summaryrefslogtreecommitdiffstats
path: root/tools/testing
diff options
context:
space:
mode:
Diffstat (limited to 'tools/testing')
-rwxr-xr-xtools/testing/ktest/config-bisect.pl770
-rwxr-xr-xtools/testing/ktest/ktest.pl533
-rw-r--r--tools/testing/ktest/sample.conf60
-rw-r--r--tools/testing/nvdimm/test/nfit.c323
-rw-r--r--tools/testing/nvdimm/test/nfit_test.h16
-rw-r--r--tools/testing/radix-tree/Makefile6
-rw-r--r--tools/testing/radix-tree/idr-test.c7
-rw-r--r--tools/testing/radix-tree/linux/gfp.h1
-rw-r--r--tools/testing/radix-tree/multiorder.c63
-rw-r--r--tools/testing/radix-tree/test.c19
-rw-r--r--tools/testing/radix-tree/test.h3
-rw-r--r--tools/testing/selftests/Makefile7
-rw-r--r--tools/testing/selftests/android/Makefile8
-rwxr-xr-xtools/testing/selftests/android/ion/ion_test.sh7
-rw-r--r--tools/testing/selftests/bpf/.gitignore7
-rw-r--r--tools/testing/selftests/bpf/Makefile53
-rw-r--r--tools/testing/selftests/bpf/bpf_helpers.h39
-rw-r--r--tools/testing/selftests/bpf/bpf_rand.h80
-rw-r--r--tools/testing/selftests/bpf/cgroup_helpers.c57
-rw-r--r--tools/testing/selftests/bpf/cgroup_helpers.h1
-rw-r--r--tools/testing/selftests/bpf/config2
-rw-r--r--tools/testing/selftests/bpf/get_cgroup_id_kern.c28
-rw-r--r--tools/testing/selftests/bpf/get_cgroup_id_user.c141
-rw-r--r--tools/testing/selftests/bpf/sendmsg4_prog.c49
-rw-r--r--tools/testing/selftests/bpf/sendmsg6_prog.c60
-rw-r--r--tools/testing/selftests/bpf/test_adjust_tail.c30
-rw-r--r--tools/testing/selftests/bpf/test_btf.c2315
-rw-r--r--tools/testing/selftests/bpf/test_btf_haskv.c48
-rw-r--r--tools/testing/selftests/bpf/test_btf_nokv.c43
-rw-r--r--tools/testing/selftests/bpf/test_get_stack_rawtp.c102
-rwxr-xr-xtools/testing/selftests/bpf/test_lirc_mode2.sh28
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_kern.c23
-rw-r--r--tools/testing/selftests/bpf/test_lirc_mode2_user.c149
-rw-r--r--tools/testing/selftests/bpf/test_lwt_seg6local.c437
-rwxr-xr-xtools/testing/selftests/bpf/test_lwt_seg6local.sh140
-rw-r--r--tools/testing/selftests/bpf/test_progs.c568
-rw-r--r--tools/testing/selftests/bpf/test_sock.c1
-rw-r--r--tools/testing/selftests/bpf/test_sock_addr.c1156
-rwxr-xr-xtools/testing/selftests/bpf/test_sock_addr.sh4
-rw-r--r--tools/testing/selftests/bpf/test_sockhash_kern.c5
-rw-r--r--tools/testing/selftests/bpf/test_sockmap.c1524
-rw-r--r--tools/testing/selftests/bpf/test_sockmap_kern.c5
-rw-r--r--tools/testing/selftests/bpf/test_sockmap_kern.h363
-rw-r--r--tools/testing/selftests/bpf/test_stacktrace_build_id.c20
-rw-r--r--tools/testing/selftests/bpf/test_stacktrace_map.c19
-rwxr-xr-xtools/testing/selftests/bpf/test_tunnel.sh729
-rw-r--r--tools/testing/selftests/bpf/test_tunnel_kern.c713
-rw-r--r--tools/testing/selftests/bpf/test_verifier.c940
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.c165
-rw-r--r--tools/testing/selftests/bpf/trace_helpers.h21
-rw-r--r--tools/testing/selftests/bpf/urandom_read.c10
-rw-r--r--tools/testing/selftests/breakpoints/step_after_suspend_test.c6
-rw-r--r--tools/testing/selftests/cgroup/Makefile10
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.c331
-rw-r--r--tools/testing/selftests/cgroup/cgroup_util.h41
-rw-r--r--tools/testing/selftests/cgroup/test_memcontrol.c1015
-rwxr-xr-xtools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh14
-rwxr-xr-xtools/testing/selftests/cpufreq/main.sh5
-rwxr-xr-xtools/testing/selftests/drivers/usb/usbip/usbip_test.sh198
-rwxr-xr-xtools/testing/selftests/efivarfs/efivarfs.sh7
-rw-r--r--tools/testing/selftests/exec/execveat.c6
-rw-r--r--tools/testing/selftests/filesystems/Makefile9
-rw-r--r--tools/testing/selftests/filesystems/devpts_pts.c15
-rw-r--r--tools/testing/selftests/firmware/Makefile1
-rwxr-xr-xtools/testing/selftests/firmware/fw_fallback.sh4
-rwxr-xr-xtools/testing/selftests/firmware/fw_filesystem.sh4
-rwxr-xr-xtools/testing/selftests/firmware/fw_lib.sh17
-rwxr-xr-xtools/testing/selftests/firmware/fw_run_tests.sh2
-rw-r--r--tools/testing/selftests/ftrace/test.d/functions30
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc39
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc54
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc58
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc44
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc50
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc50
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc48
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc54
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc49
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc74
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc68
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc66
-rw-r--r--tools/testing/selftests/futex/Makefile12
-rwxr-xr-xtools/testing/selftests/gpio/gpio-mockup.sh12
-rw-r--r--tools/testing/selftests/intel_pstate/aperf.c6
-rwxr-xr-xtools/testing/selftests/intel_pstate/run.sh47
-rw-r--r--tools/testing/selftests/ipc/msgque.c7
-rwxr-xr-xtools/testing/selftests/kmod/kmod.sh13
-rw-r--r--tools/testing/selftests/kselftest.h2
-rw-r--r--tools/testing/selftests/kvm/.gitignore3
-rw-r--r--tools/testing/selftests/kvm/Makefile40
-rw-r--r--tools/testing/selftests/kvm/include/kvm_util.h145
-rw-r--r--tools/testing/selftests/kvm/include/sparsebit.h75
-rw-r--r--tools/testing/selftests/kvm/include/test_util.h46
-rw-r--r--tools/testing/selftests/kvm/include/vmx.h494
-rw-r--r--tools/testing/selftests/kvm/include/x86.h1043
-rw-r--r--tools/testing/selftests/kvm/lib/assert.c92
-rw-r--r--tools/testing/selftests/kvm/lib/elf.c197
-rw-r--r--tools/testing/selftests/kvm/lib/io.c158
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util.c1486
-rw-r--r--tools/testing/selftests/kvm/lib/kvm_util_internal.h67
-rw-r--r--tools/testing/selftests/kvm/lib/sparsebit.c2087
-rw-r--r--tools/testing/selftests/kvm/lib/vmx.c243
-rw-r--r--tools/testing/selftests/kvm/lib/x86.c700
-rw-r--r--tools/testing/selftests/kvm/set_sregs_test.c54
-rw-r--r--tools/testing/selftests/kvm/sync_regs_test.c254
-rw-r--r--tools/testing/selftests/kvm/vmx_tsc_adjust_test.c233
-rw-r--r--tools/testing/selftests/lib.mk63
-rw-r--r--tools/testing/selftests/lib/Makefile2
-rwxr-xr-xtools/testing/selftests/lib/bitmap.sh8
-rwxr-xr-xtools/testing/selftests/lib/prime_numbers.sh9
-rwxr-xr-xtools/testing/selftests/lib/printf.sh8
-rw-r--r--tools/testing/selftests/locking/Makefile10
-rwxr-xr-x[-rw-r--r--]tools/testing/selftests/locking/ww_mutex.sh8
-rw-r--r--tools/testing/selftests/media_tests/Makefile3
-rw-r--r--tools/testing/selftests/media_tests/media_device_open.c8
-rw-r--r--tools/testing/selftests/media_tests/media_device_test.c10
-rw-r--r--tools/testing/selftests/membarrier/membarrier_test.c7
-rw-r--r--tools/testing/selftests/memfd/Makefile6
-rwxr-xr-xtools/testing/selftests/memfd/run_hugetlbfs_test.sh (renamed from tools/testing/selftests/memfd/run_tests.sh)18
-rw-r--r--tools/testing/selftests/memory-hotplug/Makefile5
-rwxr-xr-xtools/testing/selftests/memory-hotplug/mem-on-off-test.sh14
-rw-r--r--tools/testing/selftests/mount/Makefile12
-rwxr-xr-xtools/testing/selftests/mount/run_tests.sh12
-rw-r--r--tools/testing/selftests/mqueue/Makefile12
-rw-r--r--tools/testing/selftests/mqueue/mq_open_tests.c37
-rw-r--r--tools/testing/selftests/mqueue/mq_perf_tests.c8
-rw-r--r--tools/testing/selftests/net/.gitignore5
-rw-r--r--tools/testing/selftests/net/Makefile8
-rw-r--r--tools/testing/selftests/net/config5
-rwxr-xr-xtools/testing/selftests/net/fib_rule_tests.sh248
-rw-r--r--[-rwxr-xr-x]tools/testing/selftests/net/fib_tests.sh868
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_vlan_aware.sh26
-rwxr-xr-xtools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh26
-rw-r--r--tools/testing/selftests/net/forwarding/lib.sh190
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre.sh159
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_bound.sh226
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh121
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_changes.sh278
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_flower.sh137
-rw-r--r--tools/testing/selftests/net/forwarding/mirror_gre_lib.sh130
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_neigh.sh115
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_nh.sh127
-rw-r--r--tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh94
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_vlan.sh92
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh270
-rw-r--r--tools/testing/selftests/net/forwarding/mirror_lib.sh132
-rw-r--r--tools/testing/selftests/net/forwarding/mirror_topo_lib.sh101
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_vlan.sh131
-rwxr-xr-xtools/testing/selftests/net/forwarding/router.sh14
-rwxr-xr-xtools/testing/selftests/net/forwarding/router_multipath.sh29
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_actions.sh25
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_chains.sh7
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_flower.sh80
-rwxr-xr-xtools/testing/selftests/net/forwarding/tc_shblocks.sh5
-rwxr-xr-xtools/testing/selftests/net/msg_zerocopy.sh8
-rwxr-xr-xtools/testing/selftests/net/netdevice.sh16
-rwxr-xr-xtools/testing/selftests/net/pmtu.sh9
-rw-r--r--tools/testing/selftests/net/psock_snd.c397
-rwxr-xr-xtools/testing/selftests/net/psock_snd.sh98
-rw-r--r--tools/testing/selftests/net/psock_tpacket.c4
-rw-r--r--tools/testing/selftests/net/reuseport_bpf_numa.c4
-rwxr-xr-xtools/testing/selftests/net/rtnetlink.sh134
-rw-r--r--tools/testing/selftests/net/tcp_inq.c189
-rw-r--r--tools/testing/selftests/net/tcp_mmap.c447
-rw-r--r--tools/testing/selftests/net/udpgso.c693
-rwxr-xr-xtools/testing/selftests/net/udpgso.sh29
-rwxr-xr-xtools/testing/selftests/net/udpgso_bench.sh74
-rw-r--r--tools/testing/selftests/net/udpgso_bench_rx.c265
-rw-r--r--tools/testing/selftests/net/udpgso_bench_tx.c420
-rw-r--r--tools/testing/selftests/proc/.gitignore8
-rw-r--r--tools/testing/selftests/proc/Makefile13
-rw-r--r--tools/testing/selftests/proc/config1
-rw-r--r--tools/testing/selftests/proc/proc-loadavg-001.c83
-rw-r--r--tools/testing/selftests/proc/proc-self-map-files-001.c82
-rw-r--r--tools/testing/selftests/proc/proc-self-map-files-002.c85
-rw-r--r--tools/testing/selftests/proc/proc-self-syscall.c60
-rw-r--r--tools/testing/selftests/proc/proc-self-wchan.c40
-rw-r--r--tools/testing/selftests/proc/proc-uptime-001.c45
-rw-r--r--tools/testing/selftests/proc/proc-uptime-002.c79
-rw-r--r--tools/testing/selftests/proc/proc-uptime.h74
-rw-r--r--tools/testing/selftests/proc/read.c147
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh56
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh12
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh4
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh1
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-console.sh115
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/parse-torture.sh105
-rw-r--r--tools/testing/selftests/rtc/.gitignore2
-rw-r--r--tools/testing/selftests/rtc/Makefile9
-rw-r--r--tools/testing/selftests/rtc/rtctest.c238
-rw-r--r--tools/testing/selftests/rtc/setdate.c (renamed from tools/testing/selftests/timers/rtctest_setdate.c)0
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c22
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json11
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/csum.json74
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/ife.json1036
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json24
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/police.json4
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/sample.json588
-rw-r--r--tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json320
-rw-r--r--tools/testing/selftests/timers/.gitignore3
-rw-r--r--tools/testing/selftests/timers/Makefile4
-rw-r--r--tools/testing/selftests/timers/rtcpie.c134
-rw-r--r--tools/testing/selftests/timers/rtctest.c403
-rw-r--r--tools/testing/selftests/uevent/Makefile17
-rw-r--r--tools/testing/selftests/uevent/config2
-rw-r--r--tools/testing/selftests/uevent/uevent_filtering.c486
-rw-r--r--tools/testing/selftests/x86/Makefile10
-rw-r--r--tools/testing/selftests/x86/mov_ss_trap.c285
-rw-r--r--tools/testing/selftests/x86/mpx-mini-test.c7
-rw-r--r--tools/testing/selftests/x86/pkey-helpers.h20
-rw-r--r--tools/testing/selftests/x86/protection_keys.c254
-rw-r--r--tools/testing/selftests/x86/test_syscall_vdso.c35
-rw-r--r--tools/testing/selftests/x86/trivial_program.c10
213 files changed, 31894 insertions, 1593 deletions
diff --git a/tools/testing/ktest/config-bisect.pl b/tools/testing/ktest/config-bisect.pl
new file mode 100755
index 000000000000..b28feea7c363
--- /dev/null
+++ b/tools/testing/ktest/config-bisect.pl
@@ -0,0 +1,770 @@
+#!/usr/bin/perl -w
+#
+# Copyright 2015 - Steven Rostedt, Red Hat Inc.
+# Copyright 2017 - Steven Rostedt, VMware, Inc.
+#
+# Licensed under the terms of the GNU GPL License version 2
+#
+
+# usage:
+# config-bisect.pl [options] good-config bad-config [good|bad]
+#
+
+# Compares a good config to a bad config, then takes half of the diffs
+# and produces a config that is somewhere between the good config and
+# the bad config. That is, the resulting config will start with the
+# good config and will try to make half of the differences of between
+# the good and bad configs match the bad config. It tries because of
+# dependencies between the two configs it may not be able to change
+# exactly half of the configs that are different between the two config
+# files.
+
+# Here's a normal way to use it:
+#
+# $ cd /path/to/linux/kernel
+# $ config-bisect.pl /path/to/good/config /path/to/bad/config
+
+# This will now pull in good config (blowing away .config in that directory
+# so do not make that be one of the good or bad configs), and then
+# build the config with "make oldconfig" to make sure it matches the
+# current kernel. It will then store the configs in that result for
+# the good config. It does the same for the bad config as well.
+# The algorithm will run, merging half of the differences between
+# the two configs and building them with "make oldconfig" to make sure
+# the result changes (dependencies may reset changes the tool had made).
+# It then copies the result of its good config to /path/to/good/config.tmp
+# and the bad config to /path/to/bad/config.tmp (just appends ".tmp" to the
+# files passed in). And the ".config" that you should test will be in
+# directory
+
+# After the first run, determine if the result is good or bad then
+# run the same command appending the result
+
+# For good results:
+# $ config-bisect.pl /path/to/good/config /path/to/bad/config good
+
+# For bad results:
+# $ config-bisect.pl /path/to/good/config /path/to/bad/config bad
+
+# Do not change the good-config or bad-config, config-bisect.pl will
+# copy the good-config to a temp file with the same name as good-config
+# but with a ".tmp" after it. It will do the same with the bad-config.
+
+# If "good" or "bad" is not stated at the end, it will copy the good and
+# bad configs to the .tmp versions. If a .tmp version already exists, it will
+# warn before writing over them (-r will not warn, and just write over them).
+# If the last config is labeled "good", then it will copy it to the good .tmp
+# version. If the last config is labeled "bad", it will copy it to the bad
+# .tmp version. It will continue this until it can not merge the two any more
+# without the result being equal to either the good or bad .tmp configs.
+
+my $start = 0;
+my $val = "";
+
+my $pwd = `pwd`;
+chomp $pwd;
+my $tree = $pwd;
+my $build;
+
+my $output_config;
+my $reset_bisect;
+
+sub usage {
+ print << "EOF"
+
+usage: config-bisect.pl [-l linux-tree][-b build-dir] good-config bad-config [good|bad]
+ -l [optional] define location of linux-tree (default is current directory)
+ -b [optional] define location to build (O=build-dir) (default is linux-tree)
+ good-config the config that is considered good
+ bad-config the config that does not work
+ "good" add this if the last run produced a good config
+ "bad" add this if the last run produced a bad config
+ If "good" or "bad" is not specified, then it is the start of a new bisect
+
+ Note, each run will create copy of good and bad configs with ".tmp" appended.
+
+EOF
+;
+
+ exit(-1);
+}
+
+sub doprint {
+ print @_;
+}
+
+sub dodie {
+ doprint "CRITICAL FAILURE... ", @_, "\n";
+
+ die @_, "\n";
+}
+
+sub expand_path {
+ my ($file) = @_;
+
+ if ($file =~ m,^/,) {
+ return $file;
+ }
+ return "$pwd/$file";
+}
+
+sub read_prompt {
+ my ($cancel, $prompt) = @_;
+
+ my $ans;
+
+ for (;;) {
+ if ($cancel) {
+ print "$prompt [y/n/C] ";
+ } else {
+ print "$prompt [y/N] ";
+ }
+ $ans = <STDIN>;
+ chomp $ans;
+ if ($ans =~ /^\s*$/) {
+ if ($cancel) {
+ $ans = "c";
+ } else {
+ $ans = "n";
+ }
+ }
+ last if ($ans =~ /^y$/i || $ans =~ /^n$/i);
+ if ($cancel) {
+ last if ($ans =~ /^c$/i);
+ print "Please answer either 'y', 'n' or 'c'.\n";
+ } else {
+ print "Please answer either 'y' or 'n'.\n";
+ }
+ }
+ if ($ans =~ /^c/i) {
+ exit;
+ }
+ if ($ans !~ /^y$/i) {
+ return 0;
+ }
+ return 1;
+}
+
+sub read_yn {
+ my ($prompt) = @_;
+
+ return read_prompt 0, $prompt;
+}
+
+sub read_ync {
+ my ($prompt) = @_;
+
+ return read_prompt 1, $prompt;
+}
+
+sub run_command {
+ my ($command, $redirect) = @_;
+ my $start_time;
+ my $end_time;
+ my $dord = 0;
+ my $pid;
+
+ $start_time = time;
+
+ doprint("$command ... ");
+
+ $pid = open(CMD, "$command 2>&1 |") or
+ dodie "unable to exec $command";
+
+ if (defined($redirect)) {
+ open (RD, ">$redirect") or
+ dodie "failed to write to redirect $redirect";
+ $dord = 1;
+ }
+
+ while (<CMD>) {
+ print RD if ($dord);
+ }
+
+ waitpid($pid, 0);
+ my $failed = $?;
+
+ close(CMD);
+ close(RD) if ($dord);
+
+ $end_time = time;
+ my $delta = $end_time - $start_time;
+
+ if ($delta == 1) {
+ doprint "[1 second] ";
+ } else {
+ doprint "[$delta seconds] ";
+ }
+
+ if ($failed) {
+ doprint "FAILED!\n";
+ } else {
+ doprint "SUCCESS\n";
+ }
+
+ return !$failed;
+}
+
+###### CONFIG BISECT ######
+
+# config_ignore holds the configs that were set (or unset) for
+# a good config and we will ignore these configs for the rest
+# of a config bisect. These configs stay as they were.
+my %config_ignore;
+
+# config_set holds what all configs were set as.
+my %config_set;
+
+# config_off holds the set of configs that the bad config had disabled.
+# We need to record them and set them in the .config when running
+# olddefconfig, because olddefconfig keeps the defaults.
+my %config_off;
+
+# config_off_tmp holds a set of configs to turn off for now
+my @config_off_tmp;
+
+# config_list is the set of configs that are being tested
+my %config_list;
+my %null_config;
+
+my %dependency;
+
+my $make;
+
+sub make_oldconfig {
+
+ if (!run_command "$make olddefconfig") {
+ # Perhaps olddefconfig doesn't exist in this version of the kernel
+ # try oldnoconfig
+ doprint "olddefconfig failed, trying make oldnoconfig\n";
+ if (!run_command "$make oldnoconfig") {
+ doprint "oldnoconfig failed, trying yes '' | make oldconfig\n";
+ # try a yes '' | oldconfig
+ run_command "yes '' | $make oldconfig" or
+ dodie "failed make config oldconfig";
+ }
+ }
+}
+
+sub assign_configs {
+ my ($hash, $config) = @_;
+
+ doprint "Reading configs from $config\n";
+
+ open (IN, $config)
+ or dodie "Failed to read $config";
+
+ while (<IN>) {
+ chomp;
+ if (/^((CONFIG\S*)=.*)/) {
+ ${$hash}{$2} = $1;
+ } elsif (/^(# (CONFIG\S*) is not set)/) {
+ ${$hash}{$2} = $1;
+ }
+ }
+
+ close(IN);
+}
+
+sub process_config_ignore {
+ my ($config) = @_;
+
+ assign_configs \%config_ignore, $config;
+}
+
+sub get_dependencies {
+ my ($config) = @_;
+
+ my $arr = $dependency{$config};
+ if (!defined($arr)) {
+ return ();
+ }
+
+ my @deps = @{$arr};
+
+ foreach my $dep (@{$arr}) {
+ print "ADD DEP $dep\n";
+ @deps = (@deps, get_dependencies $dep);
+ }
+
+ return @deps;
+}
+
+sub save_config {
+ my ($pc, $file) = @_;
+
+ my %configs = %{$pc};
+
+ doprint "Saving configs into $file\n";
+
+ open(OUT, ">$file") or dodie "Can not write to $file";
+
+ foreach my $config (keys %configs) {
+ print OUT "$configs{$config}\n";
+ }
+ close(OUT);
+}
+
+sub create_config {
+ my ($name, $pc) = @_;
+
+ doprint "Creating old config from $name configs\n";
+
+ save_config $pc, $output_config;
+
+ make_oldconfig;
+}
+
+# compare two config hashes, and return configs with different vals.
+# It returns B's config values, but you can use A to see what A was.
+sub diff_config_vals {
+ my ($pa, $pb) = @_;
+
+ # crappy Perl way to pass in hashes.
+ my %a = %{$pa};
+ my %b = %{$pb};
+
+ my %ret;
+
+ foreach my $item (keys %a) {
+ if (defined($b{$item}) && $b{$item} ne $a{$item}) {
+ $ret{$item} = $b{$item};
+ }
+ }
+
+ return %ret;
+}
+
+# compare two config hashes and return the configs in B but not A
+sub diff_configs {
+ my ($pa, $pb) = @_;
+
+ my %ret;
+
+ # crappy Perl way to pass in hashes.
+ my %a = %{$pa};
+ my %b = %{$pb};
+
+ foreach my $item (keys %b) {
+ if (!defined($a{$item})) {
+ $ret{$item} = $b{$item};
+ }
+ }
+
+ return %ret;
+}
+
+# return if two configs are equal or not
+# 0 is equal +1 b has something a does not
+# +1 if a and b have a different item.
+# -1 if a has something b does not
+sub compare_configs {
+ my ($pa, $pb) = @_;
+
+ my %ret;
+
+ # crappy Perl way to pass in hashes.
+ my %a = %{$pa};
+ my %b = %{$pb};
+
+ foreach my $item (keys %b) {
+ if (!defined($a{$item})) {
+ return 1;
+ }
+ if ($a{$item} ne $b{$item}) {
+ return 1;
+ }
+ }
+
+ foreach my $item (keys %a) {
+ if (!defined($b{$item})) {
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+sub process_failed {
+ my ($config) = @_;
+
+ doprint "\n\n***************************************\n";
+ doprint "Found bad config: $config\n";
+ doprint "***************************************\n\n";
+}
+
+sub process_new_config {
+ my ($tc, $nc, $gc, $bc) = @_;
+
+ my %tmp_config = %{$tc};
+ my %good_configs = %{$gc};
+ my %bad_configs = %{$bc};
+
+ my %new_configs;
+
+ my $runtest = 1;
+ my $ret;
+
+ create_config "tmp_configs", \%tmp_config;
+ assign_configs \%new_configs, $output_config;
+
+ $ret = compare_configs \%new_configs, \%bad_configs;
+ if (!$ret) {
+ doprint "New config equals bad config, try next test\n";
+ $runtest = 0;
+ }
+
+ if ($runtest) {
+ $ret = compare_configs \%new_configs, \%good_configs;
+ if (!$ret) {
+ doprint "New config equals good config, try next test\n";
+ $runtest = 0;
+ }
+ }
+
+ %{$nc} = %new_configs;
+
+ return $runtest;
+}
+
+sub convert_config {
+ my ($config) = @_;
+
+ if ($config =~ /^# (.*) is not set/) {
+ $config = "$1=n";
+ }
+
+ $config =~ s/^CONFIG_//;
+ return $config;
+}
+
+sub print_config {
+ my ($sym, $config) = @_;
+
+ $config = convert_config $config;
+ doprint "$sym$config\n";
+}
+
+sub print_config_compare {
+ my ($good_config, $bad_config) = @_;
+
+ $good_config = convert_config $good_config;
+ $bad_config = convert_config $bad_config;
+
+ my $good_value = $good_config;
+ my $bad_value = $bad_config;
+ $good_value =~ s/(.*)=//;
+ my $config = $1;
+
+ $bad_value =~ s/.*=//;
+
+ doprint " $config $good_value -> $bad_value\n";
+}
+
+# Pass in:
+# $phalf: half of the configs names you want to add
+# $oconfigs: The orginial configs to start with
+# $sconfigs: The source to update $oconfigs with (from $phalf)
+# $which: The name of which half that is updating (top / bottom)
+# $type: The name of the source type (good / bad)
+sub make_half {
+ my ($phalf, $oconfigs, $sconfigs, $which, $type) = @_;
+
+ my @half = @{$phalf};
+ my %orig_configs = %{$oconfigs};
+ my %source_configs = %{$sconfigs};
+
+ my %tmp_config = %orig_configs;
+
+ doprint "Settings bisect with $which half of $type configs:\n";
+ foreach my $item (@half) {
+ doprint "Updating $item to $source_configs{$item}\n";
+ $tmp_config{$item} = $source_configs{$item};
+ }
+
+ return %tmp_config;
+}
+
+sub run_config_bisect {
+ my ($pgood, $pbad) = @_;
+
+ my %good_configs = %{$pgood};
+ my %bad_configs = %{$pbad};
+
+ my %diff_configs = diff_config_vals \%good_configs, \%bad_configs;
+ my %b_configs = diff_configs \%good_configs, \%bad_configs;
+ my %g_configs = diff_configs \%bad_configs, \%good_configs;
+
+ # diff_arr is what is in both good and bad but are different (y->n)
+ my @diff_arr = keys %diff_configs;
+ my $len_diff = $#diff_arr + 1;
+
+ # b_arr is what is in bad but not in good (has depends)
+ my @b_arr = keys %b_configs;
+ my $len_b = $#b_arr + 1;
+
+ # g_arr is what is in good but not in bad
+ my @g_arr = keys %g_configs;
+ my $len_g = $#g_arr + 1;
+
+ my $runtest = 0;
+ my %new_configs;
+ my $ret;
+
+ # Look at the configs that are different between good and bad.
