-
- printf("PASSED!\n");
- error = 0;
-err:
- bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
- close(cg_fd);
- cleanup_cgroup_environment();
- return error;
-}
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index bd12ec97a44d..1ccbe804e8e1 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -24,12 +24,12 @@
# Root namespace with metadata-mode tunnel + BPF
# Device names and addresses:
# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay)
-# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay)
+# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200, IPv6: 1::22 (overlay)
#
# Namespace at_ns0 with native tunnel
# Device names and addresses:
# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay)
-# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay)
+# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100, IPv6: 1::11 (overlay)
#
#
# End-to-end ping packet flow
@@ -250,7 +250,7 @@ add_ipip_tunnel()
ip addr add dev $DEV 10.1.1.200/24
}
-add_ipip6tnl_tunnel()
+add_ip6tnl_tunnel()
{
ip netns exec at_ns0 ip addr add ::11/96 dev veth0
ip netns exec at_ns0 ip link set dev veth0 up
@@ -262,11 +262,13 @@ add_ipip6tnl_tunnel()
ip link add dev $DEV_NS type $TYPE \
local ::11 remote ::22
ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 1::11/96
ip netns exec at_ns0 ip link set dev $DEV_NS up
# root namespace
ip link add dev $DEV type $TYPE external
ip addr add dev $DEV 10.1.1.200/24
+ ip addr add dev $DEV 1::22/96
ip link set dev $DEV up
}
@@ -534,7 +536,7 @@ test_ipip6()
check $TYPE
config_device
- add_ipip6tnl_tunnel
+ add_ip6tnl_tunnel
ip link set dev veth1 mtu 1500
attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
# underlay
@@ -553,6 +555,34 @@ test_ipip6()
echo -e ${GREEN}"PASS: $TYPE"${NC}
}
+test_ip6ip6()
+{
+ TYPE=ip6tnl
+ DEV_NS=ip6ip6tnl00
+ DEV=ip6ip6tnl11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6tnl_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ip6ip6_set_tunnel ip6ip6_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip6 over ip6
+ ping6 $PING_ARG 1::11
+ check_err $?
+ ip netns exec at_ns0 ping6 $PING_ARG 1::22
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: ip6$TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: ip6$TYPE"${NC}
+}
+
setup_xfrm_tunnel()
{
auth=0x$(printf '1%.0s' {1..40})
@@ -646,6 +676,7 @@ cleanup()
ip link del veth1 2> /dev/null
ip link del ipip11 2> /dev/null
ip link del ipip6tnl11 2> /dev/null
+ ip link del ip6ip6tnl11 2> /dev/null
ip link del gretap11 2> /dev/null
ip link del ip6gre11 2> /dev/null
ip link del ip6gretap11 2> /dev/null
@@ -742,6 +773,10 @@ bpf_tunnel_test()
test_ipip6
errors=$(( $errors + $? ))
+ echo "Testing IP6IP6 tunnel..."
+ test_ip6ip6
+ errors=$(( $errors + $? ))
+
echo "Testing IPSec tunnel..."
test_xfrm_tunnel
errors=$(( $errors + $? ))
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 9be395d9dc64..777a81404fdb 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -875,19 +875,36 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val,
__u8 tmp[TEST_DATA_LEN << 2];
__u32 size_tmp = sizeof(tmp);
uint32_t retval;
- int err;
+ int err, saved_errno;
if (unpriv)
set_admin(true);
err = bpf_prog_test_run(fd_prog, 1, data, size_data,
tmp, &size_tmp, &retval, NULL);
+ saved_errno = errno;
+
if (unpriv)
set_admin(false);
- if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
- printf("Unexpected bpf_prog_test_run error ");
- return err;
+
+ if (err) {
+ switch (saved_errno) {
+ case 524/*ENOTSUPP*/:
+ printf("Did not run the program (not supported) ");
+ return 0;
+ case EPERM:
+ if (unpriv) {
+ printf("Did not run the program (no permission) ");
+ return 0;
+ }
+ /* fallthrough; */
+ default:
+ printf("FAIL: Unexpected bpf_prog_test_run error (%s) ",
+ strerror(saved_errno));
+ return err;
+ }
}
- if (!err && retval != expected_val &&
+
+ if (retval != expected_val &&
expected_val != POINTER_VALUE) {
printf("FAIL retval %d != %d ", retval, expected_val);
return 1;
@@ -936,6 +953,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
int run_errs, run_successes;
int map_fds[MAX_NR_MAPS];
const char *expected_err;
+ int saved_errno;
int fixup_skips;
__u32 pflags;
int i, err;
@@ -997,6 +1015,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
}
fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog));
+ saved_errno = errno;
/* BPF_PROG_TYPE_TRACING requires more setup and
* bpf_probe_prog_type won't give correct answer
@@ -1013,7 +1032,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
if (expected_ret == ACCEPT || expected_ret == VERBOSE_ACCEPT) {
if (fd_prog < 0) {
printf("FAIL\nFailed to load prog '%s'!\n",
- strerror(errno));
+ strerror(saved_errno));
goto fail_log;
}
#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
@@ -1152,6 +1171,19 @@ static void get_unpriv_disabled()
static bool test_as_unpriv(struct bpf_test *test)
{
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ /* Some architectures have strict alignment requirements. In
+ * that case, the BPF verifier detects if a program has
+ * unaligned accesses and rejects them. A user can pass
+ * BPF_F_ANY_ALIGNMENT to a program to override this
+ * check. That, however, will only work when a privileged user
+ * loads a program. An unprivileged user loading a program
+ * with this flag will be rejected prior entering the
+ * verifier.
+ */
+ if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
+ return false;
+#endif
return !test->prog_type ||
test->prog_type == BPF_PROG_TYPE_SOCKET_FILTER ||
test->prog_type == BPF_PROG_TYPE_CGROUP_SKB;
diff --git a/tools/testing/selftests/bpf/test_xsk.sh b/tools/testing/selftests/bpf/test_xsk.sh
new file mode 100755
index 000000000000..88a7483eaae4
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_xsk.sh
@@ -0,0 +1,259 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright(c) 2020 Intel Corporation, Weqaar Janjua <weqaar.a.janjua@intel.com>
+
+# AF_XDP selftests based on veth
+#
+# End-to-end AF_XDP over Veth test
+#
+# Topology:
+# ---------
+# -----------
+# _ | Process | _
+# / ----------- \
+# / | \
+# / | \
+# ----------- | -----------
+# | Thread1 | | | Thread2 |
+# ----------- | -----------
+# | | |
+# ----------- | -----------
+# | xskX | | | xskY |
+# ----------- | -----------
+# | | |
+# ----------- | ----------
+# | vethX | --------- | vethY |
+# ----------- peer ----------
+# | | |
+# namespaceX | namespaceY
+#
+# AF_XDP is an address family optimized for high performance packet processing,
+# it is XDP’s user-space interface.
+#
+# An AF_XDP socket is linked to a single UMEM which is a region of virtual
+# contiguous memory, divided into equal-sized frames.
+#
+# Refer to AF_XDP Kernel Documentation for detailed information:
+# https://www.kernel.org/doc/html/latest/networking/af_xdp.html
+#
+# Prerequisites setup by script:
+#
+# Set up veth interfaces as per the topology shown ^^:
+# * setup two veth interfaces and one namespace
+# ** veth<xxxx> in root namespace
+# ** veth<yyyy> in af_xdp<xxxx> namespace
+# ** namespace af_xdp<xxxx>
+# * create a spec file veth.spec that includes this run-time configuration
+# *** xxxx and yyyy are randomly generated 4 digit numbers used to avoid
+# conflict with any existing interface
+# * tests the veth and xsk layers of the topology
+#
+# See the source xdpxceiver.c for information on each test
+#
+# Kernel configuration:
+# ---------------------
+# See "config" file for recommended kernel config options.
+#
+# Turn on XDP sockets and veth support when compiling i.e.
+# Networking support -->
+# Networking options -->
+# [ * ] XDP sockets
+#
+# Executing Tests:
+# ----------------
+# Must run with CAP_NET_ADMIN capability.
+#
+# Run (full color-coded output):
+# sudo ./test_xsk.sh -c
+#
+# If running from kselftests:
+# sudo make colorconsole=1 run_tests
+#
+# Run (full output without color-coding):
+# sudo ./test_xsk.sh
+
+. xsk_prereqs.sh
+
+while getopts c flag
+do
+ case "${flag}" in
+ c) colorconsole=1;;
+ esac
+done
+
+TEST_NAME="PREREQUISITES"
+
+URANDOM=/dev/urandom
+[ ! -e "${URANDOM}" ] && { echo "${URANDOM} not found. Skipping tests."; test_exit 1 1; }
+
+VETH0_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)
+VETH0=ve${VETH0_POSTFIX}
+VETH1_POSTFIX=$(cat ${URANDOM} | tr -dc '0-9' | fold -w 256 | head -n 1 | head --bytes 4)
+VETH1=ve${VETH1_POSTFIX}
+NS0=root
+NS1=af_xdp${VETH1_POSTFIX}
+MTU=1500
+
+setup_vethPairs() {
+ echo "setting up ${VETH0}: namespace: ${NS0}"
+ ip netns add ${NS1}
+ ip link add ${VETH0} type veth peer name ${VETH1}
+ if [ -f /proc/net/if_inet6 ]; then
+ echo 1 > /proc/sys/net/ipv6/conf/${VETH0}/disable_ipv6
+ fi
+ echo "setting up ${VETH1}: namespace: ${NS1}"
+ ip link set ${VETH1} netns ${NS1}
+ ip netns exec ${NS1} ip link set ${VETH1} mtu ${MTU}
+ ip link set ${VETH0} mtu ${MTU}
+ ip netns exec ${NS1} ip link set ${VETH1} up
+ ip link set ${VETH0} up
+}
+
+validate_root_exec
+validate_veth_support ${VETH0}
+validate_ip_utility
+setup_vethPairs
+
+retval=$?
+if [ $retval -ne 0 ]; then
+ test_status $retval "${TEST_NAME}"
+ cleanup_exit ${VETH0} ${VETH1} ${NS1}
+ exit $retval
+fi
+
+echo "${VETH0}:${VETH1},${NS1}" > ${SPECFILE}
+
+validate_veth_spec_file
+
+echo "Spec file created: ${SPECFILE}"
+
+test_status $retval "${TEST_NAME}"
+
+## START TESTS
+
+statusList=()
+
+### TEST 1
+TEST_NAME="XSK KSELFTEST FRAMEWORK"
+
+echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Generic mode"
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+retval=$?
+if [ $retval -eq 0 ]; then
+ echo "Switching interfaces [${VETH0}, ${VETH1}] to XDP Native mode"
+ vethXDPnative ${VETH0} ${VETH1} ${NS1}
+fi
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 2
+TEST_NAME="SKB NOPOLL"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 3
+TEST_NAME="SKB POLL"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S" "-p")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 4
+TEST_NAME="DRV NOPOLL"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 5
+TEST_NAME="DRV POLL"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N" "-p")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 6
+TEST_NAME="SKB SOCKET TEARDOWN"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S" "-T")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 7
+TEST_NAME="DRV SOCKET TEARDOWN"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N" "-T")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 8
+TEST_NAME="SKB BIDIRECTIONAL SOCKETS"
+
+vethXDPgeneric ${VETH0} ${VETH1} ${NS1}
+
+params=("-S" "-B")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+### TEST 9
+TEST_NAME="DRV BIDIRECTIONAL SOCKETS"
+
+vethXDPnative ${VETH0} ${VETH1} ${NS1}
+
+params=("-N" "-B")
+execxdpxceiver params
+
+retval=$?
+test_status $retval "${TEST_NAME}"
+statusList+=($retval)
+
+## END TESTS
+
+cleanup_exit ${VETH0} ${VETH1} ${NS1}
+
+for _status in "${statusList[@]}"
+do
+ if [ $_status -ne 0 ]; then
+ test_exit $ksft_fail 0
+ fi
+done
+
+test_exit $ksft_pass 0
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index 1c4b1939f5a8..bed53b561e04 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -68,7 +68,7 @@
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_W, BPF_REG_1, BPF_REG_0, 0),
- BPF_JMP_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1),
+ BPF_JMP32_IMM(BPF_JSGT, BPF_REG_1, 0xffffffff, 1),
BPF_MOV32_IMM(BPF_REG_1, 0),
BPF_MOV32_IMM(BPF_REG_2, MAX_ENTRIES),
BPF_JMP_REG(BPF_JSGT, BPF_REG_2, BPF_REG_1, 1),
diff --git a/tools/testing/selftests/bpf/verifier/bounds.c b/tools/testing/selftests/bpf/verifier/bounds.c
index dac40de3f868..57ed67b86074 100644
--- a/tools/testing/selftests/bpf/verifier/bounds.c
+++ b/tools/testing/selftests/bpf/verifier/bounds.c
@@ -703,3 +703,44 @@
.fixup_map_hash_8b = { 3 },
.result = ACCEPT,
},
+{
+ "bounds checks after 32-bit truncation. test 1",
+ .insns = {
+ 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_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, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ /* This used to reduce the max bound to 0x7fffffff */
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 0x7fffffff, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 3 },
+ .errstr_unpriv = "R0 leaks addr",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+},
+{
+ "bounds checks after 32-bit truncation. test 2",
+ .insns = {
+ 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_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, 4),
+ BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JSLT, BPF_REG_1, 1, 1),
+ BPF_JMP32_IMM(BPF_JSLT, BPF_REG_1, 0, 1),
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map_hash_8b = { 3 },
+ .errstr_unpriv = "R0 leaks addr",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
index 2ad5f974451c..fb13ca2d5606 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c
@@ -266,6 +266,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid 8-byte read from bpf_sk_lookup remote_ip4 field",
@@ -292,6 +293,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid 8-byte read from bpf_sk_lookup remote_port field",
@@ -305,6 +307,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid 8-byte read from bpf_sk_lookup local_ip4 field",
@@ -331,6 +334,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid 8-byte read from bpf_sk_lookup local_port field",
@@ -344,6 +348,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
/* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */
{
@@ -410,6 +415,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"invalid 4-byte unaligned read from bpf_sk_lookup at even offset",
@@ -422,6 +428,7 @@
.result = REJECT,
.prog_type = BPF_PROG_TYPE_SK_LOOKUP,
.expected_attach_type = BPF_SK_LOOKUP,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
/* in-bound and out-of-bound writes to bpf_sk_lookup */
{
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 2e16b8e268f2..2022c0f2cd75 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1089,3 +1089,45 @@
.errstr_unpriv = "R1 leaks addr",
.result = REJECT,
},
+{
+ "pkt > pkt_end taken check",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, // 0. r2 = *(u32 *)(r1 + data_end)
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, // 1. r4 = *(u32 *)(r1 + data)
+ offsetof(struct __sk_buff, data)),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_4), // 2. r3 = r4
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 42), // 3. r3 += 42
+ BPF_MOV64_IMM(BPF_REG_1, 0), // 4. r1 = 0
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 2), // 5. if r3 > r2 goto 8
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 14), // 6. r4 += 14
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_4), // 7. r1 = r4
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 1), // 8. if r3 > r2 goto 10
+ BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, 9), // 9. r2 = *(u8 *)(r1 + 9)
+ BPF_MOV64_IMM(BPF_REG_0, 0), // 10. r0 = 0
+ BPF_EXIT_INSN(), // 11. exit
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+},
+{
+ "pkt_end < pkt taken check",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, // 0. r2 = *(u32 *)(r1 + data_end)
+ offsetof(struct __sk_buff, data_end)),
+ BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, // 1. r4 = *(u32 *)(r1 + data)
+ offsetof(struct __sk_buff, data)),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_4), // 2. r3 = r4
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 42), // 3. r3 += 42
+ BPF_MOV64_IMM(BPF_REG_1, 0), // 4. r1 = 0
+ BPF_JMP_REG(BPF_JGT, BPF_REG_3, BPF_REG_2, 2), // 5. if r3 > r2 goto 8
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, 14), // 6. r4 += 14
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_4), // 7. r1 = r4
+ BPF_JMP_REG(BPF_JLT, BPF_REG_2, BPF_REG_3, 1), // 8. if r2 < r3 goto 10
+ BPF_LDX_MEM(BPF_H, BPF_REG_2, BPF_REG_1, 9), // 9. r2 = *(u8 *)(r1 + 9)
+ BPF_MOV64_IMM(BPF_REG_0, 0), // 10. r0 = 0
+ BPF_EXIT_INSN(), // 11. exit
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+},
diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c
index 988f46a1a4c7..c0648dc009b5 100644
--- a/tools/testing/selftests/bpf/verifier/direct_value_access.c
+++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c
@@ -69,6 +69,7 @@
.fixup_map_array_48b = { 1 },
.result = REJECT,
.errstr = "R1 min value is outside of the allowed memory range",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct map access, write test 7",
@@ -195,6 +196,7 @@
.fixup_map_array_48b = { 1, 3 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=48 off=47 size=2",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct map access, write test 17",
@@ -209,6 +211,7 @@
.fixup_map_array_48b = { 1, 3 },
.result = REJECT,
.errstr = "invalid access to map value, value_size=48 off=47 size=2",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"direct map access, write test 18",
diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c
index 637f9293bda8..b117bdd3806d 100644
--- a/tools/testing/selftests/bpf/verifier/map_ptr.c
+++ b/tools/testing/selftests/bpf/verifier/map_ptr.c
@@ -44,6 +44,7 @@
.errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN",
.result = REJECT,
.errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"bpf_map_ptr: read ops field accepted",
diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
index 95b5d70a1dc1..2978fb5a769d 100644
--- a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
+++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c
@@ -31,4 +31,5 @@
.fixup_map_hash_8b = { 1, },
.prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
.errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c
index 006b5bd99c08..3b6ee009c00b 100644
--- a/tools/testing/selftests/bpf/verifier/ref_tracking.c
+++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c
@@ -675,6 +675,7 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.errstr = "invalid mem access",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"reference tracking: use ptr from bpf_sk_fullsock() after release",
@@ -698,6 +699,7 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.errstr = "invalid mem access",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
@@ -725,6 +727,7 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.errstr = "invalid mem access",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"reference tracking: use sk after bpf_sk_release(tp)",
@@ -747,6 +750,7 @@
.prog_type = BPF_PROG_TYPE_SCHED_CLS,
.result = REJECT,
.errstr = "invalid mem access",
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
diff --git a/tools/testing/selftests/bpf/verifier/regalloc.c b/tools/testing/selftests/bpf/verifier/regalloc.c
index 4ad7e05de706..bb0dd89dd212 100644
--- a/tools/testing/selftests/bpf/verifier/regalloc.c
+++ b/tools/testing/selftests/bpf/verifier/regalloc.c
@@ -21,6 +21,7 @@
.fixup_map_hash_48b = { 4 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc negative",
@@ -71,6 +72,7 @@
.fixup_map_hash_48b = { 4 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc src_reg negative",
@@ -97,6 +99,7 @@
.result = REJECT,
.errstr = "invalid access to map value, value_size=48 off=44 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc and spill",
@@ -126,6 +129,7 @@
.fixup_map_hash_48b = { 4 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc and spill negative",
@@ -156,6 +160,7 @@
.result = REJECT,
.errstr = "invalid access to map value, value_size=48 off=48 size=8",
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc three regs",
@@ -182,6 +187,7 @@
.fixup_map_hash_48b = { 4 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc after call",
@@ -210,6 +216,7 @@
.fixup_map_hash_48b = { 4 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc in callee",
@@ -240,6 +247,7 @@
.fixup_map_hash_48b = { 4 },
.result = ACCEPT,
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
},
{
"regalloc, spill, JEQ",
diff --git a/tools/testing/selftests/bpf/verifier/unpriv.c b/tools/testing/selftests/bpf/verifier/unpriv.c
index 91bb77c24a2e..a3fe0fbaed41 100644
--- a/tools/testing/selftests/bpf/verifier/unpriv.c
+++ b/tools/testing/selftests/bpf/verifier/unpriv.c
@@ -108,8 +108,9 @@
BPF_EXIT_INSN(),
},
.fixup_map_hash_8b = { 3 },
- .errstr = "invalid indirect read from stack off -8+0 size 8",
- .result = REJECT,
+ .errstr_unpriv = "invalid indirect read from stack off -8+0 size 8",
+ .result_unpriv = REJECT,
+ .result = ACCEPT,
},
{
"unpriv: mangle pointer on stack 1",
diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c
index ccade9312d21..55af248efa93 100644
--- a/tools/testing/selftests/bpf/verifier/wide_access.c
+++ b/tools/testing/selftests/bpf/verifier/wide_access.c
@@ -1,4 +1,4 @@
-#define BPF_SOCK_ADDR_STORE(field, off, res, err) \
+#define BPF_SOCK_ADDR_STORE(field, off, res, err, flgs) \
{ \
"wide store to bpf_sock_addr." #field "[" #off "]", \
.insns = { \
@@ -11,31 +11,36 @@
.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
.errstr = err, \
+ .flags = flgs, \
}
/* user_ip6[0] is u64 aligned */
BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT,
- NULL),
+ NULL, 0),
BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT,
- "invalid bpf_context access off=12 size=8"),
+ "invalid bpf_context access off=12 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT,
- NULL),
+ NULL, 0),
BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT,
- "invalid bpf_context access off=20 size=8"),
+ "invalid bpf_context access off=20 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
/* msg_src_ip6[0] is _not_ u64 aligned */
BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT,
- "invalid bpf_context access off=44 size=8"),
+ "invalid bpf_context access off=44 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT,
- NULL),
+ NULL, 0),
BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT,
- "invalid bpf_context access off=52 size=8"),
+ "invalid bpf_context access off=52 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT,
- "invalid bpf_context access off=56 size=8"),
+ "invalid bpf_context access off=56 size=8", 0),
#undef BPF_SOCK_ADDR_STORE
-#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \
+#define BPF_SOCK_ADDR_LOAD(field, off, res, err, flgs) \
{ \
"wide load from bpf_sock_addr." #field "[" #off "]", \
.insns = { \
@@ -48,26 +53,31 @@ BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT,
.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
.errstr = err, \
+ .flags = flgs, \
}
/* user_ip6[0] is u64 aligned */
BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT,
- NULL),
+ NULL, 0),
BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT,
- "invalid bpf_context access off=12 size=8"),
+ "invalid bpf_context access off=12 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT,
- NULL),
+ NULL, 0),
BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT,
- "invalid bpf_context access off=20 size=8"),
+ "invalid bpf_context access off=20 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
/* msg_src_ip6[0] is _not_ u64 aligned */
BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT,
- "invalid bpf_context access off=44 size=8"),
+ "invalid bpf_context access off=44 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT,
- NULL),
+ NULL, 0),
BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT,
- "invalid bpf_context access off=52 size=8"),
+ "invalid bpf_context access off=52 size=8",
+ F_NEEDS_EFFICIENT_UNALIGNED_ACCESS),
BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT,
- "invalid bpf_context access off=56 size=8"),
+ "invalid bpf_context access off=56 size=8", 0),
#undef BPF_SOCK_ADDR_LOAD
diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
new file mode 100644
index 000000000000..014dedaa4dd2
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -0,0 +1,1074 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2020 Intel Corporation. */
+
+/*
+ * Some functions in this program are taken from
+ * Linux kernel samples/bpf/xdpsock* and modified
+ * for use.
+ *
+ * See test_xsk.sh for detailed information on test topology
+ * and prerequisite network setup.
+ *
+ * This test program contains two threads, each thread is single socket with
+ * a unique UMEM. It validates in-order packet delivery and packet content
+ * by sending packets to each other.
+ *
+ * Tests Information:
+ * ------------------
+ * These selftests test AF_XDP SKB and Native/DRV modes using veth
+ * Virtual Ethernet interfaces.
+ *
+ * The following tests are run:
+ *
+ * 1. AF_XDP SKB mode
+ * Generic mode XDP is driver independent, used when the driver does
+ * not have support for XDP. Works on any netdevice using sockets and
+ * generic XDP path. XDP hook from netif_receive_skb().
+ * a. nopoll - soft-irq processing
+ * b. poll - using poll() syscall
+ * c. Socket Teardown
+ * Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy
+ * both sockets, then repeat multiple times. Only nopoll mode is used
+ * d. Bi-directional sockets
+ * Configure sockets as bi-directional tx/rx sockets, sets up fill and
+ * completion rings on each socket, tx/rx in both directions. Only nopoll
+ * mode is used
+ *
+ * 2. AF_XDP DRV/Native mode
+ * Works on any netdevice with XDP_REDIRECT support, driver dependent. Processes
+ * packets before SKB allocation. Provides better performance than SKB. Driver
+ * hook available just after DMA of buffer descriptor.
+ * a. nopoll
+ * b. poll
+ * c. Socket Teardown
+ * d. Bi-directional sockets
+ * - Only copy mode is supported because veth does not currently support
+ * zero-copy mode
+ *
+ * Total tests: 8
+ *
+ * Flow:
+ * -----
+ * - Single process spawns two threads: Tx and Rx
+ * - Each of these two threads attach to a veth interface within their assigned
+ * namespaces
+ * - Each thread Creates one AF_XDP socket connected to a unique umem for each
+ * veth interface
+ * - Tx thread Transmits 10k packets from veth<xxxx> to veth<yyyy>
+ * - Rx thread verifies if all 10k packets were received and delivered in-order,
+ * and have the right content
+ *
+ * Enable/disable debug mode:
+ * --------------------------
+ * To enable L2 - L4 headers and payload dump of each packet on STDOUT, add
+ * parameter -D to params array in test_xsk.sh, i.e. params=("-S" "-D")
+ */
+
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <errno.h>
+#include <getopt.h>
+#include <asm/barrier.h>
+typedef __u16 __sum16;
+#include <linux/if_link.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <locale.h>
+#include <poll.h>
+#include <pthread.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <stddef.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/types.h>
+#include <sys/queue.h>
+#include <time.h>
+#include <unistd.h>
+#include <stdatomic.h>
+#include <bpf/xsk.h>
+#include "xdpxceiver.h"
+#include "../kselftest.h"
+
+static void __exit_with_error(int error, const char *file, const char *func, int line)
+{
+ ksft_test_result_fail
+ ("[%s:%s:%i]: ERROR: %d/\"%s\"\n", file, func, line, error, strerror(error));
+ ksft_exit_xfail();
+}
+
+#define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
+
+#define print_ksft_result(void)\
+ (ksft_test_result_pass("PASS: %s %s %s%s\n", uut ? "DRV" : "SKB", opt_poll ? "POLL" :\
+ "NOPOLL", opt_teardown ? "Socket Teardown" : "",\
+ opt_bidi ? "Bi-directional Sockets" : ""))
+
+static void pthread_init_mutex(void)
+{
+ pthread_mutex_init(&sync_mutex, NULL);
+ pthread_mutex_init(&sync_mutex_tx, NULL);
+ pthread_cond_init(&signal_rx_condition, NULL);
+ pthread_cond_init(&signal_tx_condition, NULL);
+}
+
+static void pthread_destroy_mutex(void)
+{
+ pthread_mutex_destroy(&sync_mutex);
+ pthread_mutex_destroy(&sync_mutex_tx);
+ pthread_cond_destroy(&signal_rx_condition);
+ pthread_cond_destroy(&signal_tx_condition);
+}
+
+static void *memset32_htonl(void *dest, u32 val, u32 size)
+{
+ u32 *ptr = (u32 *)dest;
+ int i;
+
+ val = htonl(val);
+
+ for (i = 0; i < (size & (~0x3)); i += 4)
+ ptr[i >> 2] = val;
+
+ for (; i < size; i++)
+ ((char *)dest)[i] = ((char *)&val)[i & 3];
+
+ return dest;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static inline unsigned short from32to16(unsigned int x)
+{
+ /* add up 16-bit and 16-bit for 16+c bit */
+ x = (x & 0xffff) + (x >> 16);
+ /* add up carry.. */
+ x = (x & 0xffff) + (x >> 16);
+ return x;
+}
+
+/*
+ * Fold a partial checksum
+ * This function code has been taken from
+ * Linux kernel include/asm-generic/checksum.h
+ */
+static inline __u16 csum_fold(__u32 csum)
+{
+ u32 sum = (__force u32)csum;
+
+ sum = (sum & 0xffff) + (sum >> 16);
+ sum = (sum & 0xffff) + (sum >> 16);
+ return (__force __u16)~sum;
+}
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+static inline u32 from64to32(u64 x)
+{
+ /* add up 32-bit and 32-bit for 32+c bit */
+ x = (x & 0xffffffff) + (x >> 32);
+ /* add up carry.. */
+ x = (x & 0xffffffff) + (x >> 32);
+ return (u32)x;
+}
+
+__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum);
+
+/*
+ * This function code has been taken from
+ * Linux kernel lib/checksum.c
+ */
+__u32 csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+{
+ unsigned long long s = (__force u32)sum;
+
+ s += (__force u32)saddr;
+ s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN__
+ s += proto + len;
+#else
+ s += (proto + len) << 8;
+#endif
+ return (__force __u32)from64to32(s);
+}
+
+/*
+ * This function has been taken from
+ * Linux kernel include/asm-generic/checksum.h
+ */
+static inline __u16
+csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __u32 sum)
+{
+ return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+static inline u16 udp_csum(u32 saddr, u32 daddr, u32 len, u8 proto, u16 *udp_pkt)
+{
+ u32 csum = 0;
+ u32 cnt = 0;
+
+ /* udp hdr and data */
+ for (; cnt < len; cnt += 2)
+ csum += udp_pkt[cnt >> 1];
+
+ return csum_tcpudp_magic(saddr, daddr, len, proto, csum);
+}
+
+static void gen_eth_hdr(void *data, struct ethhdr *eth_hdr)
+{
+ memcpy(eth_hdr->h_dest, ((struct ifobject *)data)->dst_mac, ETH_ALEN);
+ memcpy(eth_hdr->h_source, ((struct ifobject *)data)->src_mac, ETH_ALEN);
+ eth_hdr->h_proto = htons(ETH_P_IP);
+}
+
+static void gen_ip_hdr(void *data, struct iphdr *ip_hdr)
+{
+ ip_hdr->version = IP_PKT_VER;
+ ip_hdr->ihl = 0x5;
+ ip_hdr->tos = IP_PKT_TOS;
+ ip_hdr->tot_len = htons(IP_PKT_SIZE);
+ ip_hdr->id = 0;
+ ip_hdr->frag_off = 0;
+ ip_hdr->ttl = IPDEFTTL;
+ ip_hdr->protocol = IPPROTO_UDP;
+ ip_hdr->saddr = ((struct ifobject *)data)->src_ip;
+ ip_hdr->daddr = ((struct ifobject *)data)->dst_ip;
+ ip_hdr->check = 0;
+}
+
+static void gen_udp_hdr(void *data, void *arg, struct udphdr *udp_hdr)
+{
+ udp_hdr->source = htons(((struct ifobject *)arg)->src_port);
+ udp_hdr->dest = htons(((struct ifobject *)arg)->dst_port);
+ udp_hdr->len = htons(UDP_PKT_SIZE);
+ memset32_htonl(pkt_data + PKT_HDR_SIZE,
+ htonl(((struct generic_data *)data)->seqnum), UDP_PKT_DATA_SIZE);
+}
+
+static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
+{
+ udp_hdr->check = 0;
+ udp_hdr->check =
+ udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr);
+}
+
+static void gen_eth_frame(struct xsk_umem_info *umem, u64 addr)
+{
+ memcpy(xsk_umem__get_data(umem->buffer, addr), pkt_data, PKT_SIZE);
+}
+
+static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size)
+{
+ int ret;
+
+ data->umem = calloc(1, sizeof(struct xsk_umem_info));
+ if (!data->umem)
+ exit_with_error(errno);
+
+ ret = xsk_umem__create(&data->umem->umem, buffer, size,
+ &data->umem->fq, &data->umem->cq, NULL);
+ if (ret)
+ exit_with_error(ret);
+
+ data->umem->buffer = buffer;
+}
+
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
+{
+ int ret, i;
+ u32 idx;
+
+ ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
+ if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+ exit_with_error(ret);
+ for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++)
+ *xsk_ring_prod__fill_addr(&umem->fq, idx++) = i * XSK_UMEM__DEFAULT_FRAME_SIZE;
+ xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+}
+
+static int xsk_configure_socket(struct ifobject *ifobject)
+{
+ struct xsk_socket_config cfg;
+ struct xsk_ring_cons *rxr;
+ struct xsk_ring_prod *txr;
+ int ret;
+
+ ifobject->xsk = calloc(1, sizeof(struct xsk_socket_info));
+ if (!ifobject->xsk)
+ exit_with_error(errno);
+
+ ifobject->xsk->umem = ifobject->umem;
+ cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+ cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+ cfg.libbpf_flags = 0;
+ cfg.xdp_flags = opt_xdp_flags;
+ cfg.bind_flags = opt_xdp_bind_flags;
+
+ if (!opt_bidi) {
+ rxr = (ifobject->fv.vector == rx) ? &ifobject->xsk->rx : NULL;
+ txr = (ifobject->fv.vector == tx) ? &ifobject->xsk->tx : NULL;
+ } else {
+ rxr = &ifobject->xsk->rx;
+ txr = &ifobject->xsk->tx;
+ }
+
+ ret = xsk_socket__create(&ifobject->xsk->xsk, ifobject->ifname,
+ opt_queue, ifobject->umem->umem, rxr, txr, &cfg);
+
+ if (ret)
+ return 1;
+
+ return 0;
+}
+
+static struct option long_options[] = {
+ {"interface", required_argument, 0, 'i'},
+ {"queue", optional_argument, 0, 'q'},
+ {"poll", no_argument, 0, 'p'},
+ {"xdp-skb", no_argument, 0, 'S'},
+ {"xdp-native", no_argument, 0, 'N'},
+ {"copy", no_argument, 0, 'c'},
+ {"tear-down", no_argument, 0, 'T'},
+ {"bidi", optional_argument, 0, 'B'},
+ {"debug", optional_argument, 0, 'D'},
+ {"tx-pkt-count", optional_argument, 0, 'C'},
+ {0, 0, 0, 0}
+};
+
+static void usage(const char *prog)
+{
+ const char *str =
+ " Usage: %s [OPTIONS]\n"
+ " Options:\n"
+ " -i, --interface Use interface\n"
+ " -q, --queue=n Use queue n (default 0)\n"
+ " -p, --poll Use poll syscall\n"
+ " -S, --xdp-skb=n Use XDP SKB mode\n"
+ " -N, --xdp-native=n Enforce XDP DRV (native) mode\n"
+ " -c, --copy Force copy mode\n"
+ " -T, --tear-down Tear down sockets by repeatedly recreating them\n"
+ " -B, --bidi Bi-directional sockets test\n"
+ " -D, --debug Debug mode - dump packets L2 - L5\n"
+ " -C, --tx-pkt-count=n Number of packets to send\n";
+ ksft_print_msg(str, prog);
+}
+
+static bool switch_namespace(int idx)
+{
+ char fqns[26] = "/var/run/netns/";
+ int nsfd;
+
+ strncat(fqns, ifdict[idx]->nsname, sizeof(fqns) - strlen(fqns) - 1);
+ nsfd = open(fqns, O_RDONLY);
+
+ if (nsfd == -1)
+ exit_with_error(errno);
+
+ if (setns(nsfd, 0) == -1)
+ exit_with_error(errno);
+
+ return true;
+}
+
+static void *nsswitchthread(void *args)
+{
+ if (switch_namespace(((struct targs *)args)->idx)) {
+ ifdict[((struct targs *)args)->idx]->ifindex =
+ if_nametoindex(ifdict[((struct targs *)args)->idx]->ifname);
+ if (!ifdict[((struct targs *)args)->idx]->ifindex) {
+ ksft_test_result_fail
+ ("ERROR: [%s] interface \"%s\" does not exist\n",
+ __func__, ifdict[((struct targs *)args)->idx]->ifname);
+ ((struct targs *)args)->retptr = false;
+ } else {
+ ksft_print_msg("Interface found: %s\n",
+ ifdict[((struct targs *)args)->idx]->ifname);
+ ((struct targs *)args)->retptr = true;
+ }
+ } else {
+ ((struct targs *)args)->retptr = false;
+ }
+ pthread_exit(NULL);
+}
+
+static int validate_interfaces(void)
+{
+ bool ret = true;
+
+ for (int i = 0; i < MAX_INTERFACES; i++) {
+ if (!strcmp(ifdict[i]->ifname, "")) {
+ ret = false;
+ ksft_test_result_fail("ERROR: interfaces: -i <int>,<ns> -i <int>,<ns>.");
+ }
+ if (strcmp(ifdict[i]->nsname, "")) {
+ struct targs *targs;
+
+ targs = (struct targs *)malloc(sizeof(struct targs));
+ if (!targs)
+ exit_with_error(errno);
+
+ targs->idx = i;
+ if (pthread_create(&ns_thread, NULL, nsswitchthread, (void *)targs))
+ exit_with_error(errno);
+
+ pthread_join(ns_thread, NULL);
+
+ if (targs->retptr)
+ ksft_print_msg("NS switched: %s\n", ifdict[i]->nsname);
+
+ free(targs);
+ } else {
+ ifdict[i]->ifindex = if_nametoindex(ifdict[i]->ifname);
+ if (!ifdict[i]->ifindex) {
+ ksft_test_result_fail
+ ("ERROR: interface \"%s\" does not exist\n", ifdict[i]->ifname);
+ ret = false;
+ } else {
+ ksft_print_msg("Interface found: %s\n", ifdict[i]->ifname);
+ }
+ }
+ }
+ return ret;
+}
+
+static void parse_command_line(int argc, char **argv)
+{
+ int option_index, interface_index = 0, c;
+
+ opterr = 0;
+
+ for (;;) {
+ c = getopt_long(argc, argv, "i:q:pSNcTBDC:", long_options, &option_index);
+
+ if (c == -1)
+ break;
+
+ switch (c) {
+ case 'i':
+ if (interface_index == MAX_INTERFACES)
+ break;
+ char *sptr, *token;
+
+ sptr = strndupa(optarg, strlen(optarg));
+ memcpy(ifdict[interface_index]->ifname,
+ strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS);
+ token = strsep(&sptr, ",");
+ if (token)
+ memcpy(ifdict[interface_index]->nsname, token,
+ MAX_INTERFACES_NAMESPACE_CHARS);
+ interface_index++;
+ break;
+ case 'q':
+ opt_queue = atoi(optarg);
+ break;
+ case 'p':
+ opt_poll = 1;
+ break;
+ case 'S':
+ opt_xdp_flags |= XDP_FLAGS_SKB_MODE;
+ opt_xdp_bind_flags |= XDP_COPY;
+ uut = ORDER_CONTENT_VALIDATE_XDP_SKB;
+ break;
+ case 'N':
+ opt_xdp_flags |= XDP_FLAGS_DRV_MODE;
+ opt_xdp_bind_flags |= XDP_COPY;
+ uut = ORDER_CONTENT_VALIDATE_XDP_DRV;
+ break;
+ case 'c':
+ opt_xdp_bind_flags |= XDP_COPY;
+ break;
+ case 'T':
+ opt_teardown = 1;
+ break;
+ case 'B':
+ opt_bidi = 1;
+ break;
+ case 'D':
+ debug_pkt_dump = 1;
+ break;
+ case 'C':
+ opt_pkt_count = atoi(optarg);
+ break;
+ default:
+ usage(basename(argv[0]));
+ ksft_exit_xfail();
+ }
+ }
+
+ if (!validate_interfaces()) {
+ usage(basename(argv[0]));
+ ksft_exit_xfail();
+ }
+}
+
+static void kick_tx(struct xsk_socket_info *xsk)
+{
+ int ret;
+
+ ret = sendto(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, 0);
+ if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN || errno == EBUSY || errno == ENETDOWN)
+ return;
+ exit_with_error(errno);
+}
+
+static inline void complete_tx_only(struct xsk_socket_info *xsk, int batch_size)
+{
+ unsigned int rcvd;
+ u32 idx;
+
+ if (!xsk->outstanding_tx)
+ return;
+
+ if (!NEED_WAKEUP || xsk_ring_prod__needs_wakeup(&xsk->tx))
+ kick_tx(xsk);
+
+ rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
+ if (rcvd) {
+ xsk_ring_cons__release(&xsk->umem->cq, rcvd);
+ xsk->outstanding_tx -= rcvd;
+ xsk->tx_npkts += rcvd;
+ }
+}
+
+static void rx_pkt(struct xsk_socket_info *xsk, struct pollfd *fds)
+{
+ unsigned int rcvd, i;
+ u32 idx_rx = 0, idx_fq = 0;
+ int ret;
+
+ rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
+ if (!rcvd) {
+ if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+ ret = poll(fds, 1, POLL_TMOUT);
+ if (ret < 0)
+ exit_with_error(ret);
+ }
+ return;
+ }
+
+ ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+ while (ret != rcvd) {
+ if (ret < 0)
+ exit_with_error(ret);
+ if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+ ret = poll(fds, 1, POLL_TMOUT);
+ if (ret < 0)
+ exit_with_error(ret);
+ }
+ ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+ }
+
+ for (i = 0; i < rcvd; i++) {
+ u64 addr = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx)->addr;
+ (void)xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++)->len;
+ u64 orig = xsk_umem__extract_addr(addr);
+
+ addr = xsk_umem__add_offset_to_addr(addr);
+ pkt_node_rx = malloc(sizeof(struct pkt) + PKT_SIZE);
+ if (!pkt_node_rx)
+ exit_with_error(errno);
+
+ pkt_node_rx->pkt_frame = (char *)malloc(PKT_SIZE);
+ if (!pkt_node_rx->pkt_frame)
+ exit_with_error(errno);
+
+ memcpy(pkt_node_rx->pkt_frame, xsk_umem__get_data(xsk->umem->buffer, addr),
+ PKT_SIZE);
+
+ TAILQ_INSERT_HEAD(&head, pkt_node_rx, pkt_nodes);
+
+ *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
+ }
+
+ xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+ xsk_ring_cons__release(&xsk->rx, rcvd);
+ xsk->rx_npkts += rcvd;
+}
+
+static void tx_only(struct xsk_socket_info *xsk, u32 *frameptr, int batch_size)
+{
+ u32 idx;
+ unsigned int i;
+
+ while (xsk_ring_prod__reserve(&xsk->tx, batch_size, &idx) < batch_size)
+ complete_tx_only(xsk, batch_size);
+
+ for (i = 0; i < batch_size; i++) {
+ struct xdp_desc *tx_desc = xsk_ring_prod__tx_desc(&xsk->tx, idx + i);
+
+ tx_desc->addr = (*frameptr + i) << XSK_UMEM__DEFAULT_FRAME_SHIFT;
+ tx_desc->len = PKT_SIZE;
+ }
+
+ xsk_ring_prod__submit(&xsk->tx, batch_size);
+ xsk->outstanding_tx += batch_size;
+ *frameptr += batch_size;
+ *frameptr %= num_frames;
+ complete_tx_only(xsk, batch_size);
+}
+
+static inline int get_batch_size(int pkt_cnt)
+{
+ if (!opt_pkt_count)
+ return BATCH_SIZE;
+
+ if (pkt_cnt + BATCH_SIZE <= opt_pkt_count)
+ return BATCH_SIZE;
+
+ return opt_pkt_count - pkt_cnt;
+}
+
+static void complete_tx_only_all(void *arg)
+{
+ bool pending;
+
+ do {
+ pending = false;
+ if (((struct ifobject *)arg)->xsk->outstanding_tx) {
+ complete_tx_only(((struct ifobject *)
+ arg)->xsk, BATCH_SIZE);
+ pending = !!((struct ifobject *)arg)->xsk->outstanding_tx;
+ }
+ } while (pending);
+}
+
+static void tx_only_all(void *arg)
+{
+ struct pollfd fds[MAX_SOCKS] = { };
+ u32 frame_nb = 0;
+ int pkt_cnt = 0;
+ int ret;
+
+ fds[0].fd = xsk_socket__fd(((struct ifobject *)arg)->xsk->xsk);
+ fds[0].events = POLLOUT;
+
+ while ((opt_pkt_count && pkt_cnt < opt_pkt_count) || !opt_pkt_count) {
+ int batch_size = get_batch_size(pkt_cnt);
+
+ if (opt_poll) {
+ ret = poll(fds, 1, POLL_TMOUT);
+ if (ret <= 0)
+ continue;
+
+ if (!(fds[0].revents & POLLOUT))
+ continue;
+ }
+
+ tx_only(((struct ifobject *)arg)->xsk, &frame_nb, batch_size);
+ pkt_cnt += batch_size;
+ }
+
+ if (opt_pkt_count)
+ complete_tx_only_all(arg);
+}
+
+static void worker_pkt_dump(void)
+{
+ struct in_addr ipaddr;
+
+ fprintf(stdout, "---------------------------------------\n");
+ for (int iter = 0; iter < num_frames - 1; iter++) {
+ /*extract L2 frame */
+ fprintf(stdout, "DEBUG>> L2: dst mac: ");
+ for (int i = 0; i < ETH_ALEN; i++)
+ fprintf(stdout, "%02X", ((struct ethhdr *)
+ pkt_buf[iter]->payload)->h_dest[i]);
+
+ fprintf(stdout, "\nDEBUG>> L2: src mac: ");
+ for (int i = 0; i < ETH_ALEN; i++)
+ fprintf(stdout, "%02X", ((struct ethhdr *)
+ pkt_buf[iter]->payload)->h_source[i]);
+
+ /*extract L3 frame */
+ fprintf(stdout, "\nDEBUG>> L3: ip_hdr->ihl: %02X\n",
+ ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->ihl);
+
+ ipaddr.s_addr =
+ ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->saddr;
+ fprintf(stdout, "DEBUG>> L3: ip_hdr->saddr: %s\n", inet_ntoa(ipaddr));
+
+ ipaddr.s_addr =
+ ((struct iphdr *)(pkt_buf[iter]->payload + sizeof(struct ethhdr)))->daddr;
+ fprintf(stdout, "DEBUG>> L3: ip_hdr->daddr: %s\n", inet_ntoa(ipaddr));
+
+ /*extract L4 frame */
+ fprintf(stdout, "DEBUG>> L4: udp_hdr->src: %d\n",
+ ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
+ sizeof(struct ethhdr) +
+ sizeof(struct iphdr)))->source));
+
+ fprintf(stdout, "DEBUG>> L4: udp_hdr->dst: %d\n",
+ ntohs(((struct udphdr *)(pkt_buf[iter]->payload +
+ sizeof(struct ethhdr) +
+ sizeof(struct iphdr)))->dest));
+ /*extract L5 frame */
+ int payload = *((uint32_t *)(pkt_buf[iter]->payload + PKT_HDR_SIZE));
+
+ if (payload == EOT) {
+ ksft_print_msg("End-of-tranmission frame received\n");
+ fprintf(stdout, "---------------------------------------\n");
+ break;
+ }
+ fprintf(stdout, "DEBUG>> L5: payload: %d\n", payload);
+ fprintf(stdout, "---------------------------------------\n");
+ }
+}
+
+static void worker_pkt_validate(void)
+{
+ u32 payloadseqnum = -2;
+
+ while (1) {
+ pkt_node_rx_q = malloc(sizeof(struct pkt));
+ pkt_node_rx_q = TAILQ_LAST(&head, head_s);
+ if (!pkt_node_rx_q)
+ break;
+ /*do not increment pktcounter if !(tos=0x9 and ipv4) */
+ if ((((struct iphdr *)(pkt_node_rx_q->pkt_frame +
+ sizeof(struct ethhdr)))->version == IP_PKT_VER)
+ && (((struct iphdr *)(pkt_node_rx_q->pkt_frame + sizeof(struct ethhdr)))->tos ==
+ IP_PKT_TOS)) {
+ payloadseqnum = *((uint32_t *) (pkt_node_rx_q->pkt_frame + PKT_HDR_SIZE));
+ if (debug_pkt_dump && payloadseqnum != EOT) {
+ pkt_obj = (struct pkt_frame *)malloc(sizeof(struct pkt_frame));
+ pkt_obj->payload = (char *)malloc(PKT_SIZE);
+ memcpy(pkt_obj->payload, pkt_node_rx_q->pkt_frame, PKT_SIZE);
+ pkt_buf[payloadseqnum] = pkt_obj;
+ }
+
+ if (payloadseqnum == EOT) {
+ ksft_print_msg("End-of-tranmission frame received: PASS\n");
+ sigvar = 1;
+ break;
+ }
+
+ if (prev_pkt + 1 != payloadseqnum) {
+ ksft_test_result_fail
+ ("ERROR: [%s] prev_pkt [%d], payloadseqnum [%d]\n",
+ __func__, prev_pkt, payloadseqnum);
+ ksft_exit_xfail();
+ }
+
+ TAILQ_REMOVE(&head, pkt_node_rx_q, pkt_nodes);
+ free(pkt_node_rx_q->pkt_frame);
+ free(pkt_node_rx_q);
+ pkt_node_rx_q = NULL;
+ prev_pkt = payloadseqnum;
+ pkt_counter++;
+ } else {
+ ksft_print_msg("Invalid frame received: ");
+ ksft_print_msg("[IP_PKT_VER: %02X], [IP_PKT_TOS: %02X]\n",
+ ((struct iphdr *)(pkt_node_rx_q->pkt_frame +
+ sizeof(struct ethhdr)))->version,
+ ((struct iphdr *)(pkt_node_rx_q->pkt_frame +
+ sizeof(struct ethhdr)))->tos);
+ TAILQ_REMOVE(&head, pkt_node_rx_q, pkt_nodes);
+ free(pkt_node_rx_q->pkt_frame);
+ free(pkt_node_rx_q);
+ pkt_node_rx_q = NULL;
+ }
+ }
+}
+
+static void thread_common_ops(void *arg, void *bufs, pthread_mutex_t *mutexptr,
+ atomic_int *spinningptr)
+{
+ int ctr = 0;
+ int ret;
+
+ xsk_configure_umem((struct ifobject *)arg, bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
+ ret = xsk_configure_socket((struct ifobject *)arg);
+
+ /* Retry Create Socket if it fails as xsk_socket__create()
+ * is asynchronous
+ *
+ * Essential to lock Mutex here to prevent Tx thread from
+ * entering before Rx and causing a deadlock
+ */
+ pthread_mutex_lock(mutexptr);
+ while (ret && ctr < SOCK_RECONF_CTR) {
+ atomic_store(spinningptr, 1);
+ xsk_configure_umem((struct ifobject *)arg,
+ bufs, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE);
+ ret = xsk_configure_socket((struct ifobject *)arg);
+ usleep(USLEEP_MAX);
+ ctr++;
+ }
+ atomic_store(spinningptr, 0);
+ pthread_mutex_unlock(mutexptr);
+
+ if (ctr >= SOCK_RECONF_CTR)
+ exit_with_error(ret);
+}
+
+static void *worker_testapp_validate(void *arg)
+{
+ struct udphdr *udp_hdr =
+ (struct udphdr *)(pkt_data + sizeof(struct ethhdr) + sizeof(struct iphdr));
+ struct generic_data *data = (struct generic_data *)malloc(sizeof(struct generic_data));
+ struct iphdr *ip_hdr = (struct iphdr *)(pkt_data + sizeof(struct ethhdr));
+ struct ethhdr *eth_hdr = (struct ethhdr *)pkt_data;
+ void *bufs = NULL;
+
+ pthread_attr_setstacksize(&attr, THREAD_STACK);
+
+ if (!bidi_pass) {
+ bufs = mmap(NULL, num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE,
+ PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (bufs == MAP_FAILED)
+ exit_with_error(errno);
+
+ if (strcmp(((struct ifobject *)arg)->nsname, ""))
+ switch_namespace(((struct ifobject *)arg)->ifdict_index);
+ }
+
+ if (((struct ifobject *)arg)->fv.vector == tx) {
+ int spinningrxctr = 0;
+
+ if (!bidi_pass)
+ thread_common_ops(arg, bufs, &sync_mutex_tx, &spinning_tx);
+
+ while (atomic_load(&spinning_rx) && spinningrxctr < SOCK_RECONF_CTR) {
+ spinningrxctr++;
+ usleep(USLEEP_MAX);
+ }
+
+ ksft_print_msg("Interface [%s] vector [Tx]\n", ((struct ifobject *)arg)->ifname);
+ for (int i = 0; i < num_frames; i++) {
+ /*send EOT frame */
+ if (i == (num_frames - 1))
+ data->seqnum = -1;
+ else
+ data->seqnum = i;
+ gen_udp_hdr((void *)data, (void *)arg, udp_hdr);
+ gen_ip_hdr((void *)arg, ip_hdr);
+ gen_udp_csum(udp_hdr, ip_hdr);
+ gen_eth_hdr((void *)arg, eth_hdr);
+ gen_eth_frame(((struct ifobject *)arg)->umem,
+ i * XSK_UMEM__DEFAULT_FRAME_SIZE);
+ }
+
+ free(data);
+ ksft_print_msg("Sending %d packets on interface %s\n",
+ (opt_pkt_count - 1), ((struct ifobject *)arg)->ifname);
+ tx_only_all(arg);
+ } else if (((struct ifobject *)arg)->fv.vector == rx) {
+ struct pollfd fds[MAX_SOCKS] = { };
+ int ret;
+
+ if (!bidi_pass)
+ thread_common_ops(arg, bufs, &sync_mutex_tx, &spinning_rx);
+
+ ksft_print_msg("Interface [%s] vector [Rx]\n", ((struct ifobject *)arg)->ifname);
+ xsk_populate_fill_ring(((struct ifobject *)arg)->umem);
+
+ TAILQ_INIT(&head);
+ if (debug_pkt_dump) {
+ pkt_buf = malloc(sizeof(struct pkt_frame **) * num_frames);
+ if (!pkt_buf)
+ exit_with_error(errno);
+ }
+
+ fds[0].fd = xsk_socket__fd(((struct ifobject *)arg)->xsk->xsk);
+ fds[0].events = POLLIN;
+
+ pthread_mutex_lock(&sync_mutex);
+ pthread_cond_signal(&signal_rx_condition);
+ pthread_mutex_unlock(&sync_mutex);
+
+ while (1) {
+ if (opt_poll) {
+ ret = poll(fds, 1, POLL_TMOUT);
+ if (ret <= 0)
+ continue;
+ }
+ rx_pkt(((struct ifobject *)arg)->xsk, fds);
+ worker_pkt_validate();
+
+ if (sigvar)
+ break;
+ }
+
+ ksft_print_msg("Received %d packets on interface %s\n",
+ pkt_counter, ((struct ifobject *)arg)->ifname);
+
+ if (opt_teardown)
+ ksft_print_msg("Destroying socket\n");
+ }
+
+ if (!opt_bidi || (opt_bidi && bidi_pass)) {
+ xsk_socket__delete(((struct ifobject *)arg)->xsk->xsk);
+ (void)xsk_umem__delete(((struct ifobject *)arg)->umem->umem);
+ }
+ pthread_exit(NULL);
+}
+
+static void testapp_validate(void)
+{
+ pthread_attr_init(&attr);
+ pthread_attr_setstacksize(&attr, THREAD_STACK);
+
+ if (opt_bidi && bidi_pass) {
+ pthread_init_mutex();
+ if (!switching_notify) {
+ ksft_print_msg("Switching Tx/Rx vectors\n");
+ switching_notify++;
+ }
+ }
+
+ pthread_mutex_lock(&sync_mutex);
+
+ /*Spawn RX thread */
+ if (!opt_bidi || (opt_bidi && !bidi_pass)) {
+ if (pthread_create(&t0, &attr, worker_testapp_validate, (void *)ifdict[1]))
+ exit_with_error(errno);
+ } else if (opt_bidi && bidi_pass) {
+ /*switch Tx/Rx vectors */
+ ifdict[0]->fv.vector = rx;
+ if (pthread_create(&t0, &attr, worker_testapp_validate, (void *)ifdict[0]))
+ exit_with_error(errno);
+ }
+
+ struct timespec max_wait = { 0, 0 };
+
+ if (clock_gettime(CLOCK_REALTIME, &max_wait))
+ exit_with_error(errno);
+ max_wait.tv_sec += TMOUT_SEC;
+
+ if (pthread_cond_timedwait(&signal_rx_condition, &sync_mutex, &max_wait) == ETIMEDOUT)
+ exit_with_error(errno);
+
+ pthread_mutex_unlock(&sync_mutex);
+
+ /*Spawn TX thread */
+ if (!opt_bidi || (opt_bidi && !bidi_pass)) {
+ if (pthread_create(&t1, &attr, worker_testapp_validate, (void *)ifdict[0]))
+ exit_with_error(errno);
+ } else if (opt_bidi && bidi_pass) {
+ /*switch Tx/Rx vectors */
+ ifdict[1]->fv.vector = tx;
+ if (pthread_create(&t1, &attr, worker_testapp_validate, (void *)ifdict[1]))
+ exit_with_error(errno);
+ }
+
+ pthread_join(t1, NULL);
+ pthread_join(t0, NULL);
+
+ if (debug_pkt_dump) {
+ worker_pkt_dump();
+ for (int iter = 0; iter < num_frames - 1; iter++) {
+ free(pkt_buf[iter]->payload);
+ free(pkt_buf[iter]);
+ }
+ free(pkt_buf);
+ }
+
+ if (!opt_teardown && !opt_bidi)
+ print_ksft_result();
+}
+
+static void testapp_sockets(void)
+{
+ for (int i = 0; i < (opt_teardown ? MAX_TEARDOWN_ITER : MAX_BIDI_ITER); i++) {
+ pkt_counter = 0;
+ prev_pkt = -1;
+ sigvar = 0;
+ ksft_print_msg("Creating socket\n");
+ testapp_validate();
+ opt_bidi ? bidi_pass++ : bidi_pass;
+ }
+
+ print_ksft_result();
+}
+
+static void init_iface_config(void *ifaceconfig)
+{
+ /*Init interface0 */
+ ifdict[0]->fv.vector = tx;
+ memcpy(ifdict[0]->dst_mac, ((struct ifaceconfigobj *)ifaceconfig)->dst_mac, ETH_ALEN);
+ memcpy(ifdict[0]->src_mac, ((struct ifaceconfigobj *)ifaceconfig)->src_mac, ETH_ALEN);
+ ifdict[0]->dst_ip = ((struct ifaceconfigobj *)ifaceconfig)->dst_ip.s_addr;
+ ifdict[0]->src_ip = ((struct ifaceconfigobj *)ifaceconfig)->src_ip.s_addr;
+ ifdict[0]->dst_port = ((struct ifaceconfigobj *)ifaceconfig)->dst_port;
+ ifdict[0]->src_port = ((struct ifaceconfigobj *)ifaceconfig)->src_port;
+
+ /*Init interface1 */
+ ifdict[1]->fv.vector = rx;
+ memcpy(ifdict[1]->dst_mac, ((struct ifaceconfigobj *)ifaceconfig)->src_mac, ETH_ALEN);
+ memcpy(ifdict[1]->src_mac, ((struct ifaceconfigobj *)ifaceconfig)->dst_mac, ETH_ALEN);
+ ifdict[1]->dst_ip = ((struct ifaceconfigobj *)ifaceconfig)->src_ip.s_addr;
+ ifdict[1]->src_ip = ((struct ifaceconfigobj *)ifaceconfig)->dst_ip.s_addr;
+ ifdict[1]->dst_port = ((struct ifaceconfigobj *)ifaceconfig)->src_port;
+ ifdict[1]->src_port = ((struct ifaceconfigobj *)ifaceconfig)->dst_port;
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+
+ if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
+ exit_with_error(errno);
+
+ const char *MAC1 = "\x00\x0A\x56\x9E\xEE\x62";
+ const char *MAC2 = "\x00\x0A\x56\x9E\xEE\x61";
+ const char *IP1 = "192.168.100.162";
+ const char *IP2 = "192.168.100.161";
+ u16 UDP_DST_PORT = 2020;
+ u16 UDP_SRC_PORT = 2121;
+
+ ifaceconfig = (struct ifaceconfigobj *)malloc(sizeof(struct ifaceconfigobj));
+ memcpy(ifaceconfig->dst_mac, MAC1, ETH_ALEN);
+ memcpy(ifaceconfig->src_mac, MAC2, ETH_ALEN);
+ inet_aton(IP1, &ifaceconfig->dst_ip);
+ inet_aton(IP2, &ifaceconfig->src_ip);
+ ifaceconfig->dst_port = UDP_DST_PORT;
+ ifaceconfig->src_port = UDP_SRC_PORT;
+
+ for (int i = 0; i < MAX_INTERFACES; i++) {
+ ifdict[i] = (struct ifobject *)malloc(sizeof(struct ifobject));
+ if (!ifdict[i])
+ exit_with_error(errno);
+
+ ifdict[i]->ifdict_index = i;
+ }
+
+ setlocale(LC_ALL, "");
+
+ parse_command_line(argc, argv);
+
+ num_frames = ++opt_pkt_count;
+
+ init_iface_config((void *)ifaceconfig);
+
+ pthread_init_mutex();
+
+ ksft_set_plan(1);
+
+ if (!opt_teardown && !opt_bidi) {
+ testapp_validate();
+ } else if (opt_teardown && opt_bidi) {
+ ksft_test_result_fail("ERROR: parameters -T and -B cannot be used together\n");
+ ksft_exit_xfail();
+ } else {
+ testapp_sockets();
+ }
+
+ for (int i = 0; i < MAX_INTERFACES; i++)
+ free(ifdict[i]);
+
+ pthread_destroy_mutex();
+
+ ksft_exit_pass();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
new file mode 100644
index 000000000000..61f595b6f200
--- /dev/null
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -0,0 +1,160 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright(c) 2020 Intel Corporation.
+ */
+
+#ifndef XDPXCEIVER_H_
+#define XDPXCEIVER_H_
+
+#ifndef SOL_XDP
+#define SOL_XDP 283
+#endif
+
+#ifndef AF_XDP
+#define AF_XDP 44
+#endif
+
+#ifndef PF_XDP
+#define PF_XDP AF_XDP
+#endif
+
+#define MAX_INTERFACES 2
+#define MAX_INTERFACE_NAME_CHARS 7
+#define MAX_INTERFACES_NAMESPACE_CHARS 10
+#define MAX_SOCKS 1
+#define MAX_TEARDOWN_ITER 10
+#define MAX_BIDI_ITER 2
+#define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
+ sizeof(struct udphdr))
+#define MIN_PKT_SIZE 64
+#define ETH_FCS_SIZE 4
+#define PKT_SIZE (MIN_PKT_SIZE - ETH_FCS_SIZE)
+#define IP_PKT_SIZE (PKT_SIZE - sizeof(struct ethhdr))
+#define IP_PKT_VER 0x4
+#define IP_PKT_TOS 0x9
+#define UDP_PKT_SIZE (IP_PKT_SIZE - sizeof(struct iphdr))
+#define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
+#define TMOUT_SEC (3)
+#define EOT (-1)
+#define USLEEP_MAX 200000
+#define THREAD_STACK 60000000
+#define SOCK_RECONF_CTR 10
+#define BATCH_SIZE 64
+#define POLL_TMOUT 1000
+#define NEED_WAKEUP true
+
+typedef __u32 u32;
+typedef __u16 u16;
+typedef __u8 u8;
+
+enum TESTS {
+ ORDER_CONTENT_VALIDATE_XDP_SKB = 0,
+ ORDER_CONTENT_VALIDATE_XDP_DRV = 1,
+};
+
+u8 uut;
+u8 debug_pkt_dump;
+u32 num_frames;
+u8 switching_notify;
+u8 bidi_pass;
+
+static u32 opt_xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+static int opt_queue;
+static int opt_pkt_count;
+static int opt_poll;
+static int opt_teardown;
+static int opt_bidi;
+static u32 opt_xdp_bind_flags = XDP_USE_NEED_WAKEUP;
+static u8 pkt_data[XSK_UMEM__DEFAULT_FRAME_SIZE];
+static u32 pkt_counter;
+static u32 prev_pkt = -1;
+static int sigvar;
+
+struct xsk_umem_info {
+ struct xsk_ring_prod fq;
+ struct xsk_ring_cons cq;
+ struct xsk_umem *umem;
+ void *buffer;
+};
+
+struct xsk_socket_info {
+ struct xsk_ring_cons rx;
+ struct xsk_ring_prod tx;
+ struct xsk_umem_info *umem;
+ struct xsk_socket *xsk;
+ unsigned long rx_npkts;
+ unsigned long tx_npkts;
+ unsigned long prev_rx_npkts;
+ unsigned long prev_tx_npkts;
+ u32 outstanding_tx;
+};
+
+struct flow_vector {
+ enum fvector {
+ tx,
+ rx,
+ bidi,
+ undef,
+ } vector;
+};
+
+struct generic_data {
+ u32 seqnum;
+};
+
+struct ifaceconfigobj {
+ u8 dst_mac[ETH_ALEN];
+ u8 src_mac[ETH_ALEN];
+ struct in_addr dst_ip;
+ struct in_addr src_ip;
+ u16 src_port;
+ u16 dst_port;
+} *ifaceconfig;
+
+struct ifobject {
+ int ifindex;
+ int ifdict_index;
+ char ifname[MAX_INTERFACE_NAME_CHARS];
+ char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
+ struct flow_vector fv;
+ struct xsk_socket_info *xsk;
+ struct xsk_umem_info *umem;
+ u8 dst_mac[ETH_ALEN];
+ u8 src_mac[ETH_ALEN];
+ u32 dst_ip;
+ u32 src_ip;
+ u16 src_port;
+ u16 dst_port;
+};
+
+static struct ifobject *ifdict[MAX_INTERFACES];
+
+/*threads*/
+atomic_int spinning_tx;
+atomic_int spinning_rx;
+pthread_mutex_t sync_mutex;
+pthread_mutex_t sync_mutex_tx;
+pthread_cond_t signal_rx_condition;
+pthread_cond_t signal_tx_condition;
+pthread_t t0, t1, ns_thread;
+pthread_attr_t attr;
+
+struct targs {
+ bool retptr;
+ int idx;
+};
+
+TAILQ_HEAD(head_s, pkt) head = TAILQ_HEAD_INITIALIZER(head);
+struct head_s *head_p;
+struct pkt {
+ char *pkt_frame;
+
+ TAILQ_ENTRY(pkt) pkt_nodes;
+} *pkt_node_rx, *pkt_node_rx_q;
+
+struct pkt_frame {
+ char *payload;
+} *pkt_obj;
+
+struct pkt_frame **pkt_buf;
+
+#endif /* XDPXCEIVER_H */
diff --git a/tools/testing/selftests/bpf/xsk_prereqs.sh b/tools/testing/selftests/bpf/xsk_prereqs.sh
new file mode 100755
index 000000000000..9d54c4645127
--- /dev/null
+++ b/tools/testing/selftests/bpf/xsk_prereqs.sh
@@ -0,0 +1,135 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright(c) 2020 Intel Corporation.
+
+ksft_pass=0
+ksft_fail=1
+ksft_xfail=2
+ksft_xpass=3
+ksft_skip=4
+
+GREEN='\033[0;92m'
+YELLOW='\033[0;93m'
+RED='\033[0;31m'
+NC='\033[0m'
+STACK_LIM=131072
+SPECFILE=veth.spec
+XSKOBJ=xdpxceiver
+NUMPKTS=10000
+
+validate_root_exec()
+{
+ msg="skip all tests:"
+ if [ $UID != 0 ]; then
+ echo $msg must be run as root >&2
+ test_exit $ksft_fail 2
+ else
+ return $ksft_pass
+ fi
+}
+
+validate_veth_support()
+{
+ msg="skip all tests:"
+ if [ $(ip link add $1 type veth 2>/dev/null; echo $?;) != 0 ]; then
+ echo $msg veth kernel support not available >&2
+ test_exit $ksft_skip 1
+ else
+ ip link del $1
+ return $ksft_pass
+ fi
+}
+
+validate_veth_spec_file()
+{
+ if [ ! -f ${SPECFILE} ]; then
+ test_exit $ksft_skip 1
+ fi
+}
+
+test_status()
+{
+ statusval=$1
+ if [ -n "${colorconsole+set}" ]; then
+ if [ $statusval -eq 2 ]; then
+ echo -e "${YELLOW}$2${NC}: [ ${RED}FAIL${NC} ]"
+ elif [ $statusval -eq 1 ]; then
+ echo -e "${YELLOW}$2${NC}: [ ${RED}SKIPPED${NC} ]"
+ elif [ $statusval -eq 0 ]; then
+ echo -e "${YELLOW}$2${NC}: [ ${GREEN}PASS${NC} ]"
+ fi
+ else
+ if [ $statusval -eq 2 ]; then
+ echo -e "$2: [ FAIL ]"
+ elif [ $statusval -eq 1 ]; then
+ echo -e "$2: [ SKIPPED ]"
+ elif [ $statusval -eq 0 ]; then
+ echo -e "$2: [ PASS ]"
+ fi
+ fi
+}
+
+test_exit()
+{
+ retval=$1
+ if [ $2 -ne 0 ]; then
+ test_status $2 $(basename $0)
+ fi
+ exit $retval
+}
+
+clear_configs()
+{
+ if [ $(ip netns show | grep $3 &>/dev/null; echo $?;) == 0 ]; then
+ [ $(ip netns exec $3 ip link show $2 &>/dev/null; echo $?;) == 0 ] &&
+ { echo "removing link $1:$2"; ip netns exec $3 ip link del $2; }
+ echo "removing ns $3"
+ ip netns del $3
+ fi
+ #Once we delete a veth pair node, the entire veth pair is removed,
+ #this is just to be cautious just incase the NS does not exist then
+ #veth node inside NS won't get removed so we explicitly remove it
+ [ $(ip link show $1 &>/dev/null; echo $?;) == 0 ] &&
+ { echo "removing link $1"; ip link del $1; }
+ if [ -f ${SPECFILE} ]; then
+ echo "removing spec file:" ${SPECFILE}
+ rm -f ${SPECFILE}
+ fi
+}
+
+cleanup_exit()
+{
+ echo "cleaning up..."
+ clear_configs $1 $2 $3
+}
+
+validate_ip_utility()
+{
+ [ ! $(type -P ip) ] && { echo "'ip' not found. Skipping tests."; test_exit $ksft_skip 1; }
+}
+
+vethXDPgeneric()
+{
+ ip link set dev $1 xdpdrv off
+ ip netns exec $3 ip link set dev $2 xdpdrv off
+}
+
+vethXDPnative()
+{
+ ip link set dev $1 xdpgeneric off
+ ip netns exec $3 ip link set dev $2 xdpgeneric off
+}
+
+execxdpxceiver()
+{
+ local -a 'paramkeys=("${!'"$1"'[@]}")' copy
+ paramkeysstr=${paramkeys[*]}
+
+ for index in $paramkeysstr;
+ do
+ current=$1"[$index]"
+ copy[$index]=${!current}
+ done
+
+ ./${XSKOBJ} -i ${VETH0} -i ${VETH1},${NS1} ${copy[*]} -C ${NUMPKTS}
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
index 05853b0b8831..027014662fb2 100644
--- a/tools/testing/selftests/cgroup/cgroup_util.c
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -337,13 +337,13 @@ pid_t clone_into_cgroup(int cgroup_fd)
#ifdef CLONE_ARGS_SIZE_VER2
pid_t pid;
- struct clone_args args = {
+ struct __clone_args args = {
.flags = CLONE_INTO_CGROUP,
.exit_signal = SIGCHLD,
.cgroup = cgroup_fd,
};
- pid = sys_clone3(&args, sizeof(struct clone_args));
+ pid = sys_clone3(&args, sizeof(struct __clone_args));
/*
* Verify that this is a genuine test failure:
* ENOSYS -> clone3() not available
diff --git a/tools/testing/selftests/clone3/Makefile b/tools/testing/selftests/clone3/Makefile
index ef7564cb7abe..79b19a2863a0 100644
--- a/tools/testing/selftests/clone3/Makefile
+++ b/tools/testing/selftests/clone3/Makefile
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -g -I../../../../usr/include/
+CFLAGS += -g -std=gnu99 -I../../../../usr/include/
LDLIBS += -lcap
TEST_GEN_PROGS := clone3 clone3_clear_sighand clone3_set_tid \
diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
index 575b391ddc78..87e16d65d9d7 100644
--- a/tools/testing/selftests/core/close_range_test.c
+++ b/tools/testing/selftests/core/close_range_test.c
@@ -11,6 +11,7 @@
#include <string.h>
#include <syscall.h>
#include <unistd.h>
+#include <sys/resource.h>
#include "../kselftest_harness.h"
#include "../clone3/clone3_selftests.h"
@@ -23,6 +24,10 @@
#define CLOSE_RANGE_UNSHARE (1U << 1)
#endif
+#ifndef CLOSE_RANGE_CLOEXEC
+#define CLOSE_RANGE_CLOEXEC (1U << 2)
+#endif
+
static inline int sys_close_range(unsigned int fd, unsigned int max_fd,
unsigned int flags)
{
@@ -224,4 +229,73 @@ TEST(close_range_unshare_capped)
EXPECT_EQ(0, WEXITSTATUS(status));
}
+TEST(close_range_cloexec)
+{
+ int i, ret;
+ int open_fds[101];
+ struct rlimit rlimit;
+
+ for (i = 0; i < ARRAY_SIZE(open_fds); i++) {
+ int fd;
+
+ fd = open("/dev/null", O_RDONLY);
+ ASSERT_GE(fd, 0) {
+ if (errno == ENOENT)
+ XFAIL(return, "Skipping test since /dev/null does not exist");
+ }
+
+ open_fds[i] = fd;
+ }
+
+ ret = sys_close_range(1000, 1000, CLOSE_RANGE_CLOEXEC);
+ if (ret < 0) {
+ if (errno == ENOSYS)
+ XFAIL(return, "close_range() syscall not supported");
+ if (errno == EINVAL)
+ XFAIL(return, "close_range() doesn't support CLOSE_RANGE_CLOEXEC");
+ }
+
+ /* Ensure the FD_CLOEXEC bit is set also with a resource limit in place. */
+ ASSERT_EQ(0, getrlimit(RLIMIT_NOFILE, &rlimit));
+ rlimit.rlim_cur = 25;
+ ASSERT_EQ(0, setrlimit(RLIMIT_NOFILE, &rlimit));
+
+ /* Set close-on-exec for two ranges: [0-50] and [75-100]. */
+ ret = sys_close_range(open_fds[0], open_fds[50], CLOSE_RANGE_CLOEXEC);
+ ASSERT_EQ(0, ret);
+ ret = sys_close_range(open_fds[75], open_fds[100], CLOSE_RANGE_CLOEXEC);
+ ASSERT_EQ(0, ret);
+
+ for (i = 0; i <= 50; i++) {
+ int flags = fcntl(open_fds[i], F_GETFD);
+
+ EXPECT_GT(flags, -1);
+ EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC);
+ }
+
+ for (i = 51; i <= 74; i++) {
+ int flags = fcntl(open_fds[i], F_GETFD);
+
+ EXPECT_GT(flags, -1);
+ EXPECT_EQ(flags & FD_CLOEXEC, 0);
+ }
+
+ for (i = 75; i <= 100; i++) {
+ int flags = fcntl(open_fds[i], F_GETFD);
+
+ EXPECT_GT(flags, -1);
+ EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC);
+ }
+
+ /* Test a common pattern. */
+ ret = sys_close_range(3, UINT_MAX, CLOSE_RANGE_CLOEXEC);
+ for (i = 0; i <= 100; i++) {
+ int flags = fcntl(open_fds[i], F_GETFD);
+
+ EXPECT_GT(flags, -1);
+ EXPECT_EQ(flags & FD_CLOEXEC, FD_CLOEXEC);
+ }
+}
+
+
TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
index f5abb1ebd392..4029833f7e27 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh
@@ -52,6 +52,7 @@ ALL_TESTS="
blackhole_route_test
irif_disabled_test
erif_disabled_test
+ blackhole_nexthop_test
"
NUM_NETIFS=4
@@ -647,6 +648,41 @@ erif_disabled_test()
devlink_trap_action_set $trap_name "drop"
}
+__blackhole_nexthop_test()
+{
+ local flags=$1; shift
+ local subnet=$1; shift
+ local proto=$1; shift
+ local dip=$1; shift
+ local trap_name="blackhole_nexthop"
+ local mz_pid
+
+ RET=0
+
+ ip -$flags nexthop add id 1 blackhole
+ ip -$flags route add $subnet nhid 1
+ tc filter add dev $rp2 egress protocol $proto pref 1 handle 101 \
+ flower skip_hw dst_ip $dip ip_proto udp action drop
+
+ # Generate packets to the blackhole nexthop
+ $MZ $h1 -$flags -t udp "sp=54321,dp=12345" -c 0 -p 100 -b $rp1mac \
+ -B $dip -d 1msec -q &
+ mz_pid=$!
+
+ devlink_trap_drop_test $trap_name $rp2 101
+ log_test "Blackhole nexthop: IPv$flags"
+
+ devlink_trap_drop_cleanup $mz_pid $rp2 $proto 1 101
+ ip -$flags route del $subnet
+ ip -$flags nexthop del id 1
+}
+
+blackhole_nexthop_test()
+{
+ __blackhole_nexthop_test "4" "198.51.100.0/30" "ip" $h2_ipv4
+ __blackhole_nexthop_test "6" "2001:db8:2::/120" "ipv6" $h2_ipv6
+}
+
trap cleanup EXIT
setup_prepare
diff --git a/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh
new file mode 100755
index 000000000000..7edaed8eb86a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/q_in_q_veto.sh
@@ -0,0 +1,296 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ create_8021ad_vlan_upper_on_top_front_panel_port
+ create_8021ad_vlan_upper_on_top_bridge_port
+ create_8021ad_vlan_upper_on_top_lag
+ create_8021ad_vlan_upper_on_top_bridge
+ create_8021ad_vlan_upper_on_top_8021ad_bridge
+ create_vlan_upper_on_top_8021ad_bridge
+ create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge
+ create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge
+ enslave_front_panel_with_vlan_upper_to_8021ad_bridge
+ enslave_lag_with_vlan_upper_to_8021ad_bridge
+ add_ip_address_to_8021ad_bridge
+ switch_bridge_protocol_from_8021q_to_8021ad
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+
+ sleep 10
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+create_vlan_upper_on_top_of_bridge()
+{
+ RET=0
+
+ local bridge_proto=$1; shift
+ local netdev_proto=$1; shift
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol $bridge_proto vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 master br0
+
+ ip link add name br0.100 link br0 type vlan \
+ protocol $netdev_proto id 100 2>/dev/null
+ check_fail $? "$netdev_proto vlan upper creation on top of an $bridge_proto bridge not rejected"
+
+ ip link add name br0.100 link br0 type vlan \
+ protocol $netdev_proto id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "$netdev_proto vlan upper creation on top of an $bridge_proto bridge rejected without extack"
+
+ log_test "create $netdev_proto vlan upper on top $bridge_proto bridge"
+
+ ip link del dev br0
+}
+
+create_8021ad_vlan_upper_on_top_front_panel_port()
+{
+ RET=0
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>/dev/null
+ check_fail $? "802.1ad vlan upper creation on top of a front panel not rejected"
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad vlan upper creation on top of a front panel rejected without extack"
+
+ log_test "create 802.1ad vlan upper on top of a front panel"
+}
+
+create_8021ad_vlan_upper_on_top_bridge_port()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev $swp1 master br0
+ ip link set dev br0 up
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>/dev/null
+ check_fail $? "802.1ad vlan upper creation on top of a bridge port not rejected"
+
+ ip link add name $swp1.100 link $swp1 type vlan \
+ protocol 802.1ad id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad vlan upper creation on top of a bridge port rejected without extack"
+
+ log_test "create 802.1ad vlan upper on top of a bridge port"
+
+ ip link del dev br0
+}
+
+create_8021ad_vlan_upper_on_top_lag()
+{
+ RET=0
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1
+
+ ip link add name bond1.100 link bond1 type vlan \
+ protocol 802.1ad id 100 2>/dev/null
+ check_fail $? "802.1ad vlan upper creation on top of a lag not rejected"
+
+ ip link add name bond1.100 link bond1 type vlan \
+ protocol 802.1ad id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad vlan upper creation on top of a lag rejected without extack"
+
+ log_test "create 802.1ad vlan upper on top of a lag"
+
+ ip link del dev bond1
+}
+
+create_8021ad_vlan_upper_on_top_bridge()
+{
+ RET=0
+
+ create_vlan_upper_on_top_of_bridge "802.1q" "802.1ad"
+}
+
+create_8021ad_vlan_upper_on_top_8021ad_bridge()
+{
+ RET=0
+
+ create_vlan_upper_on_top_of_bridge "802.1ad" "802.1ad"
+}
+
+create_vlan_upper_on_top_8021ad_bridge()
+{
+ RET=0
+
+ create_vlan_upper_on_top_of_bridge "802.1ad" "802.1q"
+}
+
+create_vlan_upper_on_top_front_panel_enslaved_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link set dev $swp1 master br0
+
+ ip link add name $swp1.100 link $swp1 type vlan id 100 2>/dev/null
+ check_fail $? "vlan upper creation on top of front panel enslaved to 802.1ad bridge not rejected"
+
+ ip link add name $swp1.100 link $swp1 type vlan id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "vlan upper creation on top of front panel enslaved to 802.1ad bridge rejected without extack"
+
+ log_test "create vlan upper on top of front panel enslaved to 802.1ad bridge"
+
+ ip link del dev br0
+}
+
+create_vlan_upper_on_top_lag_enslaved_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1
+ ip link set dev bond1 master br0
+
+ ip link add name bond1.100 link bond1 type vlan id 100 2>/dev/null
+ check_fail $? "vlan upper creation on top of lag enslaved to 802.1ad bridge not rejected"
+
+ ip link add name bond1.100 link bond1 type vlan id 100 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "vlan upper creation on top of lag enslaved to 802.1ad bridge rejected without extack"
+
+ log_test "create vlan upper on top of lag enslaved to 802.1ad bridge"
+
+ ip link del dev bond1
+ ip link del dev br0
+}
+
+enslave_front_panel_with_vlan_upper_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name $swp1.100 link $swp1 type vlan id 100
+
+ ip link set dev $swp1 master br0 2>/dev/null
+ check_fail $? "front panel with vlan upper enslavemnt to 802.1ad bridge not rejected"
+
+ ip link set dev $swp1 master br0 2>&1 >/dev/null | grep -q mlxsw_spectrum
+ check_err $? "front panel with vlan upper enslavemnt to 802.1ad bridge rejected without extack"
+
+ log_test "enslave front panel with vlan upper to 802.1ad bridge"
+
+ ip link del dev $swp1.100
+ ip link del dev br0
+}
+
+enslave_lag_with_vlan_upper_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp1 master bond1
+ ip link add name bond1.100 link bond1 type vlan id 100
+
+ ip link set dev bond1 master br0 2>/dev/null
+ check_fail $? "lag with vlan upper enslavemnt to 802.1ad bridge not rejected"
+
+ ip link set dev bond1 master br0 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "lag with vlan upper enslavemnt to 802.1ad bridge rejected without extack"
+
+ log_test "enslave lag with vlan upper to 802.1ad bridge"
+
+ ip link del dev bond1
+ ip link del dev br0
+}
+
+
+add_ip_address_to_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 master br0
+
+ ip addr add dev br0 192.0.2.17/28 2>/dev/null
+ check_fail $? "IP address addition to 802.1ad bridge not rejected"
+
+ ip addr add dev br0 192.0.2.17/28 2>&1 >/dev/null | grep -q mlxsw_spectrum
+ check_err $? "IP address addition to 802.1ad bridge rejected without extack"
+
+ log_test "IP address addition to 802.1ad bridge"
+
+ ip link del dev br0
+}
+
+switch_bridge_protocol_from_8021q_to_8021ad()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 \
+ vlan_protocol 802.1ad vlan_default_pvid 0 mcast_snooping 0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 master br0
+
+ ip link set dev br0 type bridge vlan_protocol 802.1q 2>/dev/null
+ check_fail $? "switching bridge protocol from 802.1q to 802.1ad not rejected"
+
+ log_test "switch bridge protocol"
+
+ ip link del dev br0
+}
+
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index f4031002d5e9..ed346da5d3cb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -22,6 +22,7 @@ ALL_TESTS="
duplicate_vlans_test
vlan_rif_refcount_test
subport_rif_refcount_test
+ subport_rif_lag_join_test
vlan_dev_deletion_test
lag_unlink_slaves_test
lag_dev_deletion_test
@@ -29,6 +30,11 @@ ALL_TESTS="
bridge_extern_learn_test
neigh_offload_test
nexthop_offload_test
+ nexthop_obj_invalid_test
+ nexthop_obj_offload_test
+ nexthop_obj_group_offload_test
+ nexthop_obj_blackhole_offload_test
+ nexthop_obj_route_offload_test
devlink_reload_test
"
NUM_NETIFS=2
@@ -435,6 +441,48 @@ subport_rif_refcount_test()
ip link del dev bond1
}
+subport_rif_lag_join_test()
+{
+ # Test that the reference count of a RIF configured for a LAG is
+ # incremented / decremented when ports join / leave the LAG. We use the
+ # offload indication on routes configured on the RIF to understand if
+ # it was created / destroyed
+ RET=0
+
+ ip link add name bond1 type bond mode 802.3ad
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link set dev $swp1 master bond1
+ ip link set dev $swp2 master bond1
+
+ ip link set dev bond1 up
+ ip -6 address add 2001:db8:1::1/64 dev bond1
+
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
+ check_err $? "subport rif was not created on lag device"
+
+ ip link set dev $swp1 nomaster
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
+ check_err $? "subport rif of lag device was destroyed after removing one port"
+
+ ip link set dev $swp1 master bond1
+ ip link set dev $swp2 nomaster
+ busywait "$TIMEOUT" wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
+ check_err $? "subport rif of lag device was destroyed after re-adding a port and removing another"
+
+ ip link set dev $swp1 nomaster
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip -6 route get fibmatch 2001:db8:1::2 dev bond1
+ check_err $? "subport rif of lag device was not destroyed when should"
+
+ log_test "subport rif lag join"
+
+ ip link del dev bond1
+}
+
vlan_dev_deletion_test()
{
# Test that VLAN devices are correctly deleted / unlinked when enslaved
@@ -674,6 +722,209 @@ nexthop_offload_test()
sysctl_restore net.ipv6.conf.$swp2.keep_addr_on_down
}
+nexthop_obj_invalid_test()
+{
+ # Test that invalid nexthop object configurations are rejected
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2 192.0.2.2/24 2001:db8:1::2/64
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.3 fdb
+ check_fail $? "managed to configure an FDB nexthop when should not"
+
+ ip nexthop add id 1 encap mpls 200/300 via 192.0.2.3 dev $swp1
+ check_fail $? "managed to configure a nexthop with MPLS encap when should not"
+
+ ip nexthop add id 1 dev $swp1
+ ip nexthop add id 2 dev $swp1
+ ip nexthop add id 10 group 1/2
+ check_fail $? "managed to configure a nexthop group with device-only nexthops when should not"
+
+ log_test "nexthop objects - invalid configurations"
+
+ ip nexthop del id 2
+ ip nexthop del id 1
+
+ simple_if_fini $swp2 192.0.2.2/24 2001:db8:1::2/64
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_offload_test()
+{
+ # Test offload indication of nexthop objects
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop not marked as offloaded when should"
+
+ ip neigh replace 192.0.2.2 nud failed dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop marked as offloaded after setting neigh to failed state"
+
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop not marked as offloaded after neigh replace"
+
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop marked as offloaded after replacing to use an invalid address"
+
+ ip nexthop replace id 1 via 192.0.2.2 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "nexthop not marked as offloaded after replacing to use a valid address"
+
+ log_test "nexthop objects offload indication"
+
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_group_offload_test()
+{
+ # Test offload indication of nexthop group objects
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
+ ip nexthop add id 10 group 1/2
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "IPv4 nexthop not marked as offloaded when should"
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 2
+ check_err $? "IPv6 nexthop not marked as offloaded when should"
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "nexthop group not marked as offloaded when should"
+
+ # Invalidate nexthop id 1
+ ip neigh replace 192.0.2.2 nud failed dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 10
+ check_fail $? "nexthop group not marked as offloaded with one valid nexthop"
+
+ # Invalidate nexthop id 2
+ ip neigh replace 2001:db8:1::2 nud failed dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "nexthop group marked as offloaded when should not"
+
+ # Revalidate nexthop id 1
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "nexthop group not marked as offloaded after revalidating nexthop"
+
+ log_test "nexthop group objects offload indication"
+
+ ip neigh del 2001:db8:1::2 dev $swp1
+ ip neigh del 192.0.2.3 dev $swp1
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 10
+ ip nexthop del id 2
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+nexthop_obj_blackhole_offload_test()
+{
+ # Test offload indication of blackhole nexthop objects
+ RET=0
+
+ ip nexthop add id 1 blackhole
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 1
+ check_err $? "Blackhole nexthop not marked as offloaded when should"
+
+ ip nexthop add id 10 group 1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip nexthop show id 10
+ check_err $? "Nexthop group not marked as offloaded when should"
+
+ log_test "blackhole nexthop objects offload indication"
+
+ ip nexthop del id 10
+ ip nexthop del id 1
+}
+
+nexthop_obj_route_offload_test()
+{
+ # Test offload indication of routes using nexthop objects
+ RET=0
+
+ simple_if_init $swp1 192.0.2.1/24 2001:db8:1::1/64
+ simple_if_init $swp2
+ setup_wait
+
+ ip nexthop add id 1 via 192.0.2.2 dev $swp1
+ ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+ ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+ dev $swp1
+
+ ip route replace 198.51.100.0/24 nhid 1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route not marked as offloaded when using valid nexthop"
+
+ ip nexthop replace id 1 via 192.0.2.3 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route not marked as offloaded after replacing valid nexthop with a valid one"
+
+ ip nexthop replace id 1 via 192.0.2.4 dev $swp1
+ busywait "$TIMEOUT" not wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route marked as offloaded after replacing valid nexthop with an invalid one"
+
+ ip nexthop replace id 1 via 192.0.2.2 dev $swp1
+ busywait "$TIMEOUT" wait_for_offload \
+ ip route show 198.51.100.0/24
+ check_err $? "route not marked as offloaded after replacing invalid nexthop with a valid one"
+
+ log_test "routes using nexthop objects offload indication"
+
+ ip route del 198.51.100.0/24
+ ip neigh del 192.0.2.3 dev $swp1
+ ip neigh del 192.0.2.2 dev $swp1
+ ip nexthop del id 1
+
+ simple_if_fini $swp2
+ simple_if_fini $swp1 192.0.2.1/24 2001:db8:1::1/64
+}
+
devlink_reload_test()
{
# Test that after executing all the above configuration tests, a
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh
new file mode 100755
index 000000000000..0231205a7147
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/q_in_vni_veto.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../../net/forwarding
+
+VXPORT=4789
+
+ALL_TESTS="
+ create_dot1d_and_dot1ad_vxlans
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+create_dot1d_and_dot1ad_vxlans()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
+ vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \
+ "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx100 up
+
+ ip link set dev $swp1 master br0
+ ip link set dev vx100 master br0
+ bridge vlan add vid 100 dev vx100 pvid untagged
+
+ ip link add dev br1 type bridge vlan_filtering 0 mcast_snooping 0
+ ip link set dev br1 up
+
+ ip link add name vx200 type vxlan id 2000 local 192.0.2.17 dstport \
+ "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx200 up
+
+ ip link set dev $swp2 master br1
+ ip link set dev vx200 master br1 2>/dev/null
+ check_fail $? "802.1d and 802.1ad VxLANs at the same time not rejected"
+
+ ip link set dev vx200 master br1 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1d and 802.1ad VxLANs at the same time rejected without extack"
+
+ log_test "create 802.1d and 802.1ad VxLANs"
+
+ ip link del dev vx200
+ ip link del dev br1
+ ip link del dev vx100
+ ip link del dev br0
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh
new file mode 100755
index 000000000000..f0443b1b05b9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/q_in_vni_veto.sh
@@ -0,0 +1,66 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../../net/forwarding
+
+VXPORT=4789
+
+ALL_TESTS="
+ create_vxlan_on_top_of_8021ad_bridge
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+
+setup_prepare()
+{
+ swp1=${NETIFS[p1]}
+ swp2=${NETIFS[p2]}
+
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+}
+
+create_vxlan_on_top_of_8021ad_bridge()
+{
+ RET=0
+
+ ip link add dev br0 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
+ vlan_default_pvid 0 mcast_snooping 0
+ ip link set dev br0 up
+
+ ip link add name vx100 type vxlan id 1000 local 192.0.2.17 dstport \
+ "$VXPORT" nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx100 up
+
+ ip link set dev $swp1 master br0
+ ip link set dev vx100 master br0
+
+ bridge vlan add vid 100 dev vx100 pvid untagged 2>/dev/null
+ check_fail $? "802.1ad bridge with VxLAN in Spectrum-1 not rejected"
+
+ bridge vlan add vid 100 dev vx100 pvid untagged 2>&1 >/dev/null \
+ | grep -q mlxsw_spectrum
+ check_err $? "802.1ad bridge with VxLAN in Spectrum-1 rejected without extack"
+
+ log_test "create VxLAN on top of 802.1ad bridge"
+
+ ip link del dev vx100
+ ip link del dev br0
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-coalesce.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-coalesce.sh
new file mode 100755
index 000000000000..9adfba8f87e6
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-coalesce.sh
@@ -0,0 +1,132 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+function get_value {
+ local query="${SETTINGS_MAP[$1]}"
+
+ echo $(ethtool -c $NSIM_NETDEV | \
+ awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[ \t]/, "", $2); print $2}')
+}
+
+function update_current_settings {
+ for key in ${!SETTINGS_MAP[@]}; do
+ CURRENT_SETTINGS[$key]=$(get_value $key)
+ done
+ echo ${CURRENT_SETTINGS[@]}
+}
+
+if ! ethtool -h | grep -q coalesce; then
+ echo "SKIP: No --coalesce support in ethtool"
+ exit 4
+fi
+
+NSIM_NETDEV=$(make_netdev)
+
+set -o pipefail
+
+declare -A SETTINGS_MAP=(
+ ["rx-frames-low"]="rx-frame-low"
+ ["tx-frames-low"]="tx-frame-low"
+ ["rx-frames-high"]="rx-frame-high"
+ ["tx-frames-high"]="tx-frame-high"
+ ["rx-usecs"]="rx-usecs"
+ ["rx-frames"]="rx-frames"
+ ["rx-usecs-irq"]="rx-usecs-irq"
+ ["rx-frames-irq"]="rx-frames-irq"
+ ["tx-usecs"]="tx-usecs"
+ ["tx-frames"]="tx-frames"
+ ["tx-usecs-irq"]="tx-usecs-irq"
+ ["tx-frames-irq"]="tx-frames-irq"
+ ["stats-block-usecs"]="stats-block-usecs"
+ ["pkt-rate-low"]="pkt-rate-low"
+ ["rx-usecs-low"]="rx-usecs-low"
+ ["tx-usecs-low"]="tx-usecs-low"
+ ["pkt-rate-high"]="pkt-rate-high"
+ ["rx-usecs-high"]="rx-usecs-high"
+ ["tx-usecs-high"]="tx-usecs-high"
+ ["sample-interval"]="sample-interval"
+)
+
+declare -A CURRENT_SETTINGS=(
+ ["rx-frames-low"]=""
+ ["tx-frames-low"]=""
+ ["rx-frames-high"]=""
+ ["tx-frames-high"]=""
+ ["rx-usecs"]=""
+ ["rx-frames"]=""
+ ["rx-usecs-irq"]=""
+ ["rx-frames-irq"]=""
+ ["tx-usecs"]=""
+ ["tx-frames"]=""
+ ["tx-usecs-irq"]=""
+ ["tx-frames-irq"]=""
+ ["stats-block-usecs"]=""
+ ["pkt-rate-low"]=""
+ ["rx-usecs-low"]=""
+ ["tx-usecs-low"]=""
+ ["pkt-rate-high"]=""
+ ["rx-usecs-high"]=""
+ ["tx-usecs-high"]=""
+ ["sample-interval"]=""
+)
+
+declare -A EXPECTED_SETTINGS=(
+ ["rx-frames-low"]=""
+ ["tx-frames-low"]=""
+ ["rx-frames-high"]=""
+ ["tx-frames-high"]=""
+ ["rx-usecs"]=""
+ ["rx-frames"]=""
+ ["rx-usecs-irq"]=""
+ ["rx-frames-irq"]=""
+ ["tx-usecs"]=""
+ ["tx-frames"]=""
+ ["tx-usecs-irq"]=""
+ ["tx-frames-irq"]=""
+ ["stats-block-usecs"]=""
+ ["pkt-rate-low"]=""
+ ["rx-usecs-low"]=""
+ ["tx-usecs-low"]=""
+ ["pkt-rate-high"]=""
+ ["rx-usecs-high"]=""
+ ["tx-usecs-high"]=""
+ ["sample-interval"]=""
+)
+
+# populate the expected settings map
+for key in ${!SETTINGS_MAP[@]}; do
+ EXPECTED_SETTINGS[$key]=$(get_value $key)
+done
+
+# test
+for key in ${!SETTINGS_MAP[@]}; do
+ value=$((RANDOM % $((2**32-1))))
+
+ ethtool -C $NSIM_NETDEV "$key" "$value"
+
+ EXPECTED_SETTINGS[$key]="$value"
+ expected=${EXPECTED_SETTINGS[@]}
+ current=$(update_current_settings)
+
+ check $? "$current" "$expected"
+ set +x
+done
+
+# bool settings which ethtool displays on the same line
+ethtool -C $NSIM_NETDEV adaptive-rx on
+s=$(ethtool -c $NSIM_NETDEV | grep -q "Adaptive RX: on TX: off")
+check $? "$s" ""
+
+ethtool -C $NSIM_NETDEV adaptive-tx on
+s=$(ethtool -c $NSIM_NETDEV | grep -q "Adaptive RX: on TX: on")
+check $? "$s" ""
+
+if [ $num_errors -eq 0 ]; then
+ echo "PASSED all $((num_passes)) checks"
+ exit 0
+else
+ echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+ exit 1
+fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
new file mode 100644
index 000000000000..9f64d5c7107b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -0,0 +1,53 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+NSIM_ID=$((RANDOM % 1024))
+NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
+NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID/ports/0
+NSIM_NETDEV=
+num_passes=0
+num_errors=0
+
+function cleanup_nsim {
+ if [ -e $NSIM_DEV_SYS ]; then
+ echo $NSIM_ID > /sys/bus/netdevsim/del_device
+ fi
+}
+
+function cleanup {
+ cleanup_nsim
+}
+
+trap cleanup EXIT
+
+function check {
+ local code=$1
+ local str=$2
+ local exp_str=$3
+
+ if [ $code -ne 0 ]; then
+ ((num_errors++))
+ return
+ fi
+
+ if [ "$str" != "$exp_str" ]; then
+ echo -e "Expected: '$exp_str', got '$str'"
+ ((num_errors++))
+ return
+ fi
+
+ ((num_passes++))
+}
+
+function make_netdev {
+ # Make a netdevsim
+ old_netdevs=$(ls /sys/class/net)
+
+ if ! $(lsmod | grep -q netdevsim); then
+ modprobe netdevsim
+ fi
+
+ echo $NSIM_ID > /sys/bus/netdevsim/new_device
+ # get new device name
+ ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/
+}
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh
index 25c896b9e2eb..b4a7abfe5454 100755
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-pause.sh
@@ -1,60 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0-only
-NSIM_ID=$((RANDOM % 1024))
-NSIM_DEV_SYS=/sys/bus/netdevsim/devices/netdevsim$NSIM_ID
-NSIM_DEV_DFS=/sys/kernel/debug/netdevsim/netdevsim$NSIM_ID/ports/0
-NSIM_NETDEV=
-num_passes=0
-num_errors=0
-
-function cleanup_nsim {
- if [ -e $NSIM_DEV_SYS ]; then
- echo $NSIM_ID > /sys/bus/netdevsim/del_device
- fi
-}
-
-function cleanup {
- cleanup_nsim
-}
-
-trap cleanup EXIT
-
-function get_netdev_name {
- local -n old=$1
-
- new=$(ls /sys/class/net)
-
- for netdev in $new; do
- for check in $old; do
- [ $netdev == $check ] && break
- done
-
- if [ $netdev != $check ]; then
- echo $netdev
- break
- fi
- done
-}
-
-function check {
- local code=$1
- local str=$2
- local exp_str=$3
-
- if [ $code -ne 0 ]; then
- ((num_errors++))
- return
- fi
-
- if [ "$str" != "$exp_str" ]; then
- echo -e "Expected: '$exp_str', got '$str'"
- ((num_errors++))
- return
- fi
-
- ((num_passes++))
-}
+source ethtool-common.sh
# Bail if ethtool is too old
if ! ethtool -h | grep include-stat 2>&1 >/dev/null; then
@@ -62,13 +9,7 @@ if ! ethtool -h | grep include-stat 2>&1 >/dev/null; then
exit 4
fi
-# Make a netdevsim
-old_netdevs=$(ls /sys/class/net)
-
-modprobe netdevsim
-echo $NSIM_ID > /sys/bus/netdevsim/new_device
-
-NSIM_NETDEV=`get_netdev_name old_netdevs`
+NSIM_NETDEV=$(make_netdev)
set -o pipefail
diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh
new file mode 100755
index 000000000000..c969559ffa7a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh
@@ -0,0 +1,85 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+function get_value {
+ local query="${SETTINGS_MAP[$1]}"
+
+ echo $(ethtool -g $NSIM_NETDEV | \
+ tail -n +$CURR_SETT_LINE | \
+ awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[\t ]/, "", $2); print $2}')
+}
+
+function update_current_settings {
+ for key in ${!SETTINGS_MAP[@]}; do
+ CURRENT_SETTINGS[$key]=$(get_value $key)
+ done
+ echo ${CURRENT_SETTINGS[@]}
+}
+
+if ! ethtool -h | grep -q set-ring >/dev/null; then
+ echo "SKIP: No --set-ring support in ethtool"
+ exit 4
+fi
+
+NSIM_NETDEV=$(make_netdev)
+
+set -o pipefail
+
+declare -A SETTINGS_MAP=(
+ ["rx"]="RX"
+ ["rx-mini"]="RX Mini"
+ ["rx-jumbo"]="RX Jumbo"
+ ["tx"]="TX"
+)
+
+declare -A EXPECTED_SETTINGS=(
+ ["rx"]=""
+ ["rx-mini"]=""
+ ["rx-jumbo"]=""
+ ["tx"]=""
+)
+
+declare -A CURRENT_SETTINGS=(
+ ["rx"]=""
+ ["rx-mini"]=""
+ ["rx-jumbo"]=""
+ ["tx"]=""
+)
+
+MAX_VALUE=$((RANDOM % $((2**32-1))))
+RING_MAX_LIST=$(ls $NSIM_DEV_DFS/ethtool/ring/)
+
+for ring_max_entry in $RING_MAX_LIST; do
+ echo $MAX_VALUE > $NSIM_DEV_DFS/ethtool/ring/$ring_max_entry
+done
+
+CURR_SETT_LINE=$(ethtool -g $NSIM_NETDEV | grep -i -m1 -n 'Current hardware settings' | cut -f1 -d:)
+
+# populate the expected settings map
+for key in ${!SETTINGS_MAP[@]}; do
+ EXPECTED_SETTINGS[$key]=$(get_value $key)
+done
+
+# test
+for key in ${!SETTINGS_MAP[@]}; do
+ value=$((RANDOM % $MAX_VALUE))
+
+ ethtool -G $NSIM_NETDEV "$key" "$value"
+
+ EXPECTED_SETTINGS[$key]="$value"
+ expected=${EXPECTED_SETTINGS[@]}
+ current=$(update_current_settings)
+
+ check $? "$current" "$expected"
+ set +x
+done
+
+if [ $num_errors -eq 0 ]; then
+ echo "PASSED all $((num_passes)) checks"
+ exit 0
+else
+ echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+ exit 1
+fi
diff --git a/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
new file mode 100755
index 000000000000..be0c1b5ee6b8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/nexthop.sh
@@ -0,0 +1,436 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# This test is for checking the nexthop offload API. It makes use of netdevsim
+# which registers a listener to the nexthop notification chain.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+ nexthop_single_add_test
+ nexthop_single_add_err_test
+ nexthop_group_add_test
+ nexthop_group_add_err_test
+ nexthop_group_replace_test
+ nexthop_group_replace_err_test
+ nexthop_single_replace_test
+ nexthop_single_replace_err_test
+ nexthop_single_in_group_replace_test
+ nexthop_single_in_group_replace_err_test
+ nexthop_single_in_group_delete_test
+ nexthop_single_in_group_delete_err_test
+ nexthop_replay_test
+ nexthop_replay_err_test
+"
+NETDEVSIM_PATH=/sys/bus/netdevsim/
+DEV_ADDR=1337
+DEV=netdevsim${DEV_ADDR}
+DEVLINK_DEV=netdevsim/${DEV}
+SYSFS_NET_DIR=/sys/bus/netdevsim/devices/$DEV/net/
+NUM_NETIFS=0
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+nexthop_check()
+{
+ local nharg="$1"; shift
+ local expected="$1"; shift
+
+ out=$($IP nexthop show ${nharg} | sed -e 's/ *$//')
+ if [[ "$out" != "$expected" ]]; then
+ return 1
+ fi
+
+ return 0
+}
+
+nexthop_resource_check()
+{
+ local expected_occ=$1; shift
+
+ occ=$($DEVLINK -jp resource show $DEVLINK_DEV \
+ | jq '.[][][] | select(.name=="nexthops") | .["occ"]')
+
+ if [ $expected_occ -ne $occ ]; then
+ return 1
+ fi
+
+ return 0
+}
+
+nexthop_resource_set()
+{
+ local size=$1; shift
+
+ $DEVLINK resource set $DEVLINK_DEV path nexthops size $size
+ $DEVLINK dev reload $DEVLINK_DEV
+}
+
+nexthop_single_add_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy"
+
+ $IP nexthop del id 1
+ nexthop_resource_check 0
+ check_err $? "Wrong nexthop occupancy after delete"
+
+ log_test "Single nexthop add and delete"
+}
+
+nexthop_single_add_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 1
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1 &> /dev/null
+ check_fail $? "Nexthop addition succeeded when should fail"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop add failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_group_add_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+ $IP nexthop add id 10 group 1/2
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ $IP nexthop del id 10
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy after delete"
+
+ $IP nexthop add id 10 group 1,20/2,39
+ nexthop_check "id 10" "id 10 group 1,20/2,39 trap"
+ check_err $? "Unexpected weighted nexthop group entry"
+
+ nexthop_resource_check 61
+ check_err $? "Wrong weighted nexthop occupancy"
+
+ $IP nexthop del id 10
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy after delete"
+
+ log_test "Nexthop group add and delete"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_group_add_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 2
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+
+ $IP nexthop add id 10 group 1/2 &> /dev/null
+ check_fail $? "Nexthop group addition succeeded when should fail"
+
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Nexthop group add failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_group_replace_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 3 via 192.0.2.4 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 10 group 1/2/3
+ nexthop_check "id 10" "id 10 group 1/2/3 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 6
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Nexthop group replace"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_group_replace_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 5
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 3 via 192.0.2.4 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 10 group 1/2/3 &> /dev/null
+ check_fail $? "Nexthop group replacement succeeded when should fail"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry after failure"
+
+ nexthop_resource_check 5
+ check_err $? "Wrong nexthop occupancy after failure"
+
+ log_test "Nexthop group replace failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_single_replace_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+ $IP nexthop replace id 1 via 192.0.2.3 dev dummy1
+ nexthop_check "id 1" "id 1 via 192.0.2.3 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop replace"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_single_replace_err_test()
+{
+ RET=0
+
+ # This is supposed to cause the replace to fail because the new nexthop
+ # is programmed before deleting the replaced one.