+ # This does not include those that depend on other configs
+ # (configs depending on other configs that are not set would
+ # not show up even as a "# CONFIG_FOO is not set"
+
+
+ doprint "# of configs to check: $len_diff\n";
+ doprint "# of configs showing only in good: $len_g\n";
+ doprint "# of configs showing only in bad: $len_b\n";
+
+ if ($len_diff > 0) {
+ # Now test for different values
+
+ doprint "Configs left to check:\n";
+ doprint " Good Config\t\t\tBad Config\n";
+ doprint " -----------\t\t\t----------\n";
+ foreach my $item (@diff_arr) {
+ doprint " $good_configs{$item}\t$bad_configs{$item}\n";
+ }
+
+ my $half = int($#diff_arr / 2);
+ my @tophalf = @diff_arr[0 .. $half];
+
+ doprint "Set tmp config to be good config with some bad config values\n";
+
+ my %tmp_config = make_half \@tophalf, \%good_configs,
+ \%bad_configs, "top", "bad";
+
+ $runtest = process_new_config \%tmp_config, \%new_configs,
+ \%good_configs, \%bad_configs;
+
+ if (!$runtest) {
+ doprint "Set tmp config to be bad config with some good config values\n";
+
+ my %tmp_config = make_half \@tophalf, \%bad_configs,
+ \%good_configs, "top", "good";
+
+ $runtest = process_new_config \%tmp_config, \%new_configs,
+ \%good_configs, \%bad_configs;
+ }
+ }
+
+ if (!$runtest && $len_diff > 0) {
+ # do the same thing, but this time with bottom half
+
+ my $half = int($#diff_arr / 2);
+ my @bottomhalf = @diff_arr[$half+1 .. $#diff_arr];
+
+ doprint "Set tmp config to be good config with some bad config values\n";
+
+ my %tmp_config = make_half \@bottomhalf, \%good_configs,
+ \%bad_configs, "bottom", "bad";
+
+ $runtest = process_new_config \%tmp_config, \%new_configs,
+ \%good_configs, \%bad_configs;
+
+ if (!$runtest) {
+ doprint "Set tmp config to be bad config with some good config values\n";
+
+ my %tmp_config = make_half \@bottomhalf, \%bad_configs,
+ \%good_configs, "bottom", "good";
+
+ $runtest = process_new_config \%tmp_config, \%new_configs,
+ \%good_configs, \%bad_configs;
+ }
+ }
+
+ if ($runtest) {
+ make_oldconfig;
+ doprint "READY TO TEST .config IN $build\n";
+ return 0;
+ }
+
+ doprint "\n%%%%%%%% FAILED TO FIND SINGLE BAD CONFIG %%%%%%%%\n";
+ doprint "Hmm, can't make any more changes without making good == bad?\n";
+ doprint "Difference between good (+) and bad (-)\n";
+
+ foreach my $item (keys %bad_configs) {
+ if (!defined($good_configs{$item})) {
+ print_config "-", $bad_configs{$item};
+ }
+ }
+
+ foreach my $item (keys %good_configs) {
+ next if (!defined($bad_configs{$item}));
+ if ($good_configs{$item} ne $bad_configs{$item}) {
+ print_config_compare $good_configs{$item}, $bad_configs{$item};
+ }
+ }
+
+ foreach my $item (keys %good_configs) {
+ if (!defined($bad_configs{$item})) {
+ print_config "+", $good_configs{$item};
+ }
+ }
+ return -1;
+}
+
+sub config_bisect {
+ my ($good_config, $bad_config) = @_;
+ my $ret;
+
+ my %good_configs;
+ my %bad_configs;
+ my %tmp_configs;
+
+ doprint "Run good configs through make oldconfig\n";
+ assign_configs \%tmp_configs, $good_config;
+ create_config "$good_config", \%tmp_configs;
+ assign_configs \%good_configs, $output_config;
+
+ doprint "Run bad configs through make oldconfig\n";
+ assign_configs \%tmp_configs, $bad_config;
+ create_config "$bad_config", \%tmp_configs;
+ assign_configs \%bad_configs, $output_config;
+
+ save_config \%good_configs, $good_config;
+ save_config \%bad_configs, $bad_config;
+
+ return run_config_bisect \%good_configs, \%bad_configs;
+}
+
+while ($#ARGV >= 0) {
+ if ($ARGV[0] !~ m/^-/) {
+ last;
+ }
+ my $opt = shift @ARGV;
+
+ if ($opt eq "-b") {
+ $val = shift @ARGV;
+ if (!defined($val)) {
+ die "-b requires value\n";
+ }
+ $build = $val;
+ }
+
+ elsif ($opt eq "-l") {
+ $val = shift @ARGV;
+ if (!defined($val)) {
+ die "-l requires value\n";
+ }
+ $tree = $val;
+ }
+
+ elsif ($opt eq "-r") {
+ $reset_bisect = 1;
+ }
+
+ elsif ($opt eq "-h") {
+ usage;
+ }
+
+ else {
+ die "Unknow option $opt\n";
+ }
+}
+
+$build = $tree if (!defined($build));
+
+$tree = expand_path $tree;
+$build = expand_path $build;
+
+if ( ! -d $tree ) {
+ die "$tree not a directory\n";
+}
+
+if ( ! -d $build ) {
+ die "$build not a directory\n";
+}
+
+usage if $#ARGV < 1;
+
+if ($#ARGV == 1) {
+ $start = 1;
+} elsif ($#ARGV == 2) {
+ $val = $ARGV[2];
+ if ($val ne "good" && $val ne "bad") {
+ die "Unknown command '$val', bust be either \"good\" or \"bad\"\n";
+ }
+} else {
+ usage;
+}
+
+my $good_start = expand_path $ARGV[0];
+my $bad_start = expand_path $ARGV[1];
+
+my $good = "$good_start.tmp";
+my $bad = "$bad_start.tmp";
+
+$make = "make";
+
+if ($build ne $tree) {
+ $make = "make O=$build"
+}
+
+$output_config = "$build/.config";
+
+if ($start) {
+ if ( ! -f $good_start ) {
+ die "$good_start not found\n";
+ }
+ if ( ! -f $bad_start ) {
+ die "$bad_start not found\n";
+ }
+ if ( -f $good || -f $bad ) {
+ my $p = "";
+
+ if ( -f $good ) {
+ $p = "$good exists\n";
+ }
+
+ if ( -f $bad ) {
+ $p = "$p$bad exists\n";
+ }
+
+ if (!defined($reset_bisect)) {
+ if (!read_yn "${p}Overwrite and start new bisect anyway?") {
+ exit (-1);
+ }
+ }
+ }
+ run_command "cp $good_start $good" or die "failed to copy to $good\n";
+ run_command "cp $bad_start $bad" or die "faield to copy to $bad\n";
+} else {
+ if ( ! -f $good ) {
+ die "Can not find file $good\n";
+ }
+ if ( ! -f $bad ) {
+ die "Can not find file $bad\n";
+ }
+ if ($val eq "good") {
+ run_command "cp $output_config $good" or die "failed to copy $config to $good\n";
+ } elsif ($val eq "bad") {
+ run_command "cp $output_config $bad" or die "failed to copy $config to $bad\n";
+ }
+}
+
+chdir $tree || die "can't change directory to $tree";
+
+my $ret = config_bisect $good, $bad;
+
+if (!$ret) {
+ exit(0);
+}
+
+if ($ret > 0) {
+ doprint "Cleaning temp files\n";
+ run_command "rm $good";
+ run_command "rm $bad";
+ exit(1);
+} else {
+ doprint "See good and bad configs for details:\n";
+ doprint "good: $good\n";
+ doprint "bad: $bad\n";
+ doprint "%%%%%%%% FAILED TO FIND SINGLE BAD CONFIG %%%%%%%%\n";
+}
+exit(2);
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 8809f244bb7c..87af8a68ab25 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -10,6 +10,7 @@ use Fcntl qw(F_GETFL F_SETFL O_NONBLOCK);
use File::Path qw(mkpath);
use File::Copy qw(cp);
use FileHandle;
+use FindBin;
my $VERSION = "0.2";
@@ -22,6 +23,11 @@ my %evals;
#default opts
my %default = (
+ "MAILER" => "sendmail", # default mailer
+ "EMAIL_ON_ERROR" => 1,
+ "EMAIL_WHEN_FINISHED" => 1,
+ "EMAIL_WHEN_CANCELED" => 0,
+ "EMAIL_WHEN_STARTED" => 0,
"NUM_TESTS" => 1,
"TEST_TYPE" => "build",
"BUILD_TYPE" => "randconfig",
@@ -59,6 +65,7 @@ my %default = (
"GRUB_REBOOT" => "grub2-reboot",
"SYSLINUX" => "extlinux",
"SYSLINUX_PATH" => "/boot/extlinux",
+ "CONNECT_TIMEOUT" => 25,
# required, and we will ask users if they don't have them but we keep the default
# value something that is common.
@@ -163,6 +170,8 @@ my $store_failures;
my $store_successes;
my $test_name;
my $timeout;
+my $connect_timeout;
+my $config_bisect_exec;
my $booted_timeout;
my $detect_triplefault;
my $console;
@@ -204,6 +213,20 @@ my $install_time;
my $reboot_time;
my $test_time;
+my $pwd;
+my $dirname = $FindBin::Bin;
+
+my $mailto;
+my $mailer;
+my $mail_path;
+my $mail_command;
+my $email_on_error;
+my $email_when_finished;
+my $email_when_started;
+my $email_when_canceled;
+
+my $script_start_time = localtime();
+
# set when a test is something other that just building or install
# which would require more options.
my $buildonly = 1;
@@ -229,6 +252,14 @@ my $no_reboot = 1;
my $reboot_success = 0;
my %option_map = (
+ "MAILTO" => \$mailto,
+ "MAILER" => \$mailer,
+ "MAIL_PATH" => \$mail_path,
+ "MAIL_COMMAND" => \$mail_command,
+ "EMAIL_ON_ERROR" => \$email_on_error,
+ "EMAIL_WHEN_FINISHED" => \$email_when_finished,
+ "EMAIL_WHEN_STARTED" => \$email_when_started,
+ "EMAIL_WHEN_CANCELED" => \$email_when_canceled,
"MACHINE" => \$machine,
"SSH_USER" => \$ssh_user,
"TMP_DIR" => \$tmpdir,
@@ -296,6 +327,8 @@ my %option_map = (
"STORE_SUCCESSES" => \$store_successes,
"TEST_NAME" => \$test_name,
"TIMEOUT" => \$timeout,
+ "CONNECT_TIMEOUT" => \$connect_timeout,
+ "CONFIG_BISECT_EXEC" => \$config_bisect_exec,
"BOOTED_TIMEOUT" => \$booted_timeout,
"CONSOLE" => \$console,
"CLOSE_CONSOLE_SIGNAL" => \$close_console_signal,
@@ -337,6 +370,7 @@ my %used_options;
# default variables that can be used
chomp ($variable{"PWD"} = `pwd`);
+$pwd = $variable{"PWD"};
$config_help{"MACHINE"} = << "EOF"
The machine hostname that you will test.
@@ -718,22 +752,14 @@ sub set_value {
my $prvalue = process_variables($rvalue);
- if ($buildonly && $lvalue =~ /^TEST_TYPE(\[.*\])?$/ && $prvalue ne "build") {
+ if ($lvalue =~ /^(TEST|BISECT|CONFIG_BISECT)_TYPE(\[.*\])?$/ &&
+ $prvalue !~ /^(config_|)bisect$/ &&
+ $prvalue !~ /^build$/ &&
+ $buildonly) {
+
# Note if a test is something other than build, then we
# will need other mandatory options.
if ($prvalue ne "install") {
- # for bisect, we need to check BISECT_TYPE
- if ($prvalue ne "bisect") {
- $buildonly = 0;
- }
- } else {
- # install still limits some mandatory options.
- $buildonly = 2;
- }
- }
-
- if ($buildonly && $lvalue =~ /^BISECT_TYPE(\[.*\])?$/ && $prvalue ne "build") {
- if ($prvalue ne "install") {
$buildonly = 0;
} else {
# install still limits some mandatory options.
@@ -1140,7 +1166,8 @@ sub __read_config {
sub get_test_case {
print "What test case would you like to run?\n";
print " (build, install or boot)\n";
- print " Other tests are available but require editing the config file\n";
+ print " Other tests are available but require editing ktest.conf\n";
+ print " (see tools/testing/ktest/sample.conf)\n";
my $ans = <STDIN>;
chomp $ans;
$default{"TEST_TYPE"} = $ans;
@@ -1328,8 +1355,8 @@ sub reboot {
my ($time) = @_;
my $powercycle = 0;
- # test if the machine can be connected to within 5 seconds
- my $stat = run_ssh("echo check machine status", 5);
+ # test if the machine can be connected to within a few seconds
+ my $stat = run_ssh("echo check machine status", $connect_timeout);
if (!$stat) {
doprint("power cycle\n");
$powercycle = 1;
@@ -1404,10 +1431,18 @@ sub do_not_reboot {
return $test_type eq "build" || $no_reboot ||
($test_type eq "patchcheck" && $opt{"PATCHCHECK_TYPE[$i]"} eq "build") ||
- ($test_type eq "bisect" && $opt{"BISECT_TYPE[$i]"} eq "build");
+ ($test_type eq "bisect" && $opt{"BISECT_TYPE[$i]"} eq "build") ||
+ ($test_type eq "config_bisect" && $opt{"CONFIG_BISECT_TYPE[$i]"} eq "build");
}
+my $in_die = 0;
+
sub dodie {
+
+ # avoid recusion
+ return if ($in_die);
+ $in_die = 1;
+
doprint "CRITICAL FAILURE... ", @_, "\n";
my $i = $iteration;
@@ -1426,6 +1461,11 @@ sub dodie {
print " See $opt{LOG_FILE} for more info.\n";
}
+ if ($email_on_error) {
+ send_email("KTEST: critical failure for your [$test_type] test",
+ "Your test started at $script_start_time has failed with:\n@_\n");
+ }
+
if ($monitor_cnt) {
# restore terminal settings
system("stty $stty_orig");
@@ -1477,7 +1517,7 @@ sub exec_console {
close($pts);
exec $console or
- die "Can't open console $console";
+ dodie "Can't open console $console";
}
sub open_console {
@@ -1515,6 +1555,9 @@ sub close_console {
doprint "kill child process $pid\n";
kill $close_console_signal, $pid;
+ doprint "wait for child process $pid to exit\n";
+ waitpid($pid, 0);
+
print "closing!\n";
close($fp);
@@ -1625,7 +1668,7 @@ sub save_logs {
if (!-d $dir) {
mkpath($dir) or
- die "can't create $dir";
+ dodie "can't create $dir";
}
my %files = (
@@ -1638,7 +1681,7 @@ sub save_logs {
while (my ($name, $source) = each(%files)) {
if (-f "$source") {
cp "$source", "$dir/$name" or
- die "failed to copy $source";
+ dodie "failed to copy $source";
}
}
@@ -1692,6 +1735,7 @@ sub run_command {
my $end_time;
my $dolog = 0;
my $dord = 0;
+ my $dostdout = 0;
my $pid;
$command =~ s/\$SSH_USER/$ssh_user/g;
@@ -1710,9 +1754,15 @@ sub run_command {
}
if (defined($redirect)) {
- open (RD, ">$redirect") or
- dodie "failed to write to redirect $redirect";
- $dord = 1;
+ if ($redirect eq 1) {
+ $dostdout = 1;
+ # Have the output of the command on its own line
+ doprint "\n";
+ } else {
+ open (RD, ">$redirect") or
+ dodie "failed to write to redirect $redirect";
+ $dord = 1;
+ }
}
my $hit_timeout = 0;
@@ -1734,6 +1784,7 @@ sub run_command {
}
print LOG $line if ($dolog);
print RD $line if ($dord);
+ print $line if ($dostdout);
}
waitpid($pid, 0);
@@ -1812,7 +1863,7 @@ sub get_grub2_index {
$ssh_grub =~ s,\$SSH_COMMAND,cat $grub_file,g;
open(IN, "$ssh_grub |")
- or die "unable to get $grub_file";
+ or dodie "unable to get $grub_file";
my $found = 0;
@@ -1821,13 +1872,13 @@ sub get_grub2_index {
$grub_number++;
$found = 1;
last;
- } elsif (/^menuentry\s/) {
+ } elsif (/^menuentry\s|^submenu\s/) {
$grub_number++;
}
}
close(IN);
- die "Could not find '$grub_menu' in $grub_file on $machine"
+ dodie "Could not find '$grub_menu' in $grub_file on $machine"
if (!$found);
doprint "$grub_number\n";
$last_grub_menu = $grub_menu;
@@ -1855,7 +1906,7 @@ sub get_grub_index {
$ssh_grub =~ s,\$SSH_COMMAND,cat /boot/grub/menu.lst,g;
open(IN, "$ssh_grub |")
- or die "unable to get menu.lst";
+ or dodie "unable to get menu.lst";
my $found = 0;
@@ -1870,7 +1921,7 @@ sub get_grub_index {
}
close(IN);
- die "Could not find '$grub_menu' in /boot/grub/menu on $machine"
+ dodie "Could not find '$grub_menu' in /boot/grub/menu on $machine"
if (!$found);
doprint "$grub_number\n";
$last_grub_menu = $grub_menu;
@@ -1983,7 +2034,7 @@ sub monitor {
my $full_line = "";
open(DMESG, "> $dmesg") or
- die "unable to write to $dmesg";
+ dodie "unable to write to $dmesg";
reboot_to;
@@ -2862,7 +2913,7 @@ sub run_bisect {
sub update_bisect_replay {
my $tmp_log = "$tmpdir/ktest_bisect_log";
run_command "git bisect log > $tmp_log" or
- die "can't create bisect log";
+ dodie "can't create bisect log";
return $tmp_log;
}
@@ -2871,9 +2922,9 @@ sub bisect {
my $result;
- die "BISECT_GOOD[$i] not defined\n" if (!defined($bisect_good));
- die "BISECT_BAD[$i] not defined\n" if (!defined($bisect_bad));
- die "BISECT_TYPE[$i] not defined\n" if (!defined($bisect_type));
+ dodie "BISECT_GOOD[$i] not defined\n" if (!defined($bisect_good));
+ dodie "BISECT_BAD[$i] not defined\n" if (!defined($bisect_bad));
+ dodie "BISECT_TYPE[$i] not defined\n" if (!defined($bisect_type));
my $good = $bisect_good;
my $bad = $bisect_bad;
@@ -2936,7 +2987,7 @@ sub bisect {
if ($check ne "good") {
doprint "TESTING BISECT BAD [$bad]\n";
run_command "git checkout $bad" or
- die "Failed to checkout $bad";
+ dodie "Failed to checkout $bad";
$result = run_bisect $type;
@@ -2948,7 +2999,7 @@ sub bisect {
if ($check ne "bad") {
doprint "TESTING BISECT GOOD [$good]\n";
run_command "git checkout $good" or
- die "Failed to checkout $good";
+ dodie "Failed to checkout $good";
$result = run_bisect $type;
@@ -2959,7 +3010,7 @@ sub bisect {
# checkout where we started
run_command "git checkout $head" or
- die "Failed to checkout $head";
+ dodie "Failed to checkout $head";
}
run_command "git bisect start$start_files" or
@@ -3092,76 +3143,6 @@ sub create_config {
make_oldconfig;
}
-# compare two config hashes, and return configs with different vals.
-# It returns B's config values, but you can use A to see what A was.
-sub diff_config_vals {
- my ($pa, $pb) = @_;
-
- # crappy Perl way to pass in hashes.
- my %a = %{$pa};
- my %b = %{$pb};
-
- my %ret;
-
- foreach my $item (keys %a) {
- if (defined($b{$item}) && $b{$item} ne $a{$item}) {
- $ret{$item} = $b{$item};
- }
- }
-
- return %ret;
-}
-
-# compare two config hashes and return the configs in B but not A
-sub diff_configs {
- my ($pa, $pb) = @_;
-
- my %ret;
-
- # crappy Perl way to pass in hashes.
- my %a = %{$pa};
- my %b = %{$pb};
-
- foreach my $item (keys %b) {
- if (!defined($a{$item})) {
- $ret{$item} = $b{$item};
- }
- }
-
- return %ret;
-}
-
-# return if two configs are equal or not
-# 0 is equal +1 b has something a does not
-# +1 if a and b have a different item.
-# -1 if a has something b does not
-sub compare_configs {
- my ($pa, $pb) = @_;
-
- my %ret;
-
- # crappy Perl way to pass in hashes.
- my %a = %{$pa};
- my %b = %{$pb};
-
- foreach my $item (keys %b) {
- if (!defined($a{$item})) {
- return 1;
- }
- if ($a{$item} ne $b{$item}) {
- return 1;
- }
- }
-
- foreach my $item (keys %a) {
- if (!defined($b{$item})) {
- return -1;
- }
- }
-
- return 0;
-}
-
sub run_config_bisect_test {
my ($type) = @_;
@@ -3174,166 +3155,57 @@ sub run_config_bisect_test {
return $ret;
}
-sub process_failed {
- my ($config) = @_;
+sub config_bisect_end {
+ my ($good, $bad) = @_;
+ my $diffexec = "diff -u";
+ if (-f "$builddir/scripts/diffconfig") {
+ $diffexec = "$builddir/scripts/diffconfig";
+ }
doprint "\n\n***************************************\n";
- doprint "Found bad config: $config\n";
+ doprint "No more config bisecting possible.\n";
+ run_command "$diffexec $good $bad", 1;
doprint "***************************************\n\n";
}
-# used for config bisecting
-my $good_config;
-my $bad_config;
-
-sub process_new_config {
- my ($tc, $nc, $gc, $bc) = @_;
-
- my %tmp_config = %{$tc};
- my %good_configs = %{$gc};
- my %bad_configs = %{$bc};
-
- my %new_configs;
-
- my $runtest = 1;
- my $ret;
-
- create_config "tmp_configs", \%tmp_config;
- assign_configs \%new_configs, $output_config;
-
- $ret = compare_configs \%new_configs, \%bad_configs;
- if (!$ret) {
- doprint "New config equals bad config, try next test\n";
- $runtest = 0;
- }
-
- if ($runtest) {
- $ret = compare_configs \%new_configs, \%good_configs;
- if (!$ret) {
- doprint "New config equals good config, try next test\n";
- $runtest = 0;
- }
- }
-
- %{$nc} = %new_configs;
-
- return $runtest;
-}
-
sub run_config_bisect {
- my ($pgood, $pbad) = @_;
-
- my $type = $config_bisect_type;
-
- my %good_configs = %{$pgood};
- my %bad_configs = %{$pbad};
-
- my %diff_configs = diff_config_vals \%good_configs, \%bad_configs;
- my %b_configs = diff_configs \%good_configs, \%bad_configs;
- my %g_configs = diff_configs \%bad_configs, \%good_configs;
-
- my @diff_arr = keys %diff_configs;
- my $len_diff = $#diff_arr + 1;
-
- my @b_arr = keys %b_configs;
- my $len_b = $#b_arr + 1;
-
- my @g_arr = keys %g_configs;
- my $len_g = $#g_arr + 1;
-
- my $runtest = 1;
- my %new_configs;
+ my ($good, $bad, $last_result) = @_;
+ my $reset = "";
+ my $cmd;
my $ret;
- # First, lets get it down to a single subset.
- # Is the problem with a difference in values?
- # Is the problem with a missing config?
- # Is the problem with a config that breaks things?
-
- # Enable all of one set and see if we get a new bad
- # or good config.
-
- # first set the good config to the bad values.