+ nexthop_resource_set 1
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+
+ $IP nexthop replace id 1 via 192.0.2.3 dev dummy1 &> /dev/null
+ check_fail $? "Nexthop replace succeeded when should fail"
+
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after failure"
+
+ nexthop_resource_check 1
+ check_err $? "Wrong nexthop occupancy after failure"
+
+ log_test "Single nexthop replace failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_single_in_group_replace_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 1 via 192.0.2.4 dev dummy1
+ check_err $? "Failed to replace nexthop when should not"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop replace while in group"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_group_replace_err_test()
+{
+ RET=0
+
+ nexthop_resource_set 5
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop replace id 1 via 192.0.2.4 dev dummy1 &> /dev/null
+ check_fail $? "Nexthop replacement succeeded when should fail"
+
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after failure"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry after failure"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop replace while in group failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_single_in_group_delete_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $IP nexthop del id 1
+ nexthop_check "id 10" "id 10 group 2 trap"
+ check_err $? "Unexpected nexthop group entry"
+
+ nexthop_resource_check 2
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop delete while in group"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_single_in_group_delete_err_test()
+{
+ RET=0
+
+ # First, nexthop 1 will be deleted, which will reduce the occupancy to
+ # 5. Afterwards, a replace notification will be sent for nexthop group
+ # 10 with only two nexthops. Since the new group is allocated before
+ # the old is deleted, the replacement will fail as it will result in an
+ # occupancy of 7.
+ nexthop_resource_set 6
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 3 via 192.0.2.4 dev dummy1
+ $IP nexthop add id 10 group 1/2/3
+
+ $IP nexthop del id 1
+
+ nexthop_resource_check 5
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Single nexthop delete while in group failure"
+
+ $IP nexthop flush &> /dev/null
+ nexthop_resource_set 9999
+}
+
+nexthop_replay_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ $DEVLINK dev reload $DEVLINK_DEV
+ check_err $? "Failed to reload when should not"
+
+ nexthop_check "id 1" "id 1 via 192.0.2.2 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after reload"
+
+ nexthop_check "id 2" "id 2 via 192.0.2.3 dev dummy1 scope link trap"
+ check_err $? "Unexpected nexthop entry after reload"
+
+ nexthop_check "id 10" "id 10 group 1/2 trap"
+ check_err $? "Unexpected nexthop group entry after reload"
+
+ nexthop_resource_check 4
+ check_err $? "Wrong nexthop occupancy"
+
+ log_test "Nexthop replay"
+
+ $IP nexthop flush &> /dev/null
+}
+
+nexthop_replay_err_test()
+{
+ RET=0
+
+ $IP nexthop add id 1 via 192.0.2.2 dev dummy1
+ $IP nexthop add id 2 via 192.0.2.3 dev dummy1
+ $IP nexthop add id 10 group 1/2
+
+ # Reduce size of nexthop resource so that reload will fail.
+ $DEVLINK resource set $DEVLINK_DEV path nexthops size 3
+ $DEVLINK dev reload $DEVLINK_DEV &> /dev/null
+ check_fail $? "Reload succeeded when should fail"
+
+ $DEVLINK resource set $DEVLINK_DEV path nexthops size 9999
+ $DEVLINK dev reload $DEVLINK_DEV
+ check_err $? "Failed to reload when should not"
+
+ log_test "Nexthop replay failure"
+
+ $IP nexthop flush &> /dev/null
+}
+
+setup_prepare()
+{
+ local netdev
+
+ modprobe netdevsim &> /dev/null
+
+ echo "$DEV_ADDR 1" > ${NETDEVSIM_PATH}/new_device
+ while [ ! -d $SYSFS_NET_DIR ] ; do :; done
+
+ set -e
+
+ ip netns add testns1
+ devlink dev reload $DEVLINK_DEV netns testns1
+
+ IP="ip -netns testns1"
+ DEVLINK="devlink -N testns1"
+
+ $IP link add name dummy1 up type dummy
+ $IP address add 192.0.2.1/24 dev dummy1
+
+ set +e
+}
+
+cleanup()
+{
+ pre_cleanup
+ ip netns del testns1
+ echo "$DEV_ADDR" > ${NETDEVSIM_PATH}/del_device
+ modprobe -r netdevsim &> /dev/null
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/gpio/Makefile b/tools/testing/selftests/gpio/Makefile
index 32bdc978a711..41582fe485ee 100644
--- a/tools/testing/selftests/gpio/Makefile
+++ b/tools/testing/selftests/gpio/Makefile
@@ -11,22 +11,21 @@ LDLIBS += $(VAR_LDLIBS)
TEST_PROGS := gpio-mockup.sh
TEST_FILES := gpio-mockup-sysfs.sh
-TEST_PROGS_EXTENDED := gpio-mockup-chardev
+TEST_GEN_PROGS_EXTENDED := gpio-mockup-chardev
-GPIODIR := $(realpath ../../../gpio)
-GPIOOBJ := gpio-utils.o
+KSFT_KHDR_INSTALL := 1
+include ../lib.mk
-all: $(TEST_PROGS_EXTENDED)
+GPIODIR := $(realpath ../../../gpio)
+GPIOOUT := $(OUTPUT)/tools-gpio/
+GPIOOBJ := $(GPIOOUT)/gpio-utils.o
-override define CLEAN
- $(RM) $(TEST_PROGS_EXTENDED)
- $(MAKE) -C $(GPIODIR) OUTPUT=$(GPIODIR)/ clean
-endef
+CLEAN += ; $(RM) -rf $(GPIOOUT)
-KSFT_KHDR_INSTALL := 1
-include ../lib.mk
+$(TEST_GEN_PROGS_EXTENDED): $(GPIOOBJ)
-$(TEST_PROGS_EXTENDED): $(GPIODIR)/$(GPIOOBJ)
+$(GPIOOUT):
+ mkdir -p $@
-$(GPIODIR)/$(GPIOOBJ):
- $(MAKE) OUTPUT=$(GPIODIR)/ -C $(GPIODIR)
+$(GPIOOBJ): $(GPIOOUT)
+ $(MAKE) OUTPUT=$(GPIOOUT) -C $(GPIODIR)
diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c
index f6cd03a87493..a8acf3996973 100644
--- a/tools/testing/selftests/intel_pstate/aperf.c
+++ b/tools/testing/selftests/intel_pstate/aperf.c
@@ -10,8 +10,12 @@
#include <sched.h>
#include <errno.h>
#include <string.h>
+#include <time.h>
#include "../kselftest.h"
+#define MSEC_PER_SEC 1000L
+#define NSEC_PER_MSEC 1000000L
+
void usage(char *name) {
printf ("Usage: %s cpunum\n", name);
}
@@ -22,7 +26,7 @@ int main(int argc, char **argv) {
long long tsc, old_tsc, new_tsc;
long long aperf, old_aperf, new_aperf;
long long mperf, old_mperf, new_mperf;
- struct timeb before, after;
+ struct timespec before, after;
long long int start, finish, total;
cpu_set_t cpuset;
@@ -55,7 +59,10 @@ int main(int argc, char **argv) {
return 1;
}
- ftime(&before);
+ if (clock_gettime(CLOCK_MONOTONIC, &before) < 0) {
+ perror("clock_gettime");
+ return 1;
+ }
pread(fd, &old_tsc, sizeof(old_tsc), 0x10);
pread(fd, &old_aperf, sizeof(old_mperf), 0xe7);
pread(fd, &old_mperf, sizeof(old_aperf), 0xe8);
@@ -64,7 +71,10 @@ int main(int argc, char **argv) {
sqrt(i);
}
- ftime(&after);
+ if (clock_gettime(CLOCK_MONOTONIC, &after) < 0) {
+ perror("clock_gettime");
+ return 1;
+ }
pread(fd, &new_tsc, sizeof(new_tsc), 0x10);
pread(fd, &new_aperf, sizeof(new_mperf), 0xe7);
pread(fd, &new_mperf, sizeof(new_aperf), 0xe8);
@@ -73,11 +83,11 @@ int main(int argc, char **argv) {
aperf = new_aperf-old_aperf;
mperf = new_mperf-old_mperf;
- start = before.time*1000 + before.millitm;
- finish = after.time*1000 + after.millitm;
+ start = before.tv_sec*MSEC_PER_SEC + before.tv_nsec/NSEC_PER_MSEC;
+ finish = after.tv_sec*MSEC_PER_SEC + after.tv_nsec/NSEC_PER_MSEC;
total = finish - start;
- printf("runTime: %4.2f\n", 1.0*total/1000);
+ printf("runTime: %4.2f\n", 1.0*total/MSEC_PER_SEC);
printf("freq: %7.0f\n", tsc / (1.0*aperf / (1.0 * mperf)) / total);
return 0;
}
diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c
index b3ece55a2da6..6f441dd9f33c 100644
--- a/tools/testing/selftests/kvm/set_memory_region_test.c
+++ b/tools/testing/selftests/kvm/set_memory_region_test.c
@@ -156,14 +156,23 @@ static void guest_code_move_memory_region(void)
GUEST_SYNC(0);
/*
- * Spin until the memory region is moved to a misaligned address. This
- * may or may not trigger MMIO, as the window where the memslot is
- * invalid is quite small.
+ * Spin until the memory region starts getting moved to a
+ * misaligned address.
+ * Every region move may or may not trigger MMIO, as the
+ * window where the memslot is invalid is usually quite small.
*/
val = guest_spin_on_val(0);
GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
- /* Spin until the memory region is realigned. */
+ /* Spin until the misaligning memory region move completes. */
+ val = guest_spin_on_val(MMIO_VAL);
+ GUEST_ASSERT_1(val == 1 || val == 0, val);
+
+ /* Spin until the memory region starts to get re-aligned. */
+ val = guest_spin_on_val(0);
+ GUEST_ASSERT_1(val == 1 || val == MMIO_VAL, val);
+
+ /* Spin until the re-aligning memory region move completes. */
val = guest_spin_on_val(MMIO_VAL);
GUEST_ASSERT_1(val == 1, val);
diff --git a/tools/testing/selftests/lkdtm/tests.txt b/tools/testing/selftests/lkdtm/tests.txt
index 74a8d329a72c..92ba4cc41314 100644
--- a/tools/testing/selftests/lkdtm/tests.txt
+++ b/tools/testing/selftests/lkdtm/tests.txt
@@ -68,3 +68,4 @@ USERCOPY_STACK_BEYOND
USERCOPY_KERNEL
STACKLEAK_ERASING OK: the rest of the thread stack is properly erased
CFI_FORWARD_PROTO
+FORTIFIED_STRSCPY
diff --git a/tools/testing/selftests/memfd/fuse_test.c b/tools/testing/selftests/memfd/fuse_test.c
index b018e835737d..be675002f918 100644
--- a/tools/testing/selftests/memfd/fuse_test.c
+++ b/tools/testing/selftests/memfd/fuse_test.c
@@ -20,7 +20,7 @@
#include <inttypes.h>
#include <limits.h>
#include <linux/falloc.h>
-#include <linux/fcntl.h>
+#include <fcntl.h>
#include <linux/memfd.h>
#include <sched.h>
#include <stdio.h>
diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c
index 334a7eea2004..74baab83fec3 100644
--- a/tools/testing/selftests/memfd/memfd_test.c
+++ b/tools/testing/selftests/memfd/memfd_test.c
@@ -6,7 +6,7 @@
#include <inttypes.h>
#include <limits.h>
#include <linux/falloc.h>
-#include <linux/fcntl.h>
+#include <fcntl.h>
#include <linux/memfd.h>
#include <sched.h>
#include <stdio.h>
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index ef352477cac6..fa5fa425d148 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -21,6 +21,7 @@ TEST_PROGS += rxtimestamp.sh
TEST_PROGS += devlink_port_split.py
TEST_PROGS += drop_monitor_tests.sh
TEST_PROGS += vrf_route_leaking.sh
+TEST_PROGS += bareudp.sh
TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket nettest
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
diff --git a/tools/testing/selftests/net/bareudp.sh b/tools/testing/selftests/net/bareudp.sh
new file mode 100755
index 000000000000..f366cadbc5e8
--- /dev/null
+++ b/tools/testing/selftests/net/bareudp.sh
@@ -0,0 +1,546 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Test various bareudp tunnel configurations.
+#
+# The bareudp module allows to tunnel network protocols like IP or MPLS over
+# UDP, without adding any intermediate header. This scripts tests several
+# configurations of bareudp (using IPv4 or IPv6 as underlay and transporting
+# IPv4, IPv6 or MPLS packets on the overlay).
+#
+# Network topology:
+#
+# * A chain of 4 network namespaces, connected with veth pairs. Each veth
+# is assigned an IPv4 and an IPv6 address. A host-route allows a veth to
+# join its peer.
+#
+# * NS0 and NS3 are at the extremities of the chain. They have additional
+# IPv4 and IPv6 addresses on their loopback device. Routes are added in NS0
+# and NS3, so that they can communicate using these overlay IP addresses.
+# For IPv4 and IPv6 reachability tests, the route simply sets the peer's
+# veth address as gateway. For MPLS reachability tests, an MPLS header is
+# also pushed before the IP header.
+#
+# * NS1 and NS2 are the intermediate namespaces. They use a bareudp device to
+# encapsulate the traffic into UDP.
+#
+# +-----------------------------------------------------------------------+
+# | NS0 |
+# | |
+# | lo: |
+# | * IPv4 address: 192.0.2.100/32 |
+# | * IPv6 address: 2001:db8::100/128 |
+# | * IPv6 address: 2001:db8::200/128 |
+# | * IPv4 route: 192.0.2.103/32 reachable via 192.0.2.11 |
+# | * IPv6 route: 2001:db8::103/128 reachable via 2001:db8::11 |
+# | * IPv6 route: 2001:db8::203/128 reachable via 2001:db8::11 |
+# | (encapsulated with MPLS label 203) |
+# | |
+# | veth01: |
+# | ^ * IPv4 address: 192.0.2.10, peer 192.0.2.11/32 |
+# | | * IPv6 address: 2001:db8::10, peer 2001:db8::11/128 |
+# | | |
+# +---+-------------------------------------------------------------------+
+# |
+# | Traffic type: IP or MPLS (depending on test)
+# |
+# +---+-------------------------------------------------------------------+
+# | | NS1 |
+# | | |
+# | v |
+# | veth10: |
+# | * IPv4 address: 192.0.2.11, peer 192.0.2.10/32 |
+# | * IPv6 address: 2001:db8::11, peer 2001:db8::10/128 |
+# | |
+# | bareudp_ns1: |
+# | * Encapsulate IP or MPLS packets received on veth10 into UDP |
+# | and send the resulting packets through veth12. |
+# | * Decapsulate bareudp packets (either IP or MPLS, over UDP) |
+# | received on veth12 and send the inner packets through veth10. |
+# | |
+# | veth12: |
+# | ^ * IPv4 address: 192.0.2.21, peer 192.0.2.22/32 |
+# | | * IPv6 address: 2001:db8::21, peer 2001:db8::22/128 |
+# | | |
+# +---+-------------------------------------------------------------------+
+# |
+# | Traffic type: IP or MPLS (depending on test), over UDP
+# |
+# +---+-------------------------------------------------------------------+
+# | | NS2 |
+# | | |
+# | v |
+# | veth21: |
+# | * IPv4 address: 192.0.2.22, peer 192.0.2.21/32 |
+# | * IPv6 address: 2001:db8::22, peer 2001:db8::21/128 |
+# | |
+# | bareudp_ns2: |
+# | * Decapsulate bareudp packets (either IP or MPLS, over UDP) |
+# | received on veth21 and send the inner packets through veth23. |
+# | * Encapsulate IP or MPLS packets received on veth23 into UDP |
+# | and send the resulting packets through veth21. |
+# | |
+# | veth23: |
+# | ^ * IPv4 address: 192.0.2.32, peer 192.0.2.33/32 |
+# | | * IPv6 address: 2001:db8::32, peer 2001:db8::33/128 |
+# | | |
+# +---+-------------------------------------------------------------------+
+# |
+# | Traffic type: IP or MPLS (depending on test)
+# |
+# +---+-------------------------------------------------------------------+
+# | | NS3 |
+# | v |
+# | veth32: |
+# | * IPv4 address: 192.0.2.33, peer 192.0.2.32/32 |
+# | * IPv6 address: 2001:db8::33, peer 2001:db8::32/128 |
+# | |
+# | lo: |
+# | * IPv4 address: 192.0.2.103/32 |
+# | * IPv6 address: 2001:db8::103/128 |
+# | * IPv6 address: 2001:db8::203/128 |
+# | * IPv4 route: 192.0.2.100/32 reachable via 192.0.2.32 |
+# | * IPv6 route: 2001:db8::100/128 reachable via 2001:db8::32 |
+# | * IPv6 route: 2001:db8::200/128 reachable via 2001:db8::32 |
+# | (encapsulated with MPLS label 200) |
+# | |
+# +-----------------------------------------------------------------------+
+
+ERR=4 # Return 4 by default, which is the SKIP code for kselftest
+PING6="ping"
+PAUSE_ON_FAIL="no"
+
+readonly NS0=$(mktemp -u ns0-XXXXXXXX)
+readonly NS1=$(mktemp -u ns1-XXXXXXXX)
+readonly NS2=$(mktemp -u ns2-XXXXXXXX)
+readonly NS3=$(mktemp -u ns3-XXXXXXXX)
+
+# Exit the script after having removed the network namespaces it created
+#
+# Parameters:
+#
+# * The list of network namespaces to delete before exiting.
+#
+exit_cleanup()
+{
+ for ns in "$@"; do
+ ip netns delete "${ns}" 2>/dev/null || true
+ done
+
+ if [ "${ERR}" -eq 4 ]; then
+ echo "Error: Setting up the testing environment failed." >&2
+ fi
+
+ exit "${ERR}"
+}
+
+# Create the four network namespaces used by the script (NS0, NS1, NS2 and NS3)
+#
+# New namespaces are cleaned up manually in case of error, to ensure that only
+# namespaces created by this script are deleted.
+create_namespaces()
+{
+ ip netns add "${NS0}" || exit_cleanup
+ ip netns add "${NS1}" || exit_cleanup "${NS0}"
+ ip netns add "${NS2}" || exit_cleanup "${NS0}" "${NS1}"
+ ip netns add "${NS3}" || exit_cleanup "${NS0}" "${NS1}" "${NS2}"
+}
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+ exit_cleanup "${NS0}" "${NS1}" "${NS2}" "${NS3}"
+}
+
+# Configure a network interface using a host route
+#
+# Parameters
+#
+# * $1: the netns the network interface resides in,
+# * $2: the network interface name,
+# * $3: the local IPv4 address to assign to this interface,
+# * $4: the IPv4 address of the remote network interface,
+# * $5: the local IPv6 address to assign to this interface,
+# * $6: the IPv6 address of the remote network interface.
+#
+iface_config()
+{
+ local NS="${1}"; readonly NS
+ local DEV="${2}"; readonly DEV
+ local LOCAL_IP4="${3}"; readonly LOCAL_IP4
+ local PEER_IP4="${4}"; readonly PEER_IP4
+ local LOCAL_IP6="${5}"; readonly LOCAL_IP6
+ local PEER_IP6="${6}"; readonly PEER_IP6
+
+ ip -netns "${NS}" link set dev "${DEV}" up
+ ip -netns "${NS}" address add dev "${DEV}" "${LOCAL_IP4}" peer "${PEER_IP4}"
+ ip -netns "${NS}" address add dev "${DEV}" "${LOCAL_IP6}" peer "${PEER_IP6}" nodad
+}
+
+# Create base networking topology:
+#
+# * set up the loopback device in all network namespaces (NS0..NS3),
+# * set up a veth pair to connect each netns in sequence (NS0 with NS1,
+# NS1 with NS2, etc.),
+# * add and IPv4 and an IPv6 address on each veth interface,
+# * prepare the ingress qdiscs in the intermediate namespaces.
+#
+setup_underlay()
+{
+ for ns in "${NS0}" "${NS1}" "${NS2}" "${NS3}"; do
+ ip -netns "${ns}" link set dev lo up
+ done;
+
+ ip link add name veth01 netns "${NS0}" type veth peer name veth10 netns "${NS1}"
+ ip link add name veth12 netns "${NS1}" type veth peer name veth21 netns "${NS2}"
+ ip link add name veth23 netns "${NS2}" type veth peer name veth32 netns "${NS3}"
+ iface_config "${NS0}" veth01 192.0.2.10 192.0.2.11/32 2001:db8::10 2001:db8::11/128
+ iface_config "${NS1}" veth10 192.0.2.11 192.0.2.10/32 2001:db8::11 2001:db8::10/128
+ iface_config "${NS1}" veth12 192.0.2.21 192.0.2.22/32 2001:db8::21 2001:db8::22/128
+ iface_config "${NS2}" veth21 192.0.2.22 192.0.2.21/32 2001:db8::22 2001:db8::21/128
+ iface_config "${NS2}" veth23 192.0.2.32 192.0.2.33/32 2001:db8::32 2001:db8::33/128
+ iface_config "${NS3}" veth32 192.0.2.33 192.0.2.32/32 2001:db8::33 2001:db8::32/128
+
+ tc -netns "${NS1}" qdisc add dev veth10 ingress
+ tc -netns "${NS2}" qdisc add dev veth23 ingress
+}
+
+# Set up the IPv4, IPv6 and MPLS overlays.
+#
+# Configuration is similar for all protocols:
+#
+# * add an overlay IP address on the loopback interface of each edge
+# namespace,
+# * route these IP addresses via the intermediate namespaces (for the MPLS
+# tests, this is also where MPLS encapsulation is done),
+# * add routes for these IP addresses (or MPLS labels) in the intermediate
+# namespaces.
+#
+# The bareudp encapsulation isn't configured in setup_overlay_*(). That will be
+# done just before running the reachability tests.
+
+setup_overlay_ipv4()
+{
+ # Add the overlay IP addresses and route them through the veth devices
+ ip -netns "${NS0}" address add 192.0.2.100/32 dev lo
+ ip -netns "${NS3}" address add 192.0.2.103/32 dev lo
+ ip -netns "${NS0}" route add 192.0.2.103/32 src 192.0.2.100 via 192.0.2.11
+ ip -netns "${NS3}" route add 192.0.2.100/32 src 192.0.2.103 via 192.0.2.32
+
+ # Route the overlay addresses in the intermediate namespaces
+ # (used after bareudp decapsulation)
+ ip netns exec "${NS1}" sysctl -qw net.ipv4.ip_forward=1
+ ip netns exec "${NS2}" sysctl -qw net.ipv4.ip_forward=1
+ ip -netns "${NS1}" route add 192.0.2.100/32 via 192.0.2.10
+ ip -netns "${NS2}" route add 192.0.2.103/32 via 192.0.2.33
+
+ # The intermediate namespaces don't have routes for the reverse path,
+ # as it will be handled by tc. So we need to ensure that rp_filter is
+ # not going to block the traffic.
+ ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.all.rp_filter=0
+ ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
+ ip netns exec "${NS1}" sysctl -qw net.ipv4.conf.default.rp_filter=0
+ ip netns exec "${NS2}" sysctl -qw net.ipv4.conf.default.rp_filter=0
+}
+
+setup_overlay_ipv6()
+{
+ # Add the overlay IP addresses and route them through the veth devices
+ ip -netns "${NS0}" address add 2001:db8::100/128 dev lo
+ ip -netns "${NS3}" address add 2001:db8::103/128 dev lo
+ ip -netns "${NS0}" route add 2001:db8::103/128 src 2001:db8::100 via 2001:db8::11
+ ip -netns "${NS3}" route add 2001:db8::100/128 src 2001:db8::103 via 2001:db8::32
+
+ # Route the overlay addresses in the intermediate namespaces
+ # (used after bareudp decapsulation)
+ ip netns exec "${NS1}" sysctl -qw net.ipv6.conf.all.forwarding=1
+ ip netns exec "${NS2}" sysctl -qw net.ipv6.conf.all.forwarding=1
+ ip -netns "${NS1}" route add 2001:db8::100/128 via 2001:db8::10
+ ip -netns "${NS2}" route add 2001:db8::103/128 via 2001:db8::33
+}
+
+setup_overlay_mpls()
+{
+ # Add specific overlay IP addresses, routed over MPLS
+ ip -netns "${NS0}" address add 2001:db8::200/128 dev lo
+ ip -netns "${NS3}" address add 2001:db8::203/128 dev lo
+ ip -netns "${NS0}" route add 2001:db8::203/128 src 2001:db8::200 encap mpls 203 via 2001:db8::11
+ ip -netns "${NS3}" route add 2001:db8::200/128 src 2001:db8::203 encap mpls 200 via 2001:db8::32
+
+ # Route the MPLS packets in the intermediate namespaces
+ # (used after bareudp decapsulation)
+ ip netns exec "${NS1}" sysctl -qw net.mpls.platform_labels=256
+ ip netns exec "${NS2}" sysctl -qw net.mpls.platform_labels=256
+ ip -netns "${NS1}" -family mpls route add 200 via inet6 2001:db8::10
+ ip -netns "${NS2}" -family mpls route add 203 via inet6 2001:db8::33
+}
+
+# Run "ping" from NS0 and print the result
+#
+# Parameters:
+#
+# * $1: the variant of ping to use (normally either "ping" or "ping6"),
+# * $2: the IP address to ping,
+# * $3: a human readable description of the purpose of the test.
+#
+# If the test fails and PAUSE_ON_FAIL is active, the user is given the
+# possibility to continue with the next test or to quit immediately.
+#
+ping_test_one()
+{
+ local PING="$1"; readonly PING
+ local IP="$2"; readonly IP
+ local MSG="$3"; readonly MSG
+ local RET
+
+ printf "TEST: %-60s " "${MSG}"
+
+ set +e
+ ip netns exec "${NS0}" "${PING}" -w 5 -c 1 "${IP}" > /dev/null 2>&1
+ RET=$?
+ set -e
+
+ if [ "${RET}" -eq 0 ]; then
+ printf "[ OK ]\n"
+ else
+ ERR=1
+ printf "[FAIL]\n"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ printf "\nHit enter to continue, 'q' to quit\n"
+ read a
+ if [ "$a" = "q" ]; then
+ exit 1
+ fi
+ fi
+ fi
+}
+
+# Run reachability tests
+#
+# Parameters:
+#
+# * $1: human readable string describing the underlay protocol.
+#
+# $IPV4, $IPV6, $MPLS_UC and $MULTIPROTO are inherited from the calling
+# function.
+#
+ping_test()
+{
+ local UNDERLAY="$1"; readonly UNDERLAY
+ local MODE
+ local MSG
+
+ if [ "${MULTIPROTO}" = "multiproto" ]; then
+ MODE=" (multiproto mode)"
+ else
+ MODE=""
+ fi
+
+ if [ $IPV4 ]; then
+ ping_test_one "ping" "192.0.2.103" "IPv4 packets over ${UNDERLAY}${MODE}"
+ fi
+ if [ $IPV6 ]; then
+ ping_test_one "${PING6}" "2001:db8::103" "IPv6 packets over ${UNDERLAY}${MODE}"
+ fi
+ if [ $MPLS_UC ]; then
+ ping_test_one "${PING6}" "2001:db8::203" "Unicast MPLS packets over ${UNDERLAY}${MODE}"
+ fi
+}
+
+# Set up a bareudp overlay and run reachability tests over IPv4 and IPv6
+#
+# Parameters:
+#
+# * $1: the packet type (protocol) to be handled by bareudp,
+# * $2: a flag to activate or deactivate bareudp's "multiproto" mode.
+#
+test_overlay()
+{
+ local ETHERTYPE="$1"; readonly ETHERTYPE
+ local MULTIPROTO="$2"; readonly MULTIPROTO
+ local IPV4
+ local IPV6
+ local MPLS_UC
+
+ case "${ETHERTYPE}" in
+ "ipv4")
+ IPV4="ipv4"
+ if [ "${MULTIPROTO}" = "multiproto" ]; then
+ IPV6="ipv6"
+ else
+ IPV6=""
+ fi
+ MPLS_UC=""
+ ;;
+ "ipv6")
+ IPV6="ipv6"
+ IPV4=""
+ MPLS_UC=""
+ ;;
+ "mpls_uc")
+ MPLS_UC="mpls_uc"
+ IPV4=""
+ IPV6=""
+ ;;
+ *)
+ exit 1
+ ;;
+ esac
+ readonly IPV4
+ readonly IPV6
+ readonly MPLS_UC
+
+ # Create the bareudp devices in the intermediate namespaces
+ ip -netns "${NS1}" link add name bareudp_ns1 up type bareudp dstport 6635 ethertype "${ETHERTYPE}" "${MULTIPROTO}"
+ ip -netns "${NS2}" link add name bareudp_ns2 up type bareudp dstport 6635 ethertype "${ETHERTYPE}" "${MULTIPROTO}"
+
+ # IPv4 over UDPv4
+ if [ $IPV4 ]; then
+ # Encapsulation instructions for bareudp over IPv4
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.103/32 \
+ action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.100/32 \
+ action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # IPv6 over UDPv4
+ if [ $IPV6 ]; then
+ # Encapsulation instructions for bareudp over IPv4
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::103/128 \
+ action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::100/128 \
+ action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # MPLS (unicast) over UDPv4
+ if [ $MPLS_UC ]; then
+ ip netns exec "${NS1}" sysctl -qw net.mpls.conf.bareudp_ns1.input=1
+ ip netns exec "${NS2}" sysctl -qw net.mpls.conf.bareudp_ns2.input=1
+
+ # Encapsulation instructions for bareudp over IPv4
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol mpls_uc \
+ flower mpls_label 203 \
+ action tunnel_key set src_ip 192.0.2.21 dst_ip 192.0.2.22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol mpls_uc \
+ flower mpls_label 200 \
+ action tunnel_key set src_ip 192.0.2.22 dst_ip 192.0.2.21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # Test IPv4 underlay
+ ping_test "UDPv4"
+
+ # Cleanup bareudp encapsulation instructions, as they were specific to
+ # the IPv4 underlay, before setting up and testing the IPv6 underlay
+ tc -netns "${NS1}" filter delete dev veth10 ingress
+ tc -netns "${NS2}" filter delete dev veth23 ingress
+
+ # IPv4 over UDPv6
+ if [ $IPV4 ]; then
+ # New encapsulation instructions for bareudp over IPv6
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.103/32 \
+ action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv4 \
+ flower dst_ip 192.0.2.100/32 \
+ action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # IPv6 over UDPv6
+ if [ $IPV6 ]; then
+ # New encapsulation instructions for bareudp over IPv6
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::103/128 \
+ action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol ipv6 \
+ flower dst_ip 2001:db8::100/128 \
+ action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # MPLS (unicast) over UDPv6
+ if [ $MPLS_UC ]; then
+ # New encapsulation instructions for bareudp over IPv6
+ tc -netns "${NS1}" filter add dev veth10 ingress protocol mpls_uc \
+ flower mpls_label 203 \
+ action tunnel_key set src_ip 2001:db8::21 dst_ip 2001:db8::22 id 0 \
+ action mirred egress redirect dev bareudp_ns1
+ tc -netns "${NS2}" filter add dev veth23 ingress protocol mpls_uc \
+ flower mpls_label 200 \
+ action tunnel_key set src_ip 2001:db8::22 dst_ip 2001:db8::21 id 0 \
+ action mirred egress redirect dev bareudp_ns2
+ fi
+
+ # Test IPv6 underlay
+ ping_test "UDPv6"
+
+ tc -netns "${NS1}" filter delete dev veth10 ingress
+ tc -netns "${NS2}" filter delete dev veth23 ingress
+ ip -netns "${NS1}" link delete bareudp_ns1
+ ip -netns "${NS2}" link delete bareudp_ns2
+}
+
+check_features()
+{
+ ip link help 2>&1 | grep -q bareudp
+ if [ $? -ne 0 ]; then
+ echo "Missing bareudp support in iproute2" >&2
+ exit_cleanup
+ fi
+
+ # Use ping6 on systems where ping doesn't handle IPv6
+ ping -w 1 -c 1 ::1 > /dev/null 2>&1 || PING6="ping6"
+}
+
+usage()
+{
+ echo "Usage: $0 [-p]"
+ exit 1
+}
+
+while getopts :p o
+do
+ case $o in
+ p) PAUSE_ON_FAIL="yes";;
+ *) usage;;
+ esac
+done
+
+check_features
+
+# Create namespaces before setting up the exit trap.
+# Otherwise, exit_cleanup_all() could delete namespaces that were not created
+# by this script.
+create_namespaces
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_underlay
+setup_overlay_ipv4
+setup_overlay_ipv6
+setup_overlay_mpls
+
+test_overlay ipv4 nomultiproto
+test_overlay ipv6 nomultiproto
+test_overlay ipv4 multiproto
+test_overlay mpls_uc nomultiproto
+
+if [ "${ERR}" -eq 1 ]; then
+ echo "Some tests failed." >&2
+else
+ ERR=0
+fi
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 4d5df8e1eee7..614d5477365a 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -34,3 +34,10 @@ CONFIG_TRACEPOINTS=y
CONFIG_NET_DROP_MONITOR=m
CONFIG_NETDEVSIM=m
CONFIG_NET_FOU=m
+CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
+CONFIG_NET_SCH_INGRESS=m
+CONFIG_NET_CLS_FLOWER=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_BAREUDP=m
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index fb5c55dd6df8..02b0b9ead40b 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -256,6 +256,28 @@ setup_cmd_nsb()
fi
}
+setup_cmd_nsc()
+{
+ local cmd="$*"
+ local rc
+
+ run_cmd_nsc ${cmd}
+ rc=$?
+ if [ $rc -ne 0 ]; then
+ # show user the command if not done so already
+ if [ "$VERBOSE" = "0" ]; then
+ echo "setup command: $cmd"
+ fi
+ echo "failed. stopping tests"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "hit enter to continue"
+ read a
+ fi
+ exit $rc
+ fi
+}
+
# set sysctl values in NS-A
set_sysctl()
{
@@ -471,6 +493,36 @@ setup()
sleep 1
}
+setup_lla_only()
+{
+ # make sure we are starting with a clean slate
+ kill_procs
+ cleanup 2>/dev/null
+
+ log_debug "Configuring network namespaces"
+ set -e
+
+ create_ns ${NSA} "-" "-"
+ create_ns ${NSB} "-" "-"
+ create_ns ${NSC} "-" "-"
+ connect_ns ${NSA} ${NSA_DEV} "-" "-" \
+ ${NSB} ${NSB_DEV} "-" "-"
+ connect_ns ${NSA} ${NSA_DEV2} "-" "-" \
+ ${NSC} ${NSC_DEV} "-" "-"
+
+ NSA_LINKIP6=$(get_linklocal ${NSA} ${NSA_DEV})
+ NSB_LINKIP6=$(get_linklocal ${NSB} ${NSB_DEV})
+ NSC_LINKIP6=$(get_linklocal ${NSC} ${NSC_DEV})
+
+ create_vrf ${NSA} ${VRF} ${VRF_TABLE} "-" "-"
+ ip -netns ${NSA} link set dev ${NSA_DEV} vrf ${VRF}
+ ip -netns ${NSA} link set dev ${NSA_DEV2} vrf ${VRF}
+
+ set +e
+
+ sleep 1
+}
+
################################################################################
# IPv4
@@ -3787,10 +3839,53 @@ use_case_br()
setup_cmd_nsb ip li del vlan100 2>/dev/null
}
+# VRF only.
+# ns-A device is connected to both ns-B and ns-C on a single VRF but only has
+# LLA on the interfaces
+use_case_ping_lla_multi()
+{
+ setup_lla_only
+ # only want reply from ns-A
+ setup_cmd_nsb sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1
+ setup_cmd_nsc sysctl -qw net.ipv6.icmp.echo_ignore_multicast=1
+
+ log_start
+ run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV}
+ log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Pre cycle, ping out ns-B"
+
+ run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV}
+ log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Pre cycle, ping out ns-C"
+
+ # cycle/flap the first ns-A interface
+ setup_cmd ip link set ${NSA_DEV} down
+ setup_cmd ip link set ${NSA_DEV} up
+ sleep 1
+
+ log_start
+ run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV}
+ log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-B"
+ run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV}
+ log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV}, ping out ns-C"
+
+ # cycle/flap the second ns-A interface
+ setup_cmd ip link set ${NSA_DEV2} down
+ setup_cmd ip link set ${NSA_DEV2} up
+ sleep 1
+
+ log_start
+ run_cmd_nsb ping -c1 -w1 ${MCAST}%${NSB_DEV}
+ log_test_addr ${MCAST}%${NSB_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-B"
+ run_cmd_nsc ping -c1 -w1 ${MCAST}%${NSC_DEV}
+ log_test_addr ${MCAST}%${NSC_DEV} $? 0 "Post cycle ${NSA} ${NSA_DEV2}, ping out ns-C"
+}
+
use_cases()
{
log_section "Use cases"
+ log_subsection "Device enslaved to bridge"
use_case_br
+ log_subsection "Ping LLA with multiple interfaces"
+ use_case_ping_lla_multi
}
################################################################################
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 250fbb2d1625..d97bd6889446 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -48,6 +48,7 @@ TEST_PROGS = bridge_igmp.sh \
tc_chains.sh \
tc_flower_router.sh \
tc_flower.sh \
+ tc_mpls_l2vpn.sh \
tc_shblocks.sh \
tc_vlan_modify.sh \
vxlan_asymmetric.sh \
diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
index 88d2472ba151..675eff45b037 100755
--- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
@@ -1,11 +1,37 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="reportleave_test"
+ALL_TESTS="v2reportleave_test v3include_test v3inc_allow_test v3inc_is_include_test \
+ v3inc_is_exclude_test v3inc_to_exclude_test v3exc_allow_test v3exc_is_include_test \
+ v3exc_is_exclude_test v3exc_to_exclude_test v3inc_block_test v3exc_block_test \
+ v3exc_timeout_test v3star_ex_auto_add_test"
NUM_NETIFS=4
CHECK_TC="yes"
TEST_GROUP="239.10.10.10"
TEST_GROUP_MAC="01:00:5e:0a:0a:0a"
+
+ALL_GROUP="224.0.0.1"
+ALL_MAC="01:00:5e:00:00:01"
+
+# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.1,192.0.2.2,192.0.2.3
+MZPKT_IS_INC="22:00:9d:de:00:00:00:01:01:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:02:c0:00:02:03"
+# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.10,192.0.2.11,192.0.2.12
+MZPKT_IS_INC2="22:00:9d:c3:00:00:00:01:01:00:00:03:ef:0a:0a:0a:c0:00:02:0a:c0:00:02:0b:c0:00:02:0c"
+# IGMPv3 is_in report: grp 239.10.10.10 is_include 192.0.2.20,192.0.2.30
+MZPKT_IS_INC3="22:00:5f:b4:00:00:00:01:01:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 allow report: grp 239.10.10.10 allow 192.0.2.10,192.0.2.11,192.0.2.12
+MZPKT_ALLOW="22:00:99:c3:00:00:00:01:05:00:00:03:ef:0a:0a:0a:c0:00:02:0a:c0:00:02:0b:c0:00:02:0c"
+# IGMPv3 allow report: grp 239.10.10.10 allow 192.0.2.20,192.0.2.30
+MZPKT_ALLOW2="22:00:5b:b4:00:00:00:01:05:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 is_ex report: grp 239.10.10.10 is_exclude 192.0.2.1,192.0.2.2,192.0.2.20,192.0.2.21
+MZPKT_IS_EXC="22:00:da:b6:00:00:00:01:02:00:00:04:ef:0a:0a:0a:c0:00:02:01:c0:00:02:02:c0:00:02:14:c0:00:02:15"
+# IGMPv3 is_ex report: grp 239.10.10.10 is_exclude 192.0.2.20,192.0.2.30
+MZPKT_IS_EXC2="22:00:5e:b4:00:00:00:01:02:00:00:02:ef:0a:0a:0a:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 to_ex report: grp 239.10.10.10 to_exclude 192.0.2.1,192.0.2.20,192.0.2.30
+MZPKT_TO_EXC="22:00:9a:b1:00:00:00:01:04:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:14:c0:00:02:1e"
+# IGMPv3 block report: grp 239.10.10.10 block 192.0.2.1,192.0.2.20,192.0.2.30
+MZPKT_BLOCK="22:00:98:b1:00:00:00:01:06:00:00:03:ef:0a:0a:0a:c0:00:02:01:c0:00:02:14:c0:00:02:1e"
+
source lib.sh
h1_create()
@@ -79,38 +105,7 @@ cleanup()
vrf_cleanup
}
-# return 0 if the packet wasn't seen on host2_if or 1 if it was
-mcast_packet_test()
-{
- local mac=$1
- local ip=$2
- local host1_if=$3
- local host2_if=$4
- local seen=0
-
- # Add an ACL on `host2_if` which will tell us whether the packet
- # was received by it or not.