-
- doprint "d=$len_diff g=$len_g b=$len_b\n";
-
- # first lets enable things in bad config that are enabled in good config
-
- if ($len_diff > 0) {
- if ($len_b > 0 || $len_g > 0) {
- my %tmp_config = %bad_configs;
-
- doprint "Set tmp config to be bad config with good config values\n";
- foreach my $item (@diff_arr) {
- $tmp_config{$item} = $good_configs{$item};
- }
-
- $runtest = process_new_config \%tmp_config, \%new_configs,
- \%good_configs, \%bad_configs;
- }
+ if (!length($last_result)) {
+ $reset = "-r";
}
+ run_command "$config_bisect_exec $reset -b $outputdir $good $bad $last_result", 1;
- if (!$runtest && $len_diff > 0) {
-
- if ($len_diff == 1) {
- process_failed $diff_arr[0];
- return 1;
- }
- my %tmp_config = %bad_configs;
-
- my $half = int($#diff_arr / 2);
- my @tophalf = @diff_arr[0 .. $half];
-
- doprint "Settings bisect with top half:\n";
- doprint "Set tmp config to be bad config with some good config values\n";
- foreach my $item (@tophalf) {
- $tmp_config{$item} = $good_configs{$item};
- }
-
- $runtest = process_new_config \%tmp_config, \%new_configs,
- \%good_configs, \%bad_configs;
-
- if (!$runtest) {
- my %tmp_config = %bad_configs;
-
- doprint "Try bottom half\n";
-
- my @bottomhalf = @diff_arr[$half+1 .. $#diff_arr];
-
- foreach my $item (@bottomhalf) {
- $tmp_config{$item} = $good_configs{$item};
- }
-
- $runtest = process_new_config \%tmp_config, \%new_configs,
- \%good_configs, \%bad_configs;
- }
+ # config-bisect returns:
+ # 0 if there is more to bisect
+ # 1 for finding a good config
+ # 2 if it can not find any more configs
+ # -1 (255) on error
+ if ($run_command_status) {
+ return $run_command_status;
}
- if ($runtest) {
- $ret = run_config_bisect_test $type;
- if ($ret) {
- doprint "NEW GOOD CONFIG\n";
- %good_configs = %new_configs;
- run_command "mv $good_config ${good_config}.last";
- save_config \%good_configs, $good_config;
- %{$pgood} = %good_configs;
- } else {
- doprint "NEW BAD CONFIG\n";
- %bad_configs = %new_configs;
- run_command "mv $bad_config ${bad_config}.last";
- save_config \%bad_configs, $bad_config;
- %{$pbad} = %bad_configs;
- }
- return 0;
+ $ret = run_config_bisect_test $config_bisect_type;
+ if ($ret) {
+ doprint "NEW GOOD CONFIG\n";
+ # Return 3 for good config
+ return 3;
+ } else {
+ doprint "NEW BAD CONFIG\n";
+ # Return 4 for bad config
+ return 4;
}
-
- fail "Hmm, need to do a mix match?\n";
- return -1;
}
sub config_bisect {
my ($i) = @_;
+ my $good_config;
+ my $bad_config;
+
my $type = $config_bisect_type;
my $ret;
@@ -3353,6 +3225,24 @@ sub config_bisect {
$good_config = $output_config;
}
+ if (!defined($config_bisect_exec)) {
+ # First check the location that ktest.pl ran
+ my @locations = ( "$pwd/config-bisect.pl",
+ "$dirname/config-bisect.pl",
+ "$builddir/tools/testing/ktest/config-bisect.pl",
+ undef );
+ foreach my $loc (@locations) {
+ doprint "loc = $loc\n";
+ $config_bisect_exec = $loc;
+ last if (defined($config_bisect_exec && -x $config_bisect_exec));
+ }
+ if (!defined($config_bisect_exec)) {
+ fail "Could not find an executable config-bisect.pl\n",
+ " Set CONFIG_BISECT_EXEC to point to config-bisect.pl";
+ return 1;
+ }
+ }
+
# we don't want min configs to cause issues here.
doprint "Disabling 'MIN_CONFIG' for this test\n";
undef $minconfig;
@@ -3361,21 +3251,31 @@ sub config_bisect {
my %bad_configs;
my %tmp_configs;
+ if (-f "$tmpdir/good_config.tmp" || -f "$tmpdir/bad_config.tmp") {
+ if (read_yn "Interrupted config-bisect. Continue (n - will start new)?") {
+ if (-f "$tmpdir/good_config.tmp") {
+ $good_config = "$tmpdir/good_config.tmp";
+ } else {
+ $good_config = "$tmpdir/good_config";
+ }
+ if (-f "$tmpdir/bad_config.tmp") {
+ $bad_config = "$tmpdir/bad_config.tmp";
+ } else {
+ $bad_config = "$tmpdir/bad_config";
+ }
+ }
+ }
doprint "Run good configs through make oldconfig\n";
assign_configs \%tmp_configs, $good_config;
create_config "$good_config", \%tmp_configs;
- assign_configs \%good_configs, $output_config;
+ $good_config = "$tmpdir/good_config";
+ system("cp $output_config $good_config") == 0 or dodie "cp good config";
doprint "Run bad configs through make oldconfig\n";
assign_configs \%tmp_configs, $bad_config;
create_config "$bad_config", \%tmp_configs;
- assign_configs \%bad_configs, $output_config;
-
- $good_config = "$tmpdir/good_config";
$bad_config = "$tmpdir/bad_config";
-
- save_config \%good_configs, $good_config;
- save_config \%bad_configs, $bad_config;
+ system("cp $output_config $bad_config") == 0 or dodie "cp bad config";
if (defined($config_bisect_check) && $config_bisect_check ne "0") {
if ($config_bisect_check ne "good") {
@@ -3398,10 +3298,21 @@ sub config_bisect {
}
}
+ my $last_run = "";
+
do {
- $ret = run_config_bisect \%good_configs, \%bad_configs;
+ $ret = run_config_bisect $good_config, $bad_config, $last_run;
+ if ($ret == 3) {
+ $last_run = "good";
+ } elsif ($ret == 4) {
+ $last_run = "bad";
+ }
print_times;
- } while (!$ret);
+ } while ($ret == 3 || $ret == 4);
+
+ if ($ret == 2) {
+ config_bisect_end "$good_config.tmp", "$bad_config.tmp";
+ }
return $ret if ($ret < 0);
@@ -3416,9 +3327,9 @@ sub patchcheck_reboot {
sub patchcheck {
my ($i) = @_;
- die "PATCHCHECK_START[$i] not defined\n"
+ dodie "PATCHCHECK_START[$i] not defined\n"
if (!defined($patchcheck_start));
- die "PATCHCHECK_TYPE[$i] not defined\n"
+ dodie "PATCHCHECK_TYPE[$i] not defined\n"
if (!defined($patchcheck_type));
my $start = $patchcheck_start;
@@ -3432,7 +3343,7 @@ sub patchcheck {
if (defined($patchcheck_end)) {
$end = $patchcheck_end;
} elsif ($cherry) {
- die "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n";
+ dodie "PATCHCHECK_END must be defined with PATCHCHECK_CHERRY\n";
}
# Get the true sha1's since we can use things like HEAD~3
@@ -3496,7 +3407,7 @@ sub patchcheck {
doprint "\nProcessing commit \"$item\"\n\n";
run_command "git checkout $sha1" or
- die "Failed to checkout $sha1";
+ dodie "Failed to checkout $sha1";
# only clean on the first and last patch
if ($item eq $list[0] ||
@@ -3587,7 +3498,7 @@ sub read_kconfig {
}
open(KIN, "$kconfig")
- or die "Can't open $kconfig";
+ or dodie "Can't open $kconfig";
while (<KIN>) {
chomp;
@@ -3746,7 +3657,7 @@ sub get_depends {
$dep =~ s/^[^$valid]*[$valid]+//;
} else {
- die "this should never happen";
+ dodie "this should never happen";
}
}
@@ -4007,7 +3918,7 @@ sub make_min_config {
# update new ignore configs
if (defined($ignore_config)) {
open (OUT, ">$temp_config")
- or die "Can't write to $temp_config";
+ or dodie "Can't write to $temp_config";
foreach my $config (keys %save_configs) {
print OUT "$save_configs{$config}\n";
}
@@ -4035,7 +3946,7 @@ sub make_min_config {
# Save off all the current mandatory configs
open (OUT, ">$temp_config")
- or die "Can't write to $temp_config";
+ or dodie "Can't write to $temp_config";
foreach my $config (keys %keep_configs) {
print OUT "$keep_configs{$config}\n";
}
@@ -4222,6 +4133,74 @@ sub set_test_option {
return eval_option($name, $option, $i);
}
+sub find_mailer {
+ my ($mailer) = @_;
+
+ my @paths = split /:/, $ENV{PATH};
+
+ # sendmail is usually in /usr/sbin
+ $paths[$#paths + 1] = "/usr/sbin";
+
+ foreach my $path (@paths) {
+ if (-x "$path/$mailer") {
+ return $path;
+ }
+ }
+
+ return undef;
+}
+
+sub do_send_mail {
+ my ($subject, $message) = @_;
+
+ if (!defined($mail_path)) {
+ # find the mailer
+ $mail_path = find_mailer $mailer;
+ if (!defined($mail_path)) {
+ die "\nCan not find $mailer in PATH\n";
+ }
+ }
+
+ if (!defined($mail_command)) {
+ if ($mailer eq "mail" || $mailer eq "mailx") {
+ $mail_command = "\$MAIL_PATH/\$MAILER -s \'\$SUBJECT\' \$MAILTO <<< \'\$MESSAGE\'";
+ } elsif ($mailer eq "sendmail" ) {
+ $mail_command = "echo \'Subject: \$SUBJECT\n\n\$MESSAGE\' | \$MAIL_PATH/\$MAILER -t \$MAILTO";
+ } else {
+ die "\nYour mailer: $mailer is not supported.\n";
+ }
+ }
+
+ $mail_command =~ s/\$MAILER/$mailer/g;
+ $mail_command =~ s/\$MAIL_PATH/$mail_path/g;
+ $mail_command =~ s/\$MAILTO/$mailto/g;
+ $mail_command =~ s/\$SUBJECT/$subject/g;
+ $mail_command =~ s/\$MESSAGE/$message/g;
+
+ run_command $mail_command;
+}
+
+sub send_email {
+
+ if (defined($mailto)) {
+ if (!defined($mailer)) {
+ doprint "No email sent: email or mailer not specified in config.\n";
+ return;
+ }
+ do_send_mail @_;
+ }
+}
+
+sub cancel_test {
+ if ($email_when_canceled) {
+ send_email("KTEST: Your [$test_type] test was cancelled",
+ "Your test started at $script_start_time was cancelled: sig int");
+ }
+ die "\nCaught Sig Int, test interrupted: $!\n"
+}
+
+$SIG{INT} = qw(cancel_test);
+
# First we need to do is the builds
for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
@@ -4245,11 +4224,11 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
$outputdir = set_test_option("OUTPUT_DIR", $i);
$builddir = set_test_option("BUILD_DIR", $i);
- chdir $builddir || die "can't change directory to $builddir";
+ chdir $builddir || dodie "can't change directory to $builddir";
if (!-d $outputdir) {
mkpath($outputdir) or
- die "can't create $outputdir";
+ dodie "can't create $outputdir";
}
$make = "$makecmd O=$outputdir";
@@ -4262,9 +4241,15 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
$start_minconfig_defined = 1;
# The first test may override the PRE_KTEST option
- if (defined($pre_ktest) && $i == 1) {
- doprint "\n";
- run_command $pre_ktest;
+ if ($i == 1) {
+ if (defined($pre_ktest)) {
+ doprint "\n";
+ run_command $pre_ktest;
+ }
+ if ($email_when_started) {
+ send_email("KTEST: Your [$test_type] test was started",
+ "Your test was started on $script_start_time");
+ }
}
# Any test can override the POST_KTEST option
@@ -4280,7 +4265,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
if (!-d $tmpdir) {
mkpath($tmpdir) or
- die "can't create $tmpdir";
+ dodie "can't create $tmpdir";
}
$ENV{"SSH_USER"} = $ssh_user;
@@ -4353,7 +4338,7 @@ for (my $i = 1; $i <= $opt{"NUM_TESTS"}; $i++) {
if (defined($checkout)) {
run_command "git checkout $checkout" or
- die "failed to checkout $checkout";
+ dodie "failed to checkout $checkout";
}
$no_reboot = 0;
@@ -4428,4 +4413,8 @@ if ($opt{"POWEROFF_ON_SUCCESS"}) {
doprint "\n $successes of $opt{NUM_TESTS} tests were successful\n\n";
+if ($email_when_finished) {
+ send_email("KTEST: Your [$test_type] test has finished!",
+ "$successes of $opt{NUM_TESTS} tests started at $script_start_time were successful!");
+}
exit 0;
diff --git a/tools/testing/ktest/sample.conf b/tools/testing/ktest/sample.conf
index 6c58cd8bbbae..6ca6ca0ce695 100644
--- a/tools/testing/ktest/sample.conf
+++ b/tools/testing/ktest/sample.conf
@@ -1,6 +1,11 @@
#
# Config file for ktest.pl
#
+# Place your customized version of this, in the working directory that
+# ktest.pl is run from. By default, ktest.pl will look for a file
+# called "ktest.conf", but you can name it anything you like and specify
+# the name of your config file as the first argument of ktest.pl.
+#
# Note, all paths must be absolute
#
@@ -396,6 +401,44 @@
#### Optional Config Options (all have defaults) ####
+# Email options for receiving notifications. Users must setup
+# the specified mailer prior to using this feature.
+#
+# (default undefined)
+#MAILTO =
+#
+# Supported mailers: sendmail, mail, mailx
+# (default sendmail)
+#MAILER = sendmail
+#
+# The executable to run
+# (default: for sendmail "/usr/sbin/sendmail", otherwise equals ${MAILER})
+#MAIL_EXEC = /usr/sbin/sendmail
+#
+# The command used to send mail, which uses the above options
+# can be modified. By default if the mailer is "sendmail" then
+# MAIL_COMMAND = echo \'Subject: $SUBJECT\n\n$MESSAGE\' | $MAIL_PATH/$MAILER -t $MAILTO
+# For mail or mailx:
+# MAIL_COMMAND = "$MAIL_PATH/$MAILER -s \'$SUBJECT\' $MAILTO <<< \'$MESSAGE\'
+# ktest.pl will do the substitution for MAIL_PATH, MAILER, MAILTO at the time
+# it sends the mail if "$FOO" format is used. If "${FOO}" format is used,
+# then the substitutions will occur at the time the config file is read.
+# But note, MAIL_PATH and MAILER require being set by the config file if
+# ${MAIL_PATH} or ${MAILER} are used, but not if $MAIL_PATH or $MAILER are.
+#MAIL_COMMAND = echo \'Subject: $SUBJECT\n\n$MESSAGE\' | $MAIL_PATH/$MAILER -t $MAILTO
+#
+# Errors are defined as those would terminate the script
+# (default 1)
+#EMAIL_ON_ERROR = 1
+# (default 1)
+#EMAIL_WHEN_FINISHED = 1
+# (default 0)
+#EMAIL_WHEN_STARTED = 1
+#
+# Users can cancel the test by Ctrl^C
+# (default 0)
+#EMAIL_WHEN_CANCELED = 1
+
# Start a test setup. If you leave this off, all options
# will be default and the test will run once.
# This is a label and not really an option (it takes no value).
@@ -725,6 +768,13 @@
# (default 120)
#TIMEOUT = 120
+# The timeout in seconds when to test if the box can be rebooted
+# or not. Before issuing the reboot command, a ssh connection
+# is attempted to see if the target machine is still active.
+# If the target does not connect within this timeout, a power cycle
+# is issued instead of a reboot.
+# CONNECT_TIMEOUT = 25
+
# In between tests, a reboot of the box may occur, and this
# is the time to wait for the console after it stops producing
# output. Some machines may not produce a large lag on reboot
@@ -1167,6 +1217,16 @@
# Set it to "good" to test only the good config and set it
# to "bad" to only test the bad config.
#
+# CONFIG_BISECT_EXEC (optional)
+# The config bisect is a separate program that comes with ktest.pl.
+# By befault, it will look for:
+# `pwd`/config-bisect.pl # the location ktest.pl was executed from.
+# If it does not find it there, it will look for:
+# `dirname <ktest.pl>`/config-bisect.pl # The directory that holds ktest.pl
+# If it does not find it there, it will look for:
+# ${BUILD_DIR}/tools/testing/ktest/config-bisect.pl
+# Setting CONFIG_BISECT_EXEC will override where it looks.
+#
# Example:
# TEST_START
# TEST_TYPE = config_bisect
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 620fa78b3b1b..4ea385be528f 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -104,7 +104,8 @@ enum {
NUM_HINTS = 8,
NUM_BDW = NUM_DCR,
NUM_SPA = NUM_PM + NUM_DCR + NUM_BDW,
- NUM_MEM = NUM_DCR + NUM_BDW + 2 /* spa0 iset */ + 4 /* spa1 iset */,
+ NUM_MEM = NUM_DCR + NUM_BDW + 2 /* spa0 iset */
+ + 4 /* spa1 iset */ + 1 /* spa11 iset */,
DIMM_SIZE = SZ_32M,
LABEL_SIZE = SZ_128K,
SPA_VCD_SIZE = SZ_4M,
@@ -137,6 +138,7 @@ static u32 handle[] = {
};
static unsigned long dimm_fail_cmd_flags[NUM_DCR];
+static int dimm_fail_cmd_code[NUM_DCR];
struct nfit_test_fw {
enum intel_fw_update_state state;
@@ -153,6 +155,7 @@ struct nfit_test {
void *nfit_buf;
dma_addr_t nfit_dma;
size_t nfit_size;
+ size_t nfit_filled;
int dcr_idx;
int num_dcr;
int num_pm;
@@ -709,7 +712,9 @@ static void smart_notify(struct device *bus_dev,
>= thresh->media_temperature)
|| ((thresh->alarm_control & ND_INTEL_SMART_CTEMP_TRIP)
&& smart->ctrl_temperature
- >= thresh->ctrl_temperature)) {
+ >= thresh->ctrl_temperature)
+ || (smart->health != ND_INTEL_SMART_NON_CRITICAL_HEALTH)
+ || (smart->shutdown_state != 0)) {
device_lock(bus_dev);
__acpi_nvdimm_notify(dimm_dev, 0x81);
device_unlock(bus_dev);
@@ -735,6 +740,32 @@ static int nfit_test_cmd_smart_set_threshold(
return 0;
}
+static int nfit_test_cmd_smart_inject(
+ struct nd_intel_smart_inject *inj,
+ unsigned int buf_len,
+ struct nd_intel_smart_threshold *thresh,
+ struct nd_intel_smart *smart,
+ struct device *bus_dev, struct device *dimm_dev)
+{
+ if (buf_len != sizeof(*inj))
+ return -EINVAL;
+
+ if (inj->mtemp_enable)
+ smart->media_temperature = inj->media_temperature;
+ if (inj->spare_enable)
+ smart->spares = inj->spares;
+ if (inj->fatal_enable)
+ smart->health = ND_INTEL_SMART_FATAL_HEALTH;
+ if (inj->unsafe_shutdown_enable) {
+ smart->shutdown_state = 1;
+ smart->shutdown_count++;
+ }
+ inj->status = 0;
+ smart_notify(bus_dev, dimm_dev, smart, thresh);
+
+ return 0;
+}
+
static void uc_error_notify(struct work_struct *work)
{
struct nfit_test *t = container_of(work, typeof(*t), work);
@@ -862,8 +893,11 @@ static int get_dimm(struct nfit_mem *nfit_mem, unsigned int func)
if (i >= ARRAY_SIZE(handle))
return -ENXIO;
- if ((1 << func) & dimm_fail_cmd_flags[i])
+ if ((1 << func) & dimm_fail_cmd_flags[i]) {
+ if (dimm_fail_cmd_code[i])
+ return dimm_fail_cmd_code[i];
return -EIO;
+ }
return i;
}
@@ -935,6 +969,13 @@ static int nfit_test_ctl(struct nvdimm_bus_descriptor *nd_desc,
t->dcr_idx],
&t->smart[i - t->dcr_idx],
&t->pdev.dev, t->dimm_dev[i]);
+ case ND_INTEL_SMART_INJECT:
+ return nfit_test_cmd_smart_inject(buf,
+ buf_len,
+ &t->smart_threshold[i -
+ t->dcr_idx],
+ &t->smart[i - t->dcr_idx],
+ &t->pdev.dev, t->dimm_dev[i]);
default:
return -ENOTTY;
}
@@ -1125,12 +1166,12 @@ static int ars_state_init(struct device *dev, struct ars_state *ars_state)
static void put_dimms(void *data)
{
- struct device **dimm_dev = data;
+ struct nfit_test *t = data;
int i;
- for (i = 0; i < NUM_DCR; i++)
- if (dimm_dev[i])
- device_unregister(dimm_dev[i]);
+ for (i = 0; i < t->num_dcr; i++)
+ if (t->dimm_dev[i])
+ device_unregister(t->dimm_dev[i]);
}
static struct class *nfit_test_dimm;
@@ -1139,13 +1180,11 @@ static int dimm_name_to_id(struct device *dev)
{
int dimm;
- if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1
- || dimm >= NUM_DCR || dimm < 0)
+ if (sscanf(dev_name(dev), "test_dimm%d", &dimm) != 1)
return -ENXIO;
return dimm;
}
-
static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -1154,7 +1193,7 @@ static ssize_t handle_show(struct device *dev, struct device_attribute *attr,
if (dimm < 0)
return dimm;
- return sprintf(buf, "%#x", handle[dimm]);
+ return sprintf(buf, "%#x\n", handle[dimm]);
}
DEVICE_ATTR_RO(handle);
@@ -1188,8 +1227,39 @@ static ssize_t fail_cmd_store(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR_RW(fail_cmd);
+static ssize_t fail_cmd_code_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ int dimm = dimm_name_to_id(dev);
+
+ if (dimm < 0)
+ return dimm;
+
+ return sprintf(buf, "%d\n", dimm_fail_cmd_code[dimm]);
+}
+
+static ssize_t fail_cmd_code_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t size)
+{
+ int dimm = dimm_name_to_id(dev);
+ unsigned long val;
+ ssize_t rc;
+
+ if (dimm < 0)
+ return dimm;
+
+ rc = kstrtol(buf, 0, &val);
+ if (rc)
+ return rc;
+
+ dimm_fail_cmd_code[dimm] = val;
+ return size;
+}
+static DEVICE_ATTR_RW(fail_cmd_code);
+
static struct attribute *nfit_test_dimm_attributes[] = {
&dev_attr_fail_cmd.attr,
+ &dev_attr_fail_cmd_code.attr,
&dev_attr_handle.attr,
NULL,
};
@@ -1203,6 +1273,23 @@ static const struct attribute_group *nfit_test_dimm_attribute_groups[] = {
NULL,
};
+static int nfit_test_dimm_init(struct nfit_test *t)
+{
+ int i;
+
+ if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t))
+ return -ENOMEM;
+ for (i = 0; i < t->num_dcr; i++) {
+ t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
+ &t->pdev.dev, 0, NULL,
+ nfit_test_dimm_attribute_groups,
+ "test_dimm%d", i + t->dcr_idx);
+ if (!t->dimm_dev[i])
+ return -ENOMEM;
+ }
+ return 0;
+}
+
static void smart_init(struct nfit_test *t)
{
int i;
@@ -1222,7 +1309,7 @@ static void smart_init(struct nfit_test *t)
| ND_INTEL_SMART_MTEMP_VALID,
.health = ND_INTEL_SMART_NON_CRITICAL_HEALTH,
.media_temperature = 23 * 16,
- .ctrl_temperature = 30 * 16,
+ .ctrl_temperature = 25 * 16,
.pmic_temperature = 40 * 16,
.spares = 75,
.alarm_flags = ND_INTEL_SMART_SPARE_TRIP
@@ -1298,17 +1385,8 @@ static int nfit_test0_alloc(struct nfit_test *t)
if (!t->_fit)
return -ENOMEM;
- if (devm_add_action_or_reset(&t->pdev.dev, put_dimms, t->dimm_dev))
+ if (nfit_test_dimm_init(t))
return -ENOMEM;
- for (i = 0; i < NUM_DCR; i++) {
- t->dimm_dev[i] = device_create_with_groups(nfit_test_dimm,
- &t->pdev.dev, 0, NULL,
- nfit_test_dimm_attribute_groups,
- "test_dimm%d", i);
- if (!t->dimm_dev[i])
- return -ENOMEM;
- }
-
smart_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
@@ -1340,6 +1418,8 @@ static int nfit_test1_alloc(struct nfit_test *t)
if (!t->spa_set[1])
return -ENOMEM;
+ if (nfit_test_dimm_init(t))
+ return -ENOMEM;
smart_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
@@ -1366,7 +1446,7 @@ static void nfit_test0_setup(struct nfit_test *t)
struct acpi_nfit_data_region *bdw;
struct acpi_nfit_flush_address *flush;
struct acpi_nfit_capabilities *pcap;
- unsigned int offset, i;
+ unsigned int offset = 0, i;
/*
* spa0 (interleave first half of dimm0 and dimm1, note storage
@@ -1380,93 +1460,102 @@ static void nfit_test0_setup(struct nfit_test *t)
spa->range_index = 0+1;
spa->address = t->spa_set_dma[0];
spa->length = SPA0_SIZE;
+ offset += spa->header.length;
/*
* spa1 (interleave last half of the 4 DIMMS, note storage
* does not actually alias the related block-data-window
* regions)
*/
- spa = nfit_buf + sizeof(*spa);
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
spa->range_index = 1+1;
spa->address = t->spa_set_dma[1];
spa->length = SPA1_SIZE;
+ offset += spa->header.length;
/* spa2 (dcr0) dimm0 */
- spa = nfit_buf + sizeof(*spa) * 2;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
spa->range_index = 2+1;
spa->address = t->dcr_dma[0];
spa->length = DCR_SIZE;
+ offset += spa->header.length;
/* spa3 (dcr1) dimm1 */
- spa = nfit_buf + sizeof(*spa) * 3;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
spa->range_index = 3+1;
spa->address = t->dcr_dma[1];
spa->length = DCR_SIZE;
+ offset += spa->header.length;
/* spa4 (dcr2) dimm2 */
- spa = nfit_buf + sizeof(*spa) * 4;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
spa->range_index = 4+1;
spa->address = t->dcr_dma[2];
spa->length = DCR_SIZE;
+ offset += spa->header.length;
/* spa5 (dcr3) dimm3 */
- spa = nfit_buf + sizeof(*spa) * 5;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_DCR), 16);
spa->range_index = 5+1;
spa->address = t->dcr_dma[3];
spa->length = DCR_SIZE;
+ offset += spa->header.length;
/* spa6 (bdw for dcr0) dimm0 */
- spa = nfit_buf + sizeof(*spa) * 6;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
spa->range_index = 6+1;
spa->address = t->dimm_dma[0];
spa->length = DIMM_SIZE;
+ offset += spa->header.length;
/* spa7 (bdw for dcr1) dimm1 */
- spa = nfit_buf + sizeof(*spa) * 7;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
spa->range_index = 7+1;
spa->address = t->dimm_dma[1];
spa->length = DIMM_SIZE;
+ offset += spa->header.length;
/* spa8 (bdw for dcr2) dimm2 */
- spa = nfit_buf + sizeof(*spa) * 8;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
spa->range_index = 8+1;
spa->address = t->dimm_dma[2];
spa->length = DIMM_SIZE;
+ offset += spa->header.length;
/* spa9 (bdw for dcr3) dimm3 */
- spa = nfit_buf + sizeof(*spa) * 9;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
spa->range_index = 9+1;
spa->address = t->dimm_dma[3];
spa->length = DIMM_SIZE;
+ offset += spa->header.length;
- offset = sizeof(*spa) * 10;
/* mem-region0 (spa0, dimm0) */
memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -1481,9 +1570,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 2;
+ offset += memdev->header.length;
/* mem-region1 (spa0, dimm1) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map);
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[1];
@@ -1497,9 +1587,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->interleave_index = 0;
memdev->interleave_ways = 2;
memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED;
+ offset += memdev->header.length;
/* mem-region2 (spa1, dimm0) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 2;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[0];
@@ -1513,9 +1604,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->interleave_index = 0;
memdev->interleave_ways = 4;
memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED;
+ offset += memdev->header.length;
/* mem-region3 (spa1, dimm1) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 3;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[1];
@@ -1528,9 +1620,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = SPA0_SIZE/2;
memdev->interleave_index = 0;
memdev->interleave_ways = 4;
+ offset += memdev->header.length;
/* mem-region4 (spa1, dimm2) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 4;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[2];
@@ -1544,9 +1637,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->interleave_index = 0;
memdev->interleave_ways = 4;
memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED;
+ offset += memdev->header.length;
/* mem-region5 (spa1, dimm3) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 5;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[3];
@@ -1559,9 +1653,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = SPA0_SIZE/2;
memdev->interleave_index = 0;
memdev->interleave_ways = 4;
+ offset += memdev->header.length;
/* mem-region6 (spa/dcr0, dimm0) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 6;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[0];
@@ -1574,9 +1669,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region7 (spa/dcr1, dimm1) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 7;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[1];
@@ -1589,9 +1685,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region8 (spa/dcr2, dimm2) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 8;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[2];
@@ -1604,9 +1701,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region9 (spa/dcr3, dimm3) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 9;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[3];
@@ -1619,9 +1717,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region10 (spa/bdw0, dimm0) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 10;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[0];
@@ -1634,9 +1733,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region11 (spa/bdw1, dimm1) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 11;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[1];
@@ -1649,9 +1749,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region12 (spa/bdw2, dimm2) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 12;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[2];
@@ -1664,9 +1765,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
/* mem-region13 (spa/dcr3, dimm3) */
- memdev = nfit_buf + offset + sizeof(struct acpi_nfit_memory_map) * 13;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[3];
@@ -1680,12 +1782,12 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED;
+ offset += memdev->header.length;
- offset = offset + sizeof(struct acpi_nfit_memory_map) * 14;
/* dcr-descriptor0: blk */
dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
- dcr->header.length = sizeof(struct acpi_nfit_control_region);
+ dcr->header.length = sizeof(*dcr);
dcr->region_index = 0+1;
dcr_common_init(dcr);
dcr->serial_number = ~handle[0];
@@ -1696,11 +1798,12 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->command_size = 8;
dcr->status_offset = 8;
dcr->status_size = 4;
+ offset += dcr->header.length;
/* dcr-descriptor1: blk */
- dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region);
+ dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
- dcr->header.length = sizeof(struct acpi_nfit_control_region);
+ dcr->header.length = sizeof(*dcr);
dcr->region_index = 1+1;
dcr_common_init(dcr);
dcr->serial_number = ~handle[1];
@@ -1711,11 +1814,12 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->command_size = 8;
dcr->status_offset = 8;
dcr->status_size = 4;
+ offset += dcr->header.length;
/* dcr-descriptor2: blk */
- dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region) * 2;
+ dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
- dcr->header.length = sizeof(struct acpi_nfit_control_region);
+ dcr->header.length = sizeof(*dcr);
dcr->region_index = 2+1;
dcr_common_init(dcr);
dcr->serial_number = ~handle[2];
@@ -1726,11 +1830,12 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->command_size = 8;
dcr->status_offset = 8;
dcr->status_size = 4;
+ offset += dcr->header.length;
/* dcr-descriptor3: blk */
- dcr = nfit_buf + offset + sizeof(struct acpi_nfit_control_region) * 3;
+ dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
- dcr->header.length = sizeof(struct acpi_nfit_control_region);
+ dcr->header.length = sizeof(*dcr);
dcr->region_index = 3+1;
dcr_common_init(dcr);
dcr->serial_number = ~handle[3];
@@ -1741,8 +1846,8 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->command_size = 8;
dcr->status_offset = 8;
dcr->status_size = 4;
+ offset += dcr->header.length;
- offset = offset + sizeof(struct acpi_nfit_control_region) * 4;
/* dcr-descriptor0: pmem */
dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
@@ -1753,10 +1858,10 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->serial_number = ~handle[0];
dcr->code = NFIT_FIC_BYTEN;
dcr->windows = 0;
+ offset += dcr->header.length;
/* dcr-descriptor1: pmem */
- dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
- window_size);
+ dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
dcr->header.length = offsetof(struct acpi_nfit_control_region,
window_size);
@@ -1765,10 +1870,10 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->serial_number = ~handle[1];
dcr->code = NFIT_FIC_BYTEN;
dcr->windows = 0;
+ offset += dcr->header.length;
/* dcr-descriptor2: pmem */
- dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
- window_size) * 2;
+ dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
dcr->header.length = offsetof(struct acpi_nfit_control_region,
window_size);
@@ -1777,10 +1882,10 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->serial_number = ~handle[2];
dcr->code = NFIT_FIC_BYTEN;
dcr->windows = 0;
+ offset += dcr->header.length;
/* dcr-descriptor3: pmem */
- dcr = nfit_buf + offset + offsetof(struct acpi_nfit_control_region,
- window_size) * 3;
+ dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
dcr->header.length = offsetof(struct acpi_nfit_control_region,
window_size);
@@ -1789,54 +1894,56 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->serial_number = ~handle[3];
dcr->code = NFIT_FIC_BYTEN;
dcr->windows = 0;
+ offset += dcr->header.length;
- offset = offset + offsetof(struct acpi_nfit_control_region,
- window_size) * 4;
/* bdw0 (spa/dcr0, dimm0) */
bdw = nfit_buf + offset;
bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
- bdw->header.length = sizeof(struct acpi_nfit_data_region);
+ bdw->header.length = sizeof(*bdw);
bdw->region_index = 0+1;
bdw->windows = 1;
bdw->offset = 0;
bdw->size = BDW_SIZE;
bdw->capacity = DIMM_SIZE;
bdw->start_address = 0;
+ offset += bdw->header.length;
/* bdw1 (spa/dcr1, dimm1) */
- bdw = nfit_buf + offset + sizeof(struct acpi_nfit_data_region);
+ bdw = nfit_buf + offset;
bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
- bdw->header.length = sizeof(struct acpi_nfit_data_region);
+ bdw->header.length = sizeof(*bdw);
bdw->region_index = 1+1;
bdw->windows = 1;
bdw->offset = 0;
bdw->size = BDW_SIZE;
bdw->capacity = DIMM_SIZE;
bdw->start_address = 0;
+ offset += bdw->header.length;
/* bdw2 (spa/dcr2, dimm2) */
- bdw = nfit_buf + offset + sizeof(struct acpi_nfit_data_region) * 2;
+ bdw = nfit_buf + offset;
bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
- bdw->header.length = sizeof(struct acpi_nfit_data_region);
+ bdw->header.length = sizeof(*bdw);
bdw->region_index = 2+1;
bdw->windows = 1;
bdw->offset = 0;
bdw->size = BDW_SIZE;
bdw->capacity = DIMM_SIZE;
bdw->start_address = 0;
+ offset += bdw->header.length;
/* bdw3 (spa/dcr3, dimm3) */
- bdw = nfit_buf + offset + sizeof(struct acpi_nfit_data_region) * 3;
+ bdw = nfit_buf + offset;
bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
- bdw->header.length = sizeof(struct acpi_nfit_data_region);
+ bdw->header.length = sizeof(*bdw);
bdw->region_index = 3+1;
bdw->windows = 1;
bdw->offset = 0;
bdw->size = BDW_SIZE;
bdw->capacity = DIMM_SIZE;
bdw->start_address = 0;
+ offset += bdw->header.length;
- offset = offset + sizeof(struct acpi_nfit_data_region) * 4;
/* flush0 (dimm0) */
flush = nfit_buf + offset;
flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
@@ -1845,48 +1952,52 @@ static void nfit_test0_setup(struct nfit_test *t)
flush->hint_count = NUM_HINTS;
for (i = 0; i < NUM_HINTS; i++)
flush->hint_address[i] = t->flush_dma[0] + i * sizeof(u64);
+ offset += flush->header.length;
/* flush1 (dimm1) */
- flush = nfit_buf + offset + flush_hint_size * 1;
+ flush = nfit_buf + offset;
flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
flush->header.length = flush_hint_size;
flush->device_handle = handle[1];
flush->hint_count = NUM_HINTS;
for (i = 0; i < NUM_HINTS; i++)
flush->hint_address[i] = t->flush_dma[1] + i * sizeof(u64);
+ offset += flush->header.length;
/* flush2 (dimm2) */
- flush = nfit_buf + offset + flush_hint_size * 2;
+ flush = nfit_buf + offset;
flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
flush->header.length = flush_hint_size;
flush->device_handle = handle[2];
flush->hint_count = NUM_HINTS;
for (i = 0; i < NUM_HINTS; i++)
flush->hint_address[i] = t->flush_dma[2] + i * sizeof(u64);
+ offset += flush->header.length;
/* flush3 (dimm3) */
- flush = nfit_buf + offset + flush_hint_size * 3;
+ flush = nfit_buf + offset;
flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
flush->header.length = flush_hint_size;
flush->device_handle = handle[3];
flush->hint_count = NUM_HINTS;
for (i = 0; i < NUM_HINTS; i++)
flush->hint_address[i] = t->flush_dma[3] + i * sizeof(u64);
+ offset += flush->header.length;
/* platform capabilities */
- pcap = nfit_buf + offset + flush_hint_size * 4;
+ pcap = nfit_buf + offset;
pcap->header.type = ACPI_NFIT_TYPE_CAPABILITIES;
pcap->header.length = sizeof(*pcap);
pcap->highest_capability = 1;
pcap->capabilities = ACPI_NFIT_CAPABILITY_CACHE_FLUSH |
ACPI_NFIT_CAPABILITY_MEM_FLUSH;
+ offset += pcap->header.length;
if (t->setup_hotplug) {
- offset = offset + flush_hint_size * 4 + sizeof(*pcap);
/* dcr-descriptor4: blk */
dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
- dcr->header.length = sizeof(struct acpi_nfit_control_region);
+ dcr->header.length = sizeof(*dcr);
dcr->region_index = 8+1;
dcr_common_init(dcr);
dcr->serial_number = ~handle[4];
@@ -1897,8 +2008,8 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->command_size = 8;
dcr->status_offset = 8;
dcr->status_size = 4;
+ offset += dcr->header.length;
- offset = offset + sizeof(struct acpi_nfit_control_region);
/* dcr-descriptor4: pmem */
dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
@@ -1909,21 +2020,20 @@ static void nfit_test0_setup(struct nfit_test *t)
dcr->serial_number = ~handle[4];
dcr->code = NFIT_FIC_BYTEN;
dcr->windows = 0;
+ offset += dcr->header.length;
- offset = offset + offsetof(struct acpi_nfit_control_region,
- window_size);
/* bdw4 (spa/dcr4, dimm4) */
bdw = nfit_buf + offset;
bdw->header.type = ACPI_NFIT_TYPE_DATA_REGION;
- bdw->header.length = sizeof(struct acpi_nfit_data_region);
+ bdw->header.length = sizeof(*bdw);
bdw->region_index = 8+1;
bdw->windows = 1;
bdw->offset = 0;
bdw->size = BDW_SIZE;
bdw->capacity = DIMM_SIZE;
bdw->start_address = 0;
+ offset += bdw->header.length;
- offset = offset + sizeof(struct acpi_nfit_data_region);
/* spa10 (dcr4) dimm4 */
spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
@@ -1932,30 +2042,32 @@ static void nfit_test0_setup(struct nfit_test *t)
spa->range_index = 10+1;
spa->address = t->dcr_dma[4];
spa->length = DCR_SIZE;
+ offset += spa->header.length;
/*
* spa11 (single-dimm interleave for hotplug, note storage
* does not actually alias the related block-data-window
* regions)
*/
- spa = nfit_buf + offset + sizeof(*spa);
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_PM), 16);
spa->range_index = 11+1;
spa->address = t->spa_set_dma[2];
spa->length = SPA0_SIZE;
+ offset += spa->header.length;
/* spa12 (bdw for dcr4) dimm4 */
- spa = nfit_buf + offset + sizeof(*spa) * 2;
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_BDW), 16);
spa->range_index = 12+1;
spa->address = t->dimm_dma[4];
spa->length = DIMM_SIZE;
+ offset += spa->header.length;
- offset = offset + sizeof(*spa) * 3;
/* mem-region14 (spa/dcr4, dimm4) */
memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -1970,10 +2082,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
- /* mem-region15 (spa0, dimm4) */
- memdev = nfit_buf + offset +
- sizeof(struct acpi_nfit_memory_map);
+ /* mem-region15 (spa11, dimm4) */
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[4];
@@ -1987,10 +2099,10 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
memdev->flags = ACPI_NFIT_MEM_HEALTH_ENABLED;
+ offset += memdev->header.length;
/* mem-region16 (spa/bdw4, dimm4) */
- memdev = nfit_buf + offset +
- sizeof(struct acpi_nfit_memory_map) * 2;
+ memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
memdev->device_handle = handle[4];
@@ -2003,8 +2115,8 @@ static void nfit_test0_setup(struct nfit_test *t)
memdev->address = 0;
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
+ offset += memdev->header.length;
- offset = offset + sizeof(struct acpi_nfit_memory_map) * 3;
/* flush3 (dimm4) */
flush = nfit_buf + offset;
flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
@@ -2014,8 +2126,14 @@ static void nfit_test0_setup(struct nfit_test *t)
for (i = 0; i < NUM_HINTS; i++)
flush->hint_address[i] = t->flush_dma[4]
+ i * sizeof(u64);
+ offset += flush->header.length;
+
+ /* sanity check to make sure we've filled the buffer */
+ WARN_ON(offset != t->nfit_size);
}
+ t->nfit_filled = offset;
+
post_ars_status(&t->ars_state, &t->badrange, t->spa_set_dma[0],
SPA0_SIZE);
@@ -2026,6 +2144,7 @@ static void nfit_test0_setup(struct nfit_test *t)
set_bit(ND_INTEL_SMART, &acpi_desc->dimm_cmd_force_en);
set_bit(ND_INTEL_SMART_THRESHOLD, &acpi_desc->dimm_cmd_force_en);
set_bit(ND_INTEL_SMART_SET_THRESHOLD, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_INTEL_SMART_INJECT, &acpi_desc->dimm_cmd_force_en);
set_bit(ND_CMD_ARS_CAP, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_ARS_START, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
@@ -2061,17 +2180,18 @@ static void nfit_test1_setup(struct nfit_test *t)
spa->range_index = 0+1;
spa->address = t->spa_set_dma[0];
spa->length = SPA2_SIZE;
+ offset += spa->header.length;
/* virtual cd region */
- spa = nfit_buf + sizeof(*spa);
+ spa = nfit_buf + offset;
spa->header.type = ACPI_NFIT_TYPE_SYSTEM_ADDRESS;
spa->header.length = sizeof(*spa);
memcpy(spa->range_guid, to_nfit_uuid(NFIT_SPA_VCD), 16);
spa->range_index = 0;
spa->address = t->spa_set_dma[1];
spa->length = SPA_VCD_SIZE;
+ offset += spa->header.length;
- offset += sizeof(*spa) * 2;
/* mem-region0 (spa0, dimm0) */
memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
@@ -2089,8 +2209,8 @@ static void nfit_test1_setup(struct nfit_test *t)
memdev->flags = ACPI_NFIT_MEM_SAVE_FAILED | ACPI_NFIT_MEM_RESTORE_FAILED
| ACPI_NFIT_MEM_FLUSH_FAILED | ACPI_NFIT_MEM_HEALTH_OBSERVED
| ACPI_NFIT_MEM_NOT_ARMED;
+ offset += memdev->header.length;
- offset += sizeof(*memdev);
/* dcr-descriptor0 */
dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
@@ -2101,8 +2221,8 @@ static void nfit_test1_setup(struct nfit_test *t)
dcr->serial_number = ~handle[5];
dcr->code = NFIT_FIC_BYTE;
dcr->windows = 0;
-
offset += dcr->header.length;
+
memdev = nfit_buf + offset;
memdev->header.type = ACPI_NFIT_TYPE_MEMORY_MAP;
memdev->header.length = sizeof(*memdev);
@@ -2117,9 +2237,9 @@ static void nfit_test1_setup(struct nfit_test *t)
memdev->interleave_index = 0;
memdev->interleave_ways = 1;
memdev->flags = ACPI_NFIT_MEM_MAP_FAILED;
+ offset += memdev->header.length;
/* dcr-descriptor1 */
- offset += sizeof(*memdev);
dcr = nfit_buf + offset;
dcr->header.type = ACPI_NFIT_TYPE_CONTROL_REGION;
dcr->header.length = offsetof(struct acpi_nfit_control_region,
@@ -2129,6 +2249,12 @@ static void nfit_test1_setup(struct nfit_test *t)
dcr->serial_number = ~handle[6];
dcr->code = NFIT_FIC_BYTE;
dcr->windows = 0;
+ offset += dcr->header.length;
+
+ /* sanity check to make sure we've filled the buffer */
+ WARN_ON(offset != t->nfit_size);
+
+ t->nfit_filled = offset;
post_ars_status(&t->ars_state, &t->badrange, t->spa_set_dma[0],
SPA2_SIZE);
@@ -2139,6 +2265,9 @@ static void nfit_test1_setup(struct nfit_test *t)
set_bit(ND_CMD_ARS_STATUS, &acpi_desc->bus_cmd_force_en);
set_bit(ND_CMD_CLEAR_ERROR, &acpi_desc->bus_cmd_force_en);
set_bit(ND_INTEL_ENABLE_LSS_STATUS, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
+ set_bit(ND_CMD_SET_CONFIG_DATA, &acpi_desc->dimm_cmd_force_en);
}
static int nfit_test_blk_do_io(struct nd_blk_region *ndbr, resource_size_t dpa,
@@ -2487,7 +2616,7 @@ static int nfit_test_probe(struct platform_device *pdev)
nd_desc->ndctl = nfit_test_ctl;
rc = acpi_nfit_init(acpi_desc, nfit_test->nfit_buf,
- nfit_test->nfit_size);
+ nfit_test->nfit_filled);
if (rc)
return rc;
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index 428344519cdf..33752e06ff8d 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -93,6 +93,7 @@ struct nd_cmd_ars_err_inj_stat {
#define ND_INTEL_FW_FINISH_UPDATE 15
#define ND_INTEL_FW_FINISH_QUERY 16
#define ND_INTEL_SMART_SET_THRESHOLD 17
+#define ND_INTEL_SMART_INJECT 18
#define ND_INTEL_SMART_HEALTH_VALID (1 << 0)
#define ND_INTEL_SMART_SPARES_VALID (1 << 1)
@@ -111,6 +112,10 @@ struct nd_cmd_ars_err_inj_stat {
#define ND_INTEL_SMART_NON_CRITICAL_HEALTH (1 << 0)
#define ND_INTEL_SMART_CRITICAL_HEALTH (1 << 1)
#define ND_INTEL_SMART_FATAL_HEALTH (1 << 2)
+#define ND_INTEL_SMART_INJECT_MTEMP (1 << 0)
+#define ND_INTEL_SMART_INJECT_SPARE (1 << 1)
+#define ND_INTEL_SMART_INJECT_FATAL (1 << 2)
+#define ND_INTEL_SMART_INJECT_SHUTDOWN (1 << 3)
struct nd_intel_smart {
__u32 status;
@@ -158,6 +163,17 @@ struct nd_intel_smart_set_threshold {
__u32 status;
} __packed;
+struct nd_intel_smart_inject {
+ __u64 flags;
+ __u8 mtemp_enable;
+ __u16 media_temperature;
+ __u8 spare_enable;
+ __u8 spares;
+ __u8 fatal_enable;
+ __u8 unsafe_shutdown_enable;
+ __u32 status;
+} __packed;
+
#define INTEL_FW_STORAGE_SIZE 0x100000
#define INTEL_FW_MAX_SEND_LEN 0xFFEC
#define INTEL_FW_QUERY_INTERVAL 250000
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index fa7ee369b3c9..db66f8a0d4be 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -17,7 +17,7 @@ ifeq ($(BUILD), 32)
LDFLAGS += -m32
endif
-targets: mapshift $(TARGETS)
+targets: generated/map-shift.h $(TARGETS)
main: $(OFILES)
@@ -42,9 +42,7 @@ radix-tree.c: ../../../lib/radix-tree.c
idr.c: ../../../lib/idr.c
sed -e 's/^static //' -e 's/__always_inline //' -e 's/inline //' < $< > $@
-.PHONY: mapshift
-
-mapshift:
+generated/map-shift.h:
@if ! grep -qws $(SHIFT) generated/map-shift.h; then \
echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" > \
generated/map-shift.h; \
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 6c645eb77d42..ee820fcc29b0 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -252,6 +252,13 @@ void idr_checks(void)
idr_remove(&idr, 3);
idr_remove(&idr, 0);
+ assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == 0);
+ idr_remove(&idr, 1);
+ for (i = 1; i < RADIX_TREE_MAP_SIZE; i++)
+ assert(idr_alloc(&idr, DUMMY_PTR, 0, 0, GFP_KERNEL) == i);
+ idr_remove(&idr, 1 << 30);
+ idr_destroy(&idr);
+
for (i = INT_MAX - 3UL; i < INT_MAX + 1UL; i++) {
struct item *item = item_create(i, 0);
assert(idr_alloc(&idr, item, i, i + 10, GFP_KERNEL) == i);
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
index e3201ccf54c3..32159c08a52e 100644
--- a/tools/testing/radix-tree/linux/gfp.h
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -19,6 +19,7 @@
#define __GFP_RECLAIM (__GFP_DIRECT_RECLAIM|__GFP_KSWAPD_RECLAIM)
+#define GFP_ZONEMASK 0x0fu
#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM)
diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c
index 59245b3d587c..7bf405638b0b 100644
--- a/tools/testing/radix-tree/multiorder.c
+++ b/tools/testing/radix-tree/multiorder.c
@@ -16,6 +16,7 @@
#include <linux/radix-tree.h>
#include <linux/slab.h>
#include <linux/errno.h>
+#include <pthread.h>
#include "test.h"
@@ -624,6 +625,67 @@ static void multiorder_account(void)
item_kill_tree(&tree);
}
+bool stop_iteration = false;
+
+static void *creator_func(void *ptr)
+{
+ /* 'order' is set up to ensure we have sibling entries */
+ unsigned int order = RADIX_TREE_MAP_SHIFT - 1;
+ struct radix_tree_root *tree = ptr;
+ int i;
+
+ for (i = 0; i < 10000; i++) {
+ item_insert_order(tree, 0, order);
+ item_delete_rcu(tree, 0);
+ }
+
+ stop_iteration = true;
+ return NULL;
+}
+
+static void *iterator_func(void *ptr)
+{
+ struct radix_tree_root *tree = ptr;
+ struct radix_tree_iter iter;
+ struct item *item;
+ void **slot;
+
+ while (!stop_iteration) {
+ rcu_read_lock();
+ radix_tree_for_each_slot(slot, tree, &iter, 0) {
+ item = radix_tree_deref_slot(slot);
+
+ if (!item)
+ continue;
+ if (radix_tree_deref_retry(item)) {
+ slot = radix_tree_iter_retry(&iter);
+ continue;
+ }
+
+ item_sanity(item, iter.index);
+ }
+ rcu_read_unlock();
+ }
+ return NULL;
+}
+
+static void multiorder_iteration_race(void)
+{
+ const int num_threads = sysconf(_SC_NPROCESSORS_ONLN);
+ pthread_t worker_thread[num_threads];
+ RADIX_TREE(tree, GFP_KERNEL);
+ int i;
+
+ pthread_create(&worker_thread[0], NULL, &creator_func, &tree);
+ for (i = 1; i < num_threads; i++)
+ pthread_create(&worker_thread[i], NULL, &iterator_func, &tree);
+
+ for (i = 0; i < num_threads; i++)
+ pthread_join(worker_thread[i], NULL);
+
+ item_kill_tree(&tree);
+}
+
void multiorder_checks(void)
{
int i;
@@ -644,6 +706,7 @@ void multiorder_checks(void)
multiorder_join();
multiorder_split();
multiorder_account();
+ multiorder_iteration_race();
radix_tree_cpu_dead(0);
}
diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c
index 5978ab1f403d..def6015570b2 100644
--- a/tools/testing/radix-tree/test.c
+++ b/tools/testing/radix-tree/test.c
@@ -75,6 +75,25 @@ int item_delete(struct radix_tree_root *root, unsigned long index)
return 0;
}
+static void item_free_rcu(struct rcu_head *head)
+{
+ struct item *item = container_of(head, struct item, rcu_head);
+
+ free(item);
+}
+
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index)
+{
+ struct item *item = radix_tree_delete(root, index);
+
+ if (item) {
+ item_sanity(item, index);
+ call_rcu(&item->rcu_head, item_free_rcu);
+ return 1;
+ }
+ return 0;
+}
+
void item_check_present(struct radix_tree_root *root, unsigned long index)
{
struct item *item;
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index d9c031dbeb1a..31f1d9b6f506 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -5,6 +5,7 @@
#include <linux/rcupdate.h>
struct item {
+ struct rcu_head rcu_head;
unsigned long index;
unsigned int order;
};
@@ -12,9 +13,11 @@ struct item {
struct item *item_create(unsigned long index, unsigned int order);
int __item_insert(struct radix_tree_root *root, struct item *item);
int item_insert(struct radix_tree_root *root, unsigned long index);
+void item_sanity(struct item *item, unsigned long index);
int item_insert_order(struct radix_tree_root *root, unsigned long index,
unsigned order);
int item_delete(struct radix_tree_root *root, unsigned long index);
+int item_delete_rcu(struct radix_tree_root *root, unsigned long index);
struct item *item_lookup(struct radix_tree_root *root, unsigned long index);
void item_check_present(struct radix_tree_root *root, unsigned long index);
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index bae6a4e9f2ee..305130de910c 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -3,6 +3,7 @@ TARGETS = android
TARGETS += bpf
TARGETS += breakpoints
TARGETS += capabilities
+TARGETS += cgroup
TARGETS += cpufreq
TARGETS += cpu-hotplug
TARGETS += efivarfs
@@ -15,6 +16,7 @@ TARGETS += gpio
TARGETS += intel_pstate
TARGETS += ipc
TARGETS += kcmp
+TARGETS += kvm
TARGETS += lib
TARGETS += membarrier
TARGETS += memfd
@@ -24,8 +26,10 @@ TARGETS += mqueue
TARGETS += net
TARGETS += nsfs
TARGETS += powerpc
+TARGETS += proc
TARGETS += pstore
TARGETS += ptrace
+TARGETS += rtc
TARGETS += seccomp
TARGETS += sigaltstack
TARGETS += size
@@ -132,7 +136,8 @@ ifdef INSTALL_PATH
echo "else" >> $(ALL_SCRIPT)
echo " OUTPUT=/dev/stdout" >> $(ALL_SCRIPT)
echo "fi" >> $(ALL_SCRIPT)
- echo "export KSFT_TAP_LEVEL=`echo 1`" >> $(ALL_SCRIPT)
+ echo "export KSFT_TAP_LEVEL=1" >> $(ALL_SCRIPT)
+ echo "export skip=4" >> $(ALL_SCRIPT)
for TARGET in $(TARGETS); do \
BUILD_TARGET=$$BUILD/$$TARGET; \
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index f6304d2be90c..72c25a3cb658 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -18,10 +18,6 @@ all:
fi \
done
-override define RUN_TESTS
- @cd $(OUTPUT); ./run.sh
-endef
-
override define INSTALL_RULE
mkdir -p $(INSTALL_PATH)
install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
@@ -33,10 +29,6 @@ override define INSTALL_RULE
done;
endef
-override define EMIT_TESTS
- echo "./run.sh"
-endef
-
override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
diff --git a/tools/testing/selftests/android/ion/ion_test.sh b/tools/testing/selftests/android/ion/ion_test.sh
index a1aff506f5e6..69e676cfc94e 100755
--- a/tools/testing/selftests/android/ion/ion_test.sh
+++ b/tools/testing/selftests/android/ion/ion_test.sh
@@ -4,6 +4,9 @@ heapsize=4096
TCID="ion_test.sh"
errcode=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
run_test()
{
heaptype=$1
@@ -25,7 +28,7 @@ check_root()
uid=$(id -u)
if [ $uid -ne 0 ]; then
echo $TCID: must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
}
@@ -35,7 +38,7 @@ check_device()
if [ ! -e $DEVICE ]; then
echo $TCID: No $DEVICE device found >&2
echo $TCID: May be CONFIG_ION is not set >&2
- exit 0
+ exit $ksft_skip
fi
}
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 9cf83f895d98..49938d72cf63 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -12,3 +12,10 @@ test_tcpbpf_user
test_verifier_log
feature
test_libbpf_open
+test_sock
+test_sock_addr
+urandom_read
+test_btf
+test_sockmap
+test_lirc_mode2_user
+get_cgroup_id_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 0a315ddabbf4..607ed8729c06 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -10,7 +10,7 @@ ifneq ($(wildcard $(GENHDR)),)
GENFLAGS := -DHAVE_GENHDR
endif
-CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
+CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include
LDLIBS += -lcap -lelf -lrt -lpthread
TEST_CUSTOM_PROGS = $(OUTPUT)/urandom_read
@@ -19,19 +19,23 @@ all: $(TEST_CUSTOM_PROGS)
$(TEST_CUSTOM_PROGS): urandom_read
urandom_read: urandom_read.c
- $(CC) -o $(TEST_CUSTOM_PROGS) -static $<
+ $(CC) -o $(TEST_CUSTOM_PROGS) -static $< -Wl,--build-id
# 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_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
- test_sock test_sock_addr
+ test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \
test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \
sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \
- sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o
+ sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \
+ test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
+ test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
+ test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
+ get_cgroup_id_kern.o
# Order correspond to 'make run_tests' order
TEST_PROGS := test_kmod.sh \
@@ -39,10 +43,13 @@ TEST_PROGS := test_kmod.sh \
test_xdp_redirect.sh \
test_xdp_meta.sh \
test_offload.py \
- test_sock_addr.sh
+ test_sock_addr.sh \
+ test_tunnel.sh \
+ test_lwt_seg6local.sh \
+ test_lirc_mode2.sh
# Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
include ../lib.mk
@@ -55,6 +62,9 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
$(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
$(OUTPUT)/test_sock: cgroup_helpers.c
$(OUTPUT)/test_sock_addr: cgroup_helpers.c
+$(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_progs: trace_helpers.c
+$(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
.PHONY: force
@@ -66,6 +76,8 @@ $(BPFOBJ): force
CLANG ?= clang
LLC ?= llc
+LLVM_OBJCOPY ?= llvm-objcopy
+BTF_PAHOLE ?= pahole
PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
@@ -77,15 +89,42 @@ else
CPU ?= generic
endif
+# Get Clang's default includes on this system, as opposed to those seen by
+# '-target bpf'. This fixes "missing" files on some architectures/distros,
+# such as asm/byteorder.h, asm/socket.h, asm/sockios.h, sys/cdefs.h etc.