- tc qdisc add dev $host2_if ingress
- tc filter add dev $host2_if ingress protocol ip pref 1 handle 101 \
- flower dst_mac $mac action drop
-
- $MZ $host1_if -c 1 -p 64 -b $mac -B $ip -t udp "dp=4096,sp=2048" -q
- sleep 1
-
- tc -j -s filter show dev $host2_if ingress \
- | jq -e ".[] | select(.options.handle == 101) \
- | select(.options.actions[0].stats.packets == 1)" &> /dev/null
- if [[ $? -eq 0 ]]; then
- seen=1
- fi
-
- tc filter del dev $host2_if ingress protocol ip pref 1 handle 101 flower
- tc qdisc del dev $host2_if ingress
-
- return $seen
-}
-
-reportleave_test()
+v2reportleave_test()
{
RET=0
ip address add dev $h2 $TEST_GROUP/32 autojoin
@@ -118,12 +113,12 @@ reportleave_test()
sleep 5
bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
- check_err $? "Report didn't create mdb entry for $TEST_GROUP"
+ check_err $? "IGMPv2 report didn't create mdb entry for $TEST_GROUP"
- mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2
+ mcast_packet_test $TEST_GROUP_MAC 192.0.2.1 $TEST_GROUP $h1 $h2
check_fail $? "Traffic to $TEST_GROUP wasn't forwarded"
- log_test "IGMP report $TEST_GROUP"
+ log_test "IGMPv2 report $TEST_GROUP"
RET=0
bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
@@ -136,10 +131,424 @@ reportleave_test()
bridge mdb show dev br0 | grep $TEST_GROUP 1>/dev/null
check_fail $? "Leave didn't delete mdb entry for $TEST_GROUP"
- mcast_packet_test $TEST_GROUP_MAC $TEST_GROUP $h1 $h2
+ mcast_packet_test $TEST_GROUP_MAC 192.0.2.1 $TEST_GROUP $h1 $h2
check_err $? "Traffic to $TEST_GROUP was forwarded without mdb entry"
- log_test "IGMP leave $TEST_GROUP"
+ log_test "IGMPv2 leave $TEST_GROUP"
+}
+
+v3include_prepare()
+{
+ local host1_if=$1
+ local mac=$2
+ local group=$3
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.3")
+
+ ip link set dev br0 type bridge mcast_igmp_version 3
+ check_err $? "Could not change bridge IGMP version to 3"
+
+ $MZ $host1_if -b $mac -c 1 -B $group -t ip "proto=2,p=$MZPKT_IS_INC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null)" &>/dev/null
+ check_err $? "Missing *,G entry with source list"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+}
+
+v3exclude_prepare()
+{
+ local host1_if=$1
+ local mac=$2
+ local group=$3
+ local pkt=$4
+ local X=("192.0.2.1" "192.0.2.2")
+ local Y=("192.0.2.20" "192.0.2.21")
+
+ v3include_prepare $host1_if $mac $group
+
+ $MZ $host1_if -c 1 -b $mac -B $group -t ip "proto=2,p=$MZPKT_IS_EXC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.3\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.3 entry still exists"
+}
+
+v3cleanup()
+{
+ local port=$1
+ local group=$2
+
+ bridge mdb del dev br0 port $port grp $group
+ ip link set dev br0 type bridge mcast_igmp_version 2
+}
+
+v3include_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.3")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP is_include"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_allow_test()
+{
+ RET=0
+ local X=("192.0.2.10" "192.0.2.11" "192.0.2.12")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW" -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> allow"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_is_include_test()
+{
+ RET=0
+ local X=("192.0.2.10" "192.0.2.11" "192.0.2.12")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC2" -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> is_include"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_is_exclude_test()
+{
+ RET=0
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> is_exclude"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_to_exclude_test()
+{
+ RET=0
+ local X=("192.0.2.1")
+ local Y=("192.0.2.20" "192.0.2.30")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_TO_EXC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.2 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.21\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.21 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_allow_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.20" "192.0.2.30")
+ local Y=("192.0.2.21")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> allow"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_is_include_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.20" "192.0.2.30")
+ local Y=("192.0.2.21")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC3" -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> is_include"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_is_exclude_test()
+{
+ RET=0
+ local X=("192.0.2.30")
+ local Y=("192.0.2.20")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_EXC2" -q
+ sleep 1
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> is_exclude"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_to_exclude_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.30")
+ local Y=("192.0.2.20")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_TO_EXC" -q
+ sleep 1
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3inc_block_test()
+{
+ RET=0
+ local X=("192.0.2.2" "192.0.2.3")
+
+ v3include_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_BLOCK" -q
+ # make sure the lowered timers have expired (by default 2 seconds)
+ sleep 3
+ brmcast_check_sg_entries "block" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.1 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "192.0.2.100"
+
+ log_test "IGMPv3 report $TEST_GROUP include -> block"
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_block_test()
+{
+ RET=0
+ local X=("192.0.2.1" "192.0.2.2" "192.0.2.30")
+ local Y=("192.0.2.20" "192.0.2.21")
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_BLOCK" -q
+ sleep 1
+ brmcast_check_sg_entries "block" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 192.0.2.100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "IGMPv3 report $TEST_GROUP exclude -> block"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3exc_timeout_test()
+{
+ RET=0
+ local X=("192.0.2.20" "192.0.2.30")
+
+ # GMI should be 3 seconds
+ ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+ ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+ $MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
+ sleep 3
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.1 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"192.0.2.2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 192.0.2.2 entry still exists"
+
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 192.0.2.100
+
+ log_test "IGMPv3 group $TEST_GROUP exclude timeout"
+
+ ip link set dev br0 type bridge mcast_query_interval 12500 \
+ mcast_query_response_interval 1000
+
+ v3cleanup $swp1 $TEST_GROUP
+}
+
+v3star_ex_auto_add_test()
+{
+ RET=0
+
+ v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
+
+ $MZ $h2 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_IS_INC" -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"192.0.2.3\" and \
+ .port == \"$swp1\")" &>/dev/null
+ check_err $? "S,G entry for *,G port doesn't exist"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"192.0.2.3\" and \
+ .port == \"$swp1\" and \
+ .flags[] == \"added_by_star_ex\")" &>/dev/null
+ check_err $? "Auto-added S,G entry doesn't have added_by_star_ex flag"
+
+ brmcast_check_sg_fwding 1 192.0.2.3
+
+ log_test "IGMPv3 S,G port entry automatic add to a *,G port"
+
+ v3cleanup $swp1 $TEST_GROUP
+ v3cleanup $swp2 $TEST_GROUP
}
trap cleanup EXIT
diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh
new file mode 100755
index 000000000000..ffdcfa87ca2b
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh
@@ -0,0 +1,558 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="mldv2include_test mldv2inc_allow_test mldv2inc_is_include_test mldv2inc_is_exclude_test \
+ mldv2inc_to_exclude_test mldv2exc_allow_test mldv2exc_is_include_test \
+ mldv2exc_is_exclude_test mldv2exc_to_exclude_test mldv2inc_block_test \
+ mldv2exc_block_test mldv2exc_timeout_test mldv2star_ex_auto_add_test"
+NUM_NETIFS=4
+CHECK_TC="yes"
+TEST_GROUP="ff02::cc"
+TEST_GROUP_MAC="33:33:00:00:00:cc"
+
+# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::1,2001:db8:1::2,2001:db8:1::3
+MZPKT_IS_INC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:\
+00:00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:\
+00:05:02:00:00:00:00:8f:00:8e:d9:00:00:00:01:01:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:\
+00:00:00:00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:\
+00:00:00:00:00:00:02:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:03"
+# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::10,2001:db8:1::11,2001:db8:1::12
+MZPKT_IS_INC2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:\
+00:00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:\
+05:02:00:00:00:00:8f:00:8e:ac:00:00:00:01:01:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:\
+00:00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:10:20:01:0d:b8:00:01:00:00:00:00:00:00:\
+00:00:00:11:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:12"
+# MLDv2 is_in report: grp ff02::cc is_include 2001:db8:1::20,2001:db8:1::30
+MZPKT_IS_INC3="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:bc:5a:00:00:00:01:01:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 allow report: grp ff02::cc allow 2001:db8:1::10,2001:db8:1::11,2001:db8:1::12
+MZPKT_ALLOW="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:\
+00:00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:\
+02:00:00:00:00:8f:00:8a:ac:00:00:00:01:05:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:\
+00:cc:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:10:20:01:0d:b8:00:01:00:00:00:00:00:00:00:\
+00:00:11:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:12"
+# MLDv2 allow report: grp ff02::cc allow 2001:db8:1::20,2001:db8:1::30
+MZPKT_ALLOW2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:b8:5a:00:00:00:01:05:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 is_ex report: grp ff02::cc is_exclude 2001:db8:1::1,2001:db8:1::2,2001:db8:1::20,2001:db8:1::21
+MZPKT_IS_EXC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:64:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:5f:d0:00:00:00:01:02:00:00:04:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:02:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:21"
+# MLDv2 is_ex report: grp ff02::cc is_exclude 2001:db8:1::20,2001:db8:1::30
+MZPKT_IS_EXC2="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:44:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:bb:5a:00:00:00:01:02:00:00:02:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 to_ex report: grp ff02::cc to_exclude 2001:db8:1::1,2001:db8:1::20,2001:db8:1::30
+MZPKT_TO_EXC="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:00:\
+00:00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:\
+00:00:00:8f:00:8b:8e:00:00:00:01:04:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:\
+01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+# MLDv2 block report: grp ff02::cc block 2001:db8:1::1,2001:db8:1::20,2001:db8:1::30
+MZPKT_BLOCK="33:33:00:00:00:01:fe:54:00:04:5e:ba:86:dd:60:0a:2d:ae:00:54:00:01:fe:80:00:00:00:00:\
+00:00:fc:54:00:ff:fe:04:5e:ba:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:01:3a:00:05:02:00:00:\
+00:00:8f:00:89:8e:00:00:00:01:06:00:00:03:ff:02:00:00:00:00:00:00:00:00:00:00:00:00:00:cc:20:01:\
+0d:b8:00:01:00:00:00:00:00:00:00:00:00:01:20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:20:20:01:\
+0d:b8:00:01:00:00:00:00:00:00:00:00:00:30"
+
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 2001:db8:1::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 2001:db8:1::2/64
+}
+
+switch_create()
+{
+ ip link add dev br0 type bridge mcast_snooping 1 mcast_query_response_interval 100 \
+ mcast_mld_version 2 mcast_startup_query_interval 300 \
+ mcast_querier 1
+
+ ip link set dev $swp1 master br0
+ ip link set dev $swp2 master br0
+
+ ip link set dev br0 up
+ ip link set dev $swp1 up
+ ip link set dev $swp2 up
+
+ # make sure a query has been generated
+ sleep 5
+}
+
+switch_destroy()
+{
+ ip link set dev $swp2 down
+ ip link set dev $swp1 down
+
+ ip link del dev br0
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+mldv2include_prepare()
+{
+ local host1_if=$1
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::3")
+
+ ip link set dev br0 type bridge mcast_mld_version 2
+ check_err $? "Could not change bridge MLD version to 2"
+
+ $MZ $host1_if $MZPKT_IS_INC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null)" &>/dev/null
+ check_err $? "Missing *,G entry with source list"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+}
+
+mldv2exclude_prepare()
+{
+ local host1_if=$1
+ local mac=$2
+ local group=$3
+ local pkt=$4
+ local X=("2001:db8:1::1" "2001:db8:1::2")
+ local Y=("2001:db8:1::20" "2001:db8:1::21")
+
+ mldv2include_prepare $h1
+
+ $MZ $host1_if -c 1 $MZPKT_IS_EXC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::3\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::3 entry still exists"
+}
+
+mldv2cleanup()
+{
+ local port=$1
+
+ bridge mdb del dev br0 port $port grp $TEST_GROUP
+ ip link set dev br0 type bridge mcast_mld_version 1
+}
+
+mldv2include_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::3")
+
+ mldv2include_prepare $h1
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "2001:db8:1::100"
+
+ log_test "MLDv2 report $TEST_GROUP is_include"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_allow_test()
+{
+ RET=0
+ local X=("2001:db8:1::10" "2001:db8:1::11" "2001:db8:1::12")
+
+ mldv2include_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_ALLOW -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "2001:db8:1::100"
+
+ log_test "MLDv2 report $TEST_GROUP include -> allow"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_is_include_test()
+{
+ RET=0
+ local X=("2001:db8:1::10" "2001:db8:1::11" "2001:db8:1::12")
+
+ mldv2include_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_IS_INC2 -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 "2001:db8:1::100"
+
+ log_test "MLDv2 report $TEST_GROUP include -> is_include"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_is_exclude_test()
+{
+ RET=0
+
+ mldv2exclude_prepare $h1
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP include -> is_exclude"
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_to_exclude_test()
+{
+ RET=0
+ local X=("2001:db8:1::1")
+ local Y=("2001:db8:1::20" "2001:db8:1::30")
+
+ mldv2include_prepare $h1
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 $MZPKT_TO_EXC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"exclude\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::2 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::21\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::21 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP include -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_allow_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::20" "2001:db8:1::30")
+ local Y=("2001:db8:1::21")
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_ALLOW2 -q
+ sleep 1
+ brmcast_check_sg_entries "allow" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> allow"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_is_include_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::20" "2001:db8:1::30")
+ local Y=("2001:db8:1::21")
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_IS_INC3 -q
+ sleep 1
+ brmcast_check_sg_entries "is_include" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> is_include"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_is_exclude_test()
+{
+ RET=0
+ local X=("2001:db8:1::30")
+ local Y=("2001:db8:1::20")
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_IS_EXC2 -q
+ sleep 1
+ brmcast_check_sg_entries "is_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> is_exclude"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_to_exclude_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::30")
+ local Y=("2001:db8:1::20")
+
+ mldv2exclude_prepare $h1
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 $MZPKT_TO_EXC -q
+ sleep 1
+ brmcast_check_sg_entries "to_exclude" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> to_exclude"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ mldv2cleanup $swp1
+}
+
+mldv2inc_block_test()
+{
+ RET=0
+ local X=("2001:db8:1::2" "2001:db8:1::3")
+
+ mldv2include_prepare $h1
+
+ $MZ $h1 -c 1 $MZPKT_BLOCK -q
+ # make sure the lowered timers have expired (by default 2 seconds)
+ sleep 3
+ brmcast_check_sg_entries "block" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::1 entry still exists"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 2001:db8:1::100
+
+ log_test "MLDv2 report $TEST_GROUP include -> block"
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_block_test()
+{
+ RET=0
+ local X=("2001:db8:1::1" "2001:db8:1::2" "2001:db8:1::30")
+ local Y=("2001:db8:1::20" "2001:db8:1::21")
+
+ mldv2exclude_prepare $h1
+
+ ip link set dev br0 type bridge mcast_last_member_interval 500
+ check_err $? "Could not change mcast_last_member_interval to 5s"
+
+ $MZ $h1 -c 1 $MZPKT_BLOCK -q
+ sleep 1
+ brmcast_check_sg_entries "block" "${X[@]}" "${Y[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+ brmcast_check_sg_state 1 "${Y[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}" 2001:db8:1::100
+ brmcast_check_sg_fwding 0 "${Y[@]}"
+
+ log_test "MLDv2 report $TEST_GROUP exclude -> block"
+
+ ip link set dev br0 type bridge mcast_last_member_interval 100
+
+ mldv2cleanup $swp1
+}
+
+mldv2exc_timeout_test()
+{
+ RET=0
+ local X=("2001:db8:1::20" "2001:db8:1::30")
+
+ # GMI should be 3 seconds
+ ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+
+ mldv2exclude_prepare $h1
+ ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+ $MZ $h1 -c 1 $MZPKT_ALLOW2 -q
+ sleep 3
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and .filter_mode == \"include\")" &>/dev/null
+ check_err $? "Wrong *,G entry filter mode"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::1\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::1 entry still exists"
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and \
+ .source_list != null and
+ .source_list[].address == \"2001:db8:1::2\")" &>/dev/null
+ check_fail $? "Wrong *,G entry source list, 2001:db8:1::2 entry still exists"
+
+ brmcast_check_sg_entries "allow" "${X[@]}"
+
+ brmcast_check_sg_state 0 "${X[@]}"
+
+ brmcast_check_sg_fwding 1 "${X[@]}"
+ brmcast_check_sg_fwding 0 2001:db8:1::100
+
+ log_test "MLDv2 group $TEST_GROUP exclude timeout"
+
+ ip link set dev br0 type bridge mcast_query_interval 12500 \
+ mcast_query_response_interval 1000
+
+ mldv2cleanup $swp1
+}
+
+mldv2star_ex_auto_add_test()
+{
+ RET=0
+
+ mldv2exclude_prepare $h1
+
+ $MZ $h2 -c 1 $MZPKT_IS_INC -q
+ sleep 1
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"2001:db8:1::3\" and \
+ .port == \"$swp1\")" &>/dev/null
+ check_err $? "S,G entry for *,G port doesn't exist"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"2001:db8:1::3\" and \
+ .port == \"$swp1\" and \
+ .flags[] == \"added_by_star_ex\")" &>/dev/null
+ check_err $? "Auto-added S,G entry doesn't have added_by_star_ex flag"
+
+ brmcast_check_sg_fwding 1 2001:db8:1::3
+
+ log_test "MLDv2 S,G port entry automatic add to a *,G port"
+
+ mldv2cleanup $swp1
+ mldv2cleanup $swp2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/config b/tools/testing/selftests/net/forwarding/config
index da96eff72a8e..10e9a3321ae1 100644
--- a/tools/testing/selftests/net/forwarding/config
+++ b/tools/testing/selftests/net/forwarding/config
@@ -6,6 +6,9 @@ CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_NET_VRF=m
CONFIG_BPF_SYSCALL=y
CONFIG_CGROUP_BPF=y
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_MPLS=m
+CONFIG_NET_ACT_VLAN=m
CONFIG_NET_CLS_FLOWER=m
CONFIG_NET_SCH_INGRESS=m
CONFIG_NET_ACT_GACT=m
diff --git a/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
new file mode 100755
index 000000000000..d03aa2cab9fd
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_multipath_nh.sh
@@ -0,0 +1,356 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1 |
+# | $h1 + |
+# | 192.0.2.1/28 | |
+# | 2001:db8:1::1/64 | |
+# +-------------------|-----+
+# |
+# +-------------------|------------------------+
+# | SW1 | |
+# | $ol1 + |
+# | 192.0.2.2/28 |
+# | 2001:db8:1::2/64 |
+# | |
+# | + g1a (gre) + g1b (gre) |
+# | loc=192.0.2.65 loc=192.0.2.81 |
+# | rem=192.0.2.66 --. rem=192.0.2.82 --. |
+# | tos=inherit | tos=inherit | |
+# | .------------------' | |
+# | | .------------------' |
+# | v v |
+# | + $ul1.111 (vlan) + $ul1.222 (vlan) |
+# | | 192.0.2.129/28 | 192.0.2.145/28 |
+# | \ / |
+# | \________________/ |
+# | | |
+# | + $ul1 |
+# +------------|-------------------------------+
+# |
+# +------------|-------------------------------+
+# | SW2 + $ul2 |
+# | _______|________ |
+# | / \ |
+# | / \ |
+# | + $ul2.111 (vlan) + $ul2.222 (vlan) |
+# | ^ 192.0.2.130/28 ^ 192.0.2.146/28 |
+# | | | |
+# | | '------------------. |
+# | '------------------. | |
+# | + g2a (gre) | + g2b (gre) | |
+# | loc=192.0.2.66 | loc=192.0.2.82 | |
+# | rem=192.0.2.65 --' rem=192.0.2.81 --' |
+# | tos=inherit tos=inherit |
+# | |
+# | $ol2 + |
+# | 192.0.2.17/28 | |
+# | 2001:db8:2::1/64 | |
+# +-------------------|------------------------+
+# |
+# +-------------------|-----+
+# | H2 | |
+# | $h2 + |
+# | 192.0.2.18/28 |
+# | 2001:db8:2::2/64 |
+# +-------------------------+
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ multipath_ipv4
+ multipath_ipv6
+ multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+ ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+ ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+ ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+ ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+ simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+ __simple_if_init $ul1 v$ol1
+ vlan_create $ul1 111 v$ol1 192.0.2.129/28
+ vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+ tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+ __simple_if_init g1a v$ol1 192.0.2.65/32
+ ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+ tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+ __simple_if_init g1b v$ol1 192.0.2.81/32
+ ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+ ip -6 nexthop add id 101 dev g1a
+ ip -6 nexthop add id 102 dev g1b
+ ip nexthop add id 103 group 101/102
+
+ ip route add vrf v$ol1 192.0.2.16/28 nhid 103
+ ip route add vrf v$ol1 2001:db8:2::/64 nhid 103
+}
+
+sw1_destroy()
+{
+ ip route del vrf v$ol1 2001:db8:2::/64
+ ip route del vrf v$ol1 192.0.2.16/28
+
+ ip nexthop del id 103
+ ip -6 nexthop del id 102
+ ip -6 nexthop del id 101
+
+ ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+ __simple_if_fini g1b 192.0.2.81/32
+ tunnel_destroy g1b
+
+ ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+ __simple_if_fini g1a 192.0.2.65/32
+ tunnel_destroy g1a
+
+ vlan_destroy $ul1 222
+ vlan_destroy $ul1 111
+ __simple_if_fini $ul1
+ simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+ simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+ __simple_if_init $ul2 v$ol2
+ vlan_create $ul2 111 v$ol2 192.0.2.130/28
+ vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+ tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+ __simple_if_init g2a v$ol2 192.0.2.66/32
+ ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+ tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+ __simple_if_init g2b v$ol2 192.0.2.82/32
+ ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+ ip -6 nexthop add id 201 dev g2a
+ ip -6 nexthop add id 202 dev g2b
+ ip nexthop add id 203 group 201/202
+
+ ip route add vrf v$ol2 192.0.2.0/28 nhid 203
+ ip route add vrf v$ol2 2001:db8:1::/64 nhid 203
+
+ tc qdisc add dev $ul2 clsact
+ tc filter add dev $ul2 ingress pref 111 prot 802.1Q \
+ flower vlan_id 111 action pass
+ tc filter add dev $ul2 ingress pref 222 prot 802.1Q \
+ flower vlan_id 222 action pass
+}
+
+sw2_destroy()
+{
+ tc qdisc del dev $ul2 clsact
+
+ ip route del vrf v$ol2 2001:db8:1::/64
+ ip route del vrf v$ol2 192.0.2.0/28
+
+ ip nexthop del id 203
+ ip -6 nexthop del id 202
+ ip -6 nexthop del id 201
+
+ ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+ __simple_if_fini g2b 192.0.2.82/32
+ tunnel_destroy g2b
+
+ ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+ __simple_if_fini g2a 192.0.2.66/32
+ tunnel_destroy g2a
+
+ vlan_destroy $ul2 222
+ vlan_destroy $ul2 111
+ __simple_if_fini $ul2
+ simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+ ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+ ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+ ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+ simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ ol1=${NETIFS[p2]}
+
+ ul1=${NETIFS[p3]}
+ ul2=${NETIFS[p4]}
+
+ ol2=${NETIFS[p5]}
+ h2=${NETIFS[p6]}
+
+ vrf_prepare
+ h1_create
+ sw1_create
+ sw2_create
+ h2_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ h2_destroy
+ sw2_destroy
+ sw1_destroy
+ h1_destroy
+ vrf_cleanup
+}
+
+multipath4_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv4.fib_multipath_hash_policy 1
+ ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ ip vrf exec v$h1 \
+ $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+ -d 1msec -t udp "sp=1024,dp=0-32768"
+
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip nexthop replace id 103 group 101/102
+ sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv6.fib_multipath_hash_policy 0
+ ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ # Generate 16384 echo requests, each with a random flow label.
+ for ((i=0; i < 16384; ++i)); do
+ ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+ done
+
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip nexthop replace id 103 group 101/102
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+ local what=$1; shift
+ local weight1=$1; shift
+ local weight2=$1; shift
+
+ sysctl_set net.ipv6.fib_multipath_hash_policy 1
+ ip nexthop replace id 103 group 101,$weight1/102,$weight2
+
+ local t0_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t0_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ ip vrf exec v$h1 \
+ $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+ -d 1msec -t udp "sp=1024,dp=0-32768"
+
+ local t1_111=$(tc_rule_stats_get $ul2 111 ingress)
+ local t1_222=$(tc_rule_stats_get $ul2 222 ingress)
+
+ local d111=$((t1_111 - t0_111))
+ local d222=$((t1_222 - t0_222))
+ multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+ ip nexthop replace id 103 group 101/102
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+ log_info "Running IPv4 multipath tests"
+ multipath4_test "ECMP" 1 1
+ multipath4_test "Weighted MP 2:1" 2 1
+ multipath4_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6()
+{
+ log_info "Running IPv6 multipath tests"
+ multipath6_test "ECMP" 1 1
+ multipath6_test "Weighted MP 2:1" 2 1
+ multipath6_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6_l4()
+{
+ log_info "Running IPv6 L4 hash multipath tests"
+ multipath6_l4_test "ECMP" 1 1
+ multipath6_l4_test "Weighted MP 2:1" 2 1
+ multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 927f9ba49e08..98ea37d26c44 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -1270,3 +1270,110 @@ tcpdump_show()
{
tcpdump -e -n -r $capfile 2>&1
}
+
+# return 0 if the packet wasn't seen on host2_if or 1 if it was
+mcast_packet_test()
+{
+ local mac=$1
+ local src_ip=$2
+ local ip=$3
+ local host1_if=$4
+ local host2_if=$5
+ local seen=0
+ local tc_proto="ip"
+ local mz_v6arg=""
+
+ # basic check to see if we were passed an IPv4 address, if not assume IPv6
+ if [[ ! $ip =~ ^[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}$ ]]; then
+ tc_proto="ipv6"
+ mz_v6arg="-6"
+ fi
+
+ # Add an ACL on `host2_if` which will tell us whether the packet
+ # was received by it or not.
+ tc qdisc add dev $host2_if ingress
+ tc filter add dev $host2_if ingress protocol $tc_proto pref 1 handle 101 \
+ flower ip_proto udp dst_mac $mac action drop
+
+ $MZ $host1_if $mz_v6arg -c 1 -p 64 -b $mac -A $src_ip -B $ip -t udp "dp=4096,sp=2048" -q
+ sleep 1
+
+ tc -j -s filter show dev $host2_if ingress \
+ | jq -e ".[] | select(.options.handle == 101) \
+ | select(.options.actions[0].stats.packets == 1)" &> /dev/null
+ if [[ $? -eq 0 ]]; then
+ seen=1
+ fi
+
+ tc filter del dev $host2_if ingress protocol $tc_proto pref 1 handle 101 flower
+ tc qdisc del dev $host2_if ingress
+
+ return $seen
+}
+
+brmcast_check_sg_entries()
+{
+ local report=$1; shift
+ local slist=("$@")
+ local sarg=""
+
+ for src in "${slist[@]}"; do
+ sarg="${sarg} and .source_list[].address == \"$src\""
+ done
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null $sarg)" &>/dev/null
+ check_err $? "Wrong *,G entry source list after $report report"
+
+ for sgent in "${slist[@]}"; do
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"$sgent\")" &>/dev/null
+ check_err $? "Missing S,G entry ($sgent, $TEST_GROUP)"
+ done
+}
+
+brmcast_check_sg_fwding()
+{
+ local should_fwd=$1; shift
+ local sources=("$@")
+
+ for src in "${sources[@]}"; do
+ local retval=0
+
+ mcast_packet_test $TEST_GROUP_MAC $src $TEST_GROUP $h2 $h1
+ retval=$?
+ if [ $should_fwd -eq 1 ]; then
+ check_fail $retval "Didn't forward traffic from S,G ($src, $TEST_GROUP)"
+ else
+ check_err $retval "Forwarded traffic for blocked S,G ($src, $TEST_GROUP)"
+ fi
+ done
+}
+
+brmcast_check_sg_state()
+{
+ local is_blocked=$1; shift
+ local sources=("$@")
+ local should_fail=1
+
+ if [ $is_blocked -eq 1 ]; then
+ should_fail=0
+ fi
+
+ for src in "${sources[@]}"; do
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .source_list != null) |
+ .source_list[] |
+ select(.address == \"$src\") |
+ select(.timer == \"0.00\")" &>/dev/null
+ check_err_fail $should_fail $? "Entry $src has zero timer"
+
+ bridge -j -d -s mdb show dev br0 \
+ | jq -e ".[].mdb[] | \
+ select(.grp == \"$TEST_GROUP\" and .src == \"$src\" and \
+ .flags[] == \"blocked\")" &>/dev/null
+ check_err_fail $should_fail $? "Entry $src has blocked flag"
+ done
+}
diff --git a/tools/testing/selftests/net/forwarding/q_in_vni.sh b/tools/testing/selftests/net/forwarding/q_in_vni.sh
new file mode 100755
index 000000000000..4c50c0234bce
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/q_in_vni.sh
@@ -0,0 +1,347 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+ +------------------------+
+# | H1 (vrf) | | H2 (vrf) |
+# | + $h1.10 | | + $h2.10 |
+# | | 192.0.2.1/28 | | | 192.0.2.2/28 |
+# | | | | | |
+# | | + $h1.20 | | | + $h2.20 |
+# | \ | 198.51.100.1/24 | | \ | 198.51.100.2/24 |
+# | \| | | \| |
+# | + $h1 | | + $h2 |
+# +----|------------------+ +----|-------------------+
+# | |
+# +----|--------------------------------------------------|-------------------+
+# | SW | | |
+# | +--|--------------------------------------------------|-----------------+ |
+# | | + $swp1 BR1 (802.1ad) + $swp2 | |
+# | | vid 100 pvid untagged vid 100 pvid | |
+# | | untagged | |
+# | | + vx100 (vxlan) | |
+# | | local 192.0.2.17 | |
+# | | remote 192.0.2.34 192.0.2.50 | |
+# | | id 1000 dstport $VXPORT | |
+# | | vid 100 pvid untagged | |
+# | +-----------------------------------------------------------------------+ |
+# | |
+# | 192.0.2.32/28 via 192.0.2.18 |
+# | 192.0.2.48/28 via 192.0.2.18 |
+# | |
+# | + $rp1 |
+# | | 192.0.2.17/28 |
+# +----|----------------------------------------------------------------------+
+# |
+# +----|--------------------------------------------------------+
+# | | VRP2 (vrf) |
+# | + $rp2 |
+# | 192.0.2.18/28 |
+# | | (maybe) HW
+# =============================================================================
+# | | (likely) SW
+# | + v1 (veth) + v3 (veth) |
+# | | 192.0.2.33/28 | 192.0.2.49/28 |
+# +----|---------------------------------------|----------------+
+# | |
+# +----|------------------------------+ +----|------------------------------+
+# | + v2 (veth) NS1 (netns) | | + v4 (veth) NS2 (netns) |
+# | 192.0.2.34/28 | | 192.0.2.50/28 |
+# | | | |
+# | 192.0.2.16/28 via 192.0.2.33 | | 192.0.2.16/28 via 192.0.2.49 |
+# | 192.0.2.50/32 via 192.0.2.33 | | 192.0.2.34/32 via 192.0.2.49 |
+# | | | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# | | BR2 (802.1ad) | | | | BR2 (802.1ad) | |
+# | | + vx100 (vxlan) | | | | + vx100 (vxlan) | |
+# | | local 192.0.2.34 | | | | local 192.0.2.50 | |
+# | | remote 192.0.2.17 | | | | remote 192.0.2.17 | |
+# | | remote 192.0.2.50 | | | | remote 192.0.2.34 | |
+# | | id 1000 dstport $VXPORT | | | | id 1000 dstport $VXPORT | |
+# | | vid 100 pvid untagged | | | | vid 100 pvid untagged | |
+# | | | | | | | |
+# | | + w1 (veth) | | | | + w1 (veth) | |
+# | | | vid 100 pvid untagged | | | | | vid 100 pvid untagged | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | | | |
+# | +--|----------------------------+ | | +--|----------------------------+ |
+# | | | VW2 (vrf) | | | | | VW2 (vrf) | |
+# | | + w2 (veth) | | | | + w2 (veth) | |
+# | | |\ | | | | |\ | |
+# | | | + w2.10 | | | | | + w2.10 | |
+# | | | 192.0.2.3/28 | | | | | 192.0.2.4/28 | |
+# | | | | | | | | | |
+# | | + w2.20 | | | | + w2.20 | |
+# | | 198.51.100.3/24 | | | | 198.51.100.4/24 | |
+# | +-------------------------------+ | | +-------------------------------+ |
+# +-----------------------------------+ +-----------------------------------+
+
+: ${VXPORT:=4789}
+export VXPORT
+
+: ${ALL_TESTS:="
+ ping_ipv4
+ "}
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1
+ tc qdisc add dev $h1 clsact
+ vlan_create $h1 10 v$h1 192.0.2.1/28
+ vlan_create $h1 20 v$h1 198.51.100.1/24
+}
+
+h1_destroy()
+{
+ vlan_destroy $h1 20
+ vlan_destroy $h1 10
+ tc qdisc del dev $h1 clsact
+ simple_if_fini $h1
+}
+
+h2_create()
+{
+ simple_if_init $h2
+ tc qdisc add dev $h2 clsact
+ vlan_create $h2 10 v$h2 192.0.2.2/28
+ vlan_create $h2 20 v$h2 198.51.100.2/24
+}
+
+h2_destroy()
+{
+ vlan_destroy $h2 20
+ vlan_destroy $h2 10
+ tc qdisc del dev $h2 clsact
+ simple_if_fini $h2
+}
+
+rp1_set_addr()
+{
+ ip address add dev $rp1 192.0.2.17/28
+
+ ip route add 192.0.2.32/28 nexthop via 192.0.2.18
+ ip route add 192.0.2.48/28 nexthop via 192.0.2.18
+}
+
+rp1_unset_addr()
+{
+ ip route del 192.0.2.48/28 nexthop via 192.0.2.18
+ ip route del 192.0.2.32/28 nexthop via 192.0.2.18
+
+ ip address del dev $rp1 192.0.2.17/28
+}
+
+switch_create()
+{
+ ip link add name br1 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
+ vlan_default_pvid 0 mcast_snooping 0
+ # Make sure the bridge uses the MAC address of the local port and not
+ # that of the VxLAN's device.
+ ip link set dev br1 address $(mac_get $swp1)
+ ip link set dev br1 up
+
+ ip link set dev $rp1 up
+ rp1_set_addr
+
+ ip link add name vx100 type vxlan id 1000 \
+ local 192.0.2.17 dstport "$VXPORT" \
+ nolearning noudpcsum tos inherit ttl 100
+ ip link set dev vx100 up
+
+ ip link set dev vx100 master br1
+ bridge vlan add vid 100 dev vx100 pvid untagged
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+ bridge vlan add vid 100 dev $swp1 pvid untagged
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+ bridge vlan add vid 100 dev $swp2 pvid untagged
+
+ bridge fdb append dev vx100 00:00:00:00:00:00 dst 192.0.2.34 self
+ bridge fdb append dev vx100 00:00:00:00:00:00 dst 192.0.2.50 self
+}
+
+switch_destroy()
+{
+ bridge fdb del dev vx100 00:00:00:00:00:00 dst 192.0.2.50 self
+ bridge fdb del dev vx100 00:00:00:00:00:00 dst 192.0.2.34 self
+
+ bridge vlan del vid 100 dev $swp2
+ ip link set dev $swp2 down
+ ip link set dev $swp2 nomaster
+
+ bridge vlan del vid 100 dev $swp1
+ ip link set dev $swp1 down
+ ip link set dev $swp1 nomaster
+
+ ip link set dev vx100 nomaster
+ ip link set dev vx100 down
+ ip link del dev vx100
+
+ rp1_unset_addr
+ ip link set dev $rp1 down
+
+ ip link set dev br1 down
+ ip link del dev br1
+}
+
+vrp2_create()
+{
+ simple_if_init $rp2 192.0.2.18/28
+ __simple_if_init v1 v$rp2 192.0.2.33/28
+ __simple_if_init v3 v$rp2 192.0.2.49/28
+ tc qdisc add dev v1 clsact
+}
+
+vrp2_destroy()
+{
+ tc qdisc del dev v1 clsact
+ __simple_if_fini v3 192.0.2.49/28
+ __simple_if_fini v1 192.0.2.33/28
+ simple_if_fini $rp2 192.0.2.18/28
+}
+
+ns_init_common()
+{
+ local in_if=$1; shift
+ local in_addr=$1; shift
+ local other_in_addr=$1; shift
+ local nh_addr=$1; shift
+ local host_addr1=$1; shift
+ local host_addr2=$1; shift
+
+ ip link set dev $in_if up
+ ip address add dev $in_if $in_addr/28
+ tc qdisc add dev $in_if clsact
+
+ ip link add name br2 type bridge vlan_filtering 1 vlan_protocol 802.1ad \
+ vlan_default_pvid 0
+ ip link set dev br2 up
+
+ ip link add name w1 type veth peer name w2
+
+ ip link set dev w1 master br2
+ ip link set dev w1 up
+ bridge vlan add vid 100 dev w1 pvid untagged
+
+ ip link add name vx100 type vxlan id 1000 local $in_addr \
+ dstport "$VXPORT"
+ ip link set dev vx100 up
+ bridge fdb append dev vx100 00:00:00:00:00:00 dst 192.0.2.17 self
+ bridge fdb append dev vx100 00:00:00:00:00:00 dst $other_in_addr self
+
+ ip link set dev vx100 master br2
+ tc qdisc add dev vx100 clsact
+
+ bridge vlan add vid 100 dev vx100 pvid untagged
+
+ simple_if_init w2
+ vlan_create w2 10 vw2 $host_addr1/28
+ vlan_create w2 20 vw2 $host_addr2/24
+
+ ip route add 192.0.2.16/28 nexthop via $nh_addr
+ ip route add $other_in_addr/32 nexthop via $nh_addr
+}
+export -f ns_init_common
+
+ns1_create()
+{
+ ip netns add ns1
+ ip link set dev v2 netns ns1
+ in_ns ns1 \
+ ns_init_common v2 192.0.2.34 192.0.2.50 192.0.2.33 \
+ 192.0.2.3 198.51.100.3
+}
+
+ns1_destroy()
+{
+ ip netns exec ns1 ip link set dev v2 netns 1
+ ip netns del ns1
+}
+
+ns2_create()
+{
+ ip netns add ns2
+ ip link set dev v4 netns ns2
+ in_ns ns2 \
+ ns_init_common v4 192.0.2.50 192.0.2.34 192.0.2.49 \
+ 192.0.2.4 198.51.100.4
+}
+
+ns2_destroy()
+{
+ ip netns exec ns2 ip link set dev v4 netns 1
+ ip netns del ns2
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1=${NETIFS[p5]}
+ rp2=${NETIFS[p6]}
+
+ vrf_prepare
+ forwarding_enable
+
+ h1_create
+ h2_create
+ switch_create
+
+ ip link add name v1 type veth peer name v2
+ ip link add name v3 type veth peer name v4
+ vrp2_create
+ ns1_create
+ ns2_create
+
+ r1_mac=$(in_ns ns1 mac_get w2)
+ r2_mac=$(in_ns ns2 mac_get w2)
+ h2_mac=$(mac_get $h2)
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ns2_destroy
+ ns1_destroy
+ vrp2_destroy
+ ip link del dev v3
+ ip link del dev v1
+
+ switch_destroy
+ h2_destroy
+ h1_destroy
+
+ forwarding_restore
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2 ": local->local"
+ ping_test $h1 192.0.2.3 ": local->remote 1"
+ ping_test $h1 192.0.2.4 ": local->remote 2"
+}
+
+test_all()
+{
+ echo "Running tests with UDP port $VXPORT"
+ tests_run
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+test_all
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
index cf3d26c233e8..388e4492b81b 100755
--- a/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
+++ b/tools/testing/selftests/net/forwarding/router_mpath_nh.sh
@@ -1,7 +1,13 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
-ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test"
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+ multipath_test
+ ping_ipv4_blackhole
+ ping_ipv6_blackhole
+"
NUM_NETIFS=8
source lib.sh
@@ -280,6 +286,17 @@ multipath_test()
multipath4_test "Weighted MP 2:1" 2 1
multipath4_test "Weighted MP 11:45" 11 45
+ log_info "Running IPv4 multipath tests with IPv6 link-local nexthops"
+ ip nexthop replace id 101 via fe80:2::22 dev $rp12
+ ip nexthop replace id 102 via fe80:3::23 dev $rp13
+
+ multipath4_test "ECMP" 1 1
+ multipath4_test "Weighted MP 2:1" 2 1
+ multipath4_test "Weighted MP 11:45" 11 45
+
+ ip nexthop replace id 102 via 169.254.3.23 dev $rp13
+ ip nexthop replace id 101 via 169.254.2.22 dev $rp12
+
log_info "Running IPv6 multipath tests"
multipath6_test "ECMP" 1 1
multipath6_test "Weighted MP 2:1" 2 1
@@ -291,6 +308,56 @@ multipath_test()
multipath6_l4_test "Weighted MP 11:45" 11 45
}
+ping_ipv4_blackhole()
+{
+ RET=0
+
+ ip nexthop add id 1001 blackhole
+ ip nexthop add id 1002 group 1001
+
+ ip route replace 198.51.100.0/24 vrf vrf-r1 nhid 1001
+ ping_do $h1 198.51.100.2
+ check_fail $? "ping did not fail when using a blackhole nexthop"
+
+ ip route replace 198.51.100.0/24 vrf vrf-r1 nhid 1002
+ ping_do $h1 198.51.100.2
+ check_fail $? "ping did not fail when using a blackhole nexthop group"
+
+ ip route replace 198.51.100.0/24 vrf vrf-r1 nhid 103
+ ping_do $h1 198.51.100.2
+ check_err $? "ping failed with a valid nexthop"
+
+ log_test "IPv4 blackhole ping"
+
+ ip nexthop del id 1002
+ ip nexthop del id 1001
+}
+
+ping_ipv6_blackhole()
+{
+ RET=0
+
+ ip -6 nexthop add id 1001 blackhole
+ ip nexthop add id 1002 group 1001
+
+ ip route replace 2001:db8:2::/64 vrf vrf-r1 nhid 1001
+ ping6_do $h1 2001:db8:2::2
+ check_fail $? "ping did not fail when using a blackhole nexthop"
+
+ ip route replace 2001:db8:2::/64 vrf vrf-r1 nhid 1002
+ ping6_do $h1 2001:db8:2::2
+ check_fail $? "ping did not fail when using a blackhole nexthop group"
+
+ ip route replace 2001:db8:2::/64 vrf vrf-r1 nhid 106
+ ping6_do $h1 2001:db8:2::2
+ check_err $? "ping failed with a valid nexthop"
+
+ log_test "IPv6 blackhole ping"
+
+ ip nexthop del id 1002
+ ip -6 nexthop del id 1001
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
@@ -312,7 +379,6 @@ setup_prepare()
router1_create
router2_create
- routing_nh_obj
forwarding_enable
}
diff --git a/tools/testing/selftests/net/forwarding/router_nh.sh b/tools/testing/selftests/net/forwarding/router_nh.sh
new file mode 100755
index 000000000000..f3a53738bdcc
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_nh.sh
@@ -0,0 +1,160 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+ ping_ipv4
+ ping_ipv6
+"
+
+NUM_NETIFS=4
+source lib.sh
+source tc_common.sh
+
+h1_create()
+{
+ vrf_create "vrf-h1"
+ ip link set dev $h1 master vrf-h1
+
+ ip link set dev vrf-h1 up
+ ip link set dev $h1 up
+
+ ip address add 192.0.2.2/24 dev $h1
+ ip address add 2001:db8:1::2/64 dev $h1
+
+ ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+ ip route add 2001:db8:2::/64 vrf vrf-h1 nexthop via 2001:db8:1::1
+}
+
+h1_destroy()
+{
+ ip route del 2001:db8:2::/64 vrf vrf-h1
+ ip route del 198.51.100.0/24 vrf vrf-h1
+
+ ip address del 2001:db8:1::2/64 dev $h1
+ ip address del 192.0.2.2/24 dev $h1
+
+ ip link set dev $h1 down
+ vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+ vrf_create "vrf-h2"
+ ip link set dev $h2 master vrf-h2
+
+ ip link set dev vrf-h2 up
+ ip link set dev $h2 up
+
+ ip address add 198.51.100.2/24 dev $h2
+ ip address add 2001:db8:2::2/64 dev $h2
+
+ ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+ ip route add 2001:db8:1::/64 vrf vrf-h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+ ip route del 2001:db8:1::/64 vrf vrf-h2
+ ip route del 192.0.2.0/24 vrf vrf-h2
+
+ ip address del 2001:db8:2::2/64 dev $h2
+ ip address del 198.51.100.2/24 dev $h2
+
+ ip link set dev $h2 down
+ vrf_destroy "vrf-h2"
+}
+
+router_create()
+{
+ ip link set dev $rp1 up
+ ip link set dev $rp2 up
+
+ tc qdisc add dev $rp2 clsact
+
+ ip address add 192.0.2.1/24 dev $rp1
+ ip address add 2001:db8:1::1/64 dev $rp1
+
+ ip address add 198.51.100.1/24 dev $rp2
+ ip address add 2001:db8:2::1/64 dev $rp2
+}
+
+router_destroy()
+{
+ ip address del 2001:db8:2::1/64 dev $rp2
+ ip address del 198.51.100.1/24 dev $rp2
+
+ ip address del 2001:db8:1::1/64 dev $rp1
+ ip address del 192.0.2.1/24 dev $rp1
+
+ tc qdisc del dev $rp2 clsact
+
+ ip link set dev $rp2 down
+ ip link set dev $rp1 down
+}
+
+routing_nh_obj()
+{
+ # Create the nexthops as AF_INET6, so that IPv4 and IPv6 routes could
+ # use them.
+ ip -6 nexthop add id 101 dev $rp1
+ ip -6 nexthop add id 102 dev $rp2
+
+ ip route replace 192.0.2.0/24 nhid 101
+ ip route replace 2001:db8:1::/64 nhid 101
+ ip route replace 198.51.100.0/24 nhid 102
+ ip route replace 2001:db8:2::/64 nhid 102
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ rp1=${NETIFS[p2]}
+
+ rp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ rp1mac=$(mac_get $rp1)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+
+ router_create
+
+ forwarding_enable
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ forwarding_restore
+
+ router_destroy
+
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+ping_ipv4()
+{
+ ping_test $h1 198.51.100.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+routing_nh_obj
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_mpls_l2vpn.sh b/tools/testing/selftests/net/forwarding/tc_mpls_l2vpn.sh
new file mode 100755
index 000000000000..03743f04e178
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/tc_mpls_l2vpn.sh
@@ -0,0 +1,192 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +-----------------------+
+# | H1 (v$h1) |
+# | 192.0.2.1/24 |
+# | 2001:db8::1/124 |
+# | + $h1 |
+# +-----------------|-----+
+# |
+# | (Plain Ethernet traffic)
+# |
+# +-----------------|-----------------------------------------+
+# | LER1 + $edge1 |
+# | -ingress: |
+# | -encapsulate Ethernet into MPLS |
+# | -add outer Ethernet header |
+# | -redirect to $mpls1 (egress) |
+# | |
+# | + $mpls1 |
+# | | -ingress: |
+# | | -remove outer Ethernet header |
+# | | -remove MPLS header |
+# | | -redirect to $edge1 (egress) |
+# +-----------------|-----------------------------------------+
+# |
+# | (Ethernet over MPLS traffic)
+# |
+# +-----------------|-----------------------------------------+
+# | LER2 + $mpls2 |
+# | -ingress: |
+# | -remove outer Ethernet header |
+# | -remove MPLS header |
+# | -redirect to $edge2 (egress) |
+# | |
+# | + $edge2 |
+# | | -ingress: |
+# | | -encapsulate Ethernet into MPLS |
+# | | -add outer Ethernet header |
+# | | -redirect to $mpls2 (egress) |
+# +-----------------|-----------------------------------------|
+# |
+# | (Plain Ethernet traffic)
+# |
+# +-----------------|-----+
+# | H2 (v$h2) | |
+# | + $h2 |
+# | 192.0.2.2/24 |
+# | 2001:db8::2/124 |
+# +-----------------------+
+#
+# LER1 and LER2 logically represent two different routers. However, no VRF is
+# created for them, as they don't do any IP routing.
+
+ALL_TESTS="mpls_forward_eth"
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/24 2001:db8::1/124
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/24 2001:db8::1/124
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/24 2001:db8::2/124
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/24 2001:db8::2/124
+}
+
+ler1_create()
+{
+ tc qdisc add dev $edge1 ingress
+ tc filter add dev $edge1 ingress \
+ matchall \
+ action mpls mac_push label 102 \
+ action vlan push_eth dst_mac $mpls2mac src_mac $mpls1mac \
+ action mirred egress redirect dev $mpls1
+ ip link set dev $edge1 up
+
+ tc qdisc add dev $mpls1 ingress
+ tc filter add dev $mpls1 ingress \
+ protocol mpls_uc \
+ flower mpls_label 101 \
+ action vlan pop_eth \
+ action mpls pop protocol teb \
+ action mirred egress redirect dev $edge1
+ ip link set dev $mpls1 up
+}
+
+ler1_destroy()
+{
+ ip link set dev $mpls1 down
+ tc qdisc del dev $mpls1 ingress
+
+ ip link set dev $edge1 down
+ tc qdisc del dev $edge1 ingress
+}
+
+ler2_create()
+{
+ tc qdisc add dev $edge2 ingress
+ tc filter add dev $edge2 ingress \
+ matchall \
+ action mpls mac_push label 101 \
+ action vlan push_eth dst_mac $mpls1mac src_mac $mpls2mac \
+ action mirred egress redirect dev $mpls2
+ ip link set dev $edge2 up
+
+ tc qdisc add dev $mpls2 ingress
+ tc filter add dev $mpls2 ingress \
+ protocol mpls_uc \
+ flower mpls_label 102 \
+ action vlan pop_eth \
+ action mpls pop protocol teb \
+ action mirred egress redirect dev $edge2
+ ip link set dev $mpls2 up
+}
+
+ler2_destroy()
+{
+ ip link set dev $mpls2 down
+ tc qdisc del dev $mpls2 ingress
+
+ ip link set dev $edge2 down
+ tc qdisc del dev $edge2 ingress
+}
+
+mpls_forward_eth()
+{
+ ping_test $h1 192.0.2.2
+ ping6_test $h1 2001:db8::2
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ edge1=${NETIFS[p2]}
+
+ mpls1=${NETIFS[p3]}
+ mpls2=${NETIFS[p4]}
+
+ edge2=${NETIFS[p5]}
+ h2=${NETIFS[p6]}
+
+ mpls1mac=$(mac_get $mpls1)
+ mpls2mac=$(mac_get $mpls2)
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ ler1_create
+ ler2_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ler2_destroy
+ ler1_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+tc_offload_check
+if [[ $? -ne 0 ]]; then
+ log_info "Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ tests_run
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/mptcp/config b/tools/testing/selftests/net/mptcp/config
index 741a1c4f4ae8..0faaccd21447 100644
--- a/tools/testing/selftests/net/mptcp/config
+++ b/tools/testing/selftests/net/mptcp/config
@@ -5,3 +5,13 @@ CONFIG_INET_DIAG=m
CONFIG_INET_MPTCP_DIAG=m
CONFIG_VETH=y
CONFIG_NET_SCH_NETEM=m
+CONFIG_NETFILTER=y
+CONFIG_NETFILTER_ADVANCED=y
+CONFIG_NETFILTER_NETLINK=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_COMPAT=m
+CONFIG_NETFILTER_XTABLES=m
+CONFIG_NETFILTER_XT_MATCH_BPF=m
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NF_TABLES_IPV6=y
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 08f53d86dedc..9aa9624cff97 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -5,6 +5,7 @@ ret=0
sin=""
sout=""
cin=""
+cinsent=""
cout=""
ksft_skip=4
timeout=30
@@ -13,6 +14,24 @@ capture=0
TEST_COUNT=0
+# generated using "nfbpf_compile '(ip && (ip[54] & 0xf0) == 0x30) ||
+# (ip6 && (ip6[74] & 0xf0) == 0x30)'"
+CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
+ 48 0 0 0,
+ 84 0 0 240,
+ 21 0 3 64,
+ 48 0 0 54,
+ 84 0 0 240,
+ 21 6 7 48,
+ 48 0 0 0,
+ 84 0 0 240,
+ 21 0 4 96,
+ 48 0 0 74,
+ 84 0 0 240,
+ 21 0 1 48,
+ 6 0 0 65535,
+ 6 0 0 0"
+
init()
{
capout=$(mktemp)
@@ -63,7 +82,7 @@ cleanup_partial()
cleanup()
{
rm -f "$cin" "$cout"
- rm -f "$sin" "$sout"
+ rm -f "$sin" "$sout" "$cinsent"
cleanup_partial
}
@@ -82,6 +101,26 @@ reset_with_cookies()
done
}
+reset_with_add_addr_timeout()
+{
+ local ip="${1:-4}"
+ local tables
+
+ tables="iptables"
+ if [ $ip -eq 6 ]; then
+ tables="ip6tables"
+ fi
+
+ reset
+
+ ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
+ ip netns exec $ns2 $tables -A OUTPUT -p tcp \
+ -m tcp --tcp-option 30 \
+ -m bpf --bytecode \
+ "$CBPF_MPTCP_SUBOPTION_ADD_ADDR" \
+ -j DROP
+}
+
for arg in "$@"; do
if [ "$arg" = "-c" ]; then
capture=1
@@ -94,6 +133,24 @@ if [ $? -ne 0 ];then
exit $ksft_skip
fi
+iptables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run all tests without iptables tool"
+ exit $ksft_skip
+fi
+
+ip6tables -V > /dev/null 2>&1
+if [ $? -ne 0 ];then
+ echo "SKIP: Could not run all tests without ip6tables tool"
+ exit $ksft_skip
+fi
+
+print_file_err()
+{
+ ls -l "$1" 1>&2
+ echo "Trailing bytes are: "
+ tail -c 27 "$1"
+}
check_transfer()
{
@@ -106,6 +163,7 @@ check_transfer()
echo "[ FAIL ] $what does not match (in, out):"
print_file_err "$in"
print_file_err "$out"
+ ret=1
return 1
fi
@@ -126,6 +184,23 @@ do_ping()
fi
}
+link_failure()
+{
+ ns="$1"
+
+ l=$((RANDOM%4))
+ l=$((l+1))
+
+ veth="ns1eth$l"
+ ip -net "$ns" link set "$veth" down
+}
+
+# $1: IP address
+is_v6()
+{
+ [ -z "${1##*:*}" ]
+}
+
do_transfer()
{
listener_ns="$1"
@@ -133,8 +208,10 @@ do_transfer()
cl_proto="$3"
srv_proto="$4"
connect_addr="$5"
- rm_nr_ns1="$6"
- rm_nr_ns2="$7"
+ test_link_fail="$6"
+ rm_nr_ns1="$7"
+ rm_nr_ns2="$8"
+ speed="$9"
port=$((10000+$TEST_COUNT))
TEST_COUNT=$((TEST_COUNT+1))
@@ -159,42 +236,65 @@ do_transfer()
sleep 1
fi
- if [[ $rm_nr_ns1 -eq 0 && $rm_nr_ns2 -eq 0 ]]; then
+ if [ $speed = "fast" ]; then
mptcp_connect="./mptcp_connect -j"
else
mptcp_connect="./mptcp_connect -r"
fi
- ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port -s ${srv_proto} 0.0.0.0 < "$sin" > "$sout" &
+ local local_addr
+ if is_v6 "${connect_addr}"; then
+ local_addr="::"
+ else
+ local_addr="0.0.0.0"
+ fi
+
+ ip netns exec ${listener_ns} $mptcp_connect -t $timeout -l -p $port \
+ -s ${srv_proto} ${local_addr} < "$sin" > "$sout" &
spid=$!
sleep 1
- ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+ if [ "$test_link_fail" -eq 0 ];then
+ ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr < "$cin" > "$cout" &
+ else
+ ( cat "$cin" ; sleep 2; link_failure $listener_ns ; cat "$cin" ) | tee "$cinsent" | \
+ ip netns exec ${connector_ns} $mptcp_connect -t $timeout -p $port -s ${cl_proto} $connect_addr > "$cout" &
+ fi
cpid=$!
if [ $rm_nr_ns1 -gt 0 ]; then
- counter=1
- sleep 1
+ if [ $rm_nr_ns1 -lt 8 ]; then
+ counter=1
+ sleep 1
- while [ $counter -le $rm_nr_ns1 ]
- do
- ip netns exec ${listener_ns} ./pm_nl_ctl del $counter
+ while [ $counter -le $rm_nr_ns1 ]
+ do
+ ip netns exec ${listener_ns} ./pm_nl_ctl del $counter
+ sleep 1
+ let counter+=1
+ done
+ else
sleep 1
- let counter+=1
- done
+ ip netns exec ${listener_ns} ./pm_nl_ctl flush
+ fi
fi
if [ $rm_nr_ns2 -gt 0 ]; then
- counter=1
- sleep 1
+ if [ $rm_nr_ns2 -lt 8 ]; then
+ counter=1
+ sleep 1
- while [ $counter -le $rm_nr_ns2 ]
- do
- ip netns exec ${connector_ns} ./pm_nl_ctl del $counter
+ while [ $counter -le $rm_nr_ns2 ]
+ do
+ ip netns exec ${connector_ns} ./pm_nl_ctl del $counter
+ sleep 1
+ let counter+=1
+ done
+ else
sleep 1
- let counter+=1
- done
+ ip netns exec ${connector_ns} ./pm_nl_ctl flush
+ fi
fi
wait $cpid
@@ -215,12 +315,17 @@ do_transfer()
ip netns exec ${connector_ns} ss -nita 1>&2 -o "dport = :$port"
cat "$capout"
+ ret=1
return 1
fi
check_transfer $sin $cout "file received by client"
retc=$?
- check_transfer $cin $sout "file received by server"
+ if [ "$test_link_fail" -eq 0 ];then
+ check_transfer $cin $sout "file received by server"
+ else
+ check_transfer $cinsent $sout "file received by server"
+ fi
rets=$?
if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
@@ -236,13 +341,12 @@ make_file()
{
name=$1
who=$2
+ size=$3
- SIZE=1
-
- dd if=/dev/urandom of="$name" bs=1024 count=$SIZE 2> /dev/null
+ dd if=/dev/urandom of="$name" bs=1024 count=$size 2> /dev/null
echo -e "\nMPTCP_TEST_FILE_END_MARKER" >> "$name"
- echo "Created $name (size $SIZE KB) containing data sent by $who"
+ echo "Created $name (size $size KB) containing data sent by $who"
}
run_tests()
@@ -250,27 +354,32 @@ run_tests()
listener_ns="$1"
connector_ns="$2"
connect_addr="$3"
+ test_linkfail="${4:-0}"
+ rm_nr_ns1="${5:-0}"
+ rm_nr_ns2="${6:-0}"
+ speed="${7:-fast}"
lret=0
+ oldin=""
- do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} 0 0
- lret=$?
- if [ $lret -ne 0 ]; then
- ret=$lret
- return
- fi
-}
+ if [ "$test_linkfail" -eq 1 ];then
+ size=$((RANDOM%1024))
+ size=$((size+1))
+ size=$((size*128))
-run_remove_tests()
-{
- listener_ns="$1"
- connector_ns="$2"
- connect_addr="$3"
- rm_nr_ns1="$4"
- rm_nr_ns2="$5"
- lret=0
+ oldin=$(mktemp)
+ cp "$cin" "$oldin"
+ make_file "$cin" "client" $size
+ fi
- do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} ${rm_nr_ns1} ${rm_nr_ns2}
+ do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} \
+ ${test_linkfail} ${rm_nr_ns1} ${rm_nr_ns2} ${speed}
lret=$?
+
+ if [ "$test_linkfail" -eq 1 ];then
+ cp "$oldin" "$cin"
+ rm -f "$oldin"
+ fi
+
if [ $lret -ne 0 ]; then
ret=$lret
return
@@ -403,10 +512,11 @@ chk_rm_nr()
sin=$(mktemp)
sout=$(mktemp)
cin=$(mktemp)
+cinsent=$(mktemp)
cout=$(mktemp)
init
-make_file "$cin" "client"
-make_file "$sin" "server"
+make_file "$cin" "client" 1
+make_file "$sin" "server" 1
trap cleanup EXIT
run_tests $ns1 $ns2 10.0.1.1
@@ -491,12 +601,32 @@ run_tests $ns1 $ns2 10.0.1.1
chk_join_nr "multiple subflows and signal" 3 3 3
chk_add_nr 1 1
+# accept and use add_addr with additional subflows and link loss
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1 1
+chk_join_nr "multiple flows, signal, link failure" 3 3 3
+chk_add_nr 1 1
+
+# add_addr timeout
+reset_with_add_addr_timeout
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow
+chk_join_nr "signal address, ADD_ADDR timeout" 1 1 1
+chk_add_nr 4 0
+
# single subflow, remove
reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl limits 0 1
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 0 1
+run_tests $ns1 $ns2 10.0.1.1 0 0 1 slow
chk_join_nr "remove single subflow" 1 1 1
chk_rm_nr 1 1
@@ -506,7 +636,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2
ip netns exec $ns2 ./pm_nl_ctl limits 0 2
ip netns exec $ns2 ./pm_nl_ctl add 10.0.2.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 0 2
+run_tests $ns1 $ns2 10.0.1.1 0 0 2 slow
chk_join_nr "remove multiple subflows" 2 2 2
chk_rm_nr 2 2
@@ -515,7 +645,7 @@ reset
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 1
-run_remove_tests $ns1 $ns2 10.0.1.1 1 0
+run_tests $ns1 $ns2 10.0.1.1 0 1 0 slow
chk_join_nr "remove single address" 1 1 1
chk_add_nr 1 1
chk_rm_nr 0 0
@@ -526,7 +656,7 @@ ip netns exec $ns1 ./pm_nl_ctl limits 0 2
ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 2
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 1 1
+run_tests $ns1 $ns2 10.0.1.1 0 1 1 slow
chk_join_nr "remove subflow and signal" 2 2 2
chk_add_nr 1 1
chk_rm_nr 1 1
@@ -538,11 +668,77 @@ ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
ip netns exec $ns2 ./pm_nl_ctl limits 1 3
ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
-run_remove_tests $ns1 $ns2 10.0.1.1 1 2
+run_tests $ns1 $ns2 10.0.1.1 0 1 2 slow
chk_join_nr "remove subflows and signal" 3 3 3
chk_add_nr 1 1
chk_rm_nr 2 2
+# subflows and signal, flush
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 3
+ip netns exec $ns1 ./pm_nl_ctl add 10.0.2.1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 3
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
+ip netns exec $ns2 ./pm_nl_ctl add 10.0.4.2 flags subflow
+run_tests $ns1 $ns2 10.0.1.1 0 8 8 slow
+chk_join_nr "flush subflows and signal" 3 3 3
+chk_add_nr 1 1
+chk_rm_nr 2 2
+
+# subflow IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "single subflow IPv6" 1 1 1
+
+# add_address, unused IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "unused signal address IPv6" 0 0 0
+chk_add_nr 1 1
+
+# signal address IPv6
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "single address IPv6" 1 1 1
+chk_add_nr 1 1
+
+# add_addr timeout IPv6
+reset_with_add_addr_timeout 6
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+run_tests $ns1 $ns2 dead:beef:1::1 0 0 0 slow
+chk_join_nr "signal address, ADD_ADDR6 timeout" 1 1 1
+chk_add_nr 4 0
+
+# single address IPv6, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 1
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 1
+run_tests $ns1 $ns2 dead:beef:1::1 0 1 0 slow
+chk_join_nr "remove single address IPv6" 1 1 1
+chk_add_nr 1 1
+chk_rm_nr 0 0
+
+# subflow and signal IPv6, remove
+reset
+ip netns exec $ns1 ./pm_nl_ctl limits 0 2
+ip netns exec $ns1 ./pm_nl_ctl add dead:beef:2::1 flags signal
+ip netns exec $ns2 ./pm_nl_ctl limits 1 2
+ip netns exec $ns2 ./pm_nl_ctl add dead:beef:3::2 flags subflow
+run_tests $ns1 $ns2 dead:beef:1::1 0 1 1 slow
+chk_join_nr "remove subflow and signal IPv6" 2 2 2
+chk_add_nr 1 1
+chk_rm_nr 1 1
+
# single subflow, syncookies
reset_with_cookies
ip netns exec $ns1 ./pm_nl_ctl limits 0 1
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 6bbf69a28e12..464e31eabc73 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -355,7 +355,7 @@ setup_fou_or_gue() {
encap="${3}"
if [ "${outer}" = "4" ]; then
- modprobe fou || return 2
+ modprobe fou || return $ksft_skip
a_addr="${prefix4}.${a_r1}.1"
b_addr="${prefix4}.${b_r1}.1"
if [ "${inner}" = "4" ]; then
@@ -366,7 +366,7 @@ setup_fou_or_gue() {
ipproto="41"
fi
else
- modprobe fou6 || return 2
+ modprobe fou6 || return $ksft_skip
a_addr="${prefix6}:${a_r1}::1"
b_addr="${prefix6}:${b_r1}::1"
if [ "${inner}" = "4" ]; then
@@ -380,8 +380,8 @@ setup_fou_or_gue() {
fi
fi
- run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return 2
- run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return 2
+ run_cmd ${ns_a} ip fou add port 5555 ipproto ${ipproto} || return $ksft_skip
+ run_cmd ${ns_a} ip link add ${encap}_a type ${type} ${mode} local ${a_addr} remote ${b_addr} encap ${encap} encap-sport auto encap-dport 5556 || return $ksft_skip
run_cmd ${ns_b} ip fou add port 5556 ipproto ${ipproto}
run_cmd ${ns_b} ip link add ${encap}_b type ${type} ${mode} local ${b_addr} remote ${a_addr} encap ${encap} encap-sport auto encap-dport 5555
@@ -455,7 +455,7 @@ setup_ipvX_over_ipvY() {
fi
fi
- run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return 2
+ run_cmd ${ns_a} ip link add ip_a type ${type} local ${a_addr} remote ${b_addr} mode ${mode} || return $ksft_skip
run_cmd ${ns_b} ip link add ip_b type ${type} local ${b_addr} remote ${a_addr} mode ${mode}
run_cmd ${ns_a} ip link set ip_a up
@@ -713,7 +713,7 @@ setup_routing() {
}
setup_bridge() {
- run_cmd ${ns_a} ip link add br0 type bridge || return 2
+ run_cmd ${ns_a} ip link add br0 type bridge || return $ksft_skip
run_cmd ${ns_a} ip link set br0 up
run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
@@ -765,7 +765,7 @@ setup_ovs_vxlan6() {
}
setup_ovs_bridge() {
- run_cmd ovs-vsctl add-br ovs_br0 || return 2
+ run_cmd ovs-vsctl add-br ovs_br0 || return $ksft_skip
run_cmd ip link set ovs_br0 up
run_cmd ${ns_c} ip link add veth_C-A type veth peer name veth_A-C
@@ -887,7 +887,7 @@ check_pmtu_value() {
test_pmtu_ipvX() {
family=${1}
- setup namespaces routing || return 2
+ setup namespaces routing || return $ksft_skip
trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
"${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
@@ -985,11 +985,11 @@ test_pmtu_ipvX_over_vxlanY_or_geneveY_exception() {
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing ${type}4 || return 2
+ setup namespaces routing ${type}4 || return $ksft_skip
# IPv4 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing ${type}6 || return 2
+ setup namespaces routing ${type}6 || return $ksft_skip
# IPv6 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
@@ -1060,11 +1060,11 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing bridge bridged_${type}4 || return 2
+ setup namespaces routing bridge bridged_${type}4 || return $ksft_skip
# IPv4 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing bridge bridged_${type}6 || return 2
+ setup namespaces routing bridge bridged_${type}6 || return $ksft_skip
# IPv6 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
@@ -1144,11 +1144,11 @@ test_pmtu_ipvX_over_ovs_vxlanY_or_geneveY_exception() {
ll_mtu=4000
if [ ${outer_family} -eq 4 ]; then
- setup namespaces routing ovs_bridge ovs_${type}4 || return 2
+ setup namespaces routing ovs_bridge ovs_${type}4 || return $ksft_skip
# IPv4 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 20 - 8 - 8 - 14))
else
- setup namespaces routing ovs_bridge ovs_${type}6 || return 2
+ setup namespaces routing ovs_bridge ovs_${type}6 || return $ksft_skip
# IPv6 header UDP header VXLAN/GENEVE header Ethernet header
exp_mtu=$((${ll_mtu} - 40 - 8 - 8 - 14))
fi
@@ -1230,7 +1230,7 @@ test_pmtu_ipvX_over_fouY_or_gueY() {
encap=${3}
ll_mtu=4000
- setup namespaces routing ${encap}${outer_family}${inner_family} || return 2
+ setup namespaces routing ${encap}${outer_family}${inner_family} || return $ksft_skip
trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
@@ -1309,7 +1309,7 @@ test_pmtu_ipvX_over_ipvY_exception() {
outer=${2}
ll_mtu=4000
- setup namespaces routing ip${inner}ip${outer} || return 2
+ setup namespaces routing ip${inner}ip${outer} || return $ksft_skip
trace "${ns_a}" ip_a "${ns_b}" ip_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
@@ -1363,7 +1363,7 @@ test_pmtu_ipv6_ipv6_exception() {
}
test_pmtu_vti4_exception() {
- setup namespaces veth vti4 xfrm4 || return 2
+ setup namespaces veth vti4 xfrm4 || return $ksft_skip
trace "${ns_a}" veth_a "${ns_b}" veth_b \
"${ns_a}" vti4_a "${ns_b}" vti4_b
@@ -1393,7 +1393,7 @@ test_pmtu_vti4_exception() {
}
test_pmtu_vti6_exception() {
- setup namespaces veth vti6 xfrm6 || return 2
+ setup namespaces veth vti6 xfrm6 || return $ksft_skip
trace "${ns_a}" veth_a "${ns_b}" veth_b \
"${ns_a}" vti6_a "${ns_b}" vti6_b
fail=0
@@ -1423,7 +1423,7 @@ test_pmtu_vti6_exception() {
}
test_pmtu_vti4_default_mtu() {
- setup namespaces veth vti4 || return 2
+ setup namespaces veth vti4 || return $ksft_skip
# Check that MTU of vti device is MTU of veth minus IPv4 header length
veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
@@ -1435,7 +1435,7 @@ test_pmtu_vti4_default_mtu() {
}
test_pmtu_vti6_default_mtu() {
- setup namespaces veth vti6 || return 2
+ setup namespaces veth vti6 || return $ksft_skip
# Check that MTU of vti device is MTU of veth minus IPv6 header length
veth_mtu="$(link_get_mtu "${ns_a}" veth_a)"
@@ -1447,10 +1447,10 @@ test_pmtu_vti6_default_mtu() {
}
test_pmtu_vti4_link_add_mtu() {
- setup namespaces || return 2
+ setup namespaces || return $ksft_skip
run_cmd ${ns_a} ip link add vti4_a type vti local ${veth4_a_addr} remote ${veth4_b_addr} key 10
- [ $? -ne 0 ] && err " vti not supported" && return 2
+ [ $? -ne 0 ] && err " vti not supported" && return $ksft_skip
run_cmd ${ns_a} ip link del vti4_a
fail=0
@@ -1485,10 +1485,10 @@ test_pmtu_vti4_link_add_mtu() {
}
test_pmtu_vti6_link_add_mtu() {
- setup namespaces || return 2
+ setup namespaces || return $ksft_skip
run_cmd ${ns_a} ip link add vti6_a type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
- [ $? -ne 0 ] && err " vti6 not supported" && return 2
+ [ $? -ne 0 ] && err " vti6 not supported" && return $ksft_skip
run_cmd ${ns_a} ip link del vti6_a
fail=0
@@ -1523,10 +1523,10 @@ test_pmtu_vti6_link_add_mtu() {
}
test_pmtu_vti6_link_change_mtu() {
- setup namespaces || return 2
+ setup namespaces || return $ksft_skip
run_cmd ${ns_a} ip link add dummy0 mtu 1500 type dummy
- [ $? -ne 0 ] && err " dummy not supported" && return 2
+ [ $? -ne 0 ] && err " dummy not supported" && return $ksft_skip
run_cmd ${ns_a} ip link add dummy1 mtu 3000 type dummy
run_cmd ${ns_a} ip link set dummy0 up
run_cmd ${ns_a} ip link set dummy1 up
@@ -1579,10 +1579,10 @@ test_cleanup_vxlanX_exception() {
encap="vxlan"
ll_mtu=4000
- check_command taskset || return 2
+ check_command taskset || return $ksft_skip
cpu_list=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2)
- setup namespaces routing ${encap}${outer} || return 2
+ setup namespaces routing ${encap}${outer} || return $ksft_skip
trace "${ns_a}" ${encap}_a "${ns_b}" ${encap}_b \
"${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_b}" veth_B-R1 "${ns_r1}" veth_R1-B
@@ -1644,7 +1644,7 @@ run_test() {
fi
err_flush
exit 1
- elif [ $ret -eq 2 ]; then
+ elif [ $ret -eq $ksft_skip ]; then
printf "TEST: %-60s [SKIP]\n" "${tdesc}"
err_flush
fi
@@ -1652,7 +1652,19 @@ run_test() {
return $ret
)
ret=$?
- [ $ret -ne 0 ] && exitcode=1
+ case $ret in
+ 0)
+ all_skipped=false
+ [ $exitcode=$ksft_skip ] && exitcode=0
+ ;;
+ $ksft_skip)
+ [ $all_skipped = true ] && exitcode=$ksft_skip
+ ;;
+ *)
+ all_skipped=false
+ exitcode=1
+ ;;
+ esac
return $ret
}
@@ -1667,7 +1679,7 @@ run_test_nh() {
}
test_list_flush_ipv4_exception() {
- setup namespaces routing || return 2
+ setup namespaces routing || return $ksft_skip
trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
"${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
@@ -1721,7 +1733,7 @@ test_list_flush_ipv4_exception() {
}
test_list_flush_ipv6_exception() {
- setup namespaces routing || return 2
+ setup namespaces routing || return $ksft_skip
trace "${ns_a}" veth_A-R1 "${ns_r1}" veth_R1-A \
"${ns_r1}" veth_R1-B "${ns_b}" veth_B-R1 \
"${ns_a}" veth_A-R2 "${ns_r2}" veth_R2-A \
@@ -1786,6 +1798,7 @@ usage() {
#
exitcode=0
desc=0
+all_skipped=true
while getopts :ptv o
do
@@ -1840,7 +1853,7 @@ for t in ${tests}; do
if [ $run_this -eq 1 ]; then
run_test "${name}" "${desc}"
# if test was skipped no need to retry with nexthop objects
- [ $? -eq 2 ] && rerun_nh=0
+ [ $? -eq $ksft_skip ] && rerun_nh=0
if [ "${rerun_nh}" = "1" ]; then
run_test_nh "${name}" "${desc}"
diff --git a/tools/testing/selftests/net/psock_fanout.c b/tools/testing/selftests/net/psock_fanout.c
index 2c522f7a0aec..db4521335722 100644
--- a/tools/testing/selftests/net/psock_fanout.c
+++ b/tools/testing/selftests/net/psock_fanout.c
@@ -56,12 +56,15 @@
#define RING_NUM_FRAMES 20
+static uint32_t cfg_max_num_members;
+
/* Open a socket in a given fanout mode.
* @return -1 if mode is bad, a valid socket otherwise */
static int sock_fanout_open(uint16_t typeflags, uint16_t group_id)
{
struct sockaddr_ll addr = {0};
- int fd, val;
+ struct fanout_args args;
+ int fd, val, err;
fd = socket(PF_PACKET, SOCK_RAW, 0);
if (fd < 0) {
@@ -83,8 +86,18 @@ static int sock_fanout_open(uint16_t typeflags, uint16_t group_id)
exit(1);
}
- val = (((int) typeflags) << 16) | group_id;
- if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val, sizeof(val))) {
+ if (cfg_max_num_members) {
+ args.id = group_id;
+ args.type_flags = typeflags;
+ args.max_num_members = cfg_max_num_members;
+ err = setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &args,
+ sizeof(args));
+ } else {
+ val = (((int) typeflags) << 16) | group_id;
+ err = setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &val,
+ sizeof(val));
+ }
+ if (err) {
if (close(fd)) {
perror("close packet");
exit(1);
@@ -286,6 +299,56 @@ static void test_control_group(void)
}
}
+/* Test illegal max_num_members values */
+static void test_control_group_max_num_members(void)
+{
+ int fds[3];
+
+ fprintf(stderr, "test: control multiple sockets, max_num_members\n");
+
+ /* expected failure on greater than PACKET_FANOUT_MAX */
+ cfg_max_num_members = (1 << 16) + 1;
+ if (sock_fanout_open(PACKET_FANOUT_HASH, 0) != -1) {
+ fprintf(stderr, "ERROR: max_num_members > PACKET_FANOUT_MAX\n");
+ exit(1);
+ }
+
+ cfg_max_num_members = 256;
+ fds[0] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
+ if (fds[0] == -1) {
+ fprintf(stderr, "ERROR: failed open\n");
+ exit(1);
+ }
+
+ /* expected failure on joining group with different max_num_members */
+ cfg_max_num_members = 257;
+ if (sock_fanout_open(PACKET_FANOUT_HASH, 0) != -1) {
+ fprintf(stderr, "ERROR: set different max_num_members\n");
+ exit(1);
+ }
+
+ /* success on joining group with same max_num_members */
+ cfg_max_num_members = 256;
+ fds[1] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
+ if (fds[1] == -1) {
+ fprintf(stderr, "ERROR: failed to join group\n");
+ exit(1);
+ }
+
+ /* success on joining group with max_num_members unspecified */
+ cfg_max_num_members = 0;
+ fds[2] = sock_fanout_open(PACKET_FANOUT_HASH, 0);
+ if (fds[2] == -1) {
+ fprintf(stderr, "ERROR: failed to join group\n");
+ exit(1);
+ }
+
+ if (close(fds[2]) || close(fds[1]) || close(fds[0])) {
+ fprintf(stderr, "ERROR: closing sockets\n");
+ exit(1);
+ }
+}
+
/* Test creating a unique fanout group ids */
static void test_unique_fanout_group_ids(void)
{
@@ -426,8 +489,11 @@ int main(int argc, char **argv)
test_control_single();
test_control_group();
+ test_control_group_max_num_members();
test_unique_fanout_group_ids();
+ /* PACKET_FANOUT_MAX */
+ cfg_max_num_members = 1 << 16;
/* find a set of ports that do not collide onto the same socket */
ret = test_datapath(PACKET_FANOUT_HASH, port_off,
expect_hash[0], expect_hash[1]);
diff --git a/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
new file mode 100755
index 000000000000..ad7a9fc59934
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_end_dt4_l3vpn_test.sh
@@ -0,0 +1,494 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Andrea Mayer <andrea.mayer@uniroma2.it>
+
+# This test is designed for evaluating the new SRv6 End.DT4 behavior used for
+# implementing IPv4 L3 VPN use cases.
+#
+# Hereafter a network diagram is shown, where two different tenants (named 100
+# and 200) offer IPv4 L3 VPN services allowing hosts to communicate with each
+# other across an IPv6 network.
+#
+# Only hosts belonging to the same tenant (and to the same VPN) can communicate
+# with each other. Instead, the communication among hosts of different tenants
+# is forbidden.
+# In other words, hosts hs-t100-1 and hs-t100-2 are connected through the IPv4
+# L3 VPN of tenant 100 while hs-t200-3 and hs-t200-4 are connected using the
+# IPv4 L3 VPN of tenant 200. Cross connection between tenant 100 and tenant 200
+# is forbidden and thus, for example, hs-t100-1 cannot reach hs-t200-3 and vice
+# versa.
+#
+# Routers rt-1 and rt-2 implement IPv4 L3 VPN services leveraging the SRv6
+# architecture. The key components for such VPNs are: a) SRv6 Encap behavior,
+# b) SRv6 End.DT4 behavior and c) VRF.
+#
+# To explain how an IPv4 L3 VPN based on SRv6 works, let us briefly consider an
+# example where, within the same domain of tenant 100, the host hs-t100-1 pings
+# the host hs-t100-2.
+#
+# First of all, L2 reachability of the host hs-t100-2 is taken into account by
+# the router rt-1 which acts as an arp proxy.
+#
+# When the host hs-t100-1 sends an IPv4 packet destined to hs-t100-2, the
+# router rt-1 receives the packet on the internal veth-t100 interface. Such
+# interface is enslaved to the VRF vrf-100 whose associated table contains the
+# SRv6 Encap route for encapsulating any IPv4 packet in a IPv6 plus the Segment
+# Routing Header (SRH) packet. This packet is sent through the (IPv6) core
+# network up to the router rt-2 that receives it on veth0 interface.
+#
+# The rt-2 router uses the 'localsid' routing table to process incoming
+# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these
+# packets, the SRv6 End.DT4 behavior removes the outer IPv6+SRH headers and
+# performs the lookup on the vrf-100 table using the destination address of
+# the decapsulated IPv4 packet. Afterwards, the packet is sent to the host
+# hs-t100-2 through the veth-t100 interface.
+#
+# The ping response follows the same processing but this time the role of rt-1
+# and rt-2 are swapped.
+#
+# Of course, the IPv4 L3 VPN for tenant 200 works exactly as the IPv4 L3 VPN
+# for tenant 100. In this case, only hosts hs-t200-3 and hs-t200-4 are able to
+# connect with each other.
+#
+#
+# +-------------------+ +-------------------+
+# | | | |
+# | hs-t100-1 netns | | hs-t100-2 netns |
+# | | | |
+# | +-------------+ | | +-------------+ |
+# | | veth0 | | | | veth0 | |
+# | | 10.0.0.1/24 | | | | 10.0.0.2/24 | |
+# | +-------------+ | | +-------------+ |
+# | . | | . |
+# +-------------------+ +-------------------+
+# . .
+# . .
+# . .
+# +-----------------------------------+ +-----------------------------------+
+# | . | | . |
+# | +---------------+ | | +---------------- |
+# | | veth-t100 | | | | veth-t100 | |
+# | | 10.0.0.254/24 | +----------+ | | +----------+ | 10.0.0.254/24 | |
+# | +-------+-------+ | localsid | | | | localsid | +-------+-------- |
+# | | | table | | | | table | | |
+# | +----+----+ +----------+ | | +----------+ +----+----+ |
+# | | vrf-100 | | | | vrf-100 | |
+# | +---------+ +------------+ | | +------------+ +---------+ |
+# | | veth0 | | | | veth0 | |
+# | | fd00::1/64 |.|...|.| fd00::2/64 | |
+# | +---------+ +------------+ | | +------------+ +---------+ |
+# | | vrf-200 | | | | vrf-200 | |
+# | +----+----+ | | +----+----+ |
+# | | | | | |
+# | +-------+-------+ | | +-------+-------- |
+# | | veth-t200 | | | | veth-t200 | |
+# | | 10.0.0.254/24 | | | | 10.0.0.254/24 | |
+# | +---------------+ rt-1 netns | | rt-2 netns +---------------- |
+# | . | | . |
+# +-----------------------------------+ +-----------------------------------+
+# . .
+# . .
+# . .
+# . .
+# +-------------------+ +-------------------+
+# | . | | . |
+# | +-------------+ | | +-------------+ |
+# | | veth0 | | | | veth0 | |
+# | | 10.0.0.3/24 | | | | 10.0.0.4/24 | |
+# | +-------------+ | | +-------------+ |
+# | | | |
+# | hs-t200-3 netns | | hs-t200-4 netns |
+# | | | |
+# +-------------------+ +-------------------+
+#
+#
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
+# | Network configuration |
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+# rt-1: localsid table (table 90)
+# +-------------------------------------------------+
+# |SID |Action |
+# +-------------------------------------------------+
+# |fc00:21:100::6004|apply SRv6 End.DT4 vrftable 100|
+# +-------------------------------------------------+
+# |fc00:21:200::6004|apply SRv6 End.DT4 vrftable 200|
+# +-------------------------------------------------+
+#
+# rt-1: VRF tenant 100 (table 100)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |10.0.0.2 |apply seg6 encap segs fc00:12:100::6004|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth_t100 |
+# +---------------------------------------------------+
+#
+# rt-1: VRF tenant 200 (table 200)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |10.0.0.4 |apply seg6 encap segs fc00:12:200::6004|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth_t200 |
+# +---------------------------------------------------+
+#
+#
+# rt-2: localsid table (table 90)
+# +-------------------------------------------------+
+# |SID |Action |
+# +-------------------------------------------------+
+# |fc00:12:100::6004|apply SRv6 End.DT4 vrftable 100|
+# +-------------------------------------------------+
+# |fc00:12:200::6004|apply SRv6 End.DT4 vrftable 200|
+# +-------------------------------------------------+
+#
+# rt-2: VRF tenant 100 (table 100)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |10.0.0.1 |apply seg6 encap segs fc00:21:100::6004|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth_t100 |
+# +---------------------------------------------------+
+#
+# rt-2: VRF tenant 200 (table 200)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |10.0.0.3 |apply seg6 encap segs fc00:21:200::6004|
+# +---------------------------------------------------+
+# |10.0.0.0/24|forward to dev veth_t200 |
+# +---------------------------------------------------+
+#
+
+readonly LOCALSID_TABLE_ID=90
+readonly IPv6_RT_NETWORK=fd00
+readonly IPv4_HS_NETWORK=10.0.0
+readonly VPN_LOCATOR_SERVICE=fc00
+PING_TIMEOUT_SEC=4
+
+ret=0
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+
+log_test()
+{
+ local rc=$1
+ local expected=$2
+ local msg="$3"
+
+ if [ ${rc} -eq ${expected} ]; then
+ nsuccess=$((nsuccess+1))
+ printf "\n TEST: %-60s [ OK ]\n" "${msg}"
+ else
+ ret=1
+ nfail=$((nfail+1))
+ printf "\n TEST: %-60s [FAIL]\n" "${msg}"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "hit enter to continue, 'q' to quit"
+ read a
+ [ "$a" = "q" ] && exit 1
+ fi
+ fi
+}
+
+print_log_test_results()
+{
+ if [ "$TESTS" != "none" ]; then
+ printf "\nTests passed: %3d\n" ${nsuccess}
+ printf "Tests failed: %3d\n" ${nfail}
+ fi
+}
+
+log_section()
+{
+ echo
+ echo "################################################################################"
+ echo "TEST SECTION: $*"
+ echo "################################################################################"
+}
+
+cleanup()
+{
+ ip link del veth-rt-1 2>/dev/null || true
+ ip link del veth-rt-2 2>/dev/null || true
+
+ # destroy routers rt-* and hosts hs-*
+ for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do
+ ip netns del ${ns} || true
+ done
+}
+
+# Setup the basic networking for the routers
+setup_rt_networking()
+{
+ local rt=$1
+ local nsname=rt-${rt}
+
+ ip netns add ${nsname}
+ ip link set veth-rt-${rt} netns ${nsname}
+ ip -netns ${nsname} link set veth-rt-${rt} name veth0
+
+ ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0
+ ip -netns ${nsname} link set veth0 up
+ ip -netns ${nsname} link set lo up
+
+ ip netns exec ${nsname} sysctl -wq net.ipv4.ip_forward=1
+ ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1
+}
+
+setup_hs()
+{
+ local hs=$1
+ local rt=$2
+ local tid=$3
+ local hsname=hs-t${tid}-${hs}
+ local rtname=rt-${rt}
+ local rtveth=veth-t${tid}
+
+ # set the networking for the host
+ ip netns add ${hsname}
+ ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
+ ip -netns ${hsname} link set ${rtveth} netns ${rtname}
+ ip -netns ${hsname} addr add ${IPv4_HS_NETWORK}.${hs}/24 dev veth0
+ ip -netns ${hsname} link set veth0 up
+ ip -netns ${hsname} link set lo up
+
+ # configure the VRF for the tenant X on the router which is directly
+ # connected to the source host.
+ ip -netns ${rtname} link add vrf-${tid} type vrf table ${tid}
+ ip -netns ${rtname} link set vrf-${tid} up
+
+ # enslave the veth-tX interface to the vrf-X in the access router
+ ip -netns ${rtname} link set ${rtveth} master vrf-${tid}
+ ip -netns ${rtname} addr add ${IPv4_HS_NETWORK}.254/24 dev ${rtveth}
+ ip -netns ${rtname} link set ${rtveth} up
+
+ ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.proxy_arp=1
+
+ # disable the rp_filter otherwise the kernel gets confused about how
+ # to route decap ipv4 packets.
+ ip netns exec ${rtname} sysctl -wq net.ipv4.conf.all.rp_filter=0
+ ip netns exec ${rtname} sysctl -wq net.ipv4.conf.${rtveth}.rp_filter=0
+
+ ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
+}
+
+setup_vpn_config()
+{
+ local hssrc=$1
+ local rtsrc=$2
+ local hsdst=$3
+ local rtdst=$4
+ local tid=$5
+
+ local hssrc_name=hs-t${tid}-${hssrc}
+ local hsdst_name=hs-t${tid}-${hsdst}
+ local rtsrc_name=rt-${rtsrc}
+ local rtdst_name=rt-${rtdst}
+ local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6004
+
+ # set the encap route for encapsulating packets which arrive from the
+ # host hssrc and destined to the access router rtsrc.
+ ip -netns ${rtsrc_name} -4 route add ${IPv4_HS_NETWORK}.${hsdst}/32 vrf vrf-${tid} \
+ encap seg6 mode encap segs ${vpn_sid} dev veth0
+ ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 vrf vrf-${tid} \
+ via fd00::${rtdst} dev veth0
+
+ # set the decap route for decapsulating packets which arrive from
+ # the rtdst router and destined to the hsdst host.
+ ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 table ${LOCALSID_TABLE_ID} \
+ encap seg6local action End.DT4 vrftable ${tid} dev vrf-${tid}
+
+ # all sids for VPNs start with a common locator which is fc00::/16.
+ # Routes for handling the SRv6 End.DT4 behavior instances are grouped
+ # together in the 'localsid' table.
+ #
+ # NOTE: added only once
+ if [ -z "$(ip -netns ${rtdst_name} -6 rule show | \
+ grep "to ${VPN_LOCATOR_SERVICE}::/16 lookup ${LOCALSID_TABLE_ID}")" ]; then
+ ip -netns ${rtdst_name} -6 rule add \
+ to ${VPN_LOCATOR_SERVICE}::/16 \
+ lookup ${LOCALSID_TABLE_ID} prio 999
+ fi
+}
+
+setup()
+{
+ ip link add veth-rt-1 type veth peer name veth-rt-2
+ # setup the networking for router rt-1 and router rt-2
+ setup_rt_networking 1
+ setup_rt_networking 2
+
+ # setup two hosts for the tenant 100.
+ # - host hs-1 is directly connected to the router rt-1;
+ # - host hs-2 is directly connected to the router rt-2.
+ setup_hs 1 1 100 #args: host router tenant
+ setup_hs 2 2 100
+
+ # setup two hosts for the tenant 200
+ # - host hs-3 is directly connected to the router rt-1;
+ # - host hs-4 is directly connected to the router rt-2.
+ setup_hs 3 1 200
+ setup_hs 4 2 200
+
+ # setup the IPv4 L3 VPN which connects the host hs-t100-1 and host
+ # hs-t100-2 within the same tenant 100.
+ setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant
+ setup_vpn_config 2 2 1 1 100
+
+ # setup the IPv4 L3 VPN which connects the host hs-t200-3 and host
+ # hs-t200-4 within the same tenant 200.
+ setup_vpn_config 3 1 4 2 200
+ setup_vpn_config 4 2 3 1 200
+}
+
+check_rt_connectivity()
+{
+ local rtsrc=$1
+ local rtdst=$2
+
+ ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
+ >/dev/null 2>&1
+}
+
+check_and_log_rt_connectivity()
+{
+ local rtsrc=$1
+ local rtdst=$2
+
+ check_rt_connectivity ${rtsrc} ${rtdst}
+ log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}"
+}
+
+check_hs_connectivity()
+{
+ local hssrc=$1
+ local hsdst=$2
+ local tid=$3
+
+ ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+ ${IPv4_HS_NETWORK}.${hsdst} >/dev/null 2>&1
+}
+
+check_and_log_hs_connectivity()
+{
+ local hssrc=$1
+ local hsdst=$2
+ local tid=$3
+
+ check_hs_connectivity ${hssrc} ${hsdst} ${tid}
+ log_test $? 0 "Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})"
+}
+
+check_and_log_hs_isolation()
+{
+ local hssrc=$1
+ local tidsrc=$2
+ local hsdst=$3
+ local tiddst=$4
+
+ check_hs_connectivity ${hssrc} ${hsdst} ${tidsrc}
+ # NOTE: ping should fail
+ log_test $? 1 "Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}"
+}
+
+
+check_and_log_hs2gw_connectivity()
+{
+ local hssrc=$1
+ local tid=$2
+
+ check_hs_connectivity ${hssrc} 254 ${tid}
+ log_test $? 0 "Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})"
+}
+
+router_tests()
+{
+ log_section "IPv6 routers connectivity test"
+
+ check_and_log_rt_connectivity 1 2
+ check_and_log_rt_connectivity 2 1
+}
+
+host2gateway_tests()
+{
+ log_section "IPv4 connectivity test among hosts and gateway"
+
+ check_and_log_hs2gw_connectivity 1 100
+ check_and_log_hs2gw_connectivity 2 100
+
+ check_and_log_hs2gw_connectivity 3 200
+ check_and_log_hs2gw_connectivity 4 200
+}
+
+host_vpn_tests()
+{
+ log_section "SRv6 VPN connectivity test among hosts in the same tenant"
+
+ check_and_log_hs_connectivity 1 2 100
+ check_and_log_hs_connectivity 2 1 100
+
+ check_and_log_hs_connectivity 3 4 200
+ check_and_log_hs_connectivity 4 3 200
+}
+
+host_vpn_isolation_tests()
+{
+ local i
+ local j
+ local k
+ local tmp
+ local l1="1 2"
+ local l2="3 4"
+ local t1=100
+ local t2=200
+
+ log_section "SRv6 VPN isolation test among hosts in different tentants"
+
+ for k in 0 1; do
+ for i in ${l1}; do
+ for j in ${l2}; do
+ check_and_log_hs_isolation ${i} ${t1} ${j} ${t2}
+ done
+ done
+
+ # let us test the reverse path
+ tmp="${l1}"; l1="${l2}"; l2="${tmp}"
+ tmp=${t1}; t1=${t2}; t2=${tmp}
+ done
+}
+
+if [ "$(id -u)" -ne 0 ];then
+ echo "SKIP: Need root privileges"
+ exit 0
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+ echo "SKIP: Could not run test without ip tool"
+ exit 0
+fi
+
+modprobe vrf &>/dev/null
+if [ ! -e /proc/sys/net/vrf/strict_mode ]; then
+ echo "SKIP: vrf sysctl does not exist"
+ exit 0
+fi
+
+cleanup &>/dev/null
+
+setup
+
+router_tests
+host2gateway_tests
+host_vpn_tests
+host_vpn_isolation_tests
+
+print_log_test_results
+
+cleanup &>/dev/null
+
+exit ${ret}
diff --git a/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh
new file mode 100755
index 000000000000..68708f5e26a0
--- /dev/null
+++ b/tools/testing/selftests/net/srv6_end_dt6_l3vpn_test.sh
@@ -0,0 +1,502 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# author: Andrea Mayer <andrea.mayer@uniroma2.it>
+# author: Paolo Lungaroni <paolo.lungaroni@cnit.it>
+
+# This test is designed for evaluating the new SRv6 End.DT6 behavior used for
+# implementing IPv6 L3 VPN use cases.
+#
+# Hereafter a network diagram is shown, where two different tenants (named 100
+# and 200) offer IPv6 L3 VPN services allowing hosts to communicate with each
+# other across an IPv6 network.
+#
+# Only hosts belonging to the same tenant (and to the same VPN) can communicate
+# with each other. Instead, the communication among hosts of different tenants
+# is forbidden.
+# In other words, hosts hs-t100-1 and hs-t100-2 are connected through the IPv6
+# L3 VPN of tenant 100 while hs-t200-3 and hs-t200-4 are connected using the
+# IPv6 L3 VPN of tenant 200. Cross connection between tenant 100 and tenant 200
+# is forbidden and thus, for example, hs-t100-1 cannot reach hs-t200-3 and vice
+# versa.
+#
+# Routers rt-1 and rt-2 implement IPv6 L3 VPN services leveraging the SRv6
+# architecture. The key components for such VPNs are: a) SRv6 Encap behavior,
+# b) SRv6 End.DT6 behavior and c) VRF.
+#
+# To explain how an IPv6 L3 VPN based on SRv6 works, let us briefly consider an
+# example where, within the same domain of tenant 100, the host hs-t100-1 pings
+# the host hs-t100-2.
+#
+# First of all, L2 reachability of the host hs-t100-2 is taken into account by
+# the router rt-1 which acts as a ndp proxy.
+#
+# When the host hs-t100-1 sends an IPv6 packet destined to hs-t100-2, the
+# router rt-1 receives the packet on the internal veth-t100 interface. Such
+# interface is enslaved to the VRF vrf-100 whose associated table contains the
+# SRv6 Encap route for encapsulating any IPv6 packet in a IPv6 plus the Segment
+# Routing Header (SRH) packet. This packet is sent through the (IPv6) core
+# network up to the router rt-2 that receives it on veth0 interface.
+#
+# The rt-2 router uses the 'localsid' routing table to process incoming
+# IPv6+SRH packets which belong to the VPN of the tenant 100. For each of these
+# packets, the SRv6 End.DT6 behavior removes the outer IPv6+SRH headers and
+# performs the lookup on the vrf-100 table using the destination address of
+# the decapsulated IPv6 packet. Afterwards, the packet is sent to the host
+# hs-t100-2 through the veth-t100 interface.
+#
+# The ping response follows the same processing but this time the role of rt-1
+# and rt-2 are swapped.
+#
+# Of course, the IPv6 L3 VPN for tenant 200 works exactly as the IPv6 L3 VPN
+# for tenant 100. In this case, only hosts hs-t200-3 and hs-t200-4 are able to
+# connect with each other.
+#
+#
+# +-------------------+ +-------------------+
+# | | | |
+# | hs-t100-1 netns | | hs-t100-2 netns |
+# | | | |
+# | +-------------+ | | +-------------+ |
+# | | veth0 | | | | veth0 | |
+# | | cafe::1/64 | | | | cafe::2/64 | |
+# | +-------------+ | | +-------------+ |
+# | . | | . |
+# +-------------------+ +-------------------+
+# . .
+# . .
+# . .
+# +-----------------------------------+ +-----------------------------------+
+# | . | | . |
+# | +---------------+ | | +---------------- |
+# | | veth-t100 | | | | veth-t100 | |
+# | | cafe::254/64 | +----------+ | | +----------+ | cafe::254/64 | |
+# | +-------+-------+ | localsid | | | | localsid | +-------+-------- |
+# | | | table | | | | table | | |
+# | +----+----+ +----------+ | | +----------+ +----+----+ |
+# | | vrf-100 | | | | vrf-100 | |
+# | +---------+ +------------+ | | +------------+ +---------+ |
+# | | veth0 | | | | veth0 | |
+# | | fd00::1/64 |.|...|.| fd00::2/64 | |
+# | +---------+ +------------+ | | +------------+ +---------+ |
+# | | vrf-200 | | | | vrf-200 | |
+# | +----+----+ | | +----+----+ |
+# | | | | | |
+# | +-------+-------+ | | +-------+-------- |
+# | | veth-t200 | | | | veth-t200 | |
+# | | cafe::254/64 | | | | cafe::254/64 | |
+# | +---------------+ rt-1 netns | | rt-2 netns +---------------- |
+# | . | | . |
+# +-----------------------------------+ +-----------------------------------+
+# . .
+# . .
+# . .
+# . .
+# +-------------------+ +-------------------+
+# | . | | . |
+# | +-------------+ | | +-------------+ |
+# | | veth0 | | | | veth0 | |
+# | | cafe::3/64 | | | | cafe::4/64 | |
+# | +-------------+ | | +-------------+ |
+# | | | |
+# | hs-t200-3 netns | | hs-t200-4 netns |
+# | | | |
+# +-------------------+ +-------------------+
+#
+#
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
+# | Network configuration |
+# ~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+# rt-1: localsid table (table 90)
+# +-------------------------------------------------+
+# |SID |Action |
+# +-------------------------------------------------+
+# |fc00:21:100::6006|apply SRv6 End.DT6 vrftable 100|
+# +-------------------------------------------------+
+# |fc00:21:200::6006|apply SRv6 End.DT6 vrftable 200|
+# +-------------------------------------------------+
+#
+# rt-1: VRF tenant 100 (table 100)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |cafe::2 |apply seg6 encap segs fc00:12:100::6006|
+# +---------------------------------------------------+
+# |cafe::/64 |forward to dev veth_t100 |
+# +---------------------------------------------------+
+#
+# rt-1: VRF tenant 200 (table 200)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |cafe::4 |apply seg6 encap segs fc00:12:200::6006|
+# +---------------------------------------------------+
+# |cafe::/64 |forward to dev veth_t200 |
+# +---------------------------------------------------+
+#
+#
+# rt-2: localsid table (table 90)
+# +-------------------------------------------------+
+# |SID |Action |
+# +-------------------------------------------------+
+# |fc00:12:100::6006|apply SRv6 End.DT6 vrftable 100|
+# +-------------------------------------------------+
+# |fc00:12:200::6006|apply SRv6 End.DT6 vrftable 200|
+# +-------------------------------------------------+
+#
+# rt-2: VRF tenant 100 (table 100)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |cafe::1 |apply seg6 encap segs fc00:21:100::6006|
+# +---------------------------------------------------+
+# |cafe::/64 |forward to dev veth_t100 |
+# +---------------------------------------------------+
+#
+# rt-2: VRF tenant 200 (table 200)
+# +---------------------------------------------------+
+# |host |Action |
+# +---------------------------------------------------+
+# |cafe::3 |apply seg6 encap segs fc00:21:200::6006|
+# +---------------------------------------------------+
+# |cafe::/64 |forward to dev veth_t200 |
+# +---------------------------------------------------+
+#
+
+readonly LOCALSID_TABLE_ID=90
+readonly IPv6_RT_NETWORK=fd00
+readonly IPv6_HS_NETWORK=cafe
+readonly VPN_LOCATOR_SERVICE=fc00
+PING_TIMEOUT_SEC=4
+
+ret=0
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+
+log_test()
+{
+ local rc=$1
+ local expected=$2
+ local msg="$3"
+
+ if [ ${rc} -eq ${expected} ]; then
+ nsuccess=$((nsuccess+1))
+ printf "\n TEST: %-60s [ OK ]\n" "${msg}"
+ else
+ ret=1
+ nfail=$((nfail+1))
+ printf "\n TEST: %-60s [FAIL]\n" "${msg}"
+ if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
+ echo
+ echo "hit enter to continue, 'q' to quit"
+ read a
+ [ "$a" = "q" ] && exit 1
+ fi
+ fi
+}
+
+print_log_test_results()
+{
+ if [ "$TESTS" != "none" ]; then
+ printf "\nTests passed: %3d\n" ${nsuccess}
+ printf "Tests failed: %3d\n" ${nfail}
+ fi
+}
+
+log_section()
+{
+ echo
+ echo "################################################################################"
+ echo "TEST SECTION: $*"
+ echo "################################################################################"
+}
+
+cleanup()
+{
+ ip link del veth-rt-1 2>/dev/null || true
+ ip link del veth-rt-2 2>/dev/null || true
+
+ # destroy routers rt-* and hosts hs-*
+ for ns in $(ip netns show | grep -E 'rt-*|hs-*'); do
+ ip netns del ${ns} || true
+ done
+}
+
+# Setup the basic networking for the routers
+setup_rt_networking()
+{
+ local rt=$1
+ local nsname=rt-${rt}
+
+ ip netns add ${nsname}
+ ip link set veth-rt-${rt} netns ${nsname}
+ ip -netns ${nsname} link set veth-rt-${rt} name veth0
+
+ ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
+ ip netns exec ${nsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+ ip -netns ${nsname} addr add ${IPv6_RT_NETWORK}::${rt}/64 dev veth0 nodad
+ ip -netns ${nsname} link set veth0 up
+ ip -netns ${nsname} link set lo up
+
+ ip netns exec ${nsname} sysctl -wq net.ipv6.conf.all.forwarding=1
+}
+
+setup_hs()
+{
+ local hs=$1
+ local rt=$2
+ local tid=$3
+ local hsname=hs-t${tid}-${hs}
+ local rtname=rt-${rt}
+ local rtveth=veth-t${tid}
+
+ # set the networking for the host
+ ip netns add ${hsname}
+
+ ip netns exec ${hsname} sysctl -wq net.ipv6.conf.all.accept_dad=0
+ ip netns exec ${hsname} sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+ ip -netns ${hsname} link add veth0 type veth peer name ${rtveth}
+ ip -netns ${hsname} link set ${rtveth} netns ${rtname}
+ ip -netns ${hsname} addr add ${IPv6_HS_NETWORK}::${hs}/64 dev veth0 nodad
+ ip -netns ${hsname} link set veth0 up
+ ip -netns ${hsname} link set lo up
+
+ # configure the VRF for the tenant X on the router which is directly
+ # connected to the source host.
+ ip -netns ${rtname} link add vrf-${tid} type vrf table ${tid}
+ ip -netns ${rtname} link set vrf-${tid} up
+
+ ip netns exec ${rtname} sysctl -wq net.ipv6.conf.all.accept_dad=0
+ ip netns exec ${rtname} sysctl -wq net.ipv6.conf.default.accept_dad=0
+
+ # enslave the veth-tX interface to the vrf-X in the access router
+ ip -netns ${rtname} link set ${rtveth} master vrf-${tid}
+ ip -netns ${rtname} addr add ${IPv6_HS_NETWORK}::254/64 dev ${rtveth} nodad
+ ip -netns ${rtname} link set ${rtveth} up
+
+ ip netns exec ${rtname} sysctl -wq net.ipv6.conf.${rtveth}.proxy_ndp=1
+
+ ip netns exec ${rtname} sh -c "echo 1 > /proc/sys/net/vrf/strict_mode"
+}
+
+setup_vpn_config()
+{
+ local hssrc=$1
+ local rtsrc=$2
+ local hsdst=$3
+ local rtdst=$4
+ local tid=$5
+
+ local hssrc_name=hs-t${tid}-${hssrc}
+ local hsdst_name=hs-t${tid}-${hsdst}
+ local rtsrc_name=rt-${rtsrc}
+ local rtdst_name=rt-${rtdst}
+ local rtveth=veth-t${tid}
+ local vpn_sid=${VPN_LOCATOR_SERVICE}:${hssrc}${hsdst}:${tid}::6006
+
+ ip -netns ${rtsrc_name} -6 neigh add proxy ${IPv6_HS_NETWORK}::${hsdst} dev ${rtveth}
+
+ # set the encap route for encapsulating packets which arrive from the
+ # host hssrc and destined to the access router rtsrc.
+ ip -netns ${rtsrc_name} -6 route add ${IPv6_HS_NETWORK}::${hsdst}/128 vrf vrf-${tid} \
+ encap seg6 mode encap segs ${vpn_sid} dev veth0
+ ip -netns ${rtsrc_name} -6 route add ${vpn_sid}/128 vrf vrf-${tid} \
+ via fd00::${rtdst} dev veth0
+
+ # set the decap route for decapsulating packets which arrive from
+ # the rtdst router and destined to the hsdst host.
+ ip -netns ${rtdst_name} -6 route add ${vpn_sid}/128 table ${LOCALSID_TABLE_ID} \
+ encap seg6local action End.DT6 vrftable ${tid} dev vrf-${tid}
+
+ # all sids for VPNs start with a common locator which is fc00::/16.
+ # Routes for handling the SRv6 End.DT6 behavior instances are grouped
+ # together in the 'localsid' table.
+ #
+ # NOTE: added only once
+ if [ -z "$(ip -netns ${rtdst_name} -6 rule show | \
+ grep "to ${VPN_LOCATOR_SERVICE}::/16 lookup ${LOCALSID_TABLE_ID}")" ]; then
+ ip -netns ${rtdst_name} -6 rule add \
+ to ${VPN_LOCATOR_SERVICE}::/16 \
+ lookup ${LOCALSID_TABLE_ID} prio 999
+ fi
+}
+
+setup()
+{
+ ip link add veth-rt-1 type veth peer name veth-rt-2
+ # setup the networking for router rt-1 and router rt-2
+ setup_rt_networking 1
+ setup_rt_networking 2
+
+ # setup two hosts for the tenant 100.
+ # - host hs-1 is directly connected to the router rt-1;
+ # - host hs-2 is directly connected to the router rt-2.
+ setup_hs 1 1 100 #args: host router tenant
+ setup_hs 2 2 100
+
+ # setup two hosts for the tenant 200
+ # - host hs-3 is directly connected to the router rt-1;
+ # - host hs-4 is directly connected to the router rt-2.
+ setup_hs 3 1 200
+ setup_hs 4 2 200
+
+ # setup the IPv6 L3 VPN which connects the host hs-t100-1 and host
+ # hs-t100-2 within the same tenant 100.
+ setup_vpn_config 1 1 2 2 100 #args: src_host src_router dst_host dst_router tenant
+ setup_vpn_config 2 2 1 1 100
+
+ # setup the IPv6 L3 VPN which connects the host hs-t200-3 and host
+ # hs-t200-4 within the same tenant 200.