+#
+# Use '-idirafter': Don't interfere with include mechanics except where the
+# build would have failed anyways.
+CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
+ | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+
CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \
+ $(CLANG_SYS_INCLUDES) \
-Wno-compare-distinct-pointer-types
$(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline
$(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline
+BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
+BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version 2>&1 | grep LLVM)
+
+ifneq ($(BTF_LLC_PROBE),)
+ifneq ($(BTF_PAHOLE_PROBE),)
+ifneq ($(BTF_OBJCOPY_PROBE),)
+ CLANG_FLAGS += -g
+ LLC_FLAGS += -mattr=dwarfris
+ DWARF2BTF = y
+endif
+endif
+endif
+
$(OUTPUT)/%.o: %.c
$(CLANG) $(CLANG_FLAGS) \
-O2 -target bpf -emit-llvm -c $< -o - | \
- $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@
+ $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+ $(BTF_PAHOLE) -J $@
+endif
EXTRA_CLEAN := $(TEST_CUSTOM_PROGS)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index d8223d99f96d..f2f28b6c8915 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -75,9 +75,14 @@ static int (*bpf_sock_ops_cb_flags_set)(void *ctx, int flags) =
(void *) BPF_FUNC_sock_ops_cb_flags_set;
static int (*bpf_sk_redirect_map)(void *ctx, void *map, int key, int flags) =
(void *) BPF_FUNC_sk_redirect_map;
+static int (*bpf_sk_redirect_hash)(void *ctx, void *map, void *key, int flags) =
+ (void *) BPF_FUNC_sk_redirect_hash;
static int (*bpf_sock_map_update)(void *map, void *key, void *value,
unsigned long long flags) =
(void *) BPF_FUNC_sock_map_update;
+static int (*bpf_sock_hash_update)(void *map, void *key, void *value,
+ unsigned long long flags) =
+ (void *) BPF_FUNC_sock_hash_update;
static int (*bpf_perf_event_read_value)(void *map, unsigned long long flags,
void *buf, unsigned int buf_size) =
(void *) BPF_FUNC_perf_event_read_value;
@@ -88,6 +93,9 @@ static int (*bpf_override_return)(void *ctx, unsigned long rc) =
(void *) BPF_FUNC_override_return;
static int (*bpf_msg_redirect_map)(void *ctx, void *map, int key, int flags) =
(void *) BPF_FUNC_msg_redirect_map;
+static int (*bpf_msg_redirect_hash)(void *ctx,
+ void *map, void *key, int flags) =
+ (void *) BPF_FUNC_msg_redirect_hash;
static int (*bpf_msg_apply_bytes)(void *ctx, int len) =
(void *) BPF_FUNC_msg_apply_bytes;
static int (*bpf_msg_cork_bytes)(void *ctx, int len) =
@@ -96,6 +104,35 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) =
(void *) BPF_FUNC_msg_pull_data;
static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
(void *) BPF_FUNC_bind;
+static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
+ (void *) BPF_FUNC_xdp_adjust_tail;
+static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
+ int size, int flags) =
+ (void *) BPF_FUNC_skb_get_xfrm_state;
+static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
+ (void *) BPF_FUNC_get_stack;
+static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
+ int plen, __u32 flags) =
+ (void *) BPF_FUNC_fib_lookup;
+static int (*bpf_lwt_push_encap)(void *ctx, unsigned int type, void *hdr,
+ unsigned int len) =
+ (void *) BPF_FUNC_lwt_push_encap;
+static int (*bpf_lwt_seg6_store_bytes)(void *ctx, unsigned int offset,
+ void *from, unsigned int len) =
+ (void *) BPF_FUNC_lwt_seg6_store_bytes;
+static int (*bpf_lwt_seg6_action)(void *ctx, unsigned int action, void *param,
+ unsigned int param_len) =
+ (void *) BPF_FUNC_lwt_seg6_action;
+static int (*bpf_lwt_seg6_adjust_srh)(void *ctx, unsigned int offset,
+ unsigned int len) =
+ (void *) BPF_FUNC_lwt_seg6_adjust_srh;
+static int (*bpf_rc_repeat)(void *ctx) =
+ (void *) BPF_FUNC_rc_repeat;
+static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
+ unsigned long long scancode, unsigned int toggle) =
+ (void *) BPF_FUNC_rc_keydown;
+static unsigned long long (*bpf_get_current_cgroup_id)(void) =
+ (void *) BPF_FUNC_get_current_cgroup_id;
/* llvm builtin functions that eBPF C program may use to
* emit BPF_LD_ABS and BPF_LD_IND instructions
@@ -129,6 +166,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag
(void *) BPF_FUNC_l3_csum_replace;
static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
(void *) BPF_FUNC_l4_csum_replace;
+static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) =
+ (void *) BPF_FUNC_csum_diff;
static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) =
(void *) BPF_FUNC_skb_under_cgroup;
static int (*bpf_skb_change_head)(void *, int len, int flags) =
diff --git a/tools/testing/selftests/bpf/bpf_rand.h b/tools/testing/selftests/bpf/bpf_rand.h
new file mode 100644
index 000000000000..59bf3e1a9371
--- /dev/null
+++ b/tools/testing/selftests/bpf/bpf_rand.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BPF_RAND__
+#define __BPF_RAND__
+
+#include <stdint.h>
+#include <stdlib.h>
+#include <time.h>
+
+static inline uint64_t bpf_rand_mask(uint64_t mask)
+{
+ return (((uint64_t)(uint32_t)rand()) |
+ ((uint64_t)(uint32_t)rand() << 32)) & mask;
+}
+
+#define bpf_rand_ux(x, m) \
+static inline uint64_t bpf_rand_u##x(int shift) \
+{ \
+ return bpf_rand_mask((m)) << shift; \
+}
+
+bpf_rand_ux( 8, 0xffULL)
+bpf_rand_ux(16, 0xffffULL)
+bpf_rand_ux(24, 0xffffffULL)
+bpf_rand_ux(32, 0xffffffffULL)
+bpf_rand_ux(40, 0xffffffffffULL)
+bpf_rand_ux(48, 0xffffffffffffULL)
+bpf_rand_ux(56, 0xffffffffffffffULL)
+bpf_rand_ux(64, 0xffffffffffffffffULL)
+
+static inline void bpf_semi_rand_init(void)
+{
+ srand(time(NULL));
+}
+
+static inline uint64_t bpf_semi_rand_get(void)
+{
+ switch (rand() % 39) {
+ case 0: return 0x000000ff00000000ULL | bpf_rand_u8(0);
+ case 1: return 0xffffffff00000000ULL | bpf_rand_u16(0);
+ case 2: return 0x00000000ffff0000ULL | bpf_rand_u16(0);
+ case 3: return 0x8000000000000000ULL | bpf_rand_u32(0);
+ case 4: return 0x00000000f0000000ULL | bpf_rand_u32(0);
+ case 5: return 0x0000000100000000ULL | bpf_rand_u24(0);
+ case 6: return 0x800ff00000000000ULL | bpf_rand_u32(0);
+ case 7: return 0x7fffffff00000000ULL | bpf_rand_u32(0);
+ case 8: return 0xffffffffffffff00ULL ^ bpf_rand_u32(24);
+ case 9: return 0xffffffffffffff00ULL | bpf_rand_u8(0);
+ case 10: return 0x0000000010000000ULL | bpf_rand_u32(0);
+ case 11: return 0xf000000000000000ULL | bpf_rand_u8(0);
+ case 12: return 0x0000f00000000000ULL | bpf_rand_u8(8);
+ case 13: return 0x000000000f000000ULL | bpf_rand_u8(16);
+ case 14: return 0x0000000000000f00ULL | bpf_rand_u8(32);
+ case 15: return 0x00fff00000000f00ULL | bpf_rand_u8(48);
+ case 16: return 0x00007fffffffffffULL ^ bpf_rand_u32(1);
+ case 17: return 0xffff800000000000ULL | bpf_rand_u8(4);
+ case 18: return 0xffff800000000000ULL | bpf_rand_u8(20);
+ case 19: return (0xffffffc000000000ULL + 0x80000ULL) | bpf_rand_u32(0);
+ case 20: return (0xffffffc000000000ULL - 0x04000000ULL) | bpf_rand_u32(0);
+ case 21: return 0x0000000000000000ULL | bpf_rand_u8(55) | bpf_rand_u32(20);
+ case 22: return 0xffffffffffffffffULL ^ bpf_rand_u8(3) ^ bpf_rand_u32(40);
+ case 23: return 0x0000000000000000ULL | bpf_rand_u8(bpf_rand_u8(0) % 64);
+ case 24: return 0x0000000000000000ULL | bpf_rand_u16(bpf_rand_u8(0) % 64);
+ case 25: return 0xffffffffffffffffULL ^ bpf_rand_u8(bpf_rand_u8(0) % 64);
+ case 26: return 0xffffffffffffffffULL ^ bpf_rand_u40(bpf_rand_u8(0) % 64);
+ case 27: return 0x0000800000000000ULL;
+ case 28: return 0x8000000000000000ULL;
+ case 29: return 0x0000000000000000ULL;
+ case 30: return 0xffffffffffffffffULL;
+ case 31: return bpf_rand_u16(bpf_rand_u8(0) % 64);
+ case 32: return bpf_rand_u24(bpf_rand_u8(0) % 64);
+ case 33: return bpf_rand_u32(bpf_rand_u8(0) % 64);
+ case 34: return bpf_rand_u40(bpf_rand_u8(0) % 64);
+ case 35: return bpf_rand_u48(bpf_rand_u8(0) % 64);
+ case 36: return bpf_rand_u56(bpf_rand_u8(0) % 64);
+ case 37: return bpf_rand_u64(bpf_rand_u8(0) % 64);
+ default: return bpf_rand_u64(0);
+ }
+}
+
+#endif /* __BPF_RAND__ */
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index f3bca3ade0f3..c87b4e052ce9 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -6,6 +6,7 @@
#include <sys/types.h>
#include <linux/limits.h>
#include <stdio.h>
+#include <stdlib.h>
#include <linux/sched.h>
#include <fcntl.h>
#include <unistd.h>
@@ -176,3 +177,59 @@ int create_and_get_cgroup(char *path)
return fd;
}
+
+/**
+ * get_cgroup_id() - Get cgroup id for a particular cgroup path
+ * @path: The cgroup path, relative to the workdir, to join
+ *
+ * On success, it returns the cgroup id. On failure it returns 0,
+ * which is an invalid cgroup id.
+ * If there is a failure, it prints the error to stderr.
+ */
+unsigned long long get_cgroup_id(char *path)
+{
+ int dirfd, err, flags, mount_id, fhsize;
+ union {
+ unsigned long long cgid;
+ unsigned char raw_bytes[8];
+ } id;
+ char cgroup_workdir[PATH_MAX + 1];
+ struct file_handle *fhp, *fhp2;
+ unsigned long long ret = 0;
+
+ format_cgroup_path(cgroup_workdir, path);
+
+ dirfd = AT_FDCWD;
+ flags = 0;
+ fhsize = sizeof(*fhp);
+ fhp = calloc(1, fhsize);
+ if (!fhp) {
+ log_err("calloc");
+ return 0;
+ }
+ err = name_to_handle_at(dirfd, cgroup_workdir, fhp, &mount_id, flags);
+ if (err >= 0 || fhp->handle_bytes != 8) {
+ log_err("name_to_handle_at");
+ goto free_mem;
+ }
+
+ fhsize = sizeof(struct file_handle) + fhp->handle_bytes;
+ fhp2 = realloc(fhp, fhsize);
+ if (!fhp2) {
+ log_err("realloc");
+ goto free_mem;
+ }
+ err = name_to_handle_at(dirfd, cgroup_workdir, fhp2, &mount_id, flags);
+ fhp = fhp2;
+ if (err < 0) {
+ log_err("name_to_handle_at");
+ goto free_mem;
+ }
+
+ memcpy(id.raw_bytes, fhp->f_handle, 8);
+ ret = id.cgid;
+
+free_mem:
+ free(fhp);
+ return ret;
+}
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 06485e0002b3..20a4a5dcd469 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -13,5 +13,6 @@ int create_and_get_cgroup(char *path);
int join_cgroup(char *path);
int setup_cgroup_environment(void);
void cleanup_cgroup_environment(void);
+unsigned long long get_cgroup_id(char *path);
#endif
diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 983dd25d49f4..1eefe211a4a8 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -5,3 +5,5 @@ CONFIG_BPF_EVENTS=y
CONFIG_TEST_BPF=m
CONFIG_CGROUP_BPF=y
CONFIG_NETDEVSIM=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_SCH_INGRESS=y
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/get_cgroup_id_kern.c
new file mode 100644
index 000000000000..2cf8cb23f209
--- /dev/null
+++ b/tools/testing/selftests/bpf/get_cgroup_id_kern.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") cg_ids = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64),
+ .max_entries = 1,
+};
+
+SEC("tracepoint/syscalls/sys_enter_nanosleep")
+int trace(void *ctx)
+{
+ __u32 key = 0;
+ __u64 *val;
+
+ val = bpf_map_lookup_elem(&cg_ids, &key);
+ if (val)
+ *val = bpf_get_current_cgroup_id();
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/get_cgroup_id_user.c b/tools/testing/selftests/bpf/get_cgroup_id_user.c
new file mode 100644
index 000000000000..ea19a42e5894
--- /dev/null
+++ b/tools/testing/selftests/bpf/get_cgroup_id_user.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <syscall.h>
+#include <unistd.h>
+#include <linux/perf_event.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#include <linux/bpf.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
+
+#define CHECK(condition, tag, format...) ({ \
+ int __ret = !!(condition); \
+ if (__ret) { \
+ printf("%s:FAIL:%s ", __func__, tag); \
+ printf(format); \
+ } else { \
+ printf("%s:PASS:%s\n", __func__, tag); \
+ } \
+ __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)
+ return -1;
+ return bpf_map__fd(map);
+}
+
+#define TEST_CGROUP "/test-bpf-get-cgroup-id/"
+
+int main(int argc, char **argv)
+{
+ const char *probe_name = "syscalls/sys_enter_nanosleep";
+ const char *file = "get_cgroup_id_kern.o";
+ int err, bytes, efd, prog_fd, pmu_fd;
+ struct perf_event_attr attr = {};
+ int cgroup_fd, cgidmap_fd;
+ struct bpf_object *obj;
+ __u64 kcgid = 0, ucgid;
+ int exit_code = 1;
+ char buf[256];
+ __u32 key = 0;
+
+ err = setup_cgroup_environment();
+ if (CHECK(err, "setup_cgroup_environment", "err %d errno %d\n", err,
+ errno))
+ return 1;
+
+ cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+ if (CHECK(cgroup_fd < 0, "create_and_get_cgroup", "err %d errno %d\n",
+ cgroup_fd, errno))
+ goto cleanup_cgroup_env;
+
+ err = join_cgroup(TEST_CGROUP);
+ if (CHECK(err, "join_cgroup", "err %d errno %d\n", err, errno))
+ goto cleanup_cgroup_env;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno))
+ goto cleanup_cgroup_env;
+
+ cgidmap_fd = bpf_find_map(__func__, obj, "cg_ids");
+ if (CHECK(cgidmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
+ cgidmap_fd, errno))
+ goto close_prog;
+
+ snprintf(buf, sizeof(buf),
+ "/sys/kernel/debug/tracing/events/%s/id", probe_name);
+ efd = open(buf, O_RDONLY, 0);
+ if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+ bytes = read(efd, buf, sizeof(buf));
+ close(efd);
+ if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read",
+ "bytes %d errno %d\n", bytes, errno))
+ goto close_prog;
+
+ attr.config = strtol(buf, NULL, 0);
+ attr.type = PERF_TYPE_TRACEPOINT;
+ attr.sample_type = PERF_SAMPLE_RAW;
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
+
+ /* attach to this pid so the all bpf invocations will be in the
+ * cgroup associated with this pid.
+ */
+ pmu_fd = syscall(__NR_perf_event_open, &attr, getpid(), -1, -1, 0);
+ if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
+ errno))
+ goto close_prog;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err,
+ errno))
+ goto close_pmu;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+ if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err,
+ errno))
+ goto close_pmu;
+
+ /* trigger some syscalls */
+ sleep(1);
+
+ err = bpf_map_lookup_elem(cgidmap_fd, &key, &kcgid);
+ if (CHECK(err, "bpf_map_lookup_elem", "err %d errno %d\n", err, errno))
+ goto close_pmu;
+
+ ucgid = get_cgroup_id(TEST_CGROUP);
+ if (CHECK(kcgid != ucgid, "compare_cgroup_id",
+ "kern cgid %llx user cgid %llx", kcgid, ucgid))
+ goto close_pmu;
+
+ exit_code = 0;
+ printf("%s:PASS\n", argv[0]);
+
+close_pmu:
+ close(pmu_fd);
+close_prog:
+ bpf_object__close(obj);
+cleanup_cgroup_env:
+ cleanup_cgroup_environment();
+ return exit_code;
+}
diff --git a/tools/testing/selftests/bpf/sendmsg4_prog.c b/tools/testing/selftests/bpf/sendmsg4_prog.c
new file mode 100644
index 000000000000..a91536b1c47e
--- /dev/null
+++ b/tools/testing/selftests/bpf/sendmsg4_prog.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define SRC1_IP4 0xAC100001U /* 172.16.0.1 */
+#define SRC2_IP4 0x00000000U
+#define SRC_REWRITE_IP4 0x7f000004U
+#define DST_IP4 0xC0A801FEU /* 192.168.1.254 */
+#define DST_REWRITE_IP4 0x7f000001U
+#define DST_PORT 4040
+#define DST_REWRITE_PORT4 4444
+
+int _version SEC("version") = 1;
+
+SEC("cgroup/sendmsg4")
+int sendmsg_v4_prog(struct bpf_sock_addr *ctx)
+{
+ if (ctx->type != SOCK_DGRAM)
+ return 0;
+
+ /* Rewrite source. */
+ if (ctx->msg_src_ip4 == bpf_htonl(SRC1_IP4) ||
+ ctx->msg_src_ip4 == bpf_htonl(SRC2_IP4)) {
+ ctx->msg_src_ip4 = bpf_htonl(SRC_REWRITE_IP4);
+ } else {
+ /* Unexpected source. Reject sendmsg. */
+ return 0;
+ }
+
+ /* Rewrite destination. */
+ if ((ctx->user_ip4 >> 24) == (bpf_htonl(DST_IP4) >> 24) &&
+ ctx->user_port == bpf_htons(DST_PORT)) {
+ ctx->user_ip4 = bpf_htonl(DST_REWRITE_IP4);
+ ctx->user_port = bpf_htons(DST_REWRITE_PORT4);
+ } else {
+ /* Unexpected source. Reject sendmsg. */
+ return 0;
+ }
+
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/sendmsg6_prog.c b/tools/testing/selftests/bpf/sendmsg6_prog.c
new file mode 100644
index 000000000000..5aeaa284fc47
--- /dev/null
+++ b/tools/testing/selftests/bpf/sendmsg6_prog.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/stddef.h>
+#include <linux/bpf.h>
+#include <sys/socket.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define SRC_REWRITE_IP6_0 0
+#define SRC_REWRITE_IP6_1 0
+#define SRC_REWRITE_IP6_2 0
+#define SRC_REWRITE_IP6_3 6
+
+#define DST_REWRITE_IP6_0 0
+#define DST_REWRITE_IP6_1 0
+#define DST_REWRITE_IP6_2 0
+#define DST_REWRITE_IP6_3 1
+
+#define DST_REWRITE_PORT6 6666
+
+int _version SEC("version") = 1;
+
+SEC("cgroup/sendmsg6")
+int sendmsg_v6_prog(struct bpf_sock_addr *ctx)
+{
+ if (ctx->type != SOCK_DGRAM)
+ return 0;
+
+ /* Rewrite source. */
+ if (ctx->msg_src_ip6[3] == bpf_htonl(1) ||
+ ctx->msg_src_ip6[3] == bpf_htonl(0)) {
+ ctx->msg_src_ip6[0] = bpf_htonl(SRC_REWRITE_IP6_0);
+ ctx->msg_src_ip6[1] = bpf_htonl(SRC_REWRITE_IP6_1);
+ ctx->msg_src_ip6[2] = bpf_htonl(SRC_REWRITE_IP6_2);
+ ctx->msg_src_ip6[3] = bpf_htonl(SRC_REWRITE_IP6_3);
+ } else {
+ /* Unexpected source. Reject sendmsg. */
+ return 0;
+ }
+
+ /* Rewrite destination. */
+ if ((ctx->user_ip6[0] & 0xFFFF) == bpf_htons(0xFACE) &&
+ ctx->user_ip6[0] >> 16 == bpf_htons(0xB00C)) {
+ ctx->user_ip6[0] = bpf_htonl(DST_REWRITE_IP6_0);
+ ctx->user_ip6[1] = bpf_htonl(DST_REWRITE_IP6_1);
+ ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);
+ ctx->user_ip6[3] = bpf_htonl(DST_REWRITE_IP6_3);
+
+ ctx->user_port = bpf_htons(DST_REWRITE_PORT6);
+ } else {
+ /* Unexpected destination. Reject sendmsg. */
+ return 0;
+ }
+
+ return 1;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_adjust_tail.c b/tools/testing/selftests/bpf/test_adjust_tail.c
new file mode 100644
index 000000000000..4cd5e860c903
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_adjust_tail.c
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+SEC("xdp_adjust_tail")
+int _xdp_adjust_tail(struct xdp_md *xdp)
+{
+ void *data_end = (void *)(long)xdp->data_end;
+ void *data = (void *)(long)xdp->data;
+ int offset = 0;
+
+ if (data_end - data == 54)
+ offset = 256;
+ else
+ offset = 20;
+ if (bpf_xdp_adjust_tail(xdp, 0 - offset))
+ return XDP_DROP;
+ return XDP_TX;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
new file mode 100644
index 000000000000..3619f3023088
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -0,0 +1,2315 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#include <linux/bpf.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+#include <bpf/bpf.h>
+#include <sys/resource.h>
+#include <libelf.h>
+#include <gelf.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdarg.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <bpf/libbpf.h>
+#include <bpf/btf.h>
+
+#include "bpf_rlimit.h"
+
+static uint32_t pass_cnt;
+static uint32_t error_cnt;
+static uint32_t skip_cnt;
+
+#define CHECK(condition, format...) ({ \
+ int __ret = !!(condition); \
+ if (__ret) { \
+ fprintf(stderr, "%s:%d:FAIL ", __func__, __LINE__); \
+ fprintf(stderr, format); \
+ } \
+ __ret; \
+})
+
+static int count_result(int err)
+{
+ if (err)
+ error_cnt++;
+ else
+ pass_cnt++;
+
+ fprintf(stderr, "\n");
+ return err;
+}
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+#define __printf(a, b) __attribute__((format(printf, a, b)))
+
+__printf(1, 2)
+static int __base_pr(const char *format, ...)
+{
+ va_list args;
+ int err;
+
+ va_start(args, format);
+ err = vfprintf(stderr, format, args);
+ va_end(args);
+ return err;
+}
+
+#define BTF_INFO_ENC(kind, root, vlen) \
+ ((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+
+#define BTF_TYPE_ENC(name, info, size_or_type) \
+ (name), (info), (size_or_type)
+
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
+ ((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
+ BTF_INT_ENC(encoding, bits_offset, bits)
+
+#define BTF_ARRAY_ENC(type, index_type, nr_elems) \
+ (type), (index_type), (nr_elems)
+#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \
+ BTF_ARRAY_ENC(type, index_type, nr_elems)
+
+#define BTF_MEMBER_ENC(name, type, bits_offset) \
+ (name), (type), (bits_offset)
+#define BTF_ENUM_ENC(name, val) (name), (val)
+
+#define BTF_TYPEDEF_ENC(name, type) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
+
+#define BTF_PTR_ENC(name, type) \
+ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+
+#define BTF_END_RAW 0xdeadbeef
+#define NAME_TBD 0xdeadb33f
+
+#define MAX_NR_RAW_TYPES 1024
+#define BTF_LOG_BUF_SIZE 65535
+
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
+static struct args {
+ unsigned int raw_test_num;
+ unsigned int file_test_num;
+ unsigned int get_info_test_num;
+ bool raw_test;
+ bool file_test;
+ bool get_info_test;
+ bool pprint_test;
+ bool always_log;
+} args;
+
+static char btf_log_buf[BTF_LOG_BUF_SIZE];
+
+static struct btf_header hdr_tmpl = {
+ .magic = BTF_MAGIC,
+ .version = BTF_VERSION,
+ .hdr_len = sizeof(struct btf_header),
+};
+
+struct btf_raw_test {
+ const char *descr;
+ const char *str_sec;
+ const char *map_name;
+ const char *err_str;
+ __u32 raw_types[MAX_NR_RAW_TYPES];
+ __u32 str_sec_size;
+ enum bpf_map_type map_type;
+ __u32 key_size;
+ __u32 value_size;
+ __u32 key_type_id;
+ __u32 value_type_id;
+ __u32 max_entries;
+ bool btf_load_err;
+ bool map_create_err;
+ int hdr_len_delta;
+ int type_off_delta;
+ int str_off_delta;
+ int str_len_delta;
+};
+
+static struct btf_raw_test raw_tests[] = {
+/* enum E {
+ * E0,
+ * E1,
+ * };
+ *
+ * struct A {
+ * unsigned long long m;
+ * int n;
+ * char o;
+ * [3 bytes hole]
+ * int p[8];
+ * int q[4][8];
+ * enum E r;
+ * };
+ */
+{
+ .descr = "struct test #1",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* unsigned long long */
+ BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */
+ /* char */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */
+ /* int[8] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */
+ /* struct A { */ /* [5] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 6), 180),
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0), /* unsigned long long m;*/
+ BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */
+ BTF_MEMBER_ENC(NAME_TBD, 6, 384),/* int q[4][8] */
+ BTF_MEMBER_ENC(NAME_TBD, 7, 1408), /* enum E r */
+ /* } */
+ /* int[4][8] */
+ BTF_TYPE_ARRAY_ENC(4, 1, 4), /* [6] */
+ /* enum E */ /* [7] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)),
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_ENUM_ENC(NAME_TBD, 1),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_test1_map",
+ .key_size = sizeof(int),
+ .value_size = 180,
+ .key_type_id = 1,
+ .value_type_id = 5,
+ .max_entries = 4,
+},
+
+/* typedef struct b Struct_B;
+ *
+ * struct A {
+ * int m;
+ * struct b n[4];
+ * const Struct_B o[4];
+ * };
+ *
+ * struct B {
+ * int m;
+ * int n;
+ * };
+ */
+{
+ .descr = "struct test #2",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* struct b [4] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(4, 1, 4),
+
+ /* struct A { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 3), 68),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct B n[4] */
+ BTF_MEMBER_ENC(NAME_TBD, 8, 288),/* const Struct_B o[4];*/
+ /* } */
+
+ /* struct B { */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */
+ /* } */
+
+ /* const int */ /* [5] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1),
+ /* typedef struct b Struct_B */ /* [6] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 4),
+ /* const Struct_B */ /* [7] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 6),
+ /* const Struct_B [4] */ /* [8] */
+ BTF_TYPE_ARRAY_ENC(7, 1, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n\0o\0B\0m\0n\0Struct_B",
+ .str_sec_size = sizeof("\0A\0m\0n\0o\0B\0m\0n\0Struct_B"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "struct_test2_map",
+ .key_size = sizeof(int),
+ .value_size = 68,
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+},
+
+/* Test member exceeds the size of struct.
+ *
+ * struct A {
+ * int m;
+ * int n;
+ * };
+ */
+{
+ .descr = "size check test #1",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* struct A { */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n",
+ .str_sec_size = sizeof("\0A\0m\0n"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "size_check1_map",
+ .key_size = sizeof(int),
+ .value_size = 1,
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Member exceeds struct_size",
+},
+
+/* Test member exeeds the size of struct
+ *
+ * struct A {
+ * int m;
+ * int n[2];
+ * };
+ */
+{
+ .descr = "size check test #2",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
+ /* int[2] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 2),
+ /* struct A { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 3 - 1),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n[2]; */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n",
+ .str_sec_size = sizeof("\0A\0m\0n"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "size_check2_map",
+ .key_size = sizeof(int),
+ .value_size = 1,
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Member exceeds struct_size",
+},
+
+/* Test member exeeds the size of struct
+ *
+ * struct A {
+ * int m;
+ * void *n;
+ * };
+ */
+{
+ .descr = "size check test #3",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
+ /* void* */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+ /* struct A { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) + sizeof(void *) - 1),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* void *n; */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0n",
+ .str_sec_size = sizeof("\0A\0m\0n"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "size_check3_map",
+ .key_size = sizeof(int),
+ .value_size = 1,
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Member exceeds struct_size",
+},
+
+/* Test member exceeds the size of struct
+ *
+ * enum E {
+ * E0,
+ * E1,
+ * };
+ *
+ * struct A {
+ * int m;
+ * enum E n;
+ * };
+ */
+{
+ .descr = "size check test #4",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)),
+ /* enum E { */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)),
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_ENUM_ENC(NAME_TBD, 1),
+ /* } */
+ /* struct A { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* enum E n; */
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0E\0E0\0E1\0A\0m\0n",
+ .str_sec_size = sizeof("\0E\0E0\0E1\0A\0m\0n"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "size_check4_map",
+ .key_size = sizeof(int),
+ .value_size = 1,
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Member exceeds struct_size",
+},
+
+/* typedef const void * const_void_ptr;
+ * struct A {
+ * const_void_ptr m;
+ * };
+ */
+{
+ .descr = "void test #1",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* const void */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
+ /* const void* */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),
+ /* typedef const void * const_void_ptr */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
+ /* struct A { */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
+ /* const_void_ptr m; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 0),
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0const_void_ptr\0A\0m",
+ .str_sec_size = sizeof("\0const_void_ptr\0A\0m"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "void_test1_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(void *),
+ .key_type_id = 1,
+ .value_type_id = 4,
+ .max_entries = 4,
+},
+
+/* struct A {
+ * const void m;
+ * };
+ */
+{
+ .descr = "void test #2",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* const void */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
+ /* struct A { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 8),
+ /* const void m; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 0),
+ /* } */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m",
+ .str_sec_size = sizeof("\0A\0m"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "void_test2_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(void *),
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid member",
+},
+
+/* typedef const void * const_void_ptr;
+ * const_void_ptr[4]
+ */
+{
+ .descr = "void test #3",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* const void */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
+ /* const void* */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2),
+ /* typedef const void * const_void_ptr */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
+ /* const_void_ptr[4] */ /* [5] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0const_void_ptr",
+ .str_sec_size = sizeof("\0const_void_ptr"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "void_test3_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(void *) * 4,
+ .key_type_id = 1,
+ .value_type_id = 4,
+ .max_entries = 4,
+},
+
+/* const void[4] */
+{
+ .descr = "void test #4",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* const void */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
+ /* const void[4] */ /* [3] */
+ BTF_TYPE_ARRAY_ENC(2, 1, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m",
+ .str_sec_size = sizeof("\0A\0m"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "void_test4_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(void *) * 4,
+ .key_type_id = 1,
+ .value_type_id = 3,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid elem",
+},
+
+/* Array_A <------------------+
+ * elem_type == Array_B |
+ * | |
+ * | |
+ * Array_B <-------- + |
+ * elem_type == Array A --+
+ */
+{
+ .descr = "loop test #1",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* Array_A */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 8),
+ /* Array_B */ /* [3] */
+ BTF_TYPE_ARRAY_ENC(2, 1, 8),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test1_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(sizeof(int) * 8),
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+/* typedef is _before_ the BTF type of Array_A and Array_B
+ *
+ * typedef Array_B int_array;
+ *
+ * Array_A <------------------+
+ * elem_type == int_array |
+ * | |
+ * | |
+ * Array_B <-------- + |
+ * elem_type == Array_A --+
+ */
+{
+ .descr = "loop test #2",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* typedef Array_B int_array */
+ BTF_TYPEDEF_ENC(1, 4), /* [2] */
+ /* Array_A */
+ BTF_TYPE_ARRAY_ENC(2, 1, 8), /* [3] */
+ /* Array_B */
+ BTF_TYPE_ARRAY_ENC(3, 1, 8), /* [4] */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int_array\0",
+ .str_sec_size = sizeof("\0int_array"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test2_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(sizeof(int) * 8),
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+/* Array_A <------------------+
+ * elem_type == Array_B |
+ * | |
+ * | |
+ * Array_B <-------- + |
+ * elem_type == Array_A --+
+ */
+{
+ .descr = "loop test #3",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* Array_A */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 8),
+ /* Array_B */ /* [3] */
+ BTF_TYPE_ARRAY_ENC(2, 1, 8),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test3_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(sizeof(int) * 8),
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+/* typedef is _between_ the BTF type of Array_A and Array_B
+ *
+ * typedef Array_B int_array;
+ *
+ * Array_A <------------------+
+ * elem_type == int_array |
+ * | |
+ * | |
+ * Array_B <-------- + |
+ * elem_type == Array_A --+
+ */
+{
+ .descr = "loop test #4",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* Array_A */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 8),
+ /* typedef Array_B int_array */ /* [3] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 4),
+ /* Array_B */ /* [4] */
+ BTF_TYPE_ARRAY_ENC(2, 1, 8),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int_array\0",
+ .str_sec_size = sizeof("\0int_array"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test4_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(sizeof(int) * 8),
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+/* typedef struct B Struct_B
+ *
+ * struct A {
+ * int x;
+ * Struct_B y;
+ * };
+ *
+ * struct B {
+ * int x;
+ * struct A y;
+ * };
+ */
+{
+ .descr = "loop test #5",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ /* struct A */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* Struct_B y; */
+ /* typedef struct B Struct_B */
+ BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */
+ /* struct B */ /* [4] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A y; */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0x\0y\0Struct_B\0B\0x\0y",
+ .str_sec_size = sizeof("\0A\0x\0y\0Struct_B\0B\0x\0y"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test5_map",
+ .key_size = sizeof(int),
+ .value_size = 8,
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+/* struct A {
+ * int x;
+ * struct A array_a[4];
+ * };
+ */
+{
+ .descr = "loop test #6",
+ .raw_types = {
+ /* int */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */
+ /* struct A */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */
+ BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A array_a[4]; */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0x\0y",
+ .str_sec_size = sizeof("\0A\0x\0y"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test6_map",
+ .key_size = sizeof(int),
+ .value_size = 8,
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+{
+ .descr = "loop test #7",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* struct A { */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
+ /* const void *m; */
+ BTF_MEMBER_ENC(NAME_TBD, 3, 0),
+ /* CONST type_id=3 */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4),
+ /* PTR type_id=2 */ /* [4] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m",
+ .str_sec_size = sizeof("\0A\0m"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test7_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(void *),
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+{
+ .descr = "loop test #8",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* struct A { */ /* [2] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
+ /* const void *m; */
+ BTF_MEMBER_ENC(NAME_TBD, 4, 0),
+ /* struct B { */ /* [3] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)),
+ /* const void *n; */
+ BTF_MEMBER_ENC(NAME_TBD, 6, 0),
+ /* CONST type_id=5 */ /* [4] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 5),
+ /* PTR type_id=6 */ /* [5] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 6),
+ /* CONST type_id=7 */ /* [6] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 7),
+ /* PTR type_id=4 */ /* [7] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0A\0m\0B\0n",
+ .str_sec_size = sizeof("\0A\0m\0B\0n"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "loop_test8_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(void *),
+ .key_type_id = 1,
+ .value_type_id = 2,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Loop detected",
+},
+
+{
+ .descr = "string section does not end with null",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int") - 1,
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid string section",
+},
+
+{
+ .descr = "empty string section",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = 0,
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid string section",
+},
+
+{
+ .descr = "empty type section",
+ .raw_types = {
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "No type found",
+},
+
+{
+ .descr = "btf_header test. Longer hdr_len",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .hdr_len_delta = 4,
+ .err_str = "Unsupported btf_header",
+},
+
+{
+ .descr = "btf_header test. Gap between hdr and type",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .type_off_delta = 4,
+ .err_str = "Unsupported section found",
+},
+
+{
+ .descr = "btf_header test. Gap between type and str",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .str_off_delta = 4,
+ .err_str = "Unsupported section found",
+},
+
+{
+ .descr = "btf_header test. Overlap between type and str",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .str_off_delta = -4,
+ .err_str = "Section overlap found",
+},
+
+{
+ .descr = "btf_header test. Larger BTF size",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .str_len_delta = -4,
+ .err_str = "Unsupported section found",
+},
+
+{
+ .descr = "btf_header test. Smaller BTF size",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "\0int",
+ .str_sec_size = sizeof("\0int"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "hdr_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .str_len_delta = 4,
+ .err_str = "Total section length too long",
+},
+
+{
+ .descr = "array test. index_type/elem_type \"int\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(1, 1, 16),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "array test. index_type/elem_type \"const int\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 3, 16),
+ /* CONST type_id=1 */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "array test. index_type \"const int:31\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int:31 */ /* [2] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 31, 4),
+ /* int[16] */ /* [3] */
+ BTF_TYPE_ARRAY_ENC(1, 4, 16),
+ /* CONST type_id=2 */ /* [4] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid index",
+},
+
+{
+ .descr = "array test. elem_type \"const int:31\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int:31 */ /* [2] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 31, 4),
+ /* int[16] */ /* [3] */
+ BTF_TYPE_ARRAY_ENC(4, 1, 16),
+ /* CONST type_id=2 */ /* [4] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 2),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid array of int",
+},
+
+{
+ .descr = "array test. index_type \"void\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(1, 0, 16),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid index",
+},
+
+{
+ .descr = "array test. index_type \"const void\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(1, 3, 16),
+ /* CONST type_id=0 (void) */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid index",
+},
+
+{
+ .descr = "array test. elem_type \"const void\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 16),
+ /* CONST type_id=0 (void) */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid elem",
+},
+
+{
+ .descr = "array test. elem_type \"const void *\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* const void *[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 1, 16),
+ /* CONST type_id=4 */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4),
+ /* void* */ /* [4] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+},
+
+{
+ .descr = "array test. index_type \"const void *\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* const void *[16] */ /* [2] */
+ BTF_TYPE_ARRAY_ENC(3, 3, 16),
+ /* CONST type_id=4 */ /* [3] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4),
+ /* void* */ /* [4] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid index",
+},
+
+{
+ .descr = "array test. t->size != 0\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* int[16] */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 1),
+ BTF_ARRAY_ENC(1, 1, 16),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "size != 0",
+},
+
+{
+ .descr = "int test. invalid int_data",
+ .raw_types = {
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), 4),
+ 0x10000000,
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid int_data",
+},
+
+{
+ .descr = "invalid BTF_INFO",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_TYPE_ENC(0, 0x10000000, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "array_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "Invalid btf_info",
+},
+
+{
+ .descr = "fwd test. t->type != 0\"",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* fwd type */ /* [2] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FWD, 0, 0), 1),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "fwd_test_map",
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .key_type_id = 1,
+ .value_type_id = 1,
+ .max_entries = 4,
+ .btf_load_err = true,
+ .err_str = "type != 0",
+},
+
+}; /* struct btf_raw_test raw_tests[] */
+
+static const char *get_next_str(const char *start, const char *end)
+{
+ return start < end - 1 ? start + 1 : NULL;
+}
+
+static int get_type_sec_size(const __u32 *raw_types)
+{
+ int i;
+
+ for (i = MAX_NR_RAW_TYPES - 1;
+ i >= 0 && raw_types[i] != BTF_END_RAW;
+ i--)
+ ;
+
+ return i < 0 ? i : i * sizeof(raw_types[0]);
+}
+
+static void *btf_raw_create(const struct btf_header *hdr,
+ const __u32 *raw_types,
+ const char *str,
+ unsigned int str_sec_size,
+ unsigned int *btf_size)
+{
+ const char *next_str = str, *end_str = str + str_sec_size;
+ unsigned int size_needed, offset;
+ struct btf_header *ret_hdr;
+ int i, type_sec_size;
+ uint32_t *ret_types;
+ void *raw_btf;
+
+ type_sec_size = get_type_sec_size(raw_types);
+ if (CHECK(type_sec_size < 0, "Cannot get nr_raw_types"))
+ return NULL;
+
+ size_needed = sizeof(*hdr) + type_sec_size + str_sec_size;
+ raw_btf = malloc(size_needed);
+ if (CHECK(!raw_btf, "Cannot allocate memory for raw_btf"))
+ return NULL;
+
+ /* Copy header */
+ memcpy(raw_btf, hdr, sizeof(*hdr));
+ offset = sizeof(*hdr);
+
+ /* Copy type section */
+ ret_types = raw_btf + offset;
+ for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) {
+ if (raw_types[i] == NAME_TBD) {
+ next_str = get_next_str(next_str, end_str);
+ if (CHECK(!next_str, "Error in getting next_str")) {
+ free(raw_btf);
+ return NULL;
+ }
+ ret_types[i] = next_str - str;
+ next_str += strlen(next_str);
+ } else {
+ ret_types[i] = raw_types[i];
+ }
+ }
+ offset += type_sec_size;
+
+ /* Copy string section */
+ memcpy(raw_btf + offset, str, str_sec_size);
+
+ ret_hdr = (struct btf_header *)raw_btf;
+ ret_hdr->type_len = type_sec_size;
+ ret_hdr->str_off = type_sec_size;
+ ret_hdr->str_len = str_sec_size;
+
+ *btf_size = size_needed;
+
+ return raw_btf;
+}
+
+static int do_test_raw(unsigned int test_num)
+{
+ struct btf_raw_test *test = &raw_tests[test_num - 1];
+ struct bpf_create_map_attr create_attr = {};
+ int map_fd = -1, btf_fd = -1;
+ unsigned int raw_btf_size;
+ struct btf_header *hdr;
+ void *raw_btf;
+ int err;
+
+ fprintf(stderr, "BTF raw test[%u] (%s): ", test_num, test->descr);
+ raw_btf = btf_raw_create(&hdr_tmpl,
+ test->raw_types,
+ test->str_sec,
+ test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ hdr = raw_btf;
+
+ hdr->hdr_len = (int)hdr->hdr_len + test->hdr_len_delta;
+ hdr->type_off = (int)hdr->type_off + test->type_off_delta;
+ hdr->str_off = (int)hdr->str_off + test->str_off_delta;
+ hdr->str_len = (int)hdr->str_len + test->str_len_delta;
+
+ *btf_log_buf = '\0';
+ btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ free(raw_btf);
+
+ err = ((btf_fd == -1) != test->btf_load_err);
+ if (CHECK(err, "btf_fd:%d test->btf_load_err:%u",
+ btf_fd, test->btf_load_err) ||
+ CHECK(test->err_str && !strstr(btf_log_buf, test->err_str),
+ "expected err_str:%s", test->err_str)) {
+ err = -1;
+ goto done;
+ }
+
+ if (err || btf_fd == -1)
+ goto done;
+
+ create_attr.name = test->map_name;
+ create_attr.map_type = test->map_type;
+ create_attr.key_size = test->key_size;
+ create_attr.value_size = test->value_size;
+ create_attr.max_entries = test->max_entries;
+ create_attr.btf_fd = btf_fd;
+ create_attr.btf_key_type_id = test->key_type_id;
+ create_attr.btf_value_type_id = test->value_type_id;
+
+ map_fd = bpf_create_map_xattr(&create_attr);
+
+ err = ((map_fd == -1) != test->map_create_err);
+ CHECK(err, "map_fd:%d test->map_create_err:%u",
+ map_fd, test->map_create_err);
+
+done:
+ if (!err)
+ fprintf(stderr, "OK");
+
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ if (btf_fd != -1)
+ close(btf_fd);
+ if (map_fd != -1)
+ close(map_fd);
+
+ return err;
+}
+
+static int test_raw(void)
+{
+ unsigned int i;
+ int err = 0;
+
+ if (args.raw_test_num)
+ return count_result(do_test_raw(args.raw_test_num));
+
+ for (i = 1; i <= ARRAY_SIZE(raw_tests); i++)
+ err |= count_result(do_test_raw(i));
+
+ return err;
+}
+
+struct btf_get_info_test {
+ const char *descr;
+ const char *str_sec;
+ __u32 raw_types[MAX_NR_RAW_TYPES];
+ __u32 str_sec_size;
+ int btf_size_delta;
+ int (*special_test)(unsigned int test_num);
+};
+
+static int test_big_btf_info(unsigned int test_num);
+static int test_btf_id(unsigned int test_num);
+
+const struct btf_get_info_test get_info_tests[] = {
+{
+ .descr = "== raw_btf_size+1",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .btf_size_delta = 1,
+},
+{
+ .descr = "== raw_btf_size-3",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .btf_size_delta = -3,
+},
+{
+ .descr = "Large bpf_btf_info",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .special_test = test_big_btf_info,
+},
+{
+ .descr = "BTF ID",
+ .raw_types = {
+ /* int */ /* [1] */
+ BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),
+ /* unsigned int */ /* [2] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 32, 4),
+ BTF_END_RAW,
+ },
+ .str_sec = "",
+ .str_sec_size = sizeof(""),
+ .special_test = test_btf_id,
+},
+};
+
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+ return (__u64)(unsigned long)ptr;
+}
+
+static int test_big_btf_info(unsigned int test_num)
+{
+ const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
+ uint8_t *raw_btf = NULL, *user_btf = NULL;
+ unsigned int raw_btf_size;
+ struct {
+ struct bpf_btf_info info;
+ uint64_t garbage;
+ } info_garbage;
+ struct bpf_btf_info *info;
+ int btf_fd = -1, err;
+ uint32_t info_len;
+
+ raw_btf = btf_raw_create(&hdr_tmpl,
+ test->raw_types,
+ test->str_sec,
+ test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+
+ user_btf = malloc(raw_btf_size);
+ if (CHECK(!user_btf, "!user_btf")) {
+ err = -1;
+ goto done;
+ }
+
+ btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ /*
+ * GET_INFO should error out if the userspace info
+ * has non zero tailing bytes.
+ */
+ info = &info_garbage.info;
+ memset(info, 0, sizeof(*info));
+ info_garbage.garbage = 0xdeadbeef;
+ info_len = sizeof(info_garbage);
+ info->btf = ptr_to_u64(user_btf);
+ info->btf_size = raw_btf_size;
+
+ err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
+ if (CHECK(!err, "!err")) {
+ err = -1;
+ goto done;
+ }
+
+ /*
+ * GET_INFO should succeed even info_len is larger than
+ * the kernel supported as long as tailing bytes are zero.
+ * The kernel supported info len should also be returned
+ * to userspace.