+ setup_vpn_config 3 1 4 2 200
+ setup_vpn_config 4 2 3 1 200
+}
+
+check_rt_connectivity()
+{
+ local rtsrc=$1
+ local rtdst=$2
+
+ ip netns exec rt-${rtsrc} ping -c 1 -W 1 ${IPv6_RT_NETWORK}::${rtdst} \
+ >/dev/null 2>&1
+}
+
+check_and_log_rt_connectivity()
+{
+ local rtsrc=$1
+ local rtdst=$2
+
+ check_rt_connectivity ${rtsrc} ${rtdst}
+ log_test $? 0 "Routers connectivity: rt-${rtsrc} -> rt-${rtdst}"
+}
+
+check_hs_connectivity()
+{
+ local hssrc=$1
+ local hsdst=$2
+ local tid=$3
+
+ ip netns exec hs-t${tid}-${hssrc} ping -c 1 -W ${PING_TIMEOUT_SEC} \
+ ${IPv6_HS_NETWORK}::${hsdst} >/dev/null 2>&1
+}
+
+check_and_log_hs_connectivity()
+{
+ local hssrc=$1
+ local hsdst=$2
+ local tid=$3
+
+ check_hs_connectivity ${hssrc} ${hsdst} ${tid}
+ log_test $? 0 "Hosts connectivity: hs-t${tid}-${hssrc} -> hs-t${tid}-${hsdst} (tenant ${tid})"
+}
+
+check_and_log_hs_isolation()
+{
+ local hssrc=$1
+ local tidsrc=$2
+ local hsdst=$3
+ local tiddst=$4
+
+ check_hs_connectivity ${hssrc} ${hsdst} ${tidsrc}
+ # NOTE: ping should fail
+ log_test $? 1 "Hosts isolation: hs-t${tidsrc}-${hssrc} -X-> hs-t${tiddst}-${hsdst}"
+}
+
+
+check_and_log_hs2gw_connectivity()
+{
+ local hssrc=$1
+ local tid=$2
+
+ check_hs_connectivity ${hssrc} 254 ${tid}
+ log_test $? 0 "Hosts connectivity: hs-t${tid}-${hssrc} -> gw (tenant ${tid})"
+}
+
+router_tests()
+{
+ log_section "IPv6 routers connectivity test"
+
+ check_and_log_rt_connectivity 1 2
+ check_and_log_rt_connectivity 2 1
+}
+
+host2gateway_tests()
+{
+ log_section "IPv6 connectivity test among hosts and gateway"
+
+ check_and_log_hs2gw_connectivity 1 100
+ check_and_log_hs2gw_connectivity 2 100
+
+ check_and_log_hs2gw_connectivity 3 200
+ check_and_log_hs2gw_connectivity 4 200
+}
+
+host_vpn_tests()
+{
+ log_section "SRv6 VPN connectivity test among hosts in the same tenant"
+
+ check_and_log_hs_connectivity 1 2 100
+ check_and_log_hs_connectivity 2 1 100
+
+ check_and_log_hs_connectivity 3 4 200
+ check_and_log_hs_connectivity 4 3 200
+}
+
+host_vpn_isolation_tests()
+{
+ local i
+ local j
+ local k
+ local tmp
+ local l1="1 2"
+ local l2="3 4"
+ local t1=100
+ local t2=200
+
+ log_section "SRv6 VPN isolation test among hosts in different tentants"
+
+ for k in 0 1; do
+ for i in ${l1}; do
+ for j in ${l2}; do
+ check_and_log_hs_isolation ${i} ${t1} ${j} ${t2}
+ done
+ done
+
+ # let us test the reverse path
+ tmp="${l1}"; l1="${l2}"; l2="${tmp}"
+ tmp=${t1}; t1=${t2}; t2=${tmp}
+ done
+}
+
+if [ "$(id -u)" -ne 0 ];then
+ echo "SKIP: Need root privileges"
+ exit 0
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+ echo "SKIP: Could not run test without ip tool"
+ exit 0
+fi
+
+modprobe vrf &>/dev/null
+if [ ! -e /proc/sys/net/vrf/strict_mode ]; then
+ echo "SKIP: vrf sysctl does not exist"
+ exit 0
+fi
+
+cleanup &>/dev/null
+
+setup
+
+router_tests
+host2gateway_tests
+host_vpn_tests
+host_vpn_isolation_tests
+
+print_log_test_results
+
+cleanup &>/dev/null
+
+exit ${ret}
diff --git a/tools/testing/selftests/net/test_vxlan_under_vrf.sh b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
index 09f9ed92cbe4..534c8b7699ab 100755
--- a/tools/testing/selftests/net/test_vxlan_under_vrf.sh
+++ b/tools/testing/selftests/net/test_vxlan_under_vrf.sh
@@ -50,7 +50,7 @@ cleanup() {
ip link del veth-tap 2>/dev/null || true
for ns in hv-1 hv-2 vm-1 vm-2; do
- ip netns del $ns || true
+ ip netns del $ns 2>/dev/null || true
done
}
diff --git a/tools/testing/selftests/net/timestamping.c b/tools/testing/selftests/net/timestamping.c
index f4bb4fef0f39..21091be70688 100644
--- a/tools/testing/selftests/net/timestamping.c
+++ b/tools/testing/selftests/net/timestamping.c
@@ -59,7 +59,8 @@ static void usage(const char *error)
" SOF_TIMESTAMPING_SOFTWARE - request reporting of software time stamps\n"
" SOF_TIMESTAMPING_RAW_HARDWARE - request reporting of raw HW time stamps\n"
" SIOCGSTAMP - check last socket time stamp\n"
- " SIOCGSTAMPNS - more accurate socket time stamp\n");
+ " SIOCGSTAMPNS - more accurate socket time stamp\n"
+ " PTPV2 - use PTPv2 messages\n");
exit(1);
}
@@ -115,13 +116,28 @@ static const unsigned char sync[] = {
0x00, 0x00, 0x00, 0x00
};
-static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len)
+static const unsigned char sync_v2[] = {
+ 0x00, 0x02, 0x00, 0x2C,
+ 0x00, 0x00, 0x02, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0xFF,
+ 0xFE, 0x00, 0x00, 0x00,
+ 0x00, 0x01, 0x00, 0x01,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+ 0x00, 0x00, 0x00, 0x00,
+};
+
+static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len, int ptpv2)
{
+ size_t sync_len = ptpv2 ? sizeof(sync_v2) : sizeof(sync);
+ const void *sync_p = ptpv2 ? sync_v2 : sync;
struct timeval now;
int res;
- res = sendto(sock, sync, sizeof(sync), 0,
- addr, addr_len);
+ res = sendto(sock, sync_p, sync_len, 0, addr, addr_len);
gettimeofday(&now, 0);
if (res < 0)
printf("%s: %s\n", "send", strerror(errno));
@@ -134,9 +150,11 @@ static void sendpacket(int sock, struct sockaddr *addr, socklen_t addr_len)
static void printpacket(struct msghdr *msg, int res,
char *data,
int sock, int recvmsg_flags,
- int siocgstamp, int siocgstampns)
+ int siocgstamp, int siocgstampns, int ptpv2)
{
struct sockaddr_in *from_addr = (struct sockaddr_in *)msg->msg_name;
+ size_t sync_len = ptpv2 ? sizeof(sync_v2) : sizeof(sync);
+ const void *sync_p = ptpv2 ? sync_v2 : sync;
struct cmsghdr *cmsg;
struct timeval tv;
struct timespec ts;
@@ -210,10 +228,9 @@ static void printpacket(struct msghdr *msg, int res,
"probably SO_EE_ORIGIN_TIMESTAMPING"
#endif
);
- if (res < sizeof(sync))
+ if (res < sync_len)
printf(" => truncated data?!");
- else if (!memcmp(sync, data + res - sizeof(sync),
- sizeof(sync)))
+ else if (!memcmp(sync_p, data + res - sync_len, sync_len))
printf(" => GOT OUR DATA BACK (HURRAY!)");
break;
}
@@ -257,7 +274,7 @@ static void printpacket(struct msghdr *msg, int res,
}
static void recvpacket(int sock, int recvmsg_flags,
- int siocgstamp, int siocgstampns)
+ int siocgstamp, int siocgstampns, int ptpv2)
{
char data[256];
struct msghdr msg;
@@ -288,7 +305,7 @@ static void recvpacket(int sock, int recvmsg_flags,
} else {
printpacket(&msg, res, data,
sock, recvmsg_flags,
- siocgstamp, siocgstampns);
+ siocgstamp, siocgstampns, ptpv2);
}
}
@@ -300,6 +317,7 @@ int main(int argc, char **argv)
int siocgstamp = 0;
int siocgstampns = 0;
int ip_multicast_loop = 0;
+ int ptpv2 = 0;
char *interface;
int i;
int enabled = 1;
@@ -335,6 +353,8 @@ int main(int argc, char **argv)
siocgstampns = 1;
else if (!strcasecmp(argv[i], "IP_MULTICAST_LOOP"))
ip_multicast_loop = 1;
+ else if (!strcasecmp(argv[i], "PTPV2"))
+ ptpv2 = 1;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_HARDWARE"))
so_timestamping_flags |= SOF_TIMESTAMPING_TX_HARDWARE;
else if (!strcasecmp(argv[i], "SOF_TIMESTAMPING_TX_SOFTWARE"))
@@ -369,6 +389,7 @@ int main(int argc, char **argv)
HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF;
hwconfig.rx_filter =
(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;
if (ioctl(sock, SIOCSHWTSTAMP, &hwtstamp) < 0) {
@@ -496,16 +517,16 @@ int main(int argc, char **argv)
printf("has error\n");
recvpacket(sock, 0,
siocgstamp,
- siocgstampns);
+ siocgstampns, ptpv2);
recvpacket(sock, MSG_ERRQUEUE,
siocgstamp,
- siocgstampns);
+ siocgstampns, ptpv2);
}
} else {
/* write one packet */
sendpacket(sock,
(struct sockaddr *)&addr,
- sizeof(addr));
+ sizeof(addr), ptpv2);
next.tv_sec += 5;
continue;
}
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index b599f1fa99b5..cb0d1890a860 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -103,32 +103,58 @@ FIXTURE(tls)
FIXTURE_VARIANT(tls)
{
- unsigned int tls_version;
+ u16 tls_version;
+ u16 cipher_type;
};
-FIXTURE_VARIANT_ADD(tls, 12)
+FIXTURE_VARIANT_ADD(tls, 12_gcm)
{
.tls_version = TLS_1_2_VERSION,
+ .cipher_type = TLS_CIPHER_AES_GCM_128,
};
-FIXTURE_VARIANT_ADD(tls, 13)
+FIXTURE_VARIANT_ADD(tls, 13_gcm)
{
.tls_version = TLS_1_3_VERSION,
+ .cipher_type = TLS_CIPHER_AES_GCM_128,
+};
+
+FIXTURE_VARIANT_ADD(tls, 12_chacha)
+{
+ .tls_version = TLS_1_2_VERSION,
+ .cipher_type = TLS_CIPHER_CHACHA20_POLY1305,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_chacha)
+{
+ .tls_version = TLS_1_3_VERSION,
+ .cipher_type = TLS_CIPHER_CHACHA20_POLY1305,
};
FIXTURE_SETUP(tls)
{
- struct tls12_crypto_info_aes_gcm_128 tls12;
+ union tls_crypto_context tls12;
struct sockaddr_in addr;
socklen_t len;
int sfd, ret;
+ size_t tls12_sz;
self->notls = false;
len = sizeof(addr);
memset(&tls12, 0, sizeof(tls12));
tls12.info.version = variant->tls_version;
- tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+ tls12.info.cipher_type = variant->cipher_type;
+ switch (variant->cipher_type) {
+ case TLS_CIPHER_CHACHA20_POLY1305:
+ tls12_sz = sizeof(tls12_crypto_info_chacha20_poly1305);
+ break;
+ case TLS_CIPHER_AES_GCM_128:
+ tls12_sz = sizeof(tls12_crypto_info_aes_gcm_128);
+ break;
+ default:
+ tls12_sz = 0;
+ }
addr.sin_family = AF_INET;
addr.sin_addr.s_addr = htonl(INADDR_ANY);
@@ -156,7 +182,7 @@ FIXTURE_SETUP(tls)
if (!self->notls) {
ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
- sizeof(tls12));
+ tls12_sz);
ASSERT_EQ(ret, 0);
}
@@ -169,7 +195,7 @@ FIXTURE_SETUP(tls)
ASSERT_EQ(ret, 0);
ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
- sizeof(tls12));
+ tls12_sz);
ASSERT_EQ(ret, 0);
}
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
index db3d4a8b5a4c..76a24052f4b4 100644
--- a/tools/testing/selftests/net/udpgso_bench_rx.c
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -113,6 +113,9 @@ static void do_poll(int fd, int timeout_ms)
interrupted = true;
break;
}
+
+ /* no events and more time to wait, do poll again */
+ continue;
}
if (pfd.revents != POLLIN)
error(1, errno, "poll: 0x%x expected 0x%x\n",
diff --git a/tools/testing/selftests/openat2/openat2_test.c b/tools/testing/selftests/openat2/openat2_test.c
index b386367c606b..381d874cce99 100644
--- a/tools/testing/selftests/openat2/openat2_test.c
+++ b/tools/testing/selftests/openat2/openat2_test.c
@@ -155,7 +155,7 @@ struct flag_test {
int err;
};
-#define NUM_OPENAT2_FLAG_TESTS 23
+#define NUM_OPENAT2_FLAG_TESTS 24
void test_openat2_flags(void)
{
@@ -210,6 +210,12 @@ void test_openat2_flags(void)
.how.flags = O_TMPFILE | O_RDWR,
.how.mode = 0x0000A00000000000ULL, .err = -EINVAL },
+ /* ->resolve flags must not conflict. */
+ { .name = "incompatible resolve flags (BENEATH | IN_ROOT)",
+ .how.flags = O_RDONLY,
+ .how.resolve = RESOLVE_BENEATH | RESOLVE_IN_ROOT,
+ .err = -EINVAL },
+
/* ->resolve must only contain RESOLVE_* flags. */
{ .name = "invalid how.resolve and O_RDONLY",
.how.flags = O_RDONLY,
diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh
index 0e4c0b2eb7f0..80ae7f08b363 100755
--- a/tools/testing/selftests/rcutorture/bin/console-badness.sh
+++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh
@@ -13,4 +13,5 @@
egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' |
grep -v 'ODEBUG: ' |
grep -v 'This means that this is a DEBUG kernel and it is' |
-grep -v 'Warning: unable to open an initial console'
+grep -v 'Warning: unable to open an initial console' |
+grep -v 'NOHZ tick-stop error: Non-RCU local softirq work is pending, handler'
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 51f3464b96d3..82663495fb38 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -169,6 +169,7 @@ identify_qemu () {
# Output arguments for the qemu "-append" string based on CPU type
# and the TORTURE_QEMU_INTERACTIVE environment variable.
identify_qemu_append () {
+ echo debug_boot_weak_hash
local console=ttyS0
case "$1" in
qemu-system-x86_64|qemu-system-i386)
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
index 6e65c134e5f1..370406bbfeed 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-check-branches.sh
@@ -52,8 +52,7 @@ echo Results directory: $resdir/$ds
KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM
PATH=${KVM}/bin:$PATH; export PATH
. functions.sh
-cpus="`identify_qemu_vcpus`"
-echo Using up to $cpus CPUs.
+echo Using all `identify_qemu_vcpus` CPUs.
# Each pass through this loop does one command-line argument.
for gitbr in $@
@@ -74,7 +73,7 @@ do
# Test the specified commit.
git checkout $i > $resdir/$ds/$idir/git-checkout.out 2>&1
echo git checkout return code: $? "(Commit $ntry: $i)"
- kvm.sh --cpus $cpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1
+ kvm.sh --allcpus --duration 3 --trust-make > $resdir/$ds/$idir/kvm.sh.out 2>&1
ret=$?
echo kvm.sh return code $ret for commit $i from branch $gitbr
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh
index aa745152a525..b582113178ac 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuscale.sh
@@ -32,7 +32,7 @@ sed -e 's/^\[[^]]*]//' < $i/console.log |
awk '
/-scale: .* gps: .* batches:/ {
ngps = $9;
- nbatches = $11;
+ nbatches = 1;
}
/-scale: .*writer-duration/ {
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 6dc2b49b85ea..3cd03d01857c 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -206,7 +206,10 @@ do
kruntime=`gawk 'BEGIN { print systime() - '"$kstarttime"' }' < /dev/null`
if test -z "$qemu_pid" || kill -0 "$qemu_pid" > /dev/null 2>&1
then
- if test $kruntime -ge $seconds -o -f "$TORTURE_STOPFILE"
+ if test -n "$TORTURE_KCONFIG_GDB_ARG"
+ then
+ :
+ elif test $kruntime -ge $seconds || test -f "$TORTURE_STOPFILE"
then
break;
fi
@@ -223,6 +226,20 @@ do
echo "ps -fp $killpid" >> $resdir/Warnings 2>&1
ps -fp $killpid >> $resdir/Warnings 2>&1
fi
+ # Reduce probability of PID reuse by allowing a one-minute buffer
+ if test $((kruntime + 60)) -lt $seconds && test -s "$resdir/../jitter_pids"
+ then
+ awk < "$resdir/../jitter_pids" '
+ NF > 0 {
+ pidlist = pidlist " " $1;
+ n++;
+ }
+ END {
+ if (n > 0) {
+ print "kill " pidlist;
+ }
+ }' | sh
+ fi
else
echo ' ---' `date`: "Kernel done"
fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 6eb1d3f6524d..45d07b7b69f5 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -58,7 +58,7 @@ usage () {
echo " --datestamp string"
echo " --defconfig string"
echo " --dryrun sched|script"
- echo " --duration minutes"
+ echo " --duration minutes | <seconds>s | <hours>h | <days>d"
echo " --gdb"
echo " --help"
echo " --interactive"
@@ -93,7 +93,7 @@ do
TORTURE_BOOT_IMAGE="$2"
shift
;;
- --buildonly)
+ --buildonly|--build-only)
TORTURE_BUILDONLY=1
;;
--configs|--config)
@@ -128,8 +128,20 @@ do
shift
;;
--duration)
- checkarg --duration "(minutes)" $# "$2" '^[0-9]*$' '^error'
- dur=$(($2*60))
+ checkarg --duration "(minutes)" $# "$2" '^[0-9][0-9]*\(s\|m\|h\|d\|\)$' '^error'
+ mult=60
+ if echo "$2" | grep -q 's$'
+ then
+ mult=1
+ elif echo "$2" | grep -q 'h$'
+ then
+ mult=3600
+ elif echo "$2" | grep -q 'd$'
+ then
+ mult=86400
+ fi
+ ts=`echo $2 | sed -e 's/[smhd]$//'`
+ dur=$(($ts*mult))
shift
;;
--gdb)
@@ -148,7 +160,7 @@ do
jitter="$2"
shift
;;
- --kconfig)
+ --kconfig|--kconfigs)
checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$'
TORTURE_KCONFIG_ARG="$2"
shift
@@ -159,7 +171,7 @@ do
--kcsan)
TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_KCSAN_INTERRUPT_WATCHER=y"; export TORTURE_KCONFIG_KCSAN_ARG
;;
- --kmake-arg)
+ --kmake-arg|--kmake-args)
checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$'
TORTURE_KMAKE_ARG="$2"
shift
@@ -459,8 +471,11 @@ function dump(first, pastlast, batchnum)
print "if test -n \"$needqemurun\""
print "then"
print "\techo ---- Starting kernels. `date` | tee -a " rd "log";
- for (j = 0; j < njitter; j++)
+ print "\techo > " rd "jitter_pids"
+ for (j = 0; j < njitter; j++) {
print "\tjitter.sh " j " " dur " " ja[2] " " ja[3] "&"
+ print "\techo $! >> " rd "jitter_pids"
+ }
print "\twait"
print "\techo ---- All kernel runs complete. `date` | tee -a " rd "log";
print "else"
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index e03338091a06..263b1be50008 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -133,7 +133,7 @@ then
then
summary="$summary Warnings: $n_warn"
fi
- n_bugs=`egrep -c 'BUG|Oops:' $file`
+ n_bugs=`egrep -c '\bBUG|Oops:' $file`
if test "$n_bugs" -ne 0
then
summary="$summary Bugs: $n_bugs"
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t
index 6c78022c8cd8..d6557c38dfe4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-t
@@ -4,7 +4,8 @@ CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
#CHECK#CONFIG_TINY_SRCU=y
CONFIG_RCU_TRACE=n
-CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_DEBUG_ATOMIC_SLEEP=y
#CHECK#CONFIG_PREEMPT_COUNT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
index c15ada821e45..6bc24e99862f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-u
@@ -4,7 +4,6 @@ CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
#CHECK#CONFIG_TINY_SRCU=y
CONFIG_RCU_TRACE=n
-CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_PROVE_LOCKING=y
+CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_PREEMPT_COUNT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index 12e7661b86f5..34c8ff5a12f2 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -4,8 +4,8 @@ CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
-CONFIG_DEBUG_LOCK_ALLOC=y
-CONFIG_PROVE_LOCKING=y
-#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+#CHECK#CONFIG_PROVE_RCU=n
CONFIG_TASKS_TRACE_RCU_READ_MB=y
CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
index b69ed6673c41..77541eeb4e9f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
@@ -4,8 +4,8 @@ CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=n
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=y
-CONFIG_DEBUG_LOCK_ALLOC=n
-CONFIG_PROVE_LOCKING=n
-#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_DEBUG_LOCK_ALLOC=y
+CONFIG_PROVE_LOCKING=y
+#CHECK#CONFIG_PROVE_RCU=y
CONFIG_TASKS_TRACE_RCU_READ_MB=n
CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon
index 87caa0e932c7..90942bb5bebc 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon
@@ -1,2 +1,5 @@
CONFIG_RCU_SCALE_TEST=y
CONFIG_PRINTK_TIME=y
+CONFIG_TASKS_RCU_GENERIC=y
+CONFIG_TASKS_RCU=y
+CONFIG_TASKS_TRACE_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
new file mode 100644
index 000000000000..e6baa2fbaeb3
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01
@@ -0,0 +1,15 @@
+CONFIG_SMP=y
+CONFIG_PREEMPT_NONE=y
+CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT=n
+CONFIG_HZ_PERIODIC=n
+CONFIG_NO_HZ_IDLE=y
+CONFIG_NO_HZ_FULL=n
+CONFIG_RCU_FAST_NO_HZ=n
+CONFIG_RCU_NOCB_CPU=n
+CONFIG_DEBUG_LOCK_ALLOC=n
+CONFIG_PROVE_LOCKING=n
+CONFIG_RCU_BOOST=n
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
+CONFIG_RCU_EXPERT=y
+CONFIG_RCU_TRACE=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01.boot b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01.boot
new file mode 100644
index 000000000000..af0aff1457a4
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TRACE01.boot
@@ -0,0 +1 @@
+rcuscale.scale_type=tasks-tracing
diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 384589095864..699ad5f93c34 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -1133,6 +1133,8 @@ static int set_signal_handler(void)
return ret;
}
+/* Test MEMBARRIER_CMD_PRIVATE_RESTART_RSEQ_ON_CPU membarrier command. */
+#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
struct test_membarrier_thread_args {
int stop;
intptr_t percpu_list_ptr;
@@ -1286,8 +1288,6 @@ void *test_membarrier_manager_thread(void *arg)
return NULL;
}
-/* Test MEMBARRIER_CMD_PRIVATE_RESTART_RSEQ_ON_CPU membarrier command. */
-#ifdef RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV
void test_membarrier(void)
{
const int num_threads = opt_threads;
diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh
index 609a4ef9300e..97165a83df63 100755
--- a/tools/testing/selftests/run_kselftest.sh
+++ b/tools/testing/selftests/run_kselftest.sh
@@ -48,7 +48,7 @@ while true; do
-l | --list)
echo "$available"
exit 0 ;;
- -n | --dry-run)
+ -d | --dry-run)
dryrun="echo"
shift ;;
-h | --help)
diff --git a/tools/testing/selftests/seccomp/config b/tools/testing/selftests/seccomp/config
index 64c19d8eba79..ad431a5178fb 100644
--- a/tools/testing/selftests/seccomp/config
+++ b/tools/testing/selftests/seccomp/config
@@ -1,3 +1,4 @@
+CONFIG_PID_NS=y
CONFIG_SECCOMP=y
CONFIG_SECCOMP_FILTER=y
CONFIG_USER_NS=y
diff --git a/tools/testing/selftests/seccomp/seccomp_benchmark.c b/tools/testing/selftests/seccomp/seccomp_benchmark.c
index 91f5a89cadac..fcc806585266 100644
--- a/tools/testing/selftests/seccomp/seccomp_benchmark.c
+++ b/tools/testing/selftests/seccomp/seccomp_benchmark.c
@@ -4,12 +4,16 @@
*/
#define _GNU_SOURCE
#include <assert.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <unistd.h>
#include <linux/filter.h>
#include <linux/seccomp.h>
+#include <sys/param.h>
#include <sys/prctl.h>
#include <sys/syscall.h>
#include <sys/types.h>
@@ -70,18 +74,74 @@ unsigned long long calibrate(void)
return samples * seconds;
}
+bool approx(int i_one, int i_two)
+{
+ double one = i_one, one_bump = one * 0.01;
+ double two = i_two, two_bump = two * 0.01;
+
+ one_bump = one + MAX(one_bump, 2.0);
+ two_bump = two + MAX(two_bump, 2.0);
+
+ /* Equal to, or within 1% or 2 digits */
+ if (one == two ||
+ (one > two && one <= two_bump) ||
+ (two > one && two <= one_bump))
+ return true;
+ return false;
+}
+
+bool le(int i_one, int i_two)
+{
+ if (i_one <= i_two)
+ return true;
+ return false;
+}
+
+long compare(const char *name_one, const char *name_eval, const char *name_two,
+ unsigned long long one, bool (*eval)(int, int), unsigned long long two)
+{
+ bool good;
+
+ printf("\t%s %s %s (%lld %s %lld): ", name_one, name_eval, name_two,
+ (long long)one, name_eval, (long long)two);
+ if (one > INT_MAX) {
+ printf("Miscalculation! Measurement went negative: %lld\n", (long long)one);
+ return 1;
+ }
+ if (two > INT_MAX) {
+ printf("Miscalculation! Measurement went negative: %lld\n", (long long)two);
+ return 1;
+ }
+
+ good = eval(one, two);
+ printf("%s\n", good ? "✔️" : "❌");
+
+ return good ? 0 : 1;
+}
+
int main(int argc, char *argv[])
{
+ struct sock_filter bitmap_filter[] = {
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, nr)),
+ BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+ };
+ struct sock_fprog bitmap_prog = {
+ .len = (unsigned short)ARRAY_SIZE(bitmap_filter),
+ .filter = bitmap_filter,
+ };
struct sock_filter filter[] = {
+ BPF_STMT(BPF_LD|BPF_W|BPF_ABS, offsetof(struct seccomp_data, args[0])),
BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
};
struct sock_fprog prog = {
.len = (unsigned short)ARRAY_SIZE(filter),
.filter = filter,
};
- long ret;
- unsigned long long samples;
- unsigned long long native, filter1, filter2;
+
+ long ret, bits;
+ unsigned long long samples, calc;
+ unsigned long long native, filter1, filter2, bitmap1, bitmap2;
+ unsigned long long entry, per_filter1, per_filter2;
printf("Current BPF sysctl settings:\n");
system("sysctl net.core.bpf_jit_enable");
@@ -101,35 +161,82 @@ int main(int argc, char *argv[])
ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
assert(ret == 0);
- /* One filter */
- ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
+ /* One filter resulting in a bitmap */
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
assert(ret == 0);
- filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
- printf("getpid RET_ALLOW 1 filter: %llu ns\n", filter1);
+ bitmap1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+ printf("getpid RET_ALLOW 1 filter (bitmap): %llu ns\n", bitmap1);
+
+ /* Second filter resulting in a bitmap */
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
+ assert(ret == 0);
- if (filter1 == native)
- printf("No overhead measured!? Try running again with more samples.\n");
+ bitmap2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+ printf("getpid RET_ALLOW 2 filters (bitmap): %llu ns\n", bitmap2);
- /* Two filters */
+ /* Third filter, can no longer be converted to bitmap */
ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog);
assert(ret == 0);
- filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
- printf("getpid RET_ALLOW 2 filters: %llu ns\n", filter2);
-
- /* Calculations */
- printf("Estimated total seccomp overhead for 1 filter: %llu ns\n",
- filter1 - native);
+ filter1 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+ printf("getpid RET_ALLOW 3 filters (full): %llu ns\n", filter1);
- printf("Estimated total seccomp overhead for 2 filters: %llu ns\n",
- filter2 - native);
+ /* Fourth filter, can not be converted to bitmap because of filter 3 */
+ ret = prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &bitmap_prog);
+ assert(ret == 0);
- printf("Estimated seccomp per-filter overhead: %llu ns\n",
- filter2 - filter1);
+ filter2 = timing(CLOCK_PROCESS_CPUTIME_ID, samples) / samples;
+ printf("getpid RET_ALLOW 4 filters (full): %llu ns\n", filter2);
+
+ /* Estimations */
+#define ESTIMATE(fmt, var, what) do { \
+ var = (what); \
+ printf("Estimated " fmt ": %llu ns\n", var); \
+ if (var > INT_MAX) \
+ goto more_samples; \
+ } while (0)
+
+ ESTIMATE("total seccomp overhead for 1 bitmapped filter", calc,
+ bitmap1 - native);
+ ESTIMATE("total seccomp overhead for 2 bitmapped filters", calc,
+ bitmap2 - native);
+ ESTIMATE("total seccomp overhead for 3 full filters", calc,
+ filter1 - native);
+ ESTIMATE("total seccomp overhead for 4 full filters", calc,
+ filter2 - native);
+ ESTIMATE("seccomp entry overhead", entry,
+ bitmap1 - native - (bitmap2 - bitmap1));
+ ESTIMATE("seccomp per-filter overhead (last 2 diff)", per_filter1,
+ filter2 - filter1);
+ ESTIMATE("seccomp per-filter overhead (filters / 4)", per_filter2,
+ (filter2 - native - entry) / 4);
+
+ printf("Expectations:\n");
+ ret |= compare("native", "≤", "1 bitmap", native, le, bitmap1);
+ bits = compare("native", "≤", "1 filter", native, le, filter1);
+ if (bits)
+ goto more_samples;
+
+ ret |= compare("per-filter (last 2 diff)", "≈", "per-filter (filters / 4)",
+ per_filter1, approx, per_filter2);
+
+ bits = compare("1 bitmapped", "≈", "2 bitmapped",
+ bitmap1 - native, approx, bitmap2 - native);
+ if (bits) {
+ printf("Skipping constant action bitmap expectations: they appear unsupported.\n");
+ goto out;
+ }
- printf("Estimated seccomp entry overhead: %llu ns\n",
- filter1 - native - (filter2 - filter1));
+ ret |= compare("entry", "≈", "1 bitmapped", entry, approx, bitmap1 - native);
+ ret |= compare("entry", "≈", "2 bitmapped", entry, approx, bitmap2 - native);
+ ret |= compare("native + entry + (per filter * 4)", "≈", "4 filters total",
+ entry + (per_filter1 * 4) + native, approx, filter2);
+ if (ret == 0)
+ goto out;
+more_samples:
+ printf("Saw unexpected benchmark result. Try running again with more samples?\n");
+out:
return 0;
}
diff --git a/tools/testing/selftests/seccomp/settings b/tools/testing/selftests/seccomp/settings
index ba4d85f74cd6..6091b45d226b 100644
--- a/tools/testing/selftests/seccomp/settings
+++ b/tools/testing/selftests/seccomp/settings
@@ -1 +1 @@
-timeout=90
+timeout=120
diff --git a/tools/testing/selftests/sgx/.gitignore b/tools/testing/selftests/sgx/.gitignore
new file mode 100644
index 000000000000..fbaf0bda9a92
--- /dev/null
+++ b/tools/testing/selftests/sgx/.gitignore
@@ -0,0 +1,2 @@
+test_sgx
+test_encl.elf
diff --git a/tools/testing/selftests/sgx/Makefile b/tools/testing/selftests/sgx/Makefile
new file mode 100644
index 000000000000..7f12d55b97f8
--- /dev/null
+++ b/tools/testing/selftests/sgx/Makefile
@@ -0,0 +1,57 @@
+top_srcdir = ../../../..
+
+include ../lib.mk
+
+.PHONY: all clean
+
+CAN_BUILD_X86_64 := $(shell ../x86/check_cc.sh $(CC) \
+ ../x86/trivial_64bit_program.c)
+
+ifndef OBJCOPY
+OBJCOPY := $(CROSS_COMPILE)objcopy
+endif
+
+INCLUDES := -I$(top_srcdir)/tools/include
+HOST_CFLAGS := -Wall -Werror -g $(INCLUDES) -fPIC -z noexecstack
+ENCL_CFLAGS := -Wall -Werror -static -nostdlib -nostartfiles -fPIC \
+ -fno-stack-protector -mrdrnd $(INCLUDES)
+
+TEST_CUSTOM_PROGS := $(OUTPUT)/test_sgx
+
+ifeq ($(CAN_BUILD_X86_64), 1)
+all: $(TEST_CUSTOM_PROGS) $(OUTPUT)/test_encl.elf
+endif
+
+$(OUTPUT)/test_sgx: $(OUTPUT)/main.o \
+ $(OUTPUT)/load.o \
+ $(OUTPUT)/sigstruct.o \
+ $(OUTPUT)/call.o \
+ $(OUTPUT)/sign_key.o
+ $(CC) $(HOST_CFLAGS) -o $@ $^ -lcrypto
+
+$(OUTPUT)/main.o: main.c
+ $(CC) $(HOST_CFLAGS) -c $< -o $@
+
+$(OUTPUT)/load.o: load.c
+ $(CC) $(HOST_CFLAGS) -c $< -o $@
+
+$(OUTPUT)/sigstruct.o: sigstruct.c
+ $(CC) $(HOST_CFLAGS) -c $< -o $@
+
+$(OUTPUT)/call.o: call.S
+ $(CC) $(HOST_CFLAGS) -c $< -o $@
+
+$(OUTPUT)/sign_key.o: sign_key.S
+ $(CC) $(HOST_CFLAGS) -c $< -o $@
+
+$(OUTPUT)/test_encl.elf: test_encl.lds test_encl.c test_encl_bootstrap.S
+ $(CC) $(ENCL_CFLAGS) -T $^ -o $@
+
+EXTRA_CLEAN := \
+ $(OUTPUT)/test_encl.elf \
+ $(OUTPUT)/load.o \
+ $(OUTPUT)/call.o \
+ $(OUTPUT)/main.o \
+ $(OUTPUT)/sigstruct.o \
+ $(OUTPUT)/test_sgx \
+ $(OUTPUT)/test_sgx.o \
diff --git a/tools/testing/selftests/sgx/call.S b/tools/testing/selftests/sgx/call.S
new file mode 100644
index 000000000000..4ecadc7490f4
--- /dev/null
+++ b/tools/testing/selftests/sgx/call.S
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+* Copyright(c) 2016-20 Intel Corporation.
+*/
+
+ .text
+
+ .global sgx_call_vdso
+sgx_call_vdso:
+ .cfi_startproc
+ push %r15
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset %r15, 0
+ push %r14
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset %r14, 0
+ push %r13
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset %r13, 0
+ push %r12
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset %r12, 0
+ push %rbx
+ .cfi_adjust_cfa_offset 8
+ .cfi_rel_offset %rbx, 0
+ push $0
+ .cfi_adjust_cfa_offset 8
+ push 0x38(%rsp)
+ .cfi_adjust_cfa_offset 8
+ call *eenter(%rip)
+ add $0x10, %rsp
+ .cfi_adjust_cfa_offset -0x10
+ pop %rbx
+ .cfi_adjust_cfa_offset -8
+ pop %r12
+ .cfi_adjust_cfa_offset -8
+ pop %r13
+ .cfi_adjust_cfa_offset -8
+ pop %r14
+ .cfi_adjust_cfa_offset -8
+ pop %r15
+ .cfi_adjust_cfa_offset -8
+ ret
+ .cfi_endproc
diff --git a/tools/testing/selftests/sgx/defines.h b/tools/testing/selftests/sgx/defines.h
new file mode 100644
index 000000000000..592c1ccf4576
--- /dev/null
+++ b/tools/testing/selftests/sgx/defines.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(c) 2016-20 Intel Corporation.
+ */
+
+#ifndef DEFINES_H
+#define DEFINES_H
+
+#include <stdint.h>
+
+#define PAGE_SIZE 4096
+#define PAGE_MASK (~(PAGE_SIZE - 1))
+
+#define __aligned(x) __attribute__((__aligned__(x)))
+#define __packed __attribute__((packed))
+
+#include "../../../../arch/x86/kernel/cpu/sgx/arch.h"
+#include "../../../../arch/x86/include/asm/enclu.h"
+#include "../../../../arch/x86/include/uapi/asm/sgx.h"
+
+#endif /* DEFINES_H */
diff --git a/tools/testing/selftests/sgx/load.c b/tools/testing/selftests/sgx/load.c
new file mode 100644
index 000000000000..9d43b75aaa55
--- /dev/null
+++ b/tools/testing/selftests/sgx/load.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <assert.h>
+#include <elf.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include "defines.h"
+#include "main.h"
+
+void encl_delete(struct encl *encl)
+{
+ if (encl->encl_base)
+ munmap((void *)encl->encl_base, encl->encl_size);
+
+ if (encl->bin)
+ munmap(encl->bin, encl->bin_size);
+
+ if (encl->fd)
+ close(encl->fd);
+
+ if (encl->segment_tbl)
+ free(encl->segment_tbl);
+
+ memset(encl, 0, sizeof(*encl));
+}
+
+static bool encl_map_bin(const char *path, struct encl *encl)
+{
+ struct stat sb;
+ void *bin;
+ int ret;
+ int fd;
+
+ fd = open(path, O_RDONLY);
+ if (fd == -1) {
+ perror("open()");
+ return false;
+ }
+
+ ret = stat(path, &sb);
+ if (ret) {
+ perror("stat()");
+ goto err;
+ }
+
+ bin = mmap(NULL, sb.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+ if (bin == MAP_FAILED) {
+ perror("mmap()");
+ goto err;
+ }
+
+ encl->bin = bin;
+ encl->bin_size = sb.st_size;
+
+ close(fd);
+ return true;
+
+err:
+ close(fd);
+ return false;
+}
+
+static bool encl_ioc_create(struct encl *encl)
+{
+ struct sgx_secs *secs = &encl->secs;
+ struct sgx_enclave_create ioc;
+ int rc;
+
+ assert(encl->encl_base != 0);
+
+ memset(secs, 0, sizeof(*secs));
+ secs->ssa_frame_size = 1;
+ secs->attributes = SGX_ATTR_MODE64BIT;
+ secs->xfrm = 3;
+ secs->base = encl->encl_base;
+ secs->size = encl->encl_size;
+
+ ioc.src = (unsigned long)secs;
+ rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_CREATE, &ioc);
+ if (rc) {
+ fprintf(stderr, "SGX_IOC_ENCLAVE_CREATE failed: errno=%d\n",
+ errno);
+ munmap((void *)secs->base, encl->encl_size);
+ return false;
+ }
+
+ return true;
+}
+
+static bool encl_ioc_add_pages(struct encl *encl, struct encl_segment *seg)
+{
+ struct sgx_enclave_add_pages ioc;
+ struct sgx_secinfo secinfo;
+ int rc;
+
+ memset(&secinfo, 0, sizeof(secinfo));
+ secinfo.flags = seg->flags;
+
+ ioc.src = (uint64_t)encl->src + seg->offset;
+ ioc.offset = seg->offset;
+ ioc.length = seg->size;
+ ioc.secinfo = (unsigned long)&secinfo;
+ ioc.flags = SGX_PAGE_MEASURE;
+
+ rc = ioctl(encl->fd, SGX_IOC_ENCLAVE_ADD_PAGES, &ioc);
+ if (rc < 0) {
+ fprintf(stderr, "SGX_IOC_ENCLAVE_ADD_PAGES failed: errno=%d.\n",
+ errno);
+ return false;
+ }
+
+ return true;
+}
+
+bool encl_load(const char *path, struct encl *encl)
+{
+ Elf64_Phdr *phdr_tbl;
+ off_t src_offset;
+ Elf64_Ehdr *ehdr;
+ int i, j;
+ int ret;
+
+ memset(encl, 0, sizeof(*encl));
+
+ ret = open("/dev/sgx_enclave", O_RDWR);
+ if (ret < 0) {
+ fprintf(stderr, "Unable to open /dev/sgx_enclave\n");
+ goto err;
+ }
+
+ encl->fd = ret;
+
+ if (!encl_map_bin(path, encl))
+ goto err;
+
+ ehdr = encl->bin;
+ phdr_tbl = encl->bin + ehdr->e_phoff;
+
+ for (i = 0; i < ehdr->e_phnum; i++) {
+ Elf64_Phdr *phdr = &phdr_tbl[i];
+
+ if (phdr->p_type == PT_LOAD)
+ encl->nr_segments++;
+ }
+
+ encl->segment_tbl = calloc(encl->nr_segments,
+ sizeof(struct encl_segment));
+ if (!encl->segment_tbl)
+ goto err;
+
+ for (i = 0, j = 0; i < ehdr->e_phnum; i++) {
+ Elf64_Phdr *phdr = &phdr_tbl[i];
+ unsigned int flags = phdr->p_flags;
+ struct encl_segment *seg;
+
+ if (phdr->p_type != PT_LOAD)
+ continue;
+
+ seg = &encl->segment_tbl[j];
+
+ if (!!(flags & ~(PF_R | PF_W | PF_X))) {
+ fprintf(stderr,
+ "%d has invalid segment flags 0x%02x.\n", i,
+ phdr->p_flags);
+ goto err;
+ }
+
+ if (j == 0 && flags != (PF_R | PF_W)) {
+ fprintf(stderr,
+ "TCS has invalid segment flags 0x%02x.\n",
+ phdr->p_flags);
+ goto err;
+ }
+
+ if (j == 0) {
+ src_offset = phdr->p_offset & PAGE_MASK;
+
+ seg->prot = PROT_READ | PROT_WRITE;
+ seg->flags = SGX_PAGE_TYPE_TCS << 8;
+ } else {
+ seg->prot = (phdr->p_flags & PF_R) ? PROT_READ : 0;
+ seg->prot |= (phdr->p_flags & PF_W) ? PROT_WRITE : 0;
+ seg->prot |= (phdr->p_flags & PF_X) ? PROT_EXEC : 0;
+ seg->flags = (SGX_PAGE_TYPE_REG << 8) | seg->prot;
+ }
+
+ seg->offset = (phdr->p_offset & PAGE_MASK) - src_offset;
+ seg->size = (phdr->p_filesz + PAGE_SIZE - 1) & PAGE_MASK;
+
+ printf("0x%016lx 0x%016lx 0x%02x\n", seg->offset, seg->size,
+ seg->prot);
+
+ j++;
+ }
+
+ assert(j == encl->nr_segments);
+
+ encl->src = encl->bin + src_offset;
+ encl->src_size = encl->segment_tbl[j - 1].offset +
+ encl->segment_tbl[j - 1].size;
+
+ for (encl->encl_size = 4096; encl->encl_size < encl->src_size; )
+ encl->encl_size <<= 1;
+
+ return true;
+
+err:
+ encl_delete(encl);
+ return false;
+}
+
+static bool encl_map_area(struct encl *encl)
+{
+ size_t encl_size = encl->encl_size;
+ void *area;
+
+ area = mmap(NULL, encl_size * 2, PROT_NONE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (area == MAP_FAILED) {
+ perror("mmap");
+ return false;
+ }
+
+ encl->encl_base = ((uint64_t)area + encl_size - 1) & ~(encl_size - 1);
+
+ munmap(area, encl->encl_base - (uint64_t)area);
+ munmap((void *)(encl->encl_base + encl_size),
+ (uint64_t)area + encl_size - encl->encl_base);
+
+ return true;
+}
+
+bool encl_build(struct encl *encl)
+{
+ struct sgx_enclave_init ioc;
+ int ret;
+ int i;
+
+ if (!encl_map_area(encl))
+ return false;
+
+ if (!encl_ioc_create(encl))
+ return false;
+
+ /*
+ * Pages must be added before mapping VMAs because their permissions
+ * cap the VMA permissions.
+ */
+ for (i = 0; i < encl->nr_segments; i++) {
+ struct encl_segment *seg = &encl->segment_tbl[i];
+
+ if (!encl_ioc_add_pages(encl, seg))
+ return false;
+ }
+
+ ioc.sigstruct = (uint64_t)&encl->sigstruct;
+ ret = ioctl(encl->fd, SGX_IOC_ENCLAVE_INIT, &ioc);
+ if (ret) {
+ fprintf(stderr, "SGX_IOC_ENCLAVE_INIT failed: errno=%d\n",
+ errno);
+ return false;
+ }
+
+ return true;
+}
diff --git a/tools/testing/selftests/sgx/main.c b/tools/testing/selftests/sgx/main.c
new file mode 100644
index 000000000000..724cec700926
--- /dev/null
+++ b/tools/testing/selftests/sgx/main.c
@@ -0,0 +1,246 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <elf.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include "defines.h"
+#include "main.h"
+#include "../kselftest.h"
+
+static const uint64_t MAGIC = 0x1122334455667788ULL;
+vdso_sgx_enter_enclave_t eenter;
+
+struct vdso_symtab {
+ Elf64_Sym *elf_symtab;
+ const char *elf_symstrtab;
+ Elf64_Word *elf_hashtab;
+};
+
+static void *vdso_get_base_addr(char *envp[])
+{
+ Elf64_auxv_t *auxv;
+ int i;
+
+ for (i = 0; envp[i]; i++)
+ ;
+
+ auxv = (Elf64_auxv_t *)&envp[i + 1];
+
+ for (i = 0; auxv[i].a_type != AT_NULL; i++) {
+ if (auxv[i].a_type == AT_SYSINFO_EHDR)
+ return (void *)auxv[i].a_un.a_val;
+ }
+
+ return NULL;
+}
+
+static Elf64_Dyn *vdso_get_dyntab(void *addr)
+{
+ Elf64_Ehdr *ehdr = addr;
+ Elf64_Phdr *phdrtab = addr + ehdr->e_phoff;
+ int i;
+
+ for (i = 0; i < ehdr->e_phnum; i++)
+ if (phdrtab[i].p_type == PT_DYNAMIC)
+ return addr + phdrtab[i].p_offset;
+
+ return NULL;
+}
+
+static void *vdso_get_dyn(void *addr, Elf64_Dyn *dyntab, Elf64_Sxword tag)
+{
+ int i;
+
+ for (i = 0; dyntab[i].d_tag != DT_NULL; i++)
+ if (dyntab[i].d_tag == tag)
+ return addr + dyntab[i].d_un.d_ptr;
+
+ return NULL;
+}
+
+static bool vdso_get_symtab(void *addr, struct vdso_symtab *symtab)
+{
+ Elf64_Dyn *dyntab = vdso_get_dyntab(addr);
+
+ symtab->elf_symtab = vdso_get_dyn(addr, dyntab, DT_SYMTAB);
+ if (!symtab->elf_symtab)
+ return false;
+
+ symtab->elf_symstrtab = vdso_get_dyn(addr, dyntab, DT_STRTAB);
+ if (!symtab->elf_symstrtab)
+ return false;
+
+ symtab->elf_hashtab = vdso_get_dyn(addr, dyntab, DT_HASH);
+ if (!symtab->elf_hashtab)
+ return false;
+
+ return true;
+}
+
+static unsigned long elf_sym_hash(const char *name)
+{
+ unsigned long h = 0, high;
+
+ while (*name) {
+ h = (h << 4) + *name++;
+ high = h & 0xf0000000;
+
+ if (high)
+ h ^= high >> 24;
+
+ h &= ~high;
+ }
+
+ return h;
+}
+
+static Elf64_Sym *vdso_symtab_get(struct vdso_symtab *symtab, const char *name)
+{
+ Elf64_Word bucketnum = symtab->elf_hashtab[0];
+ Elf64_Word *buckettab = &symtab->elf_hashtab[2];
+ Elf64_Word *chaintab = &symtab->elf_hashtab[2 + bucketnum];
+ Elf64_Sym *sym;
+ Elf64_Word i;
+
+ for (i = buckettab[elf_sym_hash(name) % bucketnum]; i != STN_UNDEF;
+ i = chaintab[i]) {
+ sym = &symtab->elf_symtab[i];
+ if (!strcmp(name, &symtab->elf_symstrtab[sym->st_name]))
+ return sym;
+ }
+
+ return NULL;
+}
+
+bool report_results(struct sgx_enclave_run *run, int ret, uint64_t result,
+ const char *test)
+{
+ bool valid = true;
+
+ if (ret) {
+ printf("FAIL: %s() returned: %d\n", test, ret);
+ valid = false;
+ }
+
+ if (run->function != EEXIT) {
+ printf("FAIL: %s() function, expected: %u, got: %u\n", test, EEXIT,
+ run->function);
+ valid = false;
+ }
+
+ if (result != MAGIC) {
+ printf("FAIL: %s(), expected: 0x%lx, got: 0x%lx\n", test, MAGIC,
+ result);
+ valid = false;
+ }
+
+ if (run->user_data) {
+ printf("FAIL: %s() user data, expected: 0x0, got: 0x%llx\n",
+ test, run->user_data);
+ valid = false;
+ }
+
+ return valid;
+}
+
+static int user_handler(long rdi, long rsi, long rdx, long ursp, long r8, long r9,
+ struct sgx_enclave_run *run)
+{
+ run->user_data = 0;
+ return 0;
+}
+
+int main(int argc, char *argv[], char *envp[])
+{
+ struct sgx_enclave_run run;
+ struct vdso_symtab symtab;
+ Elf64_Sym *eenter_sym;
+ uint64_t result = 0;
+ struct encl encl;
+ unsigned int i;
+ void *addr;
+ int ret;
+
+ memset(&run, 0, sizeof(run));
+
+ if (!encl_load("test_encl.elf", &encl)) {
+ encl_delete(&encl);
+ ksft_exit_skip("cannot load enclaves\n");
+ }
+
+ if (!encl_measure(&encl))
+ goto err;
+
+ if (!encl_build(&encl))
+ goto err;
+
+ /*
+ * An enclave consumer only must do this.
+ */
+ for (i = 0; i < encl.nr_segments; i++) {
+ struct encl_segment *seg = &encl.segment_tbl[i];
+
+ addr = mmap((void *)encl.encl_base + seg->offset, seg->size,
+ seg->prot, MAP_SHARED | MAP_FIXED, encl.fd, 0);
+ if (addr == MAP_FAILED) {
+ fprintf(stderr, "mmap() failed, errno=%d.\n", errno);
+ exit(KSFT_FAIL);
+ }
+ }
+
+ memset(&run, 0, sizeof(run));
+ run.tcs = encl.encl_base;
+
+ addr = vdso_get_base_addr(envp);
+ if (!addr)
+ goto err;
+
+ if (!vdso_get_symtab(addr, &symtab))
+ goto err;
+
+ eenter_sym = vdso_symtab_get(&symtab, "__vdso_sgx_enter_enclave");
+ if (!eenter_sym)
+ goto err;
+
+ eenter = addr + eenter_sym->st_value;
+
+ ret = sgx_call_vdso((void *)&MAGIC, &result, 0, EENTER, NULL, NULL, &run);
+ if (!report_results(&run, ret, result, "sgx_call_vdso"))
+ goto err;
+
+
+ /* Invoke the vDSO directly. */
+ result = 0;
+ ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER,
+ 0, 0, &run);
+ if (!report_results(&run, ret, result, "eenter"))
+ goto err;
+
+ /* And with an exit handler. */
+ run.user_handler = (__u64)user_handler;
+ run.user_data = 0xdeadbeef;
+ ret = eenter((unsigned long)&MAGIC, (unsigned long)&result, 0, EENTER,
+ 0, 0, &run);
+ if (!report_results(&run, ret, result, "user_handler"))
+ goto err;
+
+ printf("SUCCESS\n");
+ encl_delete(&encl);
+ exit(KSFT_PASS);
+
+err:
+ encl_delete(&encl);
+ exit(KSFT_FAIL);
+}
diff --git a/tools/testing/selftests/sgx/main.h b/tools/testing/selftests/sgx/main.h
new file mode 100644
index 000000000000..67211a708f04
--- /dev/null
+++ b/tools/testing/selftests/sgx/main.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(c) 2016-20 Intel Corporation.
+ */
+
+#ifndef MAIN_H
+#define MAIN_H
+
+struct encl_segment {
+ off_t offset;
+ size_t size;
+ unsigned int prot;
+ unsigned int flags;
+};
+
+struct encl {
+ int fd;
+ void *bin;
+ off_t bin_size;
+ void *src;
+ size_t src_size;
+ size_t encl_size;
+ off_t encl_base;
+ unsigned int nr_segments;
+ struct encl_segment *segment_tbl;
+ struct sgx_secs secs;
+ struct sgx_sigstruct sigstruct;
+};
+
+extern unsigned char sign_key[];
+extern unsigned char sign_key_end[];
+
+void encl_delete(struct encl *ctx);
+bool encl_load(const char *path, struct encl *encl);
+bool encl_measure(struct encl *encl);
+bool encl_build(struct encl *encl);
+
+int sgx_call_vdso(void *rdi, void *rsi, long rdx, u32 function, void *r8, void *r9,
+ struct sgx_enclave_run *run);
+
+#endif /* MAIN_H */
diff --git a/tools/testing/selftests/sgx/sign_key.S b/tools/testing/selftests/sgx/sign_key.S
new file mode 100644
index 000000000000..e4fbe948444a
--- /dev/null
+++ b/tools/testing/selftests/sgx/sign_key.S
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+* Copyright(c) 2016-20 Intel Corporation.
+*/
+
+ .section ".rodata", "a"
+
+sign_key:
+ .globl sign_key
+ .incbin "sign_key.pem"
+sign_key_end:
+ .globl sign_key_end
diff --git a/tools/testing/selftests/sgx/sign_key.pem b/tools/testing/selftests/sgx/sign_key.pem
new file mode 100644
index 000000000000..d76f21f19187
--- /dev/null
+++ b/tools/testing/selftests/sgx/sign_key.pem
@@ -0,0 +1,39 @@
+-----BEGIN RSA PRIVATE KEY-----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+-----END RSA PRIVATE KEY-----
diff --git a/tools/testing/selftests/sgx/sigstruct.c b/tools/testing/selftests/sgx/sigstruct.c
new file mode 100644
index 000000000000..dee7a3d6c5a5
--- /dev/null
+++ b/tools/testing/selftests/sgx/sigstruct.c
@@ -0,0 +1,381 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#define _GNU_SOURCE
+#include <assert.h>
+#include <getopt.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <openssl/err.h>
+#include <openssl/pem.h>
+#include "defines.h"
+#include "main.h"
+
+struct q1q2_ctx {
+ BN_CTX *bn_ctx;
+ BIGNUM *m;
+ BIGNUM *s;
+ BIGNUM *q1;
+ BIGNUM *qr;
+ BIGNUM *q2;
+};
+
+static void free_q1q2_ctx(struct q1q2_ctx *ctx)
+{
+ BN_CTX_free(ctx->bn_ctx);
+ BN_free(ctx->m);
+ BN_free(ctx->s);
+ BN_free(ctx->q1);
+ BN_free(ctx->qr);
+ BN_free(ctx->q2);
+}
+
+static bool alloc_q1q2_ctx(const uint8_t *s, const uint8_t *m,
+ struct q1q2_ctx *ctx)
+{
+ ctx->bn_ctx = BN_CTX_new();
+ ctx->s = BN_bin2bn(s, SGX_MODULUS_SIZE, NULL);
+ ctx->m = BN_bin2bn(m, SGX_MODULUS_SIZE, NULL);
+ ctx->q1 = BN_new();
+ ctx->qr = BN_new();
+ ctx->q2 = BN_new();
+
+ if (!ctx->bn_ctx || !ctx->s || !ctx->m || !ctx->q1 || !ctx->qr ||
+ !ctx->q2) {
+ free_q1q2_ctx(ctx);
+ return false;
+ }
+
+ return true;
+}
+
+static bool calc_q1q2(const uint8_t *s, const uint8_t *m, uint8_t *q1,
+ uint8_t *q2)
+{
+ struct q1q2_ctx ctx;
+
+ if (!alloc_q1q2_ctx(s, m, &ctx)) {
+ fprintf(stderr, "Not enough memory for Q1Q2 calculation\n");
+ return false;
+ }
+
+ if (!BN_mul(ctx.q1, ctx.s, ctx.s, ctx.bn_ctx))
+ goto out;
+
+ if (!BN_div(ctx.q1, ctx.qr, ctx.q1, ctx.m, ctx.bn_ctx))
+ goto out;
+
+ if (BN_num_bytes(ctx.q1) > SGX_MODULUS_SIZE) {
+ fprintf(stderr, "Too large Q1 %d bytes\n",
+ BN_num_bytes(ctx.q1));
+ goto out;
+ }
+
+ if (!BN_mul(ctx.q2, ctx.s, ctx.qr, ctx.bn_ctx))
+ goto out;
+
+ if (!BN_div(ctx.q2, NULL, ctx.q2, ctx.m, ctx.bn_ctx))
+ goto out;
+
+ if (BN_num_bytes(ctx.q2) > SGX_MODULUS_SIZE) {
+ fprintf(stderr, "Too large Q2 %d bytes\n",
+ BN_num_bytes(ctx.q2));
+ goto out;
+ }
+
+ BN_bn2bin(ctx.q1, q1);
+ BN_bn2bin(ctx.q2, q2);
+
+ free_q1q2_ctx(&ctx);
+ return true;
+out:
+ free_q1q2_ctx(&ctx);
+ return false;
+}
+
+struct sgx_sigstruct_payload {
+ struct sgx_sigstruct_header header;
+ struct sgx_sigstruct_body body;
+};
+
+static bool check_crypto_errors(void)
+{
+ int err;
+ bool had_errors = false;
+ const char *filename;
+ int line;
+ char str[256];
+
+ for ( ; ; ) {
+ if (ERR_peek_error() == 0)
+ break;
+
+ had_errors = true;
+ err = ERR_get_error_line(&filename, &line);
+ ERR_error_string_n(err, str, sizeof(str));
+ fprintf(stderr, "crypto: %s: %s:%d\n", str, filename, line);
+ }
+
+ return had_errors;
+}
+
+static inline const BIGNUM *get_modulus(RSA *key)
+{
+ const BIGNUM *n;
+
+ RSA_get0_key(key, &n, NULL, NULL);
+ return n;
+}
+
+static RSA *gen_sign_key(void)
+{
+ unsigned long sign_key_length;
+ BIO *bio;
+ RSA *key;
+
+ sign_key_length = (unsigned long)&sign_key_end -
+ (unsigned long)&sign_key;
+
+ bio = BIO_new_mem_buf(&sign_key, sign_key_length);
+ if (!bio)
+ return NULL;
+
+ key = PEM_read_bio_RSAPrivateKey(bio, NULL, NULL, NULL);
+ BIO_free(bio);
+
+ 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,
+ MREEXTEND = 0x00444E4554584545,
+};
+
+static bool mrenclave_update(EVP_MD_CTX *ctx, const void *data)
+{
+ if (!EVP_DigestUpdate(ctx, data, 64)) {
+ fprintf(stderr, "digest update failed\n");
+ return false;
+ }
+
+ return true;
+}
+
+static bool mrenclave_commit(EVP_MD_CTX *ctx, uint8_t *mrenclave)
+{
+ unsigned int size;
+
+ if (!EVP_DigestFinal_ex(ctx, (unsigned char *)mrenclave, &size)) {
+ fprintf(stderr, "digest commit failed\n");
+ return false;
+ }
+
+ if (size != 32) {
+ fprintf(stderr, "invalid digest size = %u\n", size);
+ return false;
+ }
+
+ return true;
+}
+
+struct mrecreate {
+ uint64_t tag;
+ uint32_t ssaframesize;
+ uint64_t size;
+ uint8_t reserved[44];
+} __attribute__((__packed__));
+
+
+static bool mrenclave_ecreate(EVP_MD_CTX *ctx, uint64_t blob_size)
+{
+ struct mrecreate mrecreate;
+ uint64_t encl_size;
+
+ for (encl_size = 0x1000; encl_size < blob_size; )
+ encl_size <<= 1;
+
+ memset(&mrecreate, 0, sizeof(mrecreate));
+ mrecreate.tag = MRECREATE;
+ mrecreate.ssaframesize = 1;
+ mrecreate.size = encl_size;
+
+ if (!EVP_DigestInit_ex(ctx, EVP_sha256(), NULL))
+ return false;
+
+ return mrenclave_update(ctx, &mrecreate);
+}
+
+struct mreadd {
+ uint64_t tag;
+ uint64_t offset;
+ uint64_t flags; /* SECINFO flags */
+ uint8_t reserved[40];
+} __attribute__((__packed__));
+
+static bool mrenclave_eadd(EVP_MD_CTX *ctx, uint64_t offset, uint64_t flags)
+{
+ struct mreadd mreadd;
+
+ memset(&mreadd, 0, sizeof(mreadd));
+ mreadd.tag = MREADD;
+ mreadd.offset = offset;
+ mreadd.flags = flags;
+
+ return mrenclave_update(ctx, &mreadd);
+}
+
+struct mreextend {
+ uint64_t tag;
+ uint64_t offset;
+ uint8_t reserved[48];
+} __attribute__((__packed__));
+
+static bool mrenclave_eextend(EVP_MD_CTX *ctx, uint64_t offset,
+ const uint8_t *data)
+{
+ struct mreextend mreextend;
+ int i;
+
+ for (i = 0; i < 0x1000; i += 0x100) {
+ memset(&mreextend, 0, sizeof(mreextend));
+ mreextend.tag = MREEXTEND;
+ mreextend.offset = offset + i;
+
+ if (!mrenclave_update(ctx, &mreextend))
+ return false;
+
+ if (!mrenclave_update(ctx, &data[i + 0x00]))
+ return false;
+
+ if (!mrenclave_update(ctx, &data[i + 0x40]))
+ return false;
+
+ if (!mrenclave_update(ctx, &data[i + 0x80]))
+ return false;
+
+ if (!mrenclave_update(ctx, &data[i + 0xC0]))
+ return false;
+ }
+
+ return true;
+}
+
+static bool mrenclave_segment(EVP_MD_CTX *ctx, struct encl *encl,
+ struct encl_segment *seg)
+{
+ uint64_t end = seg->offset + seg->size;
+ uint64_t offset;
+
+ for (offset = seg->offset; offset < end; offset += PAGE_SIZE) {
+ if (!mrenclave_eadd(ctx, offset, seg->flags))
+ return false;
+
+ if (!mrenclave_eextend(ctx, offset, encl->src + offset))
+ return false;
+ }
+
+ return true;
+}
+
+bool encl_measure(struct encl *encl)
+{
+ uint64_t header1[2] = {0x000000E100000006, 0x0000000000010000};
+ uint64_t header2[2] = {0x0000006000000101, 0x0000000100000060};
+ struct sgx_sigstruct *sigstruct = &encl->sigstruct;
+ struct sgx_sigstruct_payload payload;
+ uint8_t digest[SHA256_DIGEST_LENGTH];
+ unsigned int siglen;
+ RSA *key = NULL;
+ EVP_MD_CTX *ctx;
+ int i;
+
+ memset(sigstruct, 0, sizeof(*sigstruct));
+
+ sigstruct->header.header1[0] = header1[0];
+ sigstruct->header.header1[1] = header1[1];
+ sigstruct->header.header2[0] = header2[0];
+ sigstruct->header.header2[1] = header2[1];
+ sigstruct->exponent = 3;
+ sigstruct->body.attributes = SGX_ATTR_MODE64BIT;
+ sigstruct->body.xfrm = 3;
+
+ /* sanity check */
+ if (check_crypto_errors())
+ goto err;
+
+ key = gen_sign_key();
+ if (!key) {
+ ERR_print_errors_fp(stdout);
+ goto err;
+ }
+
+ BN_bn2bin(get_modulus(key), sigstruct->modulus);
+
+ ctx = EVP_MD_CTX_create();
+ if (!ctx)
+ goto err;
+
+ if (!mrenclave_ecreate(ctx, encl->src_size))
+ goto err;
+
+ for (i = 0; i < encl->nr_segments; i++) {
+ struct encl_segment *seg = &encl->segment_tbl[i];
+
+ if (!mrenclave_segment(ctx, encl, seg))
+ goto err;
+ }
+
+ if (!mrenclave_commit(ctx, sigstruct->body.mrenclave))
+ goto err;
+
+ memcpy(&payload.header, &sigstruct->header, sizeof(sigstruct->header));
+ memcpy(&payload.body, &sigstruct->body, sizeof(sigstruct->body));
+
+ SHA256((unsigned char *)&payload, sizeof(payload), digest);
+
+ if (!RSA_sign(NID_sha256, digest, SHA256_DIGEST_LENGTH,
+ sigstruct->signature, &siglen, key))
+ goto err;
+
+ if (!calc_q1q2(sigstruct->signature, sigstruct->modulus, sigstruct->q1,
+ sigstruct->q2))
+ goto err;
+
+ /* 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);
+ return true;
+
+err:
+ EVP_MD_CTX_destroy(ctx);
+ RSA_free(key);
+ return false;
+}
diff --git a/tools/testing/selftests/sgx/test_encl.c b/tools/testing/selftests/sgx/test_encl.c
new file mode 100644
index 000000000000..cf25b5dc1e03
--- /dev/null
+++ b/tools/testing/selftests/sgx/test_encl.c
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2016-20 Intel Corporation. */
+
+#include <stddef.h>
+#include "defines.h"
+
+static void *memcpy(void *dest, const void *src, size_t n)
+{
+ size_t i;
+
+ for (i = 0; i < n; i++)
+ ((char *)dest)[i] = ((char *)src)[i];
+
+ return dest;
+}
+
+void encl_body(void *rdi, void *rsi)
+{
+ memcpy(rsi, rdi, 8);
+}
diff --git a/tools/testing/selftests/sgx/test_encl.lds b/tools/testing/selftests/sgx/test_encl.lds
new file mode 100644
index 000000000000..0fbbda7e665e
--- /dev/null
+++ b/tools/testing/selftests/sgx/test_encl.lds
@@ -0,0 +1,40 @@
+OUTPUT_FORMAT(elf64-x86-64)
+
+PHDRS
+{
+ tcs PT_LOAD;
+ text PT_LOAD;
+ data PT_LOAD;
+}
+
+SECTIONS
+{
+ . = 0;
+ .tcs : {
+ *(.tcs*)
+ } : tcs
+
+ . = ALIGN(4096);
+ .text : {
+ *(.text*)
+ *(.rodata*)
+ } : text
+
+ . = ALIGN(4096);
+ .data : {
+ *(.data*)
+ } : data
+
+ /DISCARD/ : {
+ *(.comment*)
+ *(.note*)
+ *(.debug*)
+ *(.eh_frame*)
+ }
+}
+
+ASSERT(!DEFINED(.altinstructions), "ALTERNATIVES are not supported in enclaves")
+ASSERT(!DEFINED(.altinstr_replacement), "ALTERNATIVES are not supported in enclaves")
+ASSERT(!DEFINED(.discard.retpoline_safe), "RETPOLINE ALTERNATIVES are not supported in enclaves")
+ASSERT(!DEFINED(.discard.nospec), "RETPOLINE ALTERNATIVES are not supported in enclaves")
+ASSERT(!DEFINED(.got.plt), "Libcalls are not supported in enclaves")
diff --git a/tools/testing/selftests/sgx/test_encl_bootstrap.S b/tools/testing/selftests/sgx/test_encl_bootstrap.S
new file mode 100644
index 000000000000..5d5680d4ea39
--- /dev/null
+++ b/tools/testing/selftests/sgx/test_encl_bootstrap.S
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright(c) 2016-20 Intel Corporation.
+ */
+
+ .macro ENCLU
+ .byte 0x0f, 0x01, 0xd7
+ .endm
+
+ .section ".tcs", "aw"
+ .balign 4096
+
+ .fill 1, 8, 0 # STATE (set by CPU)
+ .fill 1, 8, 0 # FLAGS
+ .quad encl_ssa # OSSA
+ .fill 1, 4, 0 # CSSA (set by CPU)
+ .fill 1, 4, 1 # NSSA
+ .quad encl_entry # OENTRY
+ .fill 1, 8, 0 # AEP (set by EENTER and ERESUME)
+ .fill 1, 8, 0 # OFSBASE
+ .fill 1, 8, 0 # OGSBASE
+ .fill 1, 4, 0xFFFFFFFF # FSLIMIT
+ .fill 1, 4, 0xFFFFFFFF # GSLIMIT
+ .fill 4024, 1, 0 # Reserved
+
+ # Identical to the previous TCS.
+ .fill 1, 8, 0 # STATE (set by CPU)
+ .fill 1, 8, 0 # FLAGS
+ .quad encl_ssa # OSSA
+ .fill 1, 4, 0 # CSSA (set by CPU)
+ .fill 1, 4, 1 # NSSA
+ .quad encl_entry # OENTRY
+ .fill 1, 8, 0 # AEP (set by EENTER and ERESUME)
+ .fill 1, 8, 0 # OFSBASE
+ .fill 1, 8, 0 # OGSBASE
+ .fill 1, 4, 0xFFFFFFFF # FSLIMIT
+ .fill 1, 4, 0xFFFFFFFF # GSLIMIT
+ .fill 4024, 1, 0 # Reserved
+
+ .text
+
+encl_entry:
+ # RBX contains the base address for TCS, which is also the first address
+ # inside the enclave. By adding the value of le_stack_end to it, we get
+ # the absolute address for the stack.
+ lea (encl_stack)(%rbx), %rax
+ xchg %rsp, %rax
+ push %rax
+
+ push %rcx # push the address after EENTER
+ push %rbx # push the enclave base address
+
+ call encl_body
+
+ pop %rbx # pop the enclave base address
+
+ /* Clear volatile GPRs, except RAX (EEXIT function). */
+ xor %rcx, %rcx
+ xor %rdx, %rdx
+ xor %rdi, %rdi
+ xor %rsi, %rsi
+ xor %r8, %r8
+ xor %r9, %r9
+ xor %r10, %r10
+ xor %r11, %r11
+
+ # Reset status flags.
+ add %rdx, %rdx # OF = SF = AF = CF = 0; ZF = PF = 1
+
+ # Prepare EEXIT target by popping the address of the instruction after
+ # EENTER to RBX.
+ pop %rbx
+
+ # Restore the caller stack.
+ pop %rax
+ mov %rax, %rsp
+
+ # EEXIT
+ mov $4, %rax
+ enclu
+
+ .section ".data", "aw"
+
+encl_ssa:
+ .space 4096
+
+ .balign 4096
+ .space 8192
+encl_stack:
diff --git a/tools/testing/selftests/android/ion/.gitignore b/tools/testing/selftests/syscall_user_dispatch/.gitignore
index 78eae9972bb1..f539615ad5da 100644
--- a/tools/testing/selftests/android/ion/.gitignore
+++ b/tools/testing/selftests/syscall_user_dispatch/.gitignore
@@ -1,4 +1,3 @@
# SPDX-License-Identifier: GPL-2.0-only
-ionapp_export
-ionapp_import
-ionmap_test
+sud_test
+sud_benchmark
diff --git a/tools/testing/selftests/syscall_user_dispatch/Makefile b/tools/testing/selftests/syscall_user_dispatch/Makefile
new file mode 100644
index 000000000000..03c120270953
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+top_srcdir = ../../../..
+INSTALL_HDR_PATH = $(top_srcdir)/usr
+LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
+
+CFLAGS += -Wall -I$(LINUX_HDR_PATH)
+
+TEST_GEN_PROGS := sud_test sud_benchmark
+include ../lib.mk
diff --git a/tools/testing/selftests/syscall_user_dispatch/config b/tools/testing/selftests/syscall_user_dispatch/config
new file mode 100644
index 000000000000..039e303e59d7
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/config
@@ -0,0 +1 @@
+CONFIG_GENERIC_ENTRY=y
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
new file mode 100644
index 000000000000..6689f1183dbf
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_benchmark.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ *
+ * Benchmark and test syscall user dispatch
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <signal.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <sys/sysinfo.h>
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+
+#ifndef PR_SET_SYSCALL_USER_DISPATCH
+# define PR_SET_SYSCALL_USER_DISPATCH 59
+# define PR_SYS_DISPATCH_OFF 0
+# define PR_SYS_DISPATCH_ON 1
+#endif
+
+#ifdef __NR_syscalls
+# define MAGIC_SYSCALL_1 (__NR_syscalls + 1) /* Bad Linux syscall number */
+#else
+# define MAGIC_SYSCALL_1 (0xff00) /* Bad Linux syscall number */
+#endif
+
+/*
+ * To test returning from a sigsys with selector blocked, the test
+ * requires some per-architecture support (i.e. knowledge about the
+ * signal trampoline address). On i386, we know it is on the vdso, and
+ * a small trampoline is open-coded for x86_64. Other architectures
+ * that have a trampoline in the vdso will support TEST_BLOCKED_RETURN
+ * out of the box, but don't enable them until they support syscall user
+ * dispatch.
+ */
+#if defined(__x86_64__) || defined(__i386__)
+#define TEST_BLOCKED_RETURN
+#endif
+
+#ifdef __x86_64__
+void* (syscall_dispatcher_start)(void);
+void* (syscall_dispatcher_end)(void);
+#else
+unsigned long syscall_dispatcher_start = 0;
+unsigned long syscall_dispatcher_end = 0;
+#endif
+
+unsigned long trapped_call_count = 0;
+unsigned long native_call_count = 0;
+
+char selector;
+#define SYSCALL_BLOCK (selector = PR_SYS_DISPATCH_ON)
+#define SYSCALL_UNBLOCK (selector = PR_SYS_DISPATCH_OFF)
+
+#define CALIBRATION_STEP 100000
+#define CALIBRATE_TO_SECS 5
+int factor;
+
+static double one_sysinfo_step(void)
+{
+ struct timespec t1, t2;
+ int i;
+ struct sysinfo info;
+
+ clock_gettime(CLOCK_MONOTONIC, &t1);
+ for (i = 0; i < CALIBRATION_STEP; i++)
+ sysinfo(&info);
+ clock_gettime(CLOCK_MONOTONIC, &t2);
+ return (t2.tv_sec - t1.tv_sec) + 1.0e-9 * (t2.tv_nsec - t1.tv_nsec);
+}
+
+static void calibrate_set(void)
+{
+ double elapsed = 0;
+
+ printf("Calibrating test set to last ~%d seconds...\n", CALIBRATE_TO_SECS);
+
+ while (elapsed < 1) {
+ elapsed += one_sysinfo_step();
+ factor += CALIBRATE_TO_SECS;
+ }
+
+ printf("test iterations = %d\n", CALIBRATION_STEP * factor);
+}
+
+static double perf_syscall(void)
+{
+ unsigned int i;
+ double partial = 0;
+
+ for (i = 0; i < factor; ++i)
+ partial += one_sysinfo_step()/(CALIBRATION_STEP*factor);
+ return partial;
+}
+
+static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
+{
+ char buf[1024];
+ int len;
+
+ SYSCALL_UNBLOCK;
+
+ /* printf and friends are not signal-safe. */
+ len = snprintf(buf, 1024, "Caught sys_%x\n", info->si_syscall);
+ write(1, buf, len);
+
+ if (info->si_syscall == MAGIC_SYSCALL_1)
+ trapped_call_count++;
+ else
+ native_call_count++;
+
+#ifdef TEST_BLOCKED_RETURN
+ SYSCALL_BLOCK;
+#endif
+
+#ifdef __x86_64__
+ __asm__ volatile("movq $0xf, %rax");
+ __asm__ volatile("leaveq");
+ __asm__ volatile("add $0x8, %rsp");
+ __asm__ volatile("syscall_dispatcher_start:");
+ __asm__ volatile("syscall");
+ __asm__ volatile("nop"); /* Landing pad within dispatcher area */
+ __asm__ volatile("syscall_dispatcher_end:");
+#endif
+
+}
+
+int main(void)
+{
+ struct sigaction act;
+ double time1, time2;
+ int ret;
+ sigset_t mask;
+
+ memset(&act, 0, sizeof(act));
+ sigemptyset(&mask);
+
+ act.sa_sigaction = handle_sigsys;
+ act.sa_flags = SA_SIGINFO;
+ act.sa_mask = mask;
+
+ calibrate_set();
+
+ time1 = perf_syscall();
+ printf("Avg syscall time %.0lfns.\n", time1 * 1.0e9);
+
+ ret = sigaction(SIGSYS, &act, NULL);
+ if (ret) {
+ perror("Error sigaction:");
+ exit(-1);
+ }
+
+ fprintf(stderr, "Enabling syscall trapping.\n");
+
+ if (prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON,
+ syscall_dispatcher_start,
+ (syscall_dispatcher_end - syscall_dispatcher_start + 1),
+ &selector)) {
+ perror("prctl failed\n");
+ exit(-1);
+ }
+
+ SYSCALL_BLOCK;
+ syscall(MAGIC_SYSCALL_1);
+
+#ifdef TEST_BLOCKED_RETURN
+ if (selector == PR_SYS_DISPATCH_OFF) {
+ fprintf(stderr, "Failed to return with selector blocked.\n");
+ exit(-1);
+ }
+#endif
+
+ SYSCALL_UNBLOCK;
+
+ if (!trapped_call_count) {
+ fprintf(stderr, "syscall trapping does not work.\n");
+ exit(-1);
+ }
+
+ time2 = perf_syscall();
+
+ if (native_call_count) {
+ perror("syscall trapping intercepted more syscalls than expected\n");
+ exit(-1);
+ }
+
+ printf("trapped_call_count %lu, native_call_count %lu.\n",
+ trapped_call_count, native_call_count);
+ printf("Avg syscall time %.0lfns.\n", time2 * 1.0e9);
+ printf("Interception overhead: %.1lf%% (+%.0lfns).\n",
+ 100.0 * (time2 / time1 - 1.0), 1.0e9 * (time2 - time1));
+ return 0;
+
+}
diff --git a/tools/testing/selftests/syscall_user_dispatch/sud_test.c b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
new file mode 100644
index 000000000000..6498b050ef89
--- /dev/null
+++ b/tools/testing/selftests/syscall_user_dispatch/sud_test.c
@@ -0,0 +1,310 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Collabora Ltd.
+ *
+ * Test code for syscall user dispatch
+ */
+
+#define _GNU_SOURCE
+#include <sys/prctl.h>
+#include <sys/sysinfo.h>
+#include <sys/syscall.h>
+#include <signal.h>
+
+#include <asm/unistd.h>
+#include "../kselftest_harness.h"
+
+#ifndef PR_SET_SYSCALL_USER_DISPATCH
+# define PR_SET_SYSCALL_USER_DISPATCH 59
+# define PR_SYS_DISPATCH_OFF 0
+# define PR_SYS_DISPATCH_ON 1
+#endif
+
+#ifndef SYS_USER_DISPATCH
+# define SYS_USER_DISPATCH 2
+#endif
+
+#ifdef __NR_syscalls
+# define MAGIC_SYSCALL_1 (__NR_syscalls + 1) /* Bad Linux syscall number */
+#else
+# define MAGIC_SYSCALL_1 (0xff00) /* Bad Linux syscall number */
+#endif
+
+#define SYSCALL_DISPATCH_ON(x) ((x) = 1)
+#define SYSCALL_DISPATCH_OFF(x) ((x) = 0)
+
+/* Test Summary:
+ *
+ * - dispatch_trigger_sigsys: Verify if PR_SET_SYSCALL_USER_DISPATCH is
+ * able to trigger SIGSYS on a syscall.
+ *
+ * - bad_selector: Test that a bad selector value triggers SIGSYS with
+ * si_errno EINVAL.
+ *
+ * - bad_prctl_param: Test that the API correctly rejects invalid
+ * parameters on prctl
+ *
+ * - dispatch_and_return: Test that a syscall is selectively dispatched
+ * to userspace depending on the value of selector.
+ *
+ * - disable_dispatch: Test that the PR_SYS_DISPATCH_OFF correctly
+ * disables the dispatcher
+ *
+ * - direct_dispatch_range: Test that a syscall within the allowed range
+ * can bypass the dispatcher.
+ */
+
+TEST_SIGNAL(dispatch_trigger_sigsys, SIGSYS)
+{
+ char sel = 0;
+ struct sysinfo info;
+ int ret;
+
+ ret = sysinfo(&info);
+ ASSERT_EQ(0, ret);
+
+ ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &sel);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+ }
+
+ SYSCALL_DISPATCH_ON(sel);
+
+ sysinfo(&info);
+
+ EXPECT_FALSE(true) {
+ TH_LOG("Unreachable!");
+ }
+}
+
+TEST(bad_prctl_param)
+{
+ char sel = 0;
+ int op;
+
+ /* Invalid op */
+ op = -1;
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0, 0, &sel);
+ ASSERT_EQ(EINVAL, errno);
+
+ /* PR_SYS_DISPATCH_OFF */
+ op = PR_SYS_DISPATCH_OFF;
+
+ /* offset != 0 */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x1, 0x0, 0);
+ EXPECT_EQ(EINVAL, errno);
+
+ /* len != 0 */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0xff, 0);
+ EXPECT_EQ(EINVAL, errno);
+
+ /* sel != NULL */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x0, &sel);
+ EXPECT_EQ(EINVAL, errno);
+
+ /* Valid parameter */
+ errno = 0;
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x0, 0x0);
+ EXPECT_EQ(0, errno);
+
+ /* PR_SYS_DISPATCH_ON */
+ op = PR_SYS_DISPATCH_ON;
+
+ /* Dispatcher region is bad (offset > 0 && len == 0) */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x1, 0x0, &sel);
+ EXPECT_EQ(EINVAL, errno);
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, -1L, 0x0, &sel);
+ EXPECT_EQ(EINVAL, errno);
+
+ /* Invalid selector */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, op, 0x0, 0x1, (void *) -1);
+ ASSERT_EQ(EFAULT, errno);
+
+ /*
+ * Dispatcher range overflows unsigned long
+ */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 1, -1L, &sel);
+ ASSERT_EQ(EINVAL, errno) {
+ TH_LOG("Should reject bad syscall range");
+ }
+
+ /*
+ * Allowed range overflows usigned long
+ */
+ prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, -1L, 0x1, &sel);
+ ASSERT_EQ(EINVAL, errno) {
+ TH_LOG("Should reject bad syscall range");
+ }
+}
+
+/*
+ * Use global selector for handle_sigsys tests, to avoid passing
+ * selector to signal handler
+ */
+char glob_sel;
+int nr_syscalls_emulated;
+int si_code;
+int si_errno;
+
+static void handle_sigsys(int sig, siginfo_t *info, void *ucontext)
+{
+ si_code = info->si_code;
+ si_errno = info->si_errno;
+
+ if (info->si_syscall == MAGIC_SYSCALL_1)
+ nr_syscalls_emulated++;
+
+ /* In preparation for sigreturn. */
+ SYSCALL_DISPATCH_OFF(glob_sel);
+}
+
+TEST(dispatch_and_return)
+{
+ long ret;
+ struct sigaction act;
+ sigset_t mask;
+
+ glob_sel = 0;
+ nr_syscalls_emulated = 0;
+ si_code = 0;
+ si_errno = 0;
+
+ memset(&act, 0, sizeof(act));
+ sigemptyset(&mask);
+
+ act.sa_sigaction = handle_sigsys;
+ act.sa_flags = SA_SIGINFO;
+ act.sa_mask = mask;
+
+ ret = sigaction(SIGSYS, &act, NULL);
+ ASSERT_EQ(0, ret);
+
+ /* Make sure selector is good prior to prctl. */
+ SYSCALL_DISPATCH_OFF(glob_sel);
+
+ ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &glob_sel);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+ }
+
+ /* MAGIC_SYSCALL_1 doesn't exist. */
+ SYSCALL_DISPATCH_OFF(glob_sel);
+ ret = syscall(MAGIC_SYSCALL_1);
+ EXPECT_EQ(-1, ret) {
+ TH_LOG("Dispatch triggered unexpectedly");
+ }
+
+ /* MAGIC_SYSCALL_1 should be emulated. */
+ nr_syscalls_emulated = 0;
+ SYSCALL_DISPATCH_ON(glob_sel);
+
+ ret = syscall(MAGIC_SYSCALL_1);
+ EXPECT_EQ(MAGIC_SYSCALL_1, ret) {
+ TH_LOG("Failed to intercept syscall");
+ }
+ EXPECT_EQ(1, nr_syscalls_emulated) {
+ TH_LOG("Failed to emulate syscall");
+ }
+ ASSERT_EQ(SYS_USER_DISPATCH, si_code) {
+ TH_LOG("Bad si_code in SIGSYS");
+ }
+ ASSERT_EQ(0, si_errno) {
+ TH_LOG("Bad si_errno in SIGSYS");
+ }
+}
+
+TEST_SIGNAL(bad_selector, SIGSYS)
+{
+ long ret;
+ struct sigaction act;
+ sigset_t mask;
+ struct sysinfo info;
+
+ glob_sel = 0;
+ nr_syscalls_emulated = 0;
+ si_code = 0;
+ si_errno = 0;
+
+ memset(&act, 0, sizeof(act));
+ sigemptyset(&mask);
+
+ act.sa_sigaction = handle_sigsys;
+ act.sa_flags = SA_SIGINFO;
+ act.sa_mask = mask;
+
+ ret = sigaction(SIGSYS, &act, NULL);
+ ASSERT_EQ(0, ret);
+
+ /* Make sure selector is good prior to prctl. */
+ SYSCALL_DISPATCH_OFF(glob_sel);
+
+ ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &glob_sel);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+ }
+
+ glob_sel = -1;
+
+ sysinfo(&info);
+
+ /* Even though it is ready to catch SIGSYS, the signal is
+ * supposed to be uncatchable.
+ */
+
+ EXPECT_FALSE(true) {
+ TH_LOG("Unreachable!");
+ }
+}
+
+TEST(disable_dispatch)
+{
+ int ret;
+ struct sysinfo info;
+ char sel = 0;
+
+ ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, 0, &sel);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+ }
+
+ /* MAGIC_SYSCALL_1 doesn't exist. */
+ SYSCALL_DISPATCH_OFF(glob_sel);
+
+ ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_OFF, 0, 0, 0);
+ EXPECT_EQ(0, ret) {
+ TH_LOG("Failed to unset syscall user dispatch");
+ }
+
+ /* Shouldn't have any effect... */
+ SYSCALL_DISPATCH_ON(glob_sel);
+
+ ret = syscall(__NR_sysinfo, &info);
+ EXPECT_EQ(0, ret) {
+ TH_LOG("Dispatch triggered unexpectedly");
+ }
+}
+
+TEST(direct_dispatch_range)
+{
+ int ret = 0;
+ struct sysinfo info;
+ char sel = 0;
+
+ /*
+ * Instead of calculating libc addresses; allow the entire
+ * memory map and lock the selector.
+ */
+ ret = prctl(PR_SET_SYSCALL_USER_DISPATCH, PR_SYS_DISPATCH_ON, 0, -1L, &sel);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support CONFIG_SYSCALL_USER_DISPATCH");
+ }
+
+ SYSCALL_DISPATCH_ON(sel);
+
+ ret = sysinfo(&info);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Dispatch triggered unexpectedly");
+ }
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index c33a7aac27ff..b71828df5a6d 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -59,6 +59,7 @@ CONFIG_NET_IFE_SKBPRIO=m
CONFIG_NET_IFE_SKBTCINDEX=m
CONFIG_NET_SCH_FIFO=y
CONFIG_NET_SCH_ETS=m
+CONFIG_NET_SCH_RED=m
#
## Network testing
diff --git a/tools/testing/selftests/timens/procfs.c b/tools/testing/selftests/timens/procfs.c
index 7f14f0fdac84..f2519154208a 100644
--- a/tools/testing/selftests/timens/procfs.c
+++ b/tools/testing/selftests/timens/procfs.c
@@ -93,6 +93,33 @@ static int read_proc_uptime(struct timespec *uptime)
return 0;
}
+static int read_proc_stat_btime(unsigned long long *boottime_sec)
+{
+ FILE *proc;
+ char line_buf[2048];
+
+ proc = fopen("/proc/stat", "r");
+ if (proc == NULL) {
+ pr_perror("Unable to open /proc/stat");
+ return -1;
+ }
+
+ while (fgets(line_buf, 2048, proc)) {
+ if (sscanf(line_buf, "btime %llu", boottime_sec) != 1)
+ continue;
+ fclose(proc);
+ return 0;
+ }
+ if (errno) {
+ pr_perror("fscanf");
+ fclose(proc);
+ return -errno;
+ }
+ pr_err("failed to parse /proc/stat");
+ fclose(proc);
+ return -1;
+}
+
static int check_uptime(void)
{
struct timespec uptime_new, uptime_old;
@@ -123,18 +150,47 @@ static int check_uptime(void)
return 0;
}
+static int check_stat_btime(void)
+{
+ unsigned long long btime_new, btime_old;
+ unsigned long long btime_expected;
+
+ if (switch_ns(parent_ns))
+ return pr_err("switch_ns(%d)", parent_ns);
+
+ if (read_proc_stat_btime(&btime_old))
+ return 1;
+
+ if (switch_ns(child_ns))
+ return pr_err("switch_ns(%d)", child_ns);
+
+ if (read_proc_stat_btime(&btime_new))
+ return 1;
+
+ btime_expected = btime_old - TEN_DAYS_IN_SEC;
+ if (btime_new != btime_expected) {
+ pr_fail("btime in /proc/stat: old %llu, new %llu [%llu]",
+ btime_old, btime_new, btime_expected);
+ return 1;
+ }
+
+ ksft_test_result_pass("Passed for /proc/stat btime\n");
+ return 0;
+}
+
int main(int argc, char *argv[])
{
int ret = 0;
nscheck();
- ksft_set_plan(1);
+ ksft_set_plan(2);
if (init_namespaces())
return 1;
ret |= check_uptime();
+ ret |= check_stat_btime();
if (ret)
ksft_exit_fail();
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 0069f2f83f86..d53a4d8008f9 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -5,13 +5,16 @@ uname_M := $(shell uname -m 2>/dev/null || echo not)
ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
TEST_GEN_PROGS := $(OUTPUT)/vdso_test_gettimeofday $(OUTPUT)/vdso_test_getcpu
-ifeq ($(ARCH),x86)
+TEST_GEN_PROGS += $(OUTPUT)/vdso_test_abi
+TEST_GEN_PROGS += $(OUTPUT)/vdso_test_clock_getres
+ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64))
TEST_GEN_PROGS += $(OUTPUT)/vdso_standalone_test_x86
endif
+TEST_GEN_PROGS += $(OUTPUT)/vdso_test_correctness
-ifndef CROSS_COMPILE
CFLAGS := -std=gnu99
CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
+LDFLAGS_vdso_test_correctness := -ldl
ifeq ($(CONFIG_X86_32),y)
LDLIBS += -lgcc_s
endif
@@ -19,9 +22,14 @@ endif
all: $(TEST_GEN_PROGS)
$(OUTPUT)/vdso_test_gettimeofday: parse_vdso.c vdso_test_gettimeofday.c
$(OUTPUT)/vdso_test_getcpu: parse_vdso.c vdso_test_getcpu.c
+$(OUTPUT)/vdso_test_abi: parse_vdso.c vdso_test_abi.c
+$(OUTPUT)/vdso_test_clock_getres: vdso_test_clock_getres.c
$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
$(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \
vdso_standalone_test_x86.c parse_vdso.c \
-o $@
-
-endif
+$(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c
+ $(CC) $(CFLAGS) \
+ vdso_test_correctness.c \
+ -o $@ \
+ $(LDFLAGS_vdso_test_correctness)
diff --git a/tools/testing/selftests/vDSO/vdso_config.h b/tools/testing/selftests/vDSO/vdso_config.h
new file mode 100644
index 000000000000..6a6fe8d4ff55
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_config.h
@@ -0,0 +1,92 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * vdso_config.h: Configuration options for vDSO tests.
+ * Copyright (c) 2019 Arm Ltd.
+ */
+#ifndef __VDSO_CONFIG_H__
+#define __VDSO_CONFIG_H__
+
+/*
+ * Each architecture exports its vDSO implementation with different names
+ * and a different version from the others, so we need to handle it as a
+ * special case.
+ */
+#if defined(__arm__)
+#define VDSO_VERSION 0
+#define VDSO_NAMES 1
+#define VDSO_32BIT 1
+#elif defined(__aarch64__)
+#define VDSO_VERSION 3
+#define VDSO_NAMES 0
+#elif defined(__powerpc__)
+#define VDSO_VERSION 1
+#define VDSO_NAMES 0
+#define VDSO_32BIT 1
+#elif defined(__powerpc64__)
+#define VDSO_VERSION 1
+#define VDSO_NAMES 0
+#elif defined (__s390__)
+#define VDSO_VERSION 2
+#define VDSO_NAMES 0
+#define VDSO_32BIT 1
+#elif defined (__s390X__)
+#define VDSO_VERSION 2
+#define VDSO_NAMES 0
+#elif defined(__mips__)
+#define VDSO_VERSION 0
+#define VDSO_NAMES 1
+#define VDSO_32BIT 1
+#elif defined(__sparc__)
+#define VDSO_VERSION 0
+#define VDSO_NAMES 1
+#define VDSO_32BIT 1
+#elif defined(__i386__)
+#define VDSO_VERSION 0
+#define VDSO_NAMES 1
+#define VDSO_32BIT 1
+#elif defined(__x86_64__)
+#define VDSO_VERSION 0
+#define VDSO_NAMES 1
+#elif defined(__riscv__)
+#define VDSO_VERSION 5
+#define VDSO_NAMES 1
+#define VDSO_32BIT 1
+#else /* nds32 */
+#define VDSO_VERSION 4
+#define VDSO_NAMES 1
+#define VDSO_32BIT 1
+#endif
+
+static const char *versions[6] = {
+ "LINUX_2.6",
+ "LINUX_2.6.15",
+ "LINUX_2.6.29",
+ "LINUX_2.6.39",
+ "LINUX_4",
+ "LINUX_4.15",
+};
+
+static const char *names[2][6] = {
+ {
+ "__kernel_gettimeofday",
+ "__kernel_clock_gettime",
+ "__kernel_time",
+ "__kernel_clock_getres",
+ "__kernel_getcpu",
+#if defined(VDSO_32BIT)
+ "__kernel_clock_gettime64",
+#endif
+ },
+ {
+ "__vdso_gettimeofday",
+ "__vdso_clock_gettime",
+ "__vdso_time",
+ "__vdso_clock_getres",
+ "__vdso_getcpu",
+#if defined(VDSO_32BIT)
+ "__vdso_clock_gettime64",
+#endif
+ },
+};
+
+#endif /* __VDSO_CONFIG_H__ */
diff --git a/tools/testing/selftests/vDSO/vdso_test_abi.c b/tools/testing/selftests/vDSO/vdso_test_abi.c
new file mode 100644
index 000000000000..3d603f1394af
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_test_abi.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * vdso_full_test.c: Sample code to test all the timers.
+ * Copyright (c) 2019 Arm Ltd.
+ *
+ * Compile with:
+ * gcc -std=gnu99 vdso_full_test.c parse_vdso.c
+ *
+ */
+
+#include <stdint.h>
+#include <elf.h>
+#include <stdio.h>
+#include <time.h>
+#include <sys/auxv.h>
+#include <sys/time.h>
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+
+#include "../kselftest.h"
+#include "vdso_config.h"
+
+extern void *vdso_sym(const char *version, const char *name);
+extern void vdso_init_from_sysinfo_ehdr(uintptr_t base);
+extern void vdso_init_from_auxv(void *auxv);
+
+static const char *version;
+static const char **name;
+
+typedef long (*vdso_gettimeofday_t)(struct timeval *tv, struct timezone *tz);
+typedef long (*vdso_clock_gettime_t)(clockid_t clk_id, struct timespec *ts);
+typedef long (*vdso_clock_getres_t)(clockid_t clk_id, struct timespec *ts);
+typedef time_t (*vdso_time_t)(time_t *t);
+
+static int vdso_test_gettimeofday(void)
+{
+ /* Find gettimeofday. */
+ vdso_gettimeofday_t vdso_gettimeofday =
+ (vdso_gettimeofday_t)vdso_sym(version, name[0]);
+
+ if (!vdso_gettimeofday) {
+ printf("Could not find %s\n", name[0]);
+ return KSFT_SKIP;
+ }
+
+ struct timeval tv;
+ long ret = vdso_gettimeofday(&tv, 0);
+
+ if (ret == 0) {
+ printf("The time is %lld.%06lld\n",
+ (long long)tv.tv_sec, (long long)tv.tv_usec);
+ } else {
+ printf("%s failed\n", name[0]);
+ return KSFT_FAIL;
+ }
+
+ return KSFT_PASS;
+}
+
+static int vdso_test_clock_gettime(clockid_t clk_id)
+{
+ /* Find clock_gettime. */
+ vdso_clock_gettime_t vdso_clock_gettime =
+ (vdso_clock_gettime_t)vdso_sym(version, name[1]);
+
+ if (!vdso_clock_gettime) {
+ printf("Could not find %s\n", name[1]);
+ return KSFT_SKIP;
+ }
+
+ struct timespec ts;
+ long ret = vdso_clock_gettime(clk_id, &ts);
+
+ if (ret == 0) {
+ printf("The time is %lld.%06lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ } else {
+ printf("%s failed\n", name[1]);
+ return KSFT_FAIL;
+ }
+
+ return KSFT_PASS;
+}
+
+static int vdso_test_time(void)
+{
+ /* Find time. */
+ vdso_time_t vdso_time =
+ (vdso_time_t)vdso_sym(version, name[2]);
+
+ if (!vdso_time) {
+ printf("Could not find %s\n", name[2]);
+ return KSFT_SKIP;
+ }
+
+ long ret = vdso_time(NULL);
+
+ if (ret > 0) {
+ printf("The time in hours since January 1, 1970 is %lld\n",
+ (long long)(ret / 3600));
+ } else {
+ printf("%s failed\n", name[2]);
+ return KSFT_FAIL;
+ }
+
+ return KSFT_PASS;
+}
+
+static int vdso_test_clock_getres(clockid_t clk_id)
+{
+ /* Find clock_getres. */
+ vdso_clock_getres_t vdso_clock_getres =
+ (vdso_clock_getres_t)vdso_sym(version, name[3]);
+
+ if (!vdso_clock_getres) {
+ printf("Could not find %s\n", name[3]);
+ return KSFT_SKIP;
+ }
+
+ struct timespec ts, sys_ts;
+ long ret = vdso_clock_getres(clk_id, &ts);
+
+ if (ret == 0) {
+ printf("The resolution is %lld %lld\n",
+ (long long)ts.tv_sec, (long long)ts.tv_nsec);
+ } else {
+ printf("%s failed\n", name[3]);
+ return KSFT_FAIL;
+ }
+
+ ret = syscall(SYS_clock_getres, clk_id, &sys_ts);
+
+ if ((sys_ts.tv_sec != ts.tv_sec) || (sys_ts.tv_nsec != ts.tv_nsec)) {
+ printf("%s failed\n", name[3]);
+ return KSFT_FAIL;
+ }
+
+ return KSFT_PASS;
+}
+
+const char *vdso_clock_name[12] = {
+ "CLOCK_REALTIME",
+ "CLOCK_MONOTONIC",
+ "CLOCK_PROCESS_CPUTIME_ID",
+ "CLOCK_THREAD_CPUTIME_ID",
+ "CLOCK_MONOTONIC_RAW",
+ "CLOCK_REALTIME_COARSE",
+ "CLOCK_MONOTONIC_COARSE",
+ "CLOCK_BOOTTIME",
+ "CLOCK_REALTIME_ALARM",
+ "CLOCK_BOOTTIME_ALARM",
+ "CLOCK_SGI_CYCLE",
+ "CLOCK_TAI",
+};
+
+/*
+ * This function calls vdso_test_clock_gettime and vdso_test_clock_getres
+ * with different values for clock_id.
+ */
+static inline int vdso_test_clock(clockid_t clock_id)
+{
+ int ret0, ret1;
+
+ ret0 = vdso_test_clock_gettime(clock_id);
+ /* A skipped test is considered passed */
+ if (ret0 == KSFT_SKIP)
+ ret0 = KSFT_PASS;
+
+ ret1 = vdso_test_clock_getres(clock_id);
+ /* A skipped test is considered passed */
+ if (ret1 == KSFT_SKIP)
+ ret1 = KSFT_PASS;
+
+ ret0 += ret1;
+
+ printf("clock_id: %s", vdso_clock_name[clock_id]);
+
+ if (ret0 > 0)
+ printf(" [FAIL]\n");
+ else
+ printf(" [PASS]\n");
+
+ return ret0;
+}
+
+int main(int argc, char **argv)
+{
+ unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR);
+ int ret;
+
+ if (!sysinfo_ehdr) {
+ printf("AT_SYSINFO_EHDR is not present!\n");
+ return KSFT_SKIP;
+ }
+
+ version = versions[VDSO_VERSION];
+ name = (const char **)&names[VDSO_NAMES];
+
+ printf("[vDSO kselftest] VDSO_VERSION: %s\n", version);
+
+ vdso_init_from_sysinfo_ehdr(getauxval(AT_SYSINFO_EHDR));
+
+ ret = vdso_test_gettimeofday();
+
+#if _POSIX_TIMERS > 0
+
+#ifdef CLOCK_REALTIME
+ ret += vdso_test_clock(CLOCK_REALTIME);
+#endif
+
+#ifdef CLOCK_BOOTTIME
+ ret += vdso_test_clock(CLOCK_BOOTTIME);
+#endif
+
+#ifdef CLOCK_TAI
+ ret += vdso_test_clock(CLOCK_TAI);
+#endif
+
+#ifdef CLOCK_REALTIME_COARSE
+ ret += vdso_test_clock(CLOCK_REALTIME_COARSE);
+#endif
+
+#ifdef CLOCK_MONOTONIC
+ ret += vdso_test_clock(CLOCK_MONOTONIC);
+#endif
+
+#ifdef CLOCK_MONOTONIC_RAW
+ ret += vdso_test_clock(CLOCK_MONOTONIC_RAW);
+#endif
+
+#ifdef CLOCK_MONOTONIC_COARSE
+ ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE);
+#endif
+
+#endif
+
+ ret += vdso_test_time();
+
+ if (ret > 0)
+ return KSFT_FAIL;
+
+ return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/vDSO/vdso_test_clock_getres.c b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c
new file mode 100644
index 000000000000..15dcee16ff72
--- /dev/null
+++ b/tools/testing/selftests/vDSO/vdso_test_clock_getres.c
@@ -0,0 +1,124 @@
+// SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+/*
+ * vdso_clock_getres.c: Sample code to test clock_getres.
+ * Copyright (c) 2019 Arm Ltd.
+ *
+ * Compile with:
+ * gcc -std=gnu99 vdso_clock_getres.c
+ *
+ * Tested on ARM, ARM64, MIPS32, x86 (32-bit and 64-bit),
+ * Power (32-bit and 64-bit), S390x (32-bit and 64-bit).
+ * Might work on other architectures.
+ */
+
+#define _GNU_SOURCE
+#include <elf.h>
+#include <err.h>
+#include <fcntl.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <time.h>
+#include <sys/auxv.h>
+#include <sys/mman.h>
+#include <sys/time.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+#include "../kselftest.h"
+
+static long syscall_clock_getres(clockid_t _clkid, struct timespec *_ts)
+{
+ long ret;
+
+ ret = syscall(SYS_clock_getres, _clkid, _ts);
+
+ return ret;
+}
+
+const char *vdso_clock_name[12] = {
+ "CLOCK_REALTIME",
+ "CLOCK_MONOTONIC",
+ "CLOCK_PROCESS_CPUTIME_ID",
+ "CLOCK_THREAD_CPUTIME_ID",
+ "CLOCK_MONOTONIC_RAW",
+ "CLOCK_REALTIME_COARSE",
+ "CLOCK_MONOTONIC_COARSE",
+ "CLOCK_BOOTTIME",
+ "CLOCK_REALTIME_ALARM",
+ "CLOCK_BOOTTIME_ALARM",
+ "CLOCK_SGI_CYCLE",
+ "CLOCK_TAI",
+};
+
+/*
+ * This function calls clock_getres in vdso and by system call
+ * with different values for clock_id.