+ */
+ info_garbage.garbage = 0;
+ err = bpf_obj_get_info_by_fd(btf_fd, info, &info_len);
+ if (CHECK(err || info_len != sizeof(*info),
+ "err:%d errno:%d info_len:%u sizeof(*info):%lu",
+ err, errno, info_len, sizeof(*info))) {
+ err = -1;
+ goto done;
+ }
+
+ fprintf(stderr, "OK");
+
+done:
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ free(raw_btf);
+ free(user_btf);
+
+ if (btf_fd != -1)
+ close(btf_fd);
+
+ return err;
+}
+
+static int test_btf_id(unsigned int test_num)
+{
+ const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
+ struct bpf_create_map_attr create_attr = {};
+ uint8_t *raw_btf = NULL, *user_btf[2] = {};
+ int btf_fd[2] = {-1, -1}, map_fd = -1;
+ struct bpf_map_info map_info = {};
+ struct bpf_btf_info info[2] = {};
+ unsigned int raw_btf_size;
+ uint32_t info_len;
+ int err, i, ret;
+
+ raw_btf = btf_raw_create(&hdr_tmpl,
+ test->raw_types,
+ test->str_sec,
+ test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+
+ for (i = 0; i < 2; i++) {
+ user_btf[i] = malloc(raw_btf_size);
+ if (CHECK(!user_btf[i], "!user_btf[%d]", i)) {
+ err = -1;
+ goto done;
+ }
+ info[i].btf = ptr_to_u64(user_btf[i]);
+ info[i].btf_size = raw_btf_size;
+ }
+
+ btf_fd[0] = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ /* Test BPF_OBJ_GET_INFO_BY_ID on btf_id */
+ info_len = sizeof(info[0]);
+ err = bpf_obj_get_info_by_fd(btf_fd[0], &info[0], &info_len);
+ if (CHECK(err, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ btf_fd[1] = bpf_btf_get_fd_by_id(info[0].id);
+ if (CHECK(btf_fd[1] == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ ret = 0;
+ err = bpf_obj_get_info_by_fd(btf_fd[1], &info[1], &info_len);
+ if (CHECK(err || info[0].id != info[1].id ||
+ info[0].btf_size != info[1].btf_size ||
+ (ret = memcmp(user_btf[0], user_btf[1], info[0].btf_size)),
+ "err:%d errno:%d id0:%u id1:%u btf_size0:%u btf_size1:%u memcmp:%d",
+ err, errno, info[0].id, info[1].id,
+ info[0].btf_size, info[1].btf_size, ret)) {
+ err = -1;
+ goto done;
+ }
+
+ /* Test btf members in struct bpf_map_info */
+ create_attr.name = "test_btf_id";
+ create_attr.map_type = BPF_MAP_TYPE_ARRAY;
+ create_attr.key_size = sizeof(int);
+ create_attr.value_size = sizeof(unsigned int);
+ create_attr.max_entries = 4;
+ create_attr.btf_fd = btf_fd[0];
+ create_attr.btf_key_type_id = 1;
+ create_attr.btf_value_type_id = 2;
+
+ map_fd = bpf_create_map_xattr(&create_attr);
+ if (CHECK(map_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ info_len = sizeof(map_info);
+ err = bpf_obj_get_info_by_fd(map_fd, &map_info, &info_len);
+ if (CHECK(err || map_info.btf_id != info[0].id ||
+ map_info.btf_key_type_id != 1 || map_info.btf_value_type_id != 2,
+ "err:%d errno:%d info.id:%u btf_id:%u btf_key_type_id:%u btf_value_type_id:%u",
+ err, errno, info[0].id, map_info.btf_id, map_info.btf_key_type_id,
+ map_info.btf_value_type_id)) {
+ err = -1;
+ goto done;
+ }
+
+ for (i = 0; i < 2; i++) {
+ close(btf_fd[i]);
+ btf_fd[i] = -1;
+ }
+
+ /* Test BTF ID is removed from the kernel */
+ btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
+ if (CHECK(btf_fd[0] == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+ close(btf_fd[0]);
+ btf_fd[0] = -1;
+
+ /* The map holds the last ref to BTF and its btf_id */
+ close(map_fd);
+ map_fd = -1;
+ btf_fd[0] = bpf_btf_get_fd_by_id(map_info.btf_id);
+ if (CHECK(btf_fd[0] != -1, "BTF lingers")) {
+ err = -1;
+ goto done;
+ }
+
+ fprintf(stderr, "OK");
+
+done:
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ free(raw_btf);
+ if (map_fd != -1)
+ close(map_fd);
+ for (i = 0; i < 2; i++) {
+ free(user_btf[i]);
+ if (btf_fd[i] != -1)
+ close(btf_fd[i]);
+ }
+
+ return err;
+}
+
+static int do_test_get_info(unsigned int test_num)
+{
+ const struct btf_get_info_test *test = &get_info_tests[test_num - 1];
+ unsigned int raw_btf_size, user_btf_size, expected_nbytes;
+ uint8_t *raw_btf = NULL, *user_btf = NULL;
+ struct bpf_btf_info info = {};
+ int btf_fd = -1, err, ret;
+ uint32_t info_len;
+
+ fprintf(stderr, "BTF GET_INFO test[%u] (%s): ",
+ test_num, test->descr);
+
+ if (test->special_test)
+ return test->special_test(test_num);
+
+ raw_btf = btf_raw_create(&hdr_tmpl,
+ test->raw_types,
+ test->str_sec,
+ test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+
+ user_btf = malloc(raw_btf_size);
+ if (CHECK(!user_btf, "!user_btf")) {
+ err = -1;
+ goto done;
+ }
+
+ btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ user_btf_size = (int)raw_btf_size + test->btf_size_delta;
+ expected_nbytes = min(raw_btf_size, user_btf_size);
+ if (raw_btf_size > expected_nbytes)
+ memset(user_btf + expected_nbytes, 0xff,
+ raw_btf_size - expected_nbytes);
+
+ info_len = sizeof(info);
+ info.btf = ptr_to_u64(user_btf);
+ info.btf_size = user_btf_size;
+
+ ret = 0;
+ err = bpf_obj_get_info_by_fd(btf_fd, &info, &info_len);
+ if (CHECK(err || !info.id || info_len != sizeof(info) ||
+ info.btf_size != raw_btf_size ||
+ (ret = memcmp(raw_btf, user_btf, expected_nbytes)),
+ "err:%d errno:%d info.id:%u info_len:%u sizeof(info):%lu raw_btf_size:%u info.btf_size:%u expected_nbytes:%u memcmp:%d",
+ err, errno, info.id, info_len, sizeof(info),
+ raw_btf_size, info.btf_size, expected_nbytes, ret)) {
+ err = -1;
+ goto done;
+ }
+
+ while (expected_nbytes < raw_btf_size) {
+ fprintf(stderr, "%u...", expected_nbytes);
+ if (CHECK(user_btf[expected_nbytes++] != 0xff,
+ "user_btf[%u]:%x != 0xff", expected_nbytes - 1,
+ user_btf[expected_nbytes - 1])) {
+ err = -1;
+ goto done;
+ }
+ }
+
+ fprintf(stderr, "OK");
+
+done:
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+
+ free(raw_btf);
+ free(user_btf);
+
+ if (btf_fd != -1)
+ close(btf_fd);
+
+ return err;
+}
+
+static int test_get_info(void)
+{
+ unsigned int i;
+ int err = 0;
+
+ if (args.get_info_test_num)
+ return count_result(do_test_get_info(args.get_info_test_num));
+
+ for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++)
+ err |= count_result(do_test_get_info(i));
+
+ return err;
+}
+
+struct btf_file_test {
+ const char *file;
+ bool btf_kv_notfound;
+};
+
+static struct btf_file_test file_tests[] = {
+{
+ .file = "test_btf_haskv.o",
+},
+{
+ .file = "test_btf_nokv.o",
+ .btf_kv_notfound = true,
+},
+};
+
+static int file_has_btf_elf(const char *fn)
+{
+ Elf_Scn *scn = NULL;
+ GElf_Ehdr ehdr;
+ int elf_fd;
+ Elf *elf;
+ int ret;
+
+ if (CHECK(elf_version(EV_CURRENT) == EV_NONE,
+ "elf_version(EV_CURRENT) == EV_NONE"))
+ return -1;
+
+ elf_fd = open(fn, O_RDONLY);
+ if (CHECK(elf_fd == -1, "open(%s): errno:%d", fn, errno))
+ return -1;
+
+ elf = elf_begin(elf_fd, ELF_C_READ, NULL);
+ if (CHECK(!elf, "elf_begin(%s): %s", fn, elf_errmsg(elf_errno()))) {
+ ret = -1;
+ goto done;
+ }
+
+ if (CHECK(!gelf_getehdr(elf, &ehdr), "!gelf_getehdr(%s)", fn)) {
+ ret = -1;
+ goto done;
+ }
+
+ while ((scn = elf_nextscn(elf, scn))) {
+ const char *sh_name;
+ GElf_Shdr sh;
+
+ if (CHECK(gelf_getshdr(scn, &sh) != &sh,
+ "file:%s gelf_getshdr != &sh", fn)) {
+ ret = -1;
+ goto done;
+ }
+
+ sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name);
+ if (!strcmp(sh_name, BTF_ELF_SEC)) {
+ ret = 1;
+ goto done;
+ }
+ }
+
+ ret = 0;
+
+done:
+ close(elf_fd);
+ elf_end(elf);
+ return ret;
+}
+
+static int do_test_file(unsigned int test_num)
+{
+ const struct btf_file_test *test = &file_tests[test_num - 1];
+ struct bpf_object *obj = NULL;
+ struct bpf_program *prog;
+ struct bpf_map *map;
+ int err;
+
+ fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num,
+ test->file);
+
+ err = file_has_btf_elf(test->file);
+ if (err == -1)
+ return err;
+
+ if (err == 0) {
+ fprintf(stderr, "SKIP. No ELF %s found", BTF_ELF_SEC);
+ skip_cnt++;
+ return 0;
+ }
+
+ obj = bpf_object__open(test->file);
+ if (CHECK(IS_ERR(obj), "obj: %ld", PTR_ERR(obj)))
+ return PTR_ERR(obj);
+
+ err = bpf_object__btf_fd(obj);
+ if (CHECK(err == -1, "bpf_object__btf_fd: -1"))
+ goto done;
+
+ prog = bpf_program__next(NULL, obj);
+ if (CHECK(!prog, "Cannot find bpf_prog")) {
+ err = -1;
+ goto done;
+ }
+
+ bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT);
+ err = bpf_object__load(obj);
+ if (CHECK(err < 0, "bpf_object__load: %d", err))
+ goto done;
+
+ map = bpf_object__find_map_by_name(obj, "btf_map");
+ if (CHECK(!map, "btf_map not found")) {
+ err = -1;
+ goto done;
+ }
+
+ err = (bpf_map__btf_key_type_id(map) == 0 || bpf_map__btf_value_type_id(map) == 0)
+ != test->btf_kv_notfound;
+ if (CHECK(err, "btf_key_type_id:%u btf_value_type_id:%u test->btf_kv_notfound:%u",
+ bpf_map__btf_key_type_id(map), bpf_map__btf_value_type_id(map),
+ test->btf_kv_notfound))
+ goto done;
+
+ fprintf(stderr, "OK");
+
+done:
+ bpf_object__close(obj);
+ return err;
+}
+
+static int test_file(void)
+{
+ unsigned int i;
+ int err = 0;
+
+ if (args.file_test_num)
+ return count_result(do_test_file(args.file_test_num));
+
+ for (i = 1; i <= ARRAY_SIZE(file_tests); i++)
+ err |= count_result(do_test_file(i));
+
+ return err;
+}
+
+const char *pprint_enum_str[] = {
+ "ENUM_ZERO",
+ "ENUM_ONE",
+ "ENUM_TWO",
+ "ENUM_THREE",
+};
+
+struct pprint_mapv {
+ uint32_t ui32;
+ uint16_t ui16;
+ /* 2 bytes hole */
+ int32_t si32;
+ uint32_t unused_bits2a:2,
+ bits28:28,
+ unused_bits2b:2;
+ union {
+ uint64_t ui64;
+ uint8_t ui8a[8];
+ };
+ enum {
+ ENUM_ZERO,
+ ENUM_ONE,
+ ENUM_TWO,
+ ENUM_THREE,
+ } aenum;
+};
+
+static struct btf_raw_test pprint_test = {
+ .descr = "BTF pretty print test #1",
+ .raw_types = {
+ /* unsighed char */ /* [1] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
+ /* unsigned short */ /* [2] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2),
+ /* unsigned int */ /* [3] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4),
+ /* int */ /* [4] */
+ BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4),
+ /* unsigned long long */ /* [5] */
+ BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8),
+ /* 2 bits */ /* [6] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 2, 2),
+ /* 28 bits */ /* [7] */
+ BTF_TYPE_INT_ENC(0, 0, 0, 28, 4),
+ /* uint8_t[8] */ /* [8] */
+ BTF_TYPE_ARRAY_ENC(9, 1, 8),
+ /* typedef unsigned char uint8_t */ /* [9] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 1),
+ /* typedef unsigned short uint16_t */ /* [10] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 2),
+ /* typedef unsigned int uint32_t */ /* [11] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 3),
+ /* typedef int int32_t */ /* [12] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 4),
+ /* typedef unsigned long long uint64_t *//* [13] */
+ BTF_TYPEDEF_ENC(NAME_TBD, 5),
+ /* union (anon) */ /* [14] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8),
+ BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */
+ BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */
+ /* enum (anon) */ /* [15] */
+ BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4),
+ BTF_ENUM_ENC(NAME_TBD, 0),
+ BTF_ENUM_ENC(NAME_TBD, 1),
+ BTF_ENUM_ENC(NAME_TBD, 2),
+ BTF_ENUM_ENC(NAME_TBD, 3),
+ /* struct pprint_mapv */ /* [16] */
+ BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28),
+ BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */
+ BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */
+ BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */
+ BTF_MEMBER_ENC(NAME_TBD, 6, 96), /* unused_bits2a */
+ BTF_MEMBER_ENC(NAME_TBD, 7, 98), /* bits28 */
+ BTF_MEMBER_ENC(NAME_TBD, 6, 126), /* unused_bits2b */
+ BTF_MEMBER_ENC(0, 14, 128), /* union (anon) */
+ BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */
+ BTF_END_RAW,
+ },
+ .str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
+ .str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
+ .map_type = BPF_MAP_TYPE_ARRAY,
+ .map_name = "pprint_test",
+ .key_size = sizeof(unsigned int),
+ .value_size = sizeof(struct pprint_mapv),
+ .key_type_id = 3, /* unsigned int */
+ .value_type_id = 16, /* struct pprint_mapv */
+ .max_entries = 128 * 1024,
+};
+
+static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
+{
+ v->ui32 = i;
+ v->si32 = -i;
+ v->unused_bits2a = 3;
+ v->bits28 = i;
+ v->unused_bits2b = 3;
+ v->ui64 = i;
+ v->aenum = i & 0x03;
+}
+
+static int test_pprint(void)
+{
+ const struct btf_raw_test *test = &pprint_test;
+ struct bpf_create_map_attr create_attr = {};
+ int map_fd = -1, btf_fd = -1;
+ struct pprint_mapv mapv = {};
+ unsigned int raw_btf_size;
+ char expected_line[255];
+ FILE *pin_file = NULL;
+ char pin_path[255];
+ size_t line_len = 0;
+ char *line = NULL;
+ unsigned int key;
+ uint8_t *raw_btf;
+ ssize_t nread;
+ int err, ret;
+
+ fprintf(stderr, "%s......", test->descr);
+ raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types,
+ test->str_sec, test->str_sec_size,
+ &raw_btf_size);
+
+ if (!raw_btf)
+ return -1;
+
+ *btf_log_buf = '\0';
+ btf_fd = bpf_load_btf(raw_btf, raw_btf_size,
+ btf_log_buf, BTF_LOG_BUF_SIZE,
+ args.always_log);
+ free(raw_btf);
+
+ if (CHECK(btf_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ create_attr.name = test->map_name;
+ create_attr.map_type = test->map_type;
+ create_attr.key_size = test->key_size;
+ create_attr.value_size = test->value_size;
+ create_attr.max_entries = test->max_entries;
+ create_attr.btf_fd = btf_fd;
+ create_attr.btf_key_type_id = test->key_type_id;
+ create_attr.btf_value_type_id = test->value_type_id;
+
+ map_fd = bpf_create_map_xattr(&create_attr);
+ if (CHECK(map_fd == -1, "errno:%d", errno)) {
+ err = -1;
+ goto done;
+ }
+
+ ret = snprintf(pin_path, sizeof(pin_path), "%s/%s",
+ "/sys/fs/bpf", test->map_name);
+
+ if (CHECK(ret == sizeof(pin_path), "pin_path %s/%s is too long",
+ "/sys/fs/bpf", test->map_name)) {
+ err = -1;
+ goto done;
+ }
+
+ err = bpf_obj_pin(map_fd, pin_path);
+ if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno))
+ goto done;
+
+ for (key = 0; key < test->max_entries; key++) {
+ set_pprint_mapv(&mapv, key);
+ bpf_map_update_elem(map_fd, &key, &mapv, 0);
+ }
+
+ pin_file = fopen(pin_path, "r");
+ if (CHECK(!pin_file, "fopen(%s): errno:%d", pin_path, errno)) {
+ err = -1;
+ goto done;
+ }
+
+ /* Skip lines start with '#' */
+ while ((nread = getline(&line, &line_len, pin_file)) > 0 &&
+ *line == '#')
+ ;
+
+ if (CHECK(nread <= 0, "Unexpected EOF")) {
+ err = -1;
+ goto done;
+ }
+
+ key = 0;
+ do {
+ ssize_t nexpected_line;
+
+ set_pprint_mapv(&mapv, key);
+ nexpected_line = snprintf(expected_line, sizeof(expected_line),
+ "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
+ key,
+ mapv.ui32, mapv.si32,
+ mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
+ mapv.ui64,
+ mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3],
+ mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7],
+ pprint_enum_str[mapv.aenum]);
+
+ if (CHECK(nexpected_line == sizeof(expected_line),
+ "expected_line is too long")) {
+ err = -1;
+ goto done;
+ }
+
+ if (strcmp(expected_line, line)) {
+ err = -1;
+ fprintf(stderr, "unexpected pprint output\n");
+ fprintf(stderr, "expected: %s", expected_line);
+ fprintf(stderr, " read: %s", line);
+ goto done;
+ }
+
+ nread = getline(&line, &line_len, pin_file);
+ } while (++key < test->max_entries && nread > 0);
+
+ if (CHECK(key < test->max_entries,
+ "Unexpected EOF. key:%u test->max_entries:%u",
+ key, test->max_entries)) {
+ err = -1;
+ goto done;
+ }
+
+ if (CHECK(nread > 0, "Unexpected extra pprint output: %s", line)) {
+ err = -1;
+ goto done;
+ }
+
+ err = 0;
+
+done:
+ if (!err)
+ fprintf(stderr, "OK");
+ if (*btf_log_buf && (err || args.always_log))
+ fprintf(stderr, "\n%s", btf_log_buf);
+ if (btf_fd != -1)
+ close(btf_fd);
+ if (map_fd != -1)
+ close(map_fd);
+ if (pin_file)
+ fclose(pin_file);
+ unlink(pin_path);
+ free(line);
+
+ return err;
+}
+
+static void usage(const char *cmd)
+{
+ fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
+ cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests),
+ ARRAY_SIZE(file_tests));
+}
+
+static int parse_args(int argc, char **argv)
+{
+ const char *optstr = "lpf:r:g:";
+ int opt;
+
+ while ((opt = getopt(argc, argv, optstr)) != -1) {
+ switch (opt) {
+ case 'l':
+ args.always_log = true;
+ break;
+ case 'f':
+ args.file_test_num = atoi(optarg);
+ args.file_test = true;
+ break;
+ case 'r':
+ args.raw_test_num = atoi(optarg);
+ args.raw_test = true;
+ break;
+ case 'g':
+ args.get_info_test_num = atoi(optarg);
+ args.get_info_test = true;
+ break;
+ case 'p':
+ args.pprint_test = true;
+ break;
+ case 'h':
+ usage(argv[0]);
+ exit(0);
+ default:
+ usage(argv[0]);
+ return -1;
+ }
+ }
+
+ if (args.raw_test_num &&
+ (args.raw_test_num < 1 ||
+ args.raw_test_num > ARRAY_SIZE(raw_tests))) {
+ fprintf(stderr, "BTF raw test number must be [1 - %zu]\n",
+ ARRAY_SIZE(raw_tests));
+ return -1;
+ }
+
+ if (args.file_test_num &&
+ (args.file_test_num < 1 ||
+ args.file_test_num > ARRAY_SIZE(file_tests))) {
+ fprintf(stderr, "BTF file test number must be [1 - %zu]\n",
+ ARRAY_SIZE(file_tests));
+ return -1;
+ }
+
+ if (args.get_info_test_num &&
+ (args.get_info_test_num < 1 ||
+ args.get_info_test_num > ARRAY_SIZE(get_info_tests))) {
+ fprintf(stderr, "BTF get info test number must be [1 - %zu]\n",
+ ARRAY_SIZE(get_info_tests));
+ return -1;
+ }
+
+ return 0;
+}
+
+static void print_summary(void)
+{
+ fprintf(stderr, "PASS:%u SKIP:%u FAIL:%u\n",
+ pass_cnt - skip_cnt, skip_cnt, error_cnt);
+}
+
+int main(int argc, char **argv)
+{
+ int err = 0;
+
+ err = parse_args(argc, argv);
+ if (err)
+ return err;
+
+ if (args.always_log)
+ libbpf_set_print(__base_pr, __base_pr, __base_pr);
+
+ if (args.raw_test)
+ err |= test_raw();
+
+ if (args.get_info_test)
+ err |= test_get_info();
+
+ if (args.file_test)
+ err |= test_file();
+
+ if (args.pprint_test)
+ err |= count_result(test_pprint());
+
+ if (args.raw_test || args.get_info_test || args.file_test ||
+ args.pprint_test)
+ goto done;
+
+ err |= test_raw();
+ err |= test_get_info();
+ err |= test_file();
+
+done:
+ print_summary();
+ return err;
+}
diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c
new file mode 100644
index 000000000000..8c7ca096ecf2
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_btf_haskv.c
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct ipv_counts {
+ unsigned int v4;
+ unsigned int v6;
+};
+
+typedef int btf_map_key;
+typedef struct ipv_counts btf_map_value;
+btf_map_key dumm_key;
+btf_map_value dummy_value;
+
+struct bpf_map_def SEC("maps") btf_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct ipv_counts),
+ .max_entries = 4,
+};
+
+struct dummy_tracepoint_args {
+ unsigned long long pad;
+ struct sock *sock;
+};
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+ struct ipv_counts *counts;
+ int key = 0;
+
+ if (!arg->sock)
+ return 0;
+
+ counts = bpf_map_lookup_elem(&btf_map, &key);
+ if (!counts)
+ return 0;
+
+ counts->v6++;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c
new file mode 100644
index 000000000000..0ed8e088eebf
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_btf_nokv.c
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+
+struct ipv_counts {
+ unsigned int v4;
+ unsigned int v6;
+};
+
+struct bpf_map_def SEC("maps") btf_map = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(struct ipv_counts),
+ .max_entries = 4,
+};
+
+struct dummy_tracepoint_args {
+ unsigned long long pad;
+ struct sock *sock;
+};
+
+SEC("dummy_tracepoint")
+int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
+{
+ struct ipv_counts *counts;
+ int key = 0;
+
+ if (!arg->sock)
+ return 0;
+
+ counts = bpf_map_lookup_elem(&btf_map, &key);
+ if (!counts)
+ return 0;
+
+ counts->v6++;
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/test_get_stack_rawtp.c
new file mode 100644
index 000000000000..f6d9f238e00a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_get_stack_rawtp.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+/* Permit pretty deep stack traces */
+#define MAX_STACK_RAWTP 100
+struct stack_trace_t {
+ int pid;
+ int kern_stack_size;
+ int user_stack_size;
+ int user_stack_buildid_size;
+ __u64 kern_stack[MAX_STACK_RAWTP];
+ __u64 user_stack[MAX_STACK_RAWTP];
+ struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+struct bpf_map_def SEC("maps") perfmap = {
+ .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(__u32),
+ .max_entries = 2,
+};
+
+struct bpf_map_def SEC("maps") stackdata_map = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct stack_trace_t),
+ .max_entries = 1,
+};
+
+/* Allocate per-cpu space twice the needed. For the code below
+ * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
+ * if (usize < 0)
+ * return 0;
+ * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
+ *
+ * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64),
+ * verifier will complain that access "raw_data + usize"
+ * with size "max_len - usize" may be out of bound.
+ * The maximum "raw_data + usize" is "raw_data + max_len"
+ * and the maximum "max_len - usize" is "max_len", verifier
+ * concludes that the maximum buffer access range is
+ * "raw_data[0...max_len * 2 - 1]" and hence reject the program.
+ *
+ * Doubling the to-be-used max buffer size can fix this verifier
+ * issue and avoid complicated C programming massaging.
+ * This is an acceptable workaround since there is one entry here.
+ */
+struct bpf_map_def SEC("maps") rawdata_map = {
+ .type = BPF_MAP_TYPE_PERCPU_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2,
+ .max_entries = 1,
+};
+
+SEC("tracepoint/raw_syscalls/sys_enter")
+int bpf_prog1(void *ctx)
+{
+ int max_len, max_buildid_len, usize, ksize, total_size;
+ struct stack_trace_t *data;
+ void *raw_data;
+ __u32 key = 0;
+
+ data = bpf_map_lookup_elem(&stackdata_map, &key);
+ if (!data)
+ return 0;
+
+ max_len = MAX_STACK_RAWTP * sizeof(__u64);
+ max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id);
+ data->pid = bpf_get_current_pid_tgid();
+ data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack,
+ max_len, 0);
+ data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len,
+ BPF_F_USER_STACK);
+ data->user_stack_buildid_size = bpf_get_stack(
+ ctx, data->user_stack_buildid, max_buildid_len,
+ BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+ bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data));
+
+ /* write both kernel and user stacks to the same buffer */
+ raw_data = bpf_map_lookup_elem(&rawdata_map, &key);
+ if (!raw_data)
+ return 0;
+
+ usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK);
+ if (usize < 0)
+ return 0;
+
+ ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0);
+ if (ksize < 0)
+ return 0;
+
+ total_size = usize + ksize;
+ if (total_size > 0 && total_size <= max_len)
+ bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
+__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2.sh b/tools/testing/selftests/bpf/test_lirc_mode2.sh
new file mode 100755
index 000000000000..ce2e15e4f976
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lirc_mode2.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+GREEN='\033[0;92m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+modprobe rc-loopback
+
+for i in /sys/class/rc/rc*
+do
+ if grep -q DRV_NAME=rc-loopback $i/uevent
+ then
+ LIRCDEV=$(grep DEVNAME= $i/lirc*/uevent | sed sQDEVNAME=Q/dev/Q)
+ fi
+done
+
+if [ -n $LIRCDEV ];
+then
+ TYPE=lirc_mode2
+ ./test_lirc_mode2_user $LIRCDEV
+ ret=$?
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ else
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+ fi
+fi
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_kern.c b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
new file mode 100644
index 000000000000..ba26855563a5
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_kern.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+// test ir decoder
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+#include <linux/bpf.h>
+#include <linux/lirc.h>
+#include "bpf_helpers.h"
+
+SEC("lirc_mode2")
+int bpf_decoder(unsigned int *sample)
+{
+ if (LIRC_IS_PULSE(*sample)) {
+ unsigned int duration = LIRC_VALUE(*sample);
+
+ if (duration & 0x10000)
+ bpf_rc_keydown(sample, 0x40, duration & 0xffff, 0);
+ }
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lirc_mode2_user.c b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
new file mode 100644
index 000000000000..d470d63c33db
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lirc_mode2_user.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+// test ir decoder
+//
+// Copyright (C) 2018 Sean Young <sean@mess.org>
+
+// A lirc chardev is a device representing a consumer IR (cir) device which
+// can receive infrared signals from remote control and/or transmit IR.
+//
+// IR is sent as a series of pulses and space somewhat like morse code. The
+// BPF program can decode this into scancodes so that rc-core can translate
+// this into input key codes using the rc keymap.
+//
+// This test works by sending IR over rc-loopback, so the IR is processed by
+// BPF and then decoded into scancodes. The lirc chardev must be the one
+// associated with rc-loopback, see the output of ir-keytable(1).
+//
+// The following CONFIG options must be enabled for the test to succeed:
+// CONFIG_RC_CORE=y
+// CONFIG_BPF_RAWIR_EVENT=y
+// CONFIG_RC_LOOPBACK=y
+
+// Steps:
+// 1. Open the /dev/lircN device for rc-loopback (given on command line)
+// 2. Attach bpf_lirc_mode2 program which decodes some IR.