+ *
+ * Example of output:
+ *
+ * clock_id: CLOCK_REALTIME [PASS]
+ * clock_id: CLOCK_BOOTTIME [PASS]
+ * clock_id: CLOCK_TAI [PASS]
+ * clock_id: CLOCK_REALTIME_COARSE [PASS]
+ * clock_id: CLOCK_MONOTONIC [PASS]
+ * clock_id: CLOCK_MONOTONIC_RAW [PASS]
+ * clock_id: CLOCK_MONOTONIC_COARSE [PASS]
+ */
+static inline int vdso_test_clock(unsigned int clock_id)
+{
+ struct timespec x, y;
+
+ printf("clock_id: %s", vdso_clock_name[clock_id]);
+ clock_getres(clock_id, &x);
+ syscall_clock_getres(clock_id, &y);
+
+ if ((x.tv_sec != y.tv_sec) || (x.tv_nsec != y.tv_nsec)) {
+ printf(" [FAIL]\n");
+ return KSFT_FAIL;
+ }
+
+ printf(" [PASS]\n");
+ return KSFT_PASS;
+}
+
+int main(int argc, char **argv)
+{
+ int ret;
+
+#if _POSIX_TIMERS > 0
+
+#ifdef CLOCK_REALTIME
+ ret = vdso_test_clock(CLOCK_REALTIME);
+#endif
+
+#ifdef CLOCK_BOOTTIME
+ ret += vdso_test_clock(CLOCK_BOOTTIME);
+#endif
+
+#ifdef CLOCK_TAI
+ ret += vdso_test_clock(CLOCK_TAI);
+#endif
+
+#ifdef CLOCK_REALTIME_COARSE
+ ret += vdso_test_clock(CLOCK_REALTIME_COARSE);
+#endif
+
+#ifdef CLOCK_MONOTONIC
+ ret += vdso_test_clock(CLOCK_MONOTONIC);
+#endif
+
+#ifdef CLOCK_MONOTONIC_RAW
+ ret += vdso_test_clock(CLOCK_MONOTONIC_RAW);
+#endif
+
+#ifdef CLOCK_MONOTONIC_COARSE
+ ret += vdso_test_clock(CLOCK_MONOTONIC_COARSE);
+#endif
+
+#endif
+ if (ret > 0)
+ return KSFT_FAIL;
+
+ return KSFT_PASS;
+}
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c
index 42052db0f870..5029ef9b228c 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c
@@ -19,6 +19,10 @@
#include <stdbool.h>
#include <limits.h>
+#include "vdso_config.h"
+
+static const char **name;
+
#ifndef SYS_getcpu
# ifdef __x86_64__
# define SYS_getcpu 309
@@ -27,6 +31,17 @@
# endif
#endif
+#ifndef __NR_clock_gettime64
+#define __NR_clock_gettime64 403
+#endif
+
+#ifndef __kernel_timespec
+struct __kernel_timespec {
+ long long tv_sec;
+ long long tv_nsec;
+};
+#endif
+
/* max length of lines in /proc/self/maps - anything longer is skipped here */
#define MAPS_LINE_LEN 128
@@ -36,6 +51,10 @@ typedef int (*vgettime_t)(clockid_t, struct timespec *);
vgettime_t vdso_clock_gettime;
+typedef int (*vgettime64_t)(clockid_t, struct __kernel_timespec *);
+
+vgettime64_t vdso_clock_gettime64;
+
typedef long (*vgtod_t)(struct timeval *tv, struct timezone *tz);
vgtod_t vdso_gettimeofday;
@@ -99,17 +118,23 @@ static void fill_function_pointers()
return;
}
- vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu");
+ vdso_getcpu = (getcpu_t)dlsym(vdso, name[4]);
if (!vdso_getcpu)
printf("Warning: failed to find getcpu in vDSO\n");
vgetcpu = (getcpu_t) vsyscall_getcpu();
- vdso_clock_gettime = (vgettime_t)dlsym(vdso, "__vdso_clock_gettime");
+ vdso_clock_gettime = (vgettime_t)dlsym(vdso, name[1]);
if (!vdso_clock_gettime)
printf("Warning: failed to find clock_gettime in vDSO\n");
- vdso_gettimeofday = (vgtod_t)dlsym(vdso, "__vdso_gettimeofday");
+#if defined(VDSO_32BIT)
+ vdso_clock_gettime64 = (vgettime64_t)dlsym(vdso, name[5]);
+ if (!vdso_clock_gettime64)
+ printf("Warning: failed to find clock_gettime64 in vDSO\n");
+#endif
+
+ vdso_gettimeofday = (vgtod_t)dlsym(vdso, name[0]);
if (!vdso_gettimeofday)
printf("Warning: failed to find gettimeofday in vDSO\n");
@@ -126,6 +151,11 @@ static inline int sys_clock_gettime(clockid_t id, struct timespec *ts)
return syscall(__NR_clock_gettime, id, ts);
}
+static inline int sys_clock_gettime64(clockid_t id, struct __kernel_timespec *ts)
+{
+ return syscall(__NR_clock_gettime64, id, ts);
+}
+
static inline int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
{
return syscall(__NR_gettimeofday, tv, tz);
@@ -191,6 +221,15 @@ static bool ts_leq(const struct timespec *a, const struct timespec *b)
return a->tv_nsec <= b->tv_nsec;
}
+static bool ts64_leq(const struct __kernel_timespec *a,
+ const struct __kernel_timespec *b)
+{
+ if (a->tv_sec != b->tv_sec)
+ return a->tv_sec < b->tv_sec;
+ else
+ return a->tv_nsec <= b->tv_nsec;
+}
+
static bool tv_leq(const struct timeval *a, const struct timeval *b)
{
if (a->tv_sec != b->tv_sec)
@@ -254,7 +293,10 @@ static void test_one_clock_gettime(int clock, const char *name)
if (!ts_leq(&start, &vdso) || !ts_leq(&vdso, &end)) {
printf("[FAIL]\tTimes are out of sequence\n");
nerrs++;
+ return;
}
+
+ printf("[OK]\tTest Passed.\n");
}
static void test_clock_gettime(void)
@@ -275,6 +317,70 @@ static void test_clock_gettime(void)
test_one_clock_gettime(INT_MAX, "invalid");
}
+static void test_one_clock_gettime64(int clock, const char *name)
+{
+ struct __kernel_timespec start, vdso, end;
+ int vdso_ret, end_ret;
+
+ printf("[RUN]\tTesting clock_gettime64 for clock %s (%d)...\n", name, clock);
+
+ if (sys_clock_gettime64(clock, &start) < 0) {
+ if (errno == EINVAL) {
+ vdso_ret = vdso_clock_gettime64(clock, &vdso);
+ if (vdso_ret == -EINVAL) {
+ printf("[OK]\tNo such clock.\n");
+ } else {
+ printf("[FAIL]\tNo such clock, but __vdso_clock_gettime64 returned %d\n", vdso_ret);
+ nerrs++;
+ }
+ } else {
+ printf("[WARN]\t clock_gettime64(%d) syscall returned error %d\n", clock, errno);
+ }
+ return;
+ }
+
+ vdso_ret = vdso_clock_gettime64(clock, &vdso);
+ end_ret = sys_clock_gettime64(clock, &end);
+
+ if (vdso_ret != 0 || end_ret != 0) {
+ printf("[FAIL]\tvDSO returned %d, syscall errno=%d\n",
+ vdso_ret, errno);
+ nerrs++;
+ return;
+ }
+
+ printf("\t%llu.%09ld %llu.%09ld %llu.%09ld\n",
+ (unsigned long long)start.tv_sec, start.tv_nsec,
+ (unsigned long long)vdso.tv_sec, vdso.tv_nsec,
+ (unsigned long long)end.tv_sec, end.tv_nsec);
+
+ if (!ts64_leq(&start, &vdso) || !ts64_leq(&vdso, &end)) {
+ printf("[FAIL]\tTimes are out of sequence\n");
+ nerrs++;
+ return;
+ }
+
+ printf("[OK]\tTest Passed.\n");
+}
+
+static void test_clock_gettime64(void)
+{
+ if (!vdso_clock_gettime64) {
+ printf("[SKIP]\tNo vDSO, so skipping clock_gettime64() tests\n");
+ return;
+ }
+
+ for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
+ clock++) {
+ test_one_clock_gettime64(clock, clocknames[clock]);
+ }
+
+ /* Also test some invalid clock ids */
+ test_one_clock_gettime64(-1, "invalid");
+ test_one_clock_gettime64(INT_MIN, "invalid");
+ test_one_clock_gettime64(INT_MAX, "invalid");
+}
+
static void test_gettimeofday(void)
{
struct timeval start, vdso, end;
@@ -327,9 +433,12 @@ static void test_gettimeofday(void)
int main(int argc, char **argv)
{
+ name = (const char **)&names[VDSO_NAMES];
+
fill_function_pointers();
test_clock_gettime();
+ test_clock_gettime64();
test_gettimeofday();
/*
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 849e8226395a..9a35c3f6a557 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -8,6 +8,7 @@ thuge-gen
compaction_test
mlock2-tests
mremap_dontunmap
+mremap_test
on-fault-limit
transhuge-stress
protection_keys
@@ -15,8 +16,9 @@ userfaultfd
mlock-intersect-test
mlock-random-test
virtual_address_range
-gup_benchmark
+gup_test
va_128TBswitch
map_fixed_noreplace
write_to_hugetlbfs
hmm-tests
+local_config.*
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 30873b19d04b..9a25307f6115 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -1,5 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
# Makefile for vm selftests
+
+include local_config.mk
+
uname_M := $(shell uname -m 2>/dev/null || echo not)
MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
@@ -21,23 +24,24 @@ MACHINE ?= $(shell echo $(uname_M) | sed -e 's/aarch64.*/arm64/')
MAKEFLAGS += --no-builtin-rules
CFLAGS = -Wall -I ../../../../usr/include $(EXTRA_CFLAGS)
-LDLIBS = -lrt
+LDLIBS = -lrt -lpthread
TEST_GEN_FILES = compaction_test
-TEST_GEN_FILES += gup_benchmark
+TEST_GEN_FILES += gup_test
TEST_GEN_FILES += hmm-tests
TEST_GEN_FILES += hugepage-mmap
TEST_GEN_FILES += hugepage-shm
-TEST_GEN_FILES += map_hugetlb
+TEST_GEN_FILES += khugepaged
TEST_GEN_FILES += map_fixed_noreplace
+TEST_GEN_FILES += map_hugetlb
TEST_GEN_FILES += map_populate
TEST_GEN_FILES += mlock-random-test
TEST_GEN_FILES += mlock2-tests
TEST_GEN_FILES += mremap_dontunmap
+TEST_GEN_FILES += mremap_test
TEST_GEN_FILES += on-fault-limit
TEST_GEN_FILES += thuge-gen
TEST_GEN_FILES += transhuge-stress
TEST_GEN_FILES += userfaultfd
-TEST_GEN_FILES += khugepaged
ifeq ($(ARCH),x86_64)
CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
@@ -60,24 +64,26 @@ ifeq ($(CAN_BUILD_X86_64),1)
TEST_GEN_FILES += $(BINARIES_64)
endif
else
+
+ifneq (,$(findstring $(ARCH),powerpc))
TEST_GEN_FILES += protection_keys
endif
+endif
+
ifneq (,$(filter $(MACHINE),arm64 ia64 mips64 parisc64 ppc64 ppc64le riscv64 s390x sh64 sparc64 x86_64))
TEST_GEN_FILES += va_128TBswitch
TEST_GEN_FILES += virtual_address_range
TEST_GEN_FILES += write_to_hugetlbfs
endif
-TEST_PROGS := run_vmtests
+TEST_PROGS := run_vmtests.sh
TEST_FILES := test_vmalloc.sh
KSFT_KHDR_INSTALL := 1
include ../lib.mk
-$(OUTPUT)/hmm-tests: LDLIBS += -lhugetlbfs -lpthread
-
ifeq ($(ARCH),x86_64)
BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
@@ -127,6 +133,25 @@ warn_32bit_failure:
endif
endif
-$(OUTPUT)/userfaultfd: LDLIBS += -lpthread
-
$(OUTPUT)/mlock-random-test: LDLIBS += -lcap
+
+$(OUTPUT)/gup_test: ../../../../mm/gup_test.h
+
+$(OUTPUT)/hmm-tests: local_config.h
+
+# HMM_EXTRA_LIBS may get set in local_config.mk, or it may be left empty.
+$(OUTPUT)/hmm-tests: LDLIBS += $(HMM_EXTRA_LIBS)
+
+local_config.mk local_config.h: check_config.sh
+ /bin/sh ./check_config.sh $(CC)
+
+EXTRA_CLEAN += local_config.mk local_config.h
+
+ifeq ($(HMM_EXTRA_LIBS),)
+all: warn_missing_hugelibs
+
+warn_missing_hugelibs:
+ @echo ; \
+ echo "Warning: missing libhugetlbfs support. Some HMM tests will be skipped." ; \
+ echo
+endif
diff --git a/tools/testing/selftests/vm/check_config.sh b/tools/testing/selftests/vm/check_config.sh
new file mode 100644
index 000000000000..079c8a40b85d
--- /dev/null
+++ b/tools/testing/selftests/vm/check_config.sh
@@ -0,0 +1,31 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Probe for libraries and create header files to record the results. Both C
+# header files and Makefile include fragments are created.
+
+OUTPUT_H_FILE=local_config.h
+OUTPUT_MKFILE=local_config.mk
+
+# libhugetlbfs
+tmpname=$(mktemp)
+tmpfile_c=${tmpname}.c
+tmpfile_o=${tmpname}.o
+
+echo "#include <sys/types.h>" > $tmpfile_c
+echo "#include <hugetlbfs.h>" >> $tmpfile_c
+echo "int func(void) { return 0; }" >> $tmpfile_c
+
+CC=${1:?"Usage: $0 <compiler> # example compiler: gcc"}
+$CC -c $tmpfile_c -o $tmpfile_o >/dev/null 2>&1
+
+if [ -f $tmpfile_o ]; then
+ echo "#define LOCAL_CONFIG_HAVE_LIBHUGETLBFS 1" > $OUTPUT_H_FILE
+ echo "HMM_EXTRA_LIBS = -lhugetlbfs" > $OUTPUT_MKFILE
+else
+ echo "// No libhugetlbfs support found" > $OUTPUT_H_FILE
+ echo "# No libhugetlbfs support found, so:" > $OUTPUT_MKFILE
+ echo "HMM_EXTRA_LIBS = " >> $OUTPUT_MKFILE
+fi
+
+rm ${tmpname}.*
diff --git a/tools/testing/selftests/vm/config b/tools/testing/selftests/vm/config
index 69dd0d1aa30b..60e82da0de85 100644
--- a/tools/testing/selftests/vm/config
+++ b/tools/testing/selftests/vm/config
@@ -3,4 +3,4 @@ CONFIG_USERFAULTFD=y
CONFIG_TEST_VMALLOC=m
CONFIG_DEVICE_PRIVATE=y
CONFIG_TEST_HMM=m
-CONFIG_GUP_BENCHMARK=y
+CONFIG_GUP_TEST=y
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
deleted file mode 100644
index 1d4359341e44..000000000000
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ /dev/null
@@ -1,143 +0,0 @@
-#include <fcntl.h>
-#include <stdio.h>
-#include <stdlib.h>
-#include <unistd.h>
-
-#include <sys/ioctl.h>
-#include <sys/mman.h>
-#include <sys/prctl.h>
-#include <sys/stat.h>
-#include <sys/types.h>
-
-#include <linux/types.h>
-
-#define MB (1UL << 20)
-#define PAGE_SIZE sysconf(_SC_PAGESIZE)
-
-#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark)
-#define GUP_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
-
-/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
-#define PIN_FAST_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
-#define PIN_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
-#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
-
-/* Just the flags we need, copied from mm.h: */
-#define FOLL_WRITE 0x01 /* check pte is writable */
-
-struct gup_benchmark {
- __u64 get_delta_usec;
- __u64 put_delta_usec;
- __u64 addr;
- __u64 size;
- __u32 nr_pages_per_call;
- __u32 flags;
- __u64 expansion[10]; /* For future use */
-};
-
-int main(int argc, char **argv)
-{
- struct gup_benchmark gup;
- unsigned long size = 128 * MB;
- int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
- int cmd = GUP_FAST_BENCHMARK, flags = MAP_PRIVATE;
- char *file = "/dev/zero";
- char *p;
-
- while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
- switch (opt) {
- case 'a':
- cmd = PIN_FAST_BENCHMARK;
- break;
- case 'b':
- cmd = PIN_BENCHMARK;
- break;
- case 'L':
- cmd = PIN_LONGTERM_BENCHMARK;
- break;
- case 'm':
- size = atoi(optarg) * MB;
- break;
- case 'r':
- repeats = atoi(optarg);
- break;
- case 'n':
- nr_pages = atoi(optarg);
- break;
- case 't':
- thp = 1;
- break;
- case 'T':
- thp = 0;
- break;
- case 'U':
- cmd = GUP_BENCHMARK;
- break;
- case 'u':
- cmd = GUP_FAST_BENCHMARK;
- break;
- case 'w':
- write = 1;
- break;
- case 'f':
- file = optarg;
- break;
- case 'S':
- flags &= ~MAP_PRIVATE;
- flags |= MAP_SHARED;
- break;
- case 'H':
- flags |= (MAP_HUGETLB | MAP_ANONYMOUS);
- break;
- default:
- return -1;
- }
- }
-
- filed = open(file, O_RDWR|O_CREAT);
- if (filed < 0) {
- perror("open");
- exit(filed);
- }
-
- gup.nr_pages_per_call = nr_pages;
- if (write)
- gup.flags |= FOLL_WRITE;
-
- fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
- if (fd == -1) {
- perror("open");
- exit(1);
- }
-
- p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
- if (p == MAP_FAILED) {
- perror("mmap");
- exit(1);
- }
- gup.addr = (unsigned long)p;
-
- if (thp == 1)
- madvise(p, size, MADV_HUGEPAGE);
- else if (thp == 0)
- madvise(p, size, MADV_NOHUGEPAGE);
-
- for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
- p[0] = 0;
-
- for (i = 0; i < repeats; i++) {
- gup.size = size;
- if (ioctl(fd, cmd, &gup)) {
- perror("ioctl");
- exit(1);
- }
-
- printf("Time: get:%lld put:%lld us", gup.get_delta_usec,
- gup.put_delta_usec);
- if (gup.size != size)
- printf(", truncated (size: %lld)", gup.size);
- printf("\n");
- }
-
- return 0;
-}
diff --git a/tools/testing/selftests/vm/gup_test.c b/tools/testing/selftests/vm/gup_test.c
new file mode 100644
index 000000000000..6c6336dd3b7f
--- /dev/null
+++ b/tools/testing/selftests/vm/gup_test.c
@@ -0,0 +1,194 @@
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include "../../../../mm/gup_test.h"
+
+#define MB (1UL << 20)
+#define PAGE_SIZE sysconf(_SC_PAGESIZE)
+
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE 0x01 /* check pte is writable */
+
+static char *cmd_to_str(unsigned long cmd)
+{
+ switch (cmd) {
+ case GUP_FAST_BENCHMARK:
+ return "GUP_FAST_BENCHMARK";
+ case PIN_FAST_BENCHMARK:
+ return "PIN_FAST_BENCHMARK";
+ case PIN_LONGTERM_BENCHMARK:
+ return "PIN_LONGTERM_BENCHMARK";
+ case GUP_BASIC_TEST:
+ return "GUP_BASIC_TEST";
+ case PIN_BASIC_TEST:
+ return "PIN_BASIC_TEST";
+ case DUMP_USER_PAGES_TEST:
+ return "DUMP_USER_PAGES_TEST";
+ }
+ return "Unknown command";
+}
+
+int main(int argc, char **argv)
+{
+ struct gup_test gup = { 0 };
+ unsigned long size = 128 * MB;
+ int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
+ unsigned long cmd = GUP_FAST_BENCHMARK;
+ int flags = MAP_PRIVATE;
+ char *file = "/dev/zero";
+ char *p;
+
+ while ((opt = getopt(argc, argv, "m:r:n:F:f:abctTLUuwSH")) != -1) {
+ switch (opt) {
+ case 'a':
+ cmd = PIN_FAST_BENCHMARK;
+ break;
+ case 'b':
+ cmd = PIN_BASIC_TEST;
+ break;
+ case 'L':
+ cmd = PIN_LONGTERM_BENCHMARK;
+ break;
+ case 'c':
+ cmd = DUMP_USER_PAGES_TEST;
+ /*
+ * Dump page 0 (index 1). May be overridden later, by
+ * user's non-option arguments.
+ *
+ * .which_pages is zero-based, so that zero can mean "do
+ * nothing".
+ */
+ gup.which_pages[0] = 1;
+ break;
+ case 'F':
+ /* strtol, so you can pass flags in hex form */
+ gup.flags = strtol(optarg, 0, 0);
+ break;
+ case 'm':
+ size = atoi(optarg) * MB;
+ break;
+ case 'r':
+ repeats = atoi(optarg);
+ break;
+ case 'n':
+ nr_pages = atoi(optarg);
+ break;
+ case 't':
+ thp = 1;
+ break;
+ case 'T':
+ thp = 0;
+ break;
+ case 'U':
+ cmd = GUP_BASIC_TEST;
+ break;
+ case 'u':
+ cmd = GUP_FAST_BENCHMARK;
+ break;
+ case 'w':
+ write = 1;
+ break;
+ case 'f':
+ file = optarg;
+ break;
+ case 'S':
+ flags &= ~MAP_PRIVATE;
+ flags |= MAP_SHARED;
+ break;
+ case 'H':
+ flags |= (MAP_HUGETLB | MAP_ANONYMOUS);
+ break;
+ default:
+ return -1;
+ }
+ }
+
+ if (optind < argc) {
+ int extra_arg_count = 0;
+ /*
+ * For example:
+ *
+ * ./gup_test -c 0 1 0x1001
+ *
+ * ...to dump pages 0, 1, and 4097
+ */
+
+ while ((optind < argc) &&
+ (extra_arg_count < GUP_TEST_MAX_PAGES_TO_DUMP)) {
+ /*
+ * Do the 1-based indexing here, so that the user can
+ * use normal 0-based indexing on the command line.
+ */
+ long page_index = strtol(argv[optind], 0, 0) + 1;
+
+ gup.which_pages[extra_arg_count] = page_index;
+ extra_arg_count++;
+ optind++;
+ }
+ }
+
+ filed = open(file, O_RDWR|O_CREAT);
+ if (filed < 0) {
+ perror("open");
+ exit(filed);
+ }
+
+ gup.nr_pages_per_call = nr_pages;
+ if (write)
+ gup.flags |= FOLL_WRITE;
+
+ fd = open("/sys/kernel/debug/gup_test", O_RDWR);
+ if (fd == -1) {
+ perror("open");
+ exit(1);
+ }
+
+ p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
+ if (p == MAP_FAILED) {
+ perror("mmap");
+ exit(1);
+ }
+ gup.addr = (unsigned long)p;
+
+ if (thp == 1)
+ madvise(p, size, MADV_HUGEPAGE);
+ else if (thp == 0)
+ madvise(p, size, MADV_NOHUGEPAGE);
+
+ for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
+ p[0] = 0;
+
+ /* Only report timing information on the *_BENCHMARK commands: */
+ if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) ||
+ (cmd == PIN_LONGTERM_BENCHMARK)) {
+ for (i = 0; i < repeats; i++) {
+ gup.size = size;
+ if (ioctl(fd, cmd, &gup))
+ perror("ioctl"), exit(1);
+
+ printf("%s: Time: get:%lld put:%lld us",
+ cmd_to_str(cmd), gup.get_delta_usec,
+ gup.put_delta_usec);
+ if (gup.size != size)
+ printf(", truncated (size: %lld)", gup.size);
+ printf("\n");
+ }
+ } else {
+ gup.size = size;
+ if (ioctl(fd, cmd, &gup)) {
+ perror("ioctl");
+ exit(1);
+ }
+
+ printf("%s: done\n", cmd_to_str(cmd));
+ if (gup.size != size)
+ printf("Truncated (size: %lld)\n", gup.size);
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/vm/hmm-tests.c b/tools/testing/selftests/vm/hmm-tests.c
index c9404ef9698e..5d1ac691b9f4 100644
--- a/tools/testing/selftests/vm/hmm-tests.c
+++ b/tools/testing/selftests/vm/hmm-tests.c
@@ -21,12 +21,16 @@
#include <strings.h>
#include <time.h>
#include <pthread.h>
-#include <hugetlbfs.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <sys/ioctl.h>
+#include "./local_config.h"
+#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
+#include <hugetlbfs.h>
+#endif
+
/*
* This is a private UAPI to the kernel test module so it isn't exported
* in the usual include/uapi/... directory.
@@ -662,6 +666,7 @@ TEST_F(hmm, anon_write_huge)
hmm_buffer_free(buffer);
}
+#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
/*
* Write huge TLBFS page.
*/
@@ -720,6 +725,7 @@ TEST_F(hmm, anon_write_hugetlbfs)
buffer->ptr = NULL;
hmm_buffer_free(buffer);
}
+#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */
/*
* Read mmap'ed file memory.
@@ -1336,6 +1342,7 @@ TEST_F(hmm2, snapshot)
hmm_buffer_free(buffer);
}
+#ifdef LOCAL_CONFIG_HAVE_LIBHUGETLBFS
/*
* Test the hmm_range_fault() HMM_PFN_PMD flag for large pages that
* should be mapped by a large page table entry.
@@ -1411,6 +1418,7 @@ TEST_F(hmm, compound)
buffer->ptr = NULL;
hmm_buffer_free(buffer);
}
+#endif /* LOCAL_CONFIG_HAVE_LIBHUGETLBFS */
/*
* Test two devices reading the same memory (double mapped).
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
new file mode 100644
index 000000000000..9c391d016922
--- /dev/null
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020 Google LLC
+ */
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <time.h>
+
+#include "../kselftest.h"
+
+#define EXPECT_SUCCESS 0
+#define EXPECT_FAILURE 1
+#define NON_OVERLAPPING 0
+#define OVERLAPPING 1
+#define NS_PER_SEC 1000000000ULL
+#define VALIDATION_DEFAULT_THRESHOLD 4 /* 4MB */
+#define VALIDATION_NO_THRESHOLD 0 /* Verify the entire region */
+
+#define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+
+struct config {
+ unsigned long long src_alignment;
+ unsigned long long dest_alignment;
+ unsigned long long region_size;
+ int overlapping;
+};
+
+struct test {
+ const char *name;
+ struct config config;
+ int expect_failure;
+};
+
+enum {
+ _1KB = 1ULL << 10, /* 1KB -> not page aligned */
+ _4KB = 4ULL << 10,
+ _8KB = 8ULL << 10,
+ _1MB = 1ULL << 20,
+ _2MB = 2ULL << 20,
+ _4MB = 4ULL << 20,
+ _1GB = 1ULL << 30,
+ _2GB = 2ULL << 30,
+ PTE = _4KB,
+ PMD = _2MB,
+ PUD = _1GB,
+};
+
+#define MAKE_TEST(source_align, destination_align, size, \
+ overlaps, should_fail, test_name) \
+{ \
+ .name = test_name, \
+ .config = { \
+ .src_alignment = source_align, \
+ .dest_alignment = destination_align, \
+ .region_size = size, \
+ .overlapping = overlaps, \
+ }, \
+ .expect_failure = should_fail \
+}
+
+/*
+ * Returns the start address of the mapping on success, else returns
+ * NULL on failure.
+ */
+static void *get_source_mapping(struct config c)
+{
+ unsigned long long addr = 0ULL;
+ void *src_addr = NULL;
+retry:
+ addr += c.src_alignment;
+ src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE,
+ MAP_FIXED | MAP_ANONYMOUS | MAP_SHARED, -1, 0);
+ if (src_addr == MAP_FAILED) {
+ if (errno == EPERM)
+ goto retry;
+ goto error;
+ }
+ /*
+ * Check that the address is aligned to the specified alignment.
+ * Addresses which have alignments that are multiples of that
+ * specified are not considered valid. For instance, 1GB address is
+ * 2MB-aligned, however it will not be considered valid for a
+ * requested alignment of 2MB. This is done to reduce coincidental
+ * alignment in the tests.
+ */
+ if (((unsigned long long) src_addr & (c.src_alignment - 1)) ||
+ !((unsigned long long) src_addr & c.src_alignment))
+ goto retry;
+
+ if (!src_addr)
+ goto error;
+
+ return src_addr;
+error:
+ ksft_print_msg("Failed to map source region: %s\n",
+ strerror(errno));
+ return NULL;
+}
+
+/* Returns the time taken for the remap on success else returns -1. */
+static long long remap_region(struct config c, unsigned int threshold_mb,
+ char pattern_seed)
+{
+ void *addr, *src_addr, *dest_addr;
+ unsigned long long i;
+ struct timespec t_start = {0, 0}, t_end = {0, 0};
+ long long start_ns, end_ns, align_mask, ret, offset;
+ unsigned long long threshold;
+
+ if (threshold_mb == VALIDATION_NO_THRESHOLD)
+ threshold = c.region_size;
+ else
+ threshold = MIN(threshold_mb * _1MB, c.region_size);
+
+ src_addr = get_source_mapping(c);
+ if (!src_addr) {
+ ret = -1;
+ goto out;
+ }
+
+ /* Set byte pattern */
+ srand(pattern_seed);
+ for (i = 0; i < threshold; i++)
+ memset((char *) src_addr + i, (char) rand(), 1);
+
+ /* Mask to zero out lower bits of address for alignment */
+ align_mask = ~(c.dest_alignment - 1);
+ /* Offset of destination address from the end of the source region */
+ offset = (c.overlapping) ? -c.dest_alignment : c.dest_alignment;
+ addr = (void *) (((unsigned long long) src_addr + c.region_size
+ + offset) & align_mask);
+
+ /* See comment in get_source_mapping() */
+ if (!((unsigned long long) addr & c.dest_alignment))
+ addr = (void *) ((unsigned long long) addr | c.dest_alignment);
+
+ clock_gettime(CLOCK_MONOTONIC, &t_start);
+ dest_addr = mremap(src_addr, c.region_size, c.region_size,
+ MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr);
+ clock_gettime(CLOCK_MONOTONIC, &t_end);
+
+ if (dest_addr == MAP_FAILED) {
+ ksft_print_msg("mremap failed: %s\n", strerror(errno));
+ ret = -1;
+ goto clean_up_src;
+ }
+
+ /* Verify byte pattern after remapping */
+ srand(pattern_seed);
+ for (i = 0; i < threshold; i++) {
+ char c = (char) rand();
+
+ if (((char *) dest_addr)[i] != c) {
+ ksft_print_msg("Data after remap doesn't match at offset %d\n",
+ i);
+ ksft_print_msg("Expected: %#x\t Got: %#x\n", c & 0xff,
+ ((char *) dest_addr)[i] & 0xff);
+ ret = -1;
+ goto clean_up_dest;
+ }
+ }
+
+ start_ns = t_start.tv_sec * NS_PER_SEC + t_start.tv_nsec;
+ end_ns = t_end.tv_sec * NS_PER_SEC + t_end.tv_nsec;
+ ret = end_ns - start_ns;
+
+/*
+ * Since the destination address is specified using MREMAP_FIXED, subsequent
+ * mremap will unmap any previous mapping at the address range specified by
+ * dest_addr and region_size. This significantly affects the remap time of
+ * subsequent tests. So we clean up mappings after each test.
+ */
+clean_up_dest:
+ munmap(dest_addr, c.region_size);
+clean_up_src:
+ munmap(src_addr, c.region_size);
+out:
+ return ret;
+}
+
+static void run_mremap_test_case(struct test test_case, int *failures,
+ unsigned int threshold_mb,
+ unsigned int pattern_seed)
+{
+ long long remap_time = remap_region(test_case.config, threshold_mb,
+ pattern_seed);
+
+ if (remap_time < 0) {
+ if (test_case.expect_failure)
+ ksft_test_result_pass("%s\n\tExpected mremap failure\n",
+ test_case.name);
+ else {
+ ksft_test_result_fail("%s\n", test_case.name);
+ *failures += 1;
+ }
+ } else {
+ /*
+ * Comparing mremap time is only applicable if entire region
+ * was faulted in.
+ */
+ if (threshold_mb == VALIDATION_NO_THRESHOLD ||
+ test_case.config.region_size <= threshold_mb * _1MB)
+ ksft_test_result_pass("%s\n\tmremap time: %12lldns\n",
+ test_case.name, remap_time);
+ else
+ ksft_test_result_pass("%s\n", test_case.name);
+ }
+}
+
+static void usage(const char *cmd)
+{
+ fprintf(stderr,
+ "Usage: %s [[-t <threshold_mb>] [-p <pattern_seed>]]\n"
+ "-t\t only validate threshold_mb of the remapped region\n"
+ " \t if 0 is supplied no threshold is used; all tests\n"
+ " \t are run and remapped regions validated fully.\n"
+ " \t The default threshold used is 4MB.\n"
+ "-p\t provide a seed to generate the random pattern for\n"
+ " \t validating the remapped region.\n", cmd);
+}
+
+static int parse_args(int argc, char **argv, unsigned int *threshold_mb,
+ unsigned int *pattern_seed)
+{
+ const char *optstr = "t:p:";
+ int opt;
+
+ while ((opt = getopt(argc, argv, optstr)) != -1) {
+ switch (opt) {
+ case 't':
+ *threshold_mb = atoi(optarg);
+ break;
+ case 'p':
+ *pattern_seed = atoi(optarg);
+ break;
+ default:
+ usage(argv[0]);
+ return -1;
+ }
+ }
+
+ if (optind < argc) {
+ usage(argv[0]);
+ return -1;
+ }
+
+ return 0;
+}
+
+int main(int argc, char **argv)
+{
+ int failures = 0;
+ int i, run_perf_tests;
+ unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD;
+ unsigned int pattern_seed;
+ time_t t;
+
+ pattern_seed = (unsigned int) time(&t);
+
+ if (parse_args(argc, argv, &threshold_mb, &pattern_seed) < 0)
+ exit(EXIT_FAILURE);
+
+ ksft_print_msg("Test configs:\n\tthreshold_mb=%u\n\tpattern_seed=%u\n\n",
+ threshold_mb, pattern_seed);
+
+ struct test test_cases[] = {
+ /* Expected mremap failures */
+ MAKE_TEST(_4KB, _4KB, _4KB, OVERLAPPING, EXPECT_FAILURE,
+ "mremap - Source and Destination Regions Overlapping"),
+ MAKE_TEST(_4KB, _1KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE,
+ "mremap - Destination Address Misaligned (1KB-aligned)"),
+ MAKE_TEST(_1KB, _4KB, _4KB, NON_OVERLAPPING, EXPECT_FAILURE,
+ "mremap - Source Address Misaligned (1KB-aligned)"),
+
+ /* Src addr PTE aligned */
+ MAKE_TEST(PTE, PTE, _8KB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "8KB mremap - Source PTE-aligned, Destination PTE-aligned"),
+
+ /* Src addr 1MB aligned */
+ MAKE_TEST(_1MB, PTE, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2MB mremap - Source 1MB-aligned, Destination PTE-aligned"),
+ MAKE_TEST(_1MB, _1MB, _2MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2MB mremap - Source 1MB-aligned, Destination 1MB-aligned"),
+
+ /* Src addr PMD aligned */
+ MAKE_TEST(PMD, PTE, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "4MB mremap - Source PMD-aligned, Destination PTE-aligned"),
+ MAKE_TEST(PMD, _1MB, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "4MB mremap - Source PMD-aligned, Destination 1MB-aligned"),
+ MAKE_TEST(PMD, PMD, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "4MB mremap - Source PMD-aligned, Destination PMD-aligned"),
+
+ /* Src addr PUD aligned */
+ MAKE_TEST(PUD, PTE, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination PTE-aligned"),
+ MAKE_TEST(PUD, _1MB, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination 1MB-aligned"),
+ MAKE_TEST(PUD, PMD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination PMD-aligned"),
+ MAKE_TEST(PUD, PUD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "2GB mremap - Source PUD-aligned, Destination PUD-aligned"),
+ };
+
+ struct test perf_test_cases[] = {
+ /*
+ * mremap 1GB region - Page table level aligned time
+ * comparison.
+ */
+ MAKE_TEST(PTE, PTE, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "1GB mremap - Source PTE-aligned, Destination PTE-aligned"),
+ MAKE_TEST(PMD, PMD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "1GB mremap - Source PMD-aligned, Destination PMD-aligned"),
+ MAKE_TEST(PUD, PUD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS,
+ "1GB mremap - Source PUD-aligned, Destination PUD-aligned"),
+ };
+
+ run_perf_tests = (threshold_mb == VALIDATION_NO_THRESHOLD) ||
+ (threshold_mb * _1MB >= _1GB);
+
+ ksft_set_plan(ARRAY_SIZE(test_cases) + (run_perf_tests ?
+ ARRAY_SIZE(perf_test_cases) : 0));
+
+ for (i = 0; i < ARRAY_SIZE(test_cases); i++)
+ run_mremap_test_case(test_cases[i], &failures, threshold_mb,
+ pattern_seed);
+
+ if (run_perf_tests) {
+ ksft_print_msg("\n%s\n",
+ "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:");
+ for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++)
+ run_mremap_test_case(perf_test_cases[i], &failures,
+ threshold_mb, pattern_seed);
+ }
+
+ if (failures > 0)
+ ksft_exit_fail();
+ else
+ ksft_exit_pass();
+}
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index a3f4f30f0a2e..e953f3cd9664 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -123,10 +123,10 @@ else
echo "[PASS]"
fi
-echo "--------------------------------------------"
-echo "running 'gup_benchmark -U' (normal/slow gup)"
-echo "--------------------------------------------"
-./gup_benchmark -U
+echo "------------------------------------------------------"
+echo "running: gup_test -u # get_user_pages_fast() benchmark"
+echo "------------------------------------------------------"
+./gup_test -u
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
@@ -134,10 +134,22 @@ else
echo "[PASS]"
fi
-echo "------------------------------------------"
-echo "running gup_benchmark -b (pin_user_pages)"
-echo "------------------------------------------"
-./gup_benchmark -b
+echo "------------------------------------------------------"
+echo "running: gup_test -a # pin_user_pages_fast() benchmark"
+echo "------------------------------------------------------"
+./gup_test -a
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
+echo "------------------------------------------------------------"
+echo "# Dump pages 0, 19, and 4096, using pin_user_pages:"
+echo "running: gup_test -ct -F 0x1 0 19 0x1000 # dump_page() test"
+echo "------------------------------------------------------------"
+./gup_test -ct -F 0x1 0 19 0x1000
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
@@ -148,7 +160,7 @@ fi
echo "-------------------"
echo "running userfaultfd"
echo "-------------------"
-./userfaultfd anon 128 32
+./userfaultfd anon 20 16
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
@@ -173,7 +185,7 @@ rm -f $mnt/ufd_test_file
echo "-------------------------"
echo "running userfaultfd_shmem"
echo "-------------------------"
-./userfaultfd shmem 128 32
+./userfaultfd shmem 20 16
if [ $? -ne 0 ]; then
echo "[FAIL]"
exitcode=1
@@ -241,6 +253,17 @@ else
echo "[PASS]"
fi
+echo "-------------------"
+echo "running mremap_test"
+echo "-------------------"
+./mremap_test
+if [ $? -ne 0 ]; then
+ echo "[FAIL]"
+ exitcode=1
+else
+ echo "[PASS]"
+fi
+
echo "-----------------"
echo "running thuge-gen"
echo "-----------------"
diff --git a/tools/testing/selftests/vm/userfaultfd.c b/tools/testing/selftests/vm/userfaultfd.c
index 9b0912a01777..92b8ec423201 100644
--- a/tools/testing/selftests/vm/userfaultfd.c
+++ b/tools/testing/selftests/vm/userfaultfd.c
@@ -55,6 +55,8 @@
#include <setjmp.h>
#include <stdbool.h>
#include <assert.h>
+#include <inttypes.h>
+#include <stdint.h>
#include "../kselftest.h"
@@ -135,6 +137,13 @@ static void usage(void)
exit(1);
}
+#define uffd_error(code, fmt, ...) \
+ do { \
+ fprintf(stderr, fmt, ##__VA_ARGS__); \
+ fprintf(stderr, ": %" PRId64 "\n", (int64_t)(code)); \
+ exit(1); \
+ } while (0)
+
static void uffd_stats_reset(struct uffd_stats *uffd_stats,
unsigned long n_cpus)
{
@@ -206,19 +215,19 @@ static int hugetlb_release_pages(char *rel_area)
return ret;
}
-
static void hugetlb_allocate_area(void **alloc_area)
{
void *area_alias = NULL;
char **alloc_area_alias;
+
*alloc_area = mmap(NULL, nr_pages * page_size, PROT_READ | PROT_WRITE,
(map_shared ? MAP_SHARED : MAP_PRIVATE) |
MAP_HUGETLB,
huge_fd, *alloc_area == area_src ? 0 :
nr_pages * page_size);
if (*alloc_area == MAP_FAILED) {
- fprintf(stderr, "mmap of hugetlbfs file failed\n");
- *alloc_area = NULL;
+ perror("mmap of hugetlbfs file failed");
+ goto fail;
}
if (map_shared) {
@@ -227,14 +236,11 @@ static void hugetlb_allocate_area(void **alloc_area)
huge_fd, *alloc_area == area_src ? 0 :
nr_pages * page_size);
if (area_alias == MAP_FAILED) {
- if (munmap(*alloc_area, nr_pages * page_size) < 0) {
- perror("hugetlb munmap");
- exit(1);
- }
- *alloc_area = NULL;
- return;
+ perror("mmap of hugetlb file alias failed");
+ goto fail_munmap;
}
}
+
if (*alloc_area == area_src) {
huge_fd_off0 = *alloc_area;
alloc_area_alias = &area_src_alias;
@@ -243,6 +249,16 @@ static void hugetlb_allocate_area(void **alloc_area)
}
if (area_alias)
*alloc_area_alias = area_alias;
+
+ return;
+
+fail_munmap:
+ if (munmap(*alloc_area, nr_pages * page_size) < 0) {
+ perror("hugetlb munmap");
+ exit(1);
+ }
+fail:
+ *alloc_area = NULL;
}
static void hugetlb_alias_mapping(__u64 *start, size_t len, unsigned long offset)
@@ -331,7 +347,7 @@ static int my_bcmp(char *str1, char *str2, size_t n)
static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
{
- struct uffdio_writeprotect prms = { 0 };
+ struct uffdio_writeprotect prms;
/* Write protection page faults */
prms.range.start = start;
@@ -340,7 +356,8 @@ static void wp_range(int ufd, __u64 start, __u64 len, bool wp)
prms.mode = wp ? UFFDIO_WRITEPROTECT_MODE_WP : 0;
if (ioctl(ufd, UFFDIO_WRITEPROTECT, &prms)) {
- fprintf(stderr, "clear WP failed for address 0x%Lx\n", start);
+ fprintf(stderr, "clear WP failed for address 0x%" PRIx64 "\n",
+ (uint64_t)start);
exit(1);
}
}
@@ -474,14 +491,11 @@ static void retry_copy_page(int ufd, struct uffdio_copy *uffdio_copy,
if (ioctl(ufd, UFFDIO_COPY, uffdio_copy)) {
/* real retval in ufdio_copy.copy */
if (uffdio_copy->copy != -EEXIST) {
- fprintf(stderr, "UFFDIO_COPY retry error %Ld\n",
- uffdio_copy->copy);
- exit(1);
+ uffd_error(uffdio_copy->copy,
+ "UFFDIO_COPY retry error");
}
- } else {
- fprintf(stderr, "UFFDIO_COPY retry unexpected %Ld\n",
- uffdio_copy->copy); exit(1);
- }
+ } else
+ uffd_error(uffdio_copy->copy, "UFFDIO_COPY retry unexpected");
}
static int __copy_page(int ufd, unsigned long offset, bool retry)
@@ -502,14 +516,10 @@ static int __copy_page(int ufd, unsigned long offset, bool retry)
uffdio_copy.copy = 0;
if (ioctl(ufd, UFFDIO_COPY, &uffdio_copy)) {
/* real retval in ufdio_copy.copy */
- if (uffdio_copy.copy != -EEXIST) {
- fprintf(stderr, "UFFDIO_COPY error %Ld\n",
- uffdio_copy.copy);
- exit(1);
- }
+ if (uffdio_copy.copy != -EEXIST)
+ uffd_error(uffdio_copy.copy, "UFFDIO_COPY error");
} else if (uffdio_copy.copy != page_size) {
- fprintf(stderr, "UFFDIO_COPY unexpected copy %Ld\n",
- uffdio_copy.copy); exit(1);
+ uffd_error(uffdio_copy.copy, "UFFDIO_COPY unexpected copy");
} else {
if (test_uffdio_copy_eexist && retry) {
test_uffdio_copy_eexist = false;
@@ -784,11 +794,13 @@ static int userfaultfd_open(int features)
uffdio_api.api = UFFD_API;
uffdio_api.features = features;
if (ioctl(uffd, UFFDIO_API, &uffdio_api)) {
- fprintf(stderr, "UFFDIO_API\n");
+ fprintf(stderr, "UFFDIO_API failed.\nPlease make sure to "
+ "run with either root or ptrace capability.\n");
return 1;
}
if (uffdio_api.api != UFFD_API) {
- fprintf(stderr, "UFFDIO_API error %Lu\n", uffdio_api.api);
+ fprintf(stderr, "UFFDIO_API error: %" PRIu64 "\n",
+ (uint64_t)uffdio_api.api);
return 1;
}
@@ -894,7 +906,7 @@ static int faulting_process(int signal_test)
count_verify[nr]);
}
/*
- * Trigger write protection if there is by writting
+ * Trigger write protection if there is by writing
* the same value back.
*/
*area_count(area_dst, nr) = count;
@@ -922,7 +934,7 @@ static int faulting_process(int signal_test)
count_verify[nr]); exit(1);
}
/*
- * Trigger write protection if there is by writting
+ * Trigger write protection if there is by writing
* the same value back.
*/
*area_count(area_dst, nr) = count;
@@ -950,13 +962,12 @@ static void retry_uffdio_zeropage(int ufd,
offset);
if (ioctl(ufd, UFFDIO_ZEROPAGE, uffdio_zeropage)) {
if (uffdio_zeropage->zeropage != -EEXIST) {
- fprintf(stderr, "UFFDIO_ZEROPAGE retry error %Ld\n",
- uffdio_zeropage->zeropage);
- exit(1);
+ uffd_error(uffdio_zeropage->zeropage,
+ "UFFDIO_ZEROPAGE retry error");
}
} else {
- fprintf(stderr, "UFFDIO_ZEROPAGE retry unexpected %Ld\n",
- uffdio_zeropage->zeropage); exit(1);
+ uffd_error(uffdio_zeropage->zeropage,
+ "UFFDIO_ZEROPAGE retry unexpected");
}
}
@@ -965,6 +976,7 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
struct uffdio_zeropage uffdio_zeropage;
int ret;
unsigned long has_zeropage;
+ __s64 res;
has_zeropage = uffd_test_ops->expected_ioctls & (1 << _UFFDIO_ZEROPAGE);
@@ -976,29 +988,17 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
uffdio_zeropage.range.len = page_size;
uffdio_zeropage.mode = 0;
ret = ioctl(ufd, UFFDIO_ZEROPAGE, &uffdio_zeropage);
+ res = uffdio_zeropage.zeropage;
if (ret) {
/* real retval in ufdio_zeropage.zeropage */
if (has_zeropage) {
- if (uffdio_zeropage.zeropage == -EEXIST) {
- fprintf(stderr, "UFFDIO_ZEROPAGE -EEXIST\n");
- exit(1);
- } else {
- fprintf(stderr, "UFFDIO_ZEROPAGE error %Ld\n",
- uffdio_zeropage.zeropage);
- exit(1);
- }
- } else {
- if (uffdio_zeropage.zeropage != -EINVAL) {
- fprintf(stderr,
- "UFFDIO_ZEROPAGE not -EINVAL %Ld\n",
- uffdio_zeropage.zeropage);
- exit(1);
- }
- }
+ uffd_error(res, "UFFDIO_ZEROPAGE %s",
+ res == -EEXIST ? "-EEXIST" : "error");
+ } else if (res != -EINVAL)
+ uffd_error(res, "UFFDIO_ZEROPAGE not -EINVAL");
} else if (has_zeropage) {
- if (uffdio_zeropage.zeropage != page_size) {
- fprintf(stderr, "UFFDIO_ZEROPAGE unexpected %Ld\n",
- uffdio_zeropage.zeropage); exit(1);
+ if (res != page_size) {
+ uffd_error(res, "UFFDIO_ZEROPAGE unexpected");
} else {
if (test_uffdio_zeropage_eexist && retry) {
test_uffdio_zeropage_eexist = false;
@@ -1007,11 +1007,8 @@ static int __uffdio_zeropage(int ufd, unsigned long offset, bool retry)
}
return 1;
}
- } else {
- fprintf(stderr,
- "UFFDIO_ZEROPAGE succeeded %Ld\n",
- uffdio_zeropage.zeropage); exit(1);
- }
+ } else
+ uffd_error(res, "UFFDIO_ZEROPAGE succeeded");
return 0;
}
@@ -1033,7 +1030,7 @@ static int userfaultfd_zeropage_test(void)
if (uffd_test_ops->release_pages(area_dst))
return 1;
- if (userfaultfd_open(0) < 0)
+ if (userfaultfd_open(0))
return 1;
uffdio_register.range.start = (unsigned long) area_dst;
uffdio_register.range.len = nr_pages * page_size;
@@ -1083,7 +1080,7 @@ static int userfaultfd_events_test(void)
features = UFFD_FEATURE_EVENT_FORK | UFFD_FEATURE_EVENT_REMAP |
UFFD_FEATURE_EVENT_REMOVE;
- if (userfaultfd_open(features) < 0)
+ if (userfaultfd_open(features))
return 1;
fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
@@ -1155,7 +1152,7 @@ static int userfaultfd_sig_test(void)
return 1;
features = UFFD_FEATURE_EVENT_FORK|UFFD_FEATURE_SIGBUS;
- if (userfaultfd_open(features) < 0)
+ if (userfaultfd_open(features))
return 1;
fcntl(uffd, F_SETFL, uffd_flags | O_NONBLOCK);
@@ -1235,7 +1232,7 @@ static int userfaultfd_stress(void)
if (!area_dst)
return 1;
- if (userfaultfd_open(0) < 0)
+ if (userfaultfd_open(0))
return 1;
count_verify = malloc(nr_pages * sizeof(unsigned long long));
@@ -1295,6 +1292,8 @@ static int userfaultfd_stress(void)
printf(" ver");
if (bounces & BOUNCE_POLL)
printf(" poll");
+ else
+ printf(" read");
printf(", ");
fflush(stdout);
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 6703c7906b71..333980375bc7 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -12,7 +12,7 @@ CAN_BUILD_WITH_NOPIE := $(shell ./check_cc.sh $(CC) trivial_program.c -no-pie)
TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
check_initial_reg_state sigreturn iopl ioperm \
- test_vdso test_vsyscall mov_ss_trap \
+ test_vsyscall mov_ss_trap \
syscall_arg_fault fsgsbase_restore
TARGETS_C_32BIT_ONLY := entry_from_vm86 test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 7161cfc2e60b..8c780cce941d 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -392,8 +392,8 @@ static void set_gs_and_switch_to(unsigned long local,
local = read_base(GS);
/*
- * Signal delivery seems to mess up weird selectors. Put it
- * back.
+ * Signal delivery is quite likely to change a selector
+ * of 1, 2, or 3 back to 0 due to IRET being defective.
*/
asm volatile ("mov %0, %%gs" : : "rm" (force_sel));
} else {
@@ -411,6 +411,14 @@ static void set_gs_and_switch_to(unsigned long local,
if (base == local && sel_pre_sched == sel_post_sched) {
printf("[OK]\tGS/BASE remained 0x%hx/0x%lx\n",
sel_pre_sched, local);
+ } else if (base == local && sel_pre_sched >= 1 && sel_pre_sched <= 3 &&
+ sel_post_sched == 0) {
+ /*
+ * IRET is misdesigned and will squash selectors 1, 2, or 3
+ * to zero. Don't fail the test just because this happened.
+ */
+ printf("[OK]\tGS/BASE changed from 0x%hx/0x%lx to 0x%hx/0x%lx because IRET is defective\n",
+ sel_pre_sched, local, sel_post_sched, base);
} else {
nerrs++;
printf("[FAIL]\tGS/BASE changed from 0x%hx/0x%lx to 0x%hx/0x%lx\n",
diff --git a/tools/testing/selftests/x86/raw_syscall_helper_32.S b/tools/testing/selftests/x86/raw_syscall_helper_32.S
index 94410fa2b5ed..a10d36afdca0 100644
--- a/tools/testing/selftests/x86/raw_syscall_helper_32.S
+++ b/tools/testing/selftests/x86/raw_syscall_helper_32.S
@@ -45,3 +45,5 @@ int80_and_ret:
.type int80_and_ret, @function
.size int80_and_ret, .-int80_and_ret
+
+.section .note.GNU-stack,"",%progbits
diff --git a/tools/testing/selftests/x86/thunks.S b/tools/testing/selftests/x86/thunks.S
index 1bb5d62c16a4..a2d47d8344d4 100644
--- a/tools/testing/selftests/x86/thunks.S
+++ b/tools/testing/selftests/x86/thunks.S
@@ -57,3 +57,5 @@ call32_from_64:
ret
.size call32_from_64, .-call32_from_64
+
+.section .note.GNU-stack,"",%progbits