+// 3. Send some IR to the same IR device; since it is loopback, this will
+// end up in the bpf program
+// 4. bpf program should decode IR and report keycode
+// 5. We can read keycode from same /dev/lirc device
+
+#include <linux/bpf.h>
+#include <linux/lirc.h>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <poll.h>
+#include <sys/types.h>
+#include <sys/ioctl.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "bpf_util.h"
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+int main(int argc, char **argv)
+{
+ struct bpf_object *obj;
+ int ret, lircfd, progfd, mode;
+ int testir = 0x1dead;
+ u32 prog_ids[10], prog_flags[10], prog_cnt;
+
+ if (argc != 2) {
+ printf("Usage: %s /dev/lircN\n", argv[0]);
+ return 2;
+ }
+
+ ret = bpf_prog_load("test_lirc_mode2_kern.o",
+ BPF_PROG_TYPE_LIRC_MODE2, &obj, &progfd);
+ if (ret) {
+ printf("Failed to load bpf program\n");
+ return 1;
+ }
+
+ lircfd = open(argv[1], O_RDWR | O_NONBLOCK);
+ if (lircfd == -1) {
+ printf("failed to open lirc device %s: %m\n", argv[1]);
+ return 1;
+ }
+
+ /* Let's try detach it before it was ever attached */
+ ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+ if (ret != -1 || errno != ENOENT) {
+ printf("bpf_prog_detach2 not attached should fail: %m\n");
+ return 1;
+ }
+
+ mode = LIRC_MODE_SCANCODE;
+ if (ioctl(lircfd, LIRC_SET_REC_MODE, &mode)) {
+ printf("failed to set rec mode: %m\n");
+ return 1;
+ }
+
+ prog_cnt = 10;
+ ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+ &prog_cnt);
+ if (ret) {
+ printf("Failed to query bpf programs on lirc device: %m\n");
+ return 1;
+ }
+
+ if (prog_cnt != 0) {
+ printf("Expected nothing to be attached\n");
+ return 1;
+ }
+
+ ret = bpf_prog_attach(progfd, lircfd, BPF_LIRC_MODE2, 0);
+ if (ret) {
+ printf("Failed to attach bpf to lirc device: %m\n");
+ return 1;
+ }
+
+ /* Write raw IR */
+ ret = write(lircfd, &testir, sizeof(testir));
+ if (ret != sizeof(testir)) {
+ printf("Failed to send test IR message: %m\n");
+ return 1;
+ }
+
+ struct pollfd pfd = { .fd = lircfd, .events = POLLIN };
+ struct lirc_scancode lsc;
+
+ poll(&pfd, 1, 100);
+
+ /* Read decoded IR */
+ ret = read(lircfd, &lsc, sizeof(lsc));
+ if (ret != sizeof(lsc)) {
+ printf("Failed to read decoded IR: %m\n");
+ return 1;
+ }
+
+ if (lsc.scancode != 0xdead || lsc.rc_proto != 64) {
+ printf("Incorrect scancode decoded\n");
+ return 1;
+ }
+
+ prog_cnt = 10;
+ ret = bpf_prog_query(lircfd, BPF_LIRC_MODE2, 0, prog_flags, prog_ids,
+ &prog_cnt);
+ if (ret) {
+ printf("Failed to query bpf programs on lirc device: %m\n");
+ return 1;
+ }
+
+ if (prog_cnt != 1) {
+ printf("Expected one program to be attached\n");
+ return 1;
+ }
+
+ /* Let's try detaching it now it is actually attached */
+ ret = bpf_prog_detach2(progfd, lircfd, BPF_LIRC_MODE2);
+ if (ret) {
+ printf("bpf_prog_detach2: returned %m\n");
+ return 1;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.c b/tools/testing/selftests/bpf/test_lwt_seg6local.c
new file mode 100644
index 000000000000..0575751bc1bc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.c
@@ -0,0 +1,437 @@
+#include <stddef.h>
+#include <inttypes.h>
+#include <errno.h>
+#include <linux/seg6_local.h>
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define bpf_printk(fmt, ...) \
+({ \
+ char ____fmt[] = fmt; \
+ bpf_trace_printk(____fmt, sizeof(____fmt), \
+ ##__VA_ARGS__); \
+})
+
+/* Packet parsing state machine helpers. */
+#define cursor_advance(_cursor, _len) \
+ ({ void *_tmp = _cursor; _cursor += _len; _tmp; })
+
+#define SR6_FLAG_ALERT (1 << 4)
+
+#define htonll(x) ((bpf_htonl(1)) == 1 ? (x) : ((uint64_t)bpf_htonl((x) & \
+ 0xFFFFFFFF) << 32) | bpf_htonl((x) >> 32))
+#define ntohll(x) ((bpf_ntohl(1)) == 1 ? (x) : ((uint64_t)bpf_ntohl((x) & \
+ 0xFFFFFFFF) << 32) | bpf_ntohl((x) >> 32))
+#define BPF_PACKET_HEADER __attribute__((packed))
+
+struct ip6_t {
+ unsigned int ver:4;
+ unsigned int priority:8;
+ unsigned int flow_label:20;
+ unsigned short payload_len;
+ unsigned char next_header;
+ unsigned char hop_limit;
+ unsigned long long src_hi;
+ unsigned long long src_lo;
+ unsigned long long dst_hi;
+ unsigned long long dst_lo;
+} BPF_PACKET_HEADER;
+
+struct ip6_addr_t {
+ unsigned long long hi;
+ unsigned long long lo;
+} BPF_PACKET_HEADER;
+
+struct ip6_srh_t {
+ unsigned char nexthdr;
+ unsigned char hdrlen;
+ unsigned char type;
+ unsigned char segments_left;
+ unsigned char first_segment;
+ unsigned char flags;
+ unsigned short tag;
+
+ struct ip6_addr_t segments[0];
+} BPF_PACKET_HEADER;
+
+struct sr6_tlv_t {
+ unsigned char type;
+ unsigned char len;
+ unsigned char value[0];
+} BPF_PACKET_HEADER;
+
+__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb)
+{
+ void *cursor, *data_end;
+ struct ip6_srh_t *srh;
+ struct ip6_t *ip;
+ uint8_t *ipver;
+
+ data_end = (void *)(long)skb->data_end;
+ cursor = (void *)(long)skb->data;
+ ipver = (uint8_t *)cursor;
+
+ if ((void *)ipver + sizeof(*ipver) > data_end)
+ return NULL;
+
+ if ((*ipver >> 4) != 6)
+ return NULL;
+
+ ip = cursor_advance(cursor, sizeof(*ip));
+ if ((void *)ip + sizeof(*ip) > data_end)
+ return NULL;
+
+ if (ip->next_header != 43)
+ return NULL;
+
+ srh = cursor_advance(cursor, sizeof(*srh));
+ if ((void *)srh + sizeof(*srh) > data_end)
+ return NULL;
+
+ if (srh->type != 4)
+ return NULL;
+
+ return srh;
+}
+
+__attribute__((always_inline))
+int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad,
+ uint32_t old_pad, uint32_t pad_off)
+{
+ int err;
+
+ if (new_pad != old_pad) {
+ err = bpf_lwt_seg6_adjust_srh(skb, pad_off,
+ (int) new_pad - (int) old_pad);
+ if (err)
+ return err;
+ }
+
+ if (new_pad > 0) {
+ char pad_tlv_buf[16] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0, 0, 0};
+ struct sr6_tlv_t *pad_tlv = (struct sr6_tlv_t *) pad_tlv_buf;
+
+ pad_tlv->type = SR6_TLV_PADDING;
+ pad_tlv->len = new_pad - 2;
+
+ err = bpf_lwt_seg6_store_bytes(skb, pad_off,
+ (void *)pad_tlv_buf, new_pad);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+__attribute__((always_inline))
+int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh,
+ uint32_t *tlv_off, uint32_t *pad_size,
+ uint32_t *pad_off)
+{
+ uint32_t srh_off, cur_off;
+ int offset_valid = 0;
+ int err;
+
+ srh_off = (char *)srh - (char *)(long)skb->data;
+ // cur_off = end of segments, start of possible TLVs
+ cur_off = srh_off + sizeof(*srh) +
+ sizeof(struct ip6_addr_t) * (srh->first_segment + 1);
+
+ *pad_off = 0;
+
+ // we can only go as far as ~10 TLVs due to the BPF max stack size
+ #pragma clang loop unroll(full)
+ for (int i = 0; i < 10; i++) {
+ struct sr6_tlv_t tlv;
+
+ if (cur_off == *tlv_off)
+ offset_valid = 1;
+
+ if (cur_off >= srh_off + ((srh->hdrlen + 1) << 3))
+ break;
+
+ err = bpf_skb_load_bytes(skb, cur_off, &tlv, sizeof(tlv));
+ if (err)
+ return err;
+
+ if (tlv.type == SR6_TLV_PADDING) {
+ *pad_size = tlv.len + sizeof(tlv);
+ *pad_off = cur_off;
+
+ if (*tlv_off == srh_off) {
+ *tlv_off = cur_off;
+ offset_valid = 1;
+ }
+ break;
+
+ } else if (tlv.type == SR6_TLV_HMAC) {
+ break;
+ }
+
+ cur_off += sizeof(tlv) + tlv.len;
+ } // we reached the padding or HMAC TLVs, or the end of the SRH
+
+ if (*pad_off == 0)
+ *pad_off = cur_off;
+
+ if (*tlv_off == -1)
+ *tlv_off = cur_off;
+ else if (!offset_valid)
+ return -EINVAL;
+
+ return 0;
+}
+
+__attribute__((always_inline))
+int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off,
+ struct sr6_tlv_t *itlv, uint8_t tlv_size)
+{
+ uint32_t srh_off = (char *)srh - (char *)(long)skb->data;
+ uint8_t len_remaining, new_pad;
+ uint32_t pad_off = 0;
+ uint32_t pad_size = 0;
+ uint32_t partial_srh_len;
+ int err;
+
+ if (tlv_off != -1)
+ tlv_off += srh_off;
+
+ if (itlv->type == SR6_TLV_PADDING || itlv->type == SR6_TLV_HMAC)
+ return -EINVAL;
+
+ err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off);
+ if (err)
+ return err;
+
+ err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, sizeof(*itlv) + itlv->len);
+ if (err)
+ return err;
+
+ err = bpf_lwt_seg6_store_bytes(skb, tlv_off, (void *)itlv, tlv_size);
+ if (err)
+ return err;
+
+ // the following can't be moved inside update_tlv_pad because the
+ // bpf verifier has some issues with it
+ pad_off += sizeof(*itlv) + itlv->len;
+ partial_srh_len = pad_off - srh_off;
+ len_remaining = partial_srh_len % 8;
+ new_pad = 8 - len_remaining;
+
+ if (new_pad == 1) // cannot pad for 1 byte only
+ new_pad = 9;
+ else if (new_pad == 8)
+ new_pad = 0;
+
+ return update_tlv_pad(skb, new_pad, pad_size, pad_off);
+}
+
+__attribute__((always_inline))
+int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh,
+ uint32_t tlv_off)
+{
+ uint32_t srh_off = (char *)srh - (char *)(long)skb->data;
+ uint8_t len_remaining, new_pad;
+ uint32_t partial_srh_len;
+ uint32_t pad_off = 0;
+ uint32_t pad_size = 0;
+ struct sr6_tlv_t tlv;
+ int err;
+
+ tlv_off += srh_off;
+
+ err = is_valid_tlv_boundary(skb, srh, &tlv_off, &pad_size, &pad_off);
+ if (err)
+ return err;
+
+ err = bpf_skb_load_bytes(skb, tlv_off, &tlv, sizeof(tlv));
+ if (err)
+ return err;
+
+ err = bpf_lwt_seg6_adjust_srh(skb, tlv_off, -(sizeof(tlv) + tlv.len));
+ if (err)
+ return err;
+
+ pad_off -= sizeof(tlv) + tlv.len;
+ partial_srh_len = pad_off - srh_off;
+ len_remaining = partial_srh_len % 8;
+ new_pad = 8 - len_remaining;
+ if (new_pad == 1) // cannot pad for 1 byte only
+ new_pad = 9;
+ else if (new_pad == 8)
+ new_pad = 0;
+
+ return update_tlv_pad(skb, new_pad, pad_size, pad_off);
+}
+
+__attribute__((always_inline))
+int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh)
+{
+ int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) +
+ ((srh->first_segment + 1) << 4);
+ struct sr6_tlv_t tlv;
+
+ if (bpf_skb_load_bytes(skb, tlv_offset, &tlv, sizeof(struct sr6_tlv_t)))
+ return 0;
+
+ if (tlv.type == SR6_TLV_EGRESS && tlv.len == 18) {
+ struct ip6_addr_t egr_addr;
+
+ if (bpf_skb_load_bytes(skb, tlv_offset + 4, &egr_addr, 16))
+ return 0;
+
+ // check if egress TLV value is correct
+ if (ntohll(egr_addr.hi) == 0xfd00000000000000 &&
+ ntohll(egr_addr.lo) == 0x4)
+ return 1;
+ }
+
+ return 0;
+}
+
+// This function will push a SRH with segments fd00::1, fd00::2, fd00::3,
+// fd00::4
+SEC("encap_srh")
+int __encap_srh(struct __sk_buff *skb)
+{
+ unsigned long long hi = 0xfd00000000000000;
+ struct ip6_addr_t *seg;
+ struct ip6_srh_t *srh;
+ char srh_buf[72]; // room for 4 segments
+ int err;
+
+ srh = (struct ip6_srh_t *)srh_buf;
+ srh->nexthdr = 0;
+ srh->hdrlen = 8;
+ srh->type = 4;
+ srh->segments_left = 3;
+ srh->first_segment = 3;
+ srh->flags = 0;
+ srh->tag = 0;
+
+ seg = (struct ip6_addr_t *)((char *)srh + sizeof(*srh));
+
+ #pragma clang loop unroll(full)
+ for (unsigned long long lo = 0; lo < 4; lo++) {
+ seg->lo = htonll(4 - lo);
+ seg->hi = htonll(hi);
+ seg = (struct ip6_addr_t *)((char *)seg + sizeof(*seg));
+ }
+
+ err = bpf_lwt_push_encap(skb, 0, (void *)srh, sizeof(srh_buf));
+ if (err)
+ return BPF_DROP;
+
+ return BPF_REDIRECT;
+}
+
+// Add an Egress TLV fc00::4, add the flag A,
+// and apply End.X action to fc42::1
+SEC("add_egr_x")
+int __add_egr_x(struct __sk_buff *skb)
+{
+ unsigned long long hi = 0xfc42000000000000;
+ unsigned long long lo = 0x1;
+ struct ip6_srh_t *srh = get_srh(skb);
+ uint8_t new_flags = SR6_FLAG_ALERT;
+ struct ip6_addr_t addr;
+ int err, offset;
+
+ if (srh == NULL)
+ return BPF_DROP;
+
+ uint8_t tlv[20] = {2, 18, 0, 0, 0xfd, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+ 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x4};
+
+ err = add_tlv(skb, srh, (srh->hdrlen+1) << 3,
+ (struct sr6_tlv_t *)&tlv, 20);
+ if (err)
+ return BPF_DROP;
+
+ offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags);
+ err = bpf_lwt_seg6_store_bytes(skb, offset,
+ (void *)&new_flags, sizeof(new_flags));
+ if (err)
+ return BPF_DROP;
+
+ addr.lo = htonll(lo);
+ addr.hi = htonll(hi);
+ err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_X,
+ (void *)&addr, sizeof(addr));
+ if (err)
+ return BPF_DROP;
+ return BPF_REDIRECT;
+}
+
+// Pop the Egress TLV, reset the flags, change the tag 2442 and finally do a
+// simple End action
+SEC("pop_egr")
+int __pop_egr(struct __sk_buff *skb)
+{
+ struct ip6_srh_t *srh = get_srh(skb);
+ uint16_t new_tag = bpf_htons(2442);
+ uint8_t new_flags = 0;
+ int err, offset;
+
+ if (srh == NULL)
+ return BPF_DROP;
+
+ if (srh->flags != SR6_FLAG_ALERT)
+ return BPF_DROP;
+
+ if (srh->hdrlen != 11) // 4 segments + Egress TLV + Padding TLV
+ return BPF_DROP;
+
+ if (!has_egr_tlv(skb, srh))
+ return BPF_DROP;
+
+ err = delete_tlv(skb, srh, 8 + (srh->first_segment + 1) * 16);
+ if (err)
+ return BPF_DROP;
+
+ offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, flags);
+ if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_flags,
+ sizeof(new_flags)))
+ return BPF_DROP;
+
+ offset = sizeof(struct ip6_t) + offsetof(struct ip6_srh_t, tag);
+ if (bpf_lwt_seg6_store_bytes(skb, offset, (void *)&new_tag,
+ sizeof(new_tag)))
+ return BPF_DROP;
+
+ return BPF_OK;
+}
+
+// Inspect if the Egress TLV and flag have been removed, if the tag is correct,
+// then apply a End.T action to reach the last segment
+SEC("inspect_t")
+int __inspect_t(struct __sk_buff *skb)
+{
+ struct ip6_srh_t *srh = get_srh(skb);
+ int table = 117;
+ int err;
+
+ if (srh == NULL)
+ return BPF_DROP;
+
+ if (srh->flags != 0)
+ return BPF_DROP;
+
+ if (srh->tag != bpf_htons(2442))
+ return BPF_DROP;
+
+ if (srh->hdrlen != 8) // 4 segments
+ return BPF_DROP;
+
+ err = bpf_lwt_seg6_action(skb, SEG6_LOCAL_ACTION_END_T,
+ (void *)&table, sizeof(table));
+
+ if (err)
+ return BPF_DROP;
+
+ return BPF_REDIRECT;
+}
+
+char __license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_lwt_seg6local.sh b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
new file mode 100755
index 000000000000..1c77994b5e71
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_lwt_seg6local.sh
@@ -0,0 +1,140 @@
+#!/bin/bash
+# Connects 6 network namespaces through veths.
+# Each NS may have different IPv6 global scope addresses :
+# NS1 ---- NS2 ---- NS3 ---- NS4 ---- NS5 ---- NS6
+# fb00::1 fd00::1 fd00::2 fd00::3 fb00::6
+# fc42::1 fd00::4
+#
+# All IPv6 packets going to fb00::/16 through NS2 will be encapsulated in a
+# IPv6 header with a Segment Routing Header, with segments :
+# fd00::1 -> fd00::2 -> fd00::3 -> fd00::4
+#
+# 3 fd00::/16 IPv6 addresses are binded to seg6local End.BPF actions :
+# - fd00::1 : add a TLV, change the flags and apply a End.X action to fc42::1
+# - fd00::2 : remove the TLV, change the flags, add a tag
+# - fd00::3 : apply an End.T action to fd00::4, through routing table 117
+#
+# fd00::4 is a simple Segment Routing node decapsulating the inner IPv6 packet.
+# Each End.BPF action will validate the operations applied on the SRH by the
+# previous BPF program in the chain, otherwise the packet is dropped.
+#
+# An UDP datagram is sent from fb00::1 to fb00::6. The test succeeds if this
+# datagram can be read on NS6 when binding to fb00::6.
+
+TMP_FILE="/tmp/selftest_lwt_seg6local.txt"
+
+cleanup()
+{
+ if [ "$?" = "0" ]; then
+ echo "selftests: test_lwt_seg6local [PASS]";
+ else
+ echo "selftests: test_lwt_seg6local [FAILED]";
+ fi
+
+ set +e
+ ip netns del ns1 2> /dev/null
+ ip netns del ns2 2> /dev/null
+ ip netns del ns3 2> /dev/null
+ ip netns del ns4 2> /dev/null
+ ip netns del ns5 2> /dev/null
+ ip netns del ns6 2> /dev/null
+ rm -f $TMP_FILE
+}
+
+set -e
+
+ip netns add ns1
+ip netns add ns2
+ip netns add ns3
+ip netns add ns4
+ip netns add ns5
+ip netns add ns6
+
+trap cleanup 0 2 3 6 9
+
+ip link add veth1 type veth peer name veth2
+ip link add veth3 type veth peer name veth4
+ip link add veth5 type veth peer name veth6
+ip link add veth7 type veth peer name veth8
+ip link add veth9 type veth peer name veth10
+
+ip link set veth1 netns ns1
+ip link set veth2 netns ns2
+ip link set veth3 netns ns2
+ip link set veth4 netns ns3
+ip link set veth5 netns ns3
+ip link set veth6 netns ns4
+ip link set veth7 netns ns4
+ip link set veth8 netns ns5
+ip link set veth9 netns ns5
+ip link set veth10 netns ns6
+
+ip netns exec ns1 ip link set dev veth1 up
+ip netns exec ns2 ip link set dev veth2 up
+ip netns exec ns2 ip link set dev veth3 up
+ip netns exec ns3 ip link set dev veth4 up
+ip netns exec ns3 ip link set dev veth5 up
+ip netns exec ns4 ip link set dev veth6 up
+ip netns exec ns4 ip link set dev veth7 up
+ip netns exec ns5 ip link set dev veth8 up
+ip netns exec ns5 ip link set dev veth9 up
+ip netns exec ns6 ip link set dev veth10 up
+ip netns exec ns6 ip link set dev lo up
+
+# All link scope addresses and routes required between veths
+ip netns exec ns1 ip -6 addr add fb00::12/16 dev veth1 scope link
+ip netns exec ns1 ip -6 route add fb00::21 dev veth1 scope link
+ip netns exec ns2 ip -6 addr add fb00::21/16 dev veth2 scope link
+ip netns exec ns2 ip -6 addr add fb00::34/16 dev veth3 scope link
+ip netns exec ns2 ip -6 route add fb00::43 dev veth3 scope link
+ip netns exec ns3 ip -6 route add fb00::65 dev veth5 scope link
+ip netns exec ns3 ip -6 addr add fb00::43/16 dev veth4 scope link
+ip netns exec ns3 ip -6 addr add fb00::56/16 dev veth5 scope link
+ip netns exec ns4 ip -6 addr add fb00::65/16 dev veth6 scope link
+ip netns exec ns4 ip -6 addr add fb00::78/16 dev veth7 scope link
+ip netns exec ns4 ip -6 route add fb00::87 dev veth7 scope link
+ip netns exec ns5 ip -6 addr add fb00::87/16 dev veth8 scope link
+ip netns exec ns5 ip -6 addr add fb00::910/16 dev veth9 scope link
+ip netns exec ns5 ip -6 route add fb00::109 dev veth9 scope link
+ip netns exec ns5 ip -6 route add fb00::109 table 117 dev veth9 scope link
+ip netns exec ns6 ip -6 addr add fb00::109/16 dev veth10 scope link
+
+ip netns exec ns1 ip -6 addr add fb00::1/16 dev lo
+ip netns exec ns1 ip -6 route add fb00::6 dev veth1 via fb00::21
+
+ip netns exec ns2 ip -6 route add fb00::6 encap bpf in obj test_lwt_seg6local.o sec encap_srh dev veth2
+ip netns exec ns2 ip -6 route add fd00::1 dev veth3 via fb00::43 scope link
+
+ip netns exec ns3 ip -6 route add fc42::1 dev veth5 via fb00::65
+ip netns exec ns3 ip -6 route add fd00::1 encap seg6local action End.BPF obj test_lwt_seg6local.o sec add_egr_x dev veth4
+
+ip netns exec ns4 ip -6 route add fd00::2 encap seg6local action End.BPF obj test_lwt_seg6local.o sec pop_egr dev veth6
+ip netns exec ns4 ip -6 addr add fc42::1 dev lo
+ip netns exec ns4 ip -6 route add fd00::3 dev veth7 via fb00::87
+
+ip netns exec ns5 ip -6 route add fd00::4 table 117 dev veth9 via fb00::109
+ip netns exec ns5 ip -6 route add fd00::3 encap seg6local action End.BPF obj test_lwt_seg6local.o sec inspect_t dev veth8
+
+ip netns exec ns6 ip -6 addr add fb00::6/16 dev lo
+ip netns exec ns6 ip -6 addr add fd00::4/16 dev lo
+
+ip netns exec ns1 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ns2 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ns3 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ns4 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+ip netns exec ns5 sysctl net.ipv6.conf.all.forwarding=1 > /dev/null
+
+ip netns exec ns6 sysctl net.ipv6.conf.all.seg6_enabled=1 > /dev/null
+ip netns exec ns6 sysctl net.ipv6.conf.lo.seg6_enabled=1 > /dev/null
+ip netns exec ns6 sysctl net.ipv6.conf.veth10.seg6_enabled=1 > /dev/null
+
+ip netns exec ns6 nc -l -6 -u -d 7330 > $TMP_FILE &
+ip netns exec ns1 bash -c "echo 'foobar' | nc -w0 -6 -u -p 2121 -s fb00::1 fb00::6 7330"
+sleep 5 # wait enough time to ensure the UDP datagram arrived to the last segment
+kill -INT $!
+
+if [[ $(< $TMP_FILE) != "foobar" ]]; then
+ exit 1
+fi
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index faadbe233966..0ef68204c84b 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -38,8 +38,10 @@ typedef __u16 __sum16;
#include "bpf_util.h"
#include "bpf_endian.h"
#include "bpf_rlimit.h"
+#include "trace_helpers.h"
static int error_cnt, pass_cnt;
+static bool jit_enabled;
#define MAGIC_BYTES 123
@@ -166,6 +168,37 @@ out:
bpf_object__close(obj);
}
+static void test_xdp_adjust_tail(void)
+{
+ const char *file = "./test_adjust_tail.o";
+ struct bpf_object *obj;
+ char buf[128];
+ __u32 duration, retval, size;
+ int err, prog_fd;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+ if (err) {
+ error_cnt++;
+ return;
+ }
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+ buf, &size, &retval, &duration);
+
+ CHECK(err || errno || retval != XDP_DROP,
+ "ipv4", "err %d errno %d retval %d size %d\n",
+ err, errno, retval, size);
+
+ err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6),
+ buf, &size, &retval, &duration);
+ CHECK(err || errno || retval != XDP_TX || size != 54,
+ "ipv6", "err %d errno %d retval %d size %d\n",
+ err, errno, retval, size);
+ bpf_object__close(obj);
+}
+
+
+
#define MAGIC_VAL 0x1234
#define NUM_ITER 100000
#define VIP_NUM 5
@@ -360,13 +393,30 @@ static inline __u64 ptr_to_u64(const void *ptr)
return (__u64) (unsigned long) ptr;
}
+static bool is_jit_enabled(void)
+{
+ const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
+ bool enabled = false;
+ int sysctl_fd;
+
+ sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
+ if (sysctl_fd != -1) {
+ char tmpc;
+
+ if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
+ enabled = (tmpc != '0');
+ close(sysctl_fd);
+ }
+
+ return enabled;
+}
+
static void test_bpf_obj_id(void)
{
const __u64 array_magic_value = 0xfaceb00c;
const __u32 array_key = 0;
const int nr_iters = 2;
const char *file = "./test_obj_id.o";
- const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable";
const char *expected_prog_name = "test_obj_id";
const char *expected_map_name = "test_map_id";
const __u64 nsec_per_sec = 1000000000;
@@ -383,20 +433,11 @@ static void test_bpf_obj_id(void)
char jited_insns[128], xlated_insns[128], zeros[128];
__u32 i, next_id, info_len, nr_id_found, duration = 0;
struct timespec real_time_ts, boot_time_ts;
- int sysctl_fd, jit_enabled = 0, err = 0;
+ int err = 0;
__u64 array_value;
uid_t my_uid = getuid();
time_t now, load_time;
- sysctl_fd = open(jit_sysctl, 0, O_RDONLY);
- if (sysctl_fd != -1) {
- char tmpc;
-
- if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1)
- jit_enabled = (tmpc != '0');
- close(sysctl_fd);
- }
-
err = bpf_prog_get_fd_by_id(0);
CHECK(err >= 0 || errno != ENOENT,
"get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno);
@@ -865,11 +906,47 @@ static int compare_map_keys(int map1_fd, int map2_fd)
return 0;
}
+static int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len)
+{
+ __u32 key, next_key, *cur_key_p, *next_key_p;
+ char *val_buf1, *val_buf2;
+ int i, err = 0;
+
+ val_buf1 = malloc(stack_trace_len);
+ val_buf2 = malloc(stack_trace_len);
+ cur_key_p = NULL;
+ next_key_p = &key;
+ while (bpf_map_get_next_key(smap_fd, cur_key_p, next_key_p) == 0) {
+ err = bpf_map_lookup_elem(smap_fd, next_key_p, val_buf1);
+ if (err)
+ goto out;
+ err = bpf_map_lookup_elem(amap_fd, next_key_p, val_buf2);
+ if (err)
+ goto out;
+ for (i = 0; i < stack_trace_len; i++) {
+ if (val_buf1[i] != val_buf2[i]) {
+ err = -1;
+ goto out;
+ }
+ }
+ key = *next_key_p;
+ cur_key_p = &key;
+ next_key_p = &next_key;
+ }
+ if (errno != ENOENT)
+ err = -1;
+
+out:
+ free(val_buf1);
+ free(val_buf2);
+ return err;
+}
+
static void test_stacktrace_map()
{
- int control_map_fd, stackid_hmap_fd, stackmap_fd;
+ int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
const char *file = "./test_stacktrace_map.o";
- int bytes, efd, err, pmu_fd, prog_fd;
+ int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
struct perf_event_attr attr = {};
__u32 key, val, duration = 0;
struct bpf_object *obj;
@@ -925,6 +1002,10 @@ static void test_stacktrace_map()
if (stackmap_fd < 0)
goto disable_pmu;
+ stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+ if (stack_amap_fd < 0)
+ goto disable_pmu;
+
/* give some time for bpf program run */
sleep(1);
@@ -946,6 +1027,12 @@ static void test_stacktrace_map()
"err %d errno %d\n", err, errno))
goto disable_pmu_noerr;
+ stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
+ err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
+ if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu_noerr;
+
goto disable_pmu_noerr;
disable_pmu:
error_cnt++;
@@ -1039,9 +1126,9 @@ err:
static void test_stacktrace_build_id(void)
{
- int control_map_fd, stackid_hmap_fd, stackmap_fd;
+ int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
const char *file = "./test_stacktrace_build_id.o";
- int bytes, efd, err, pmu_fd, prog_fd;
+ int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len;
struct perf_event_attr attr = {};
__u32 key, previous_key, val, duration = 0;
struct bpf_object *obj;
@@ -1106,9 +1193,14 @@ static void test_stacktrace_build_id(void)
err, errno))
goto disable_pmu;
+ stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+ if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
== 0);
- assert(system("./urandom_read if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0);
+ assert(system("./urandom_read") == 0);
/* disable stack trace collection */
key = 0;
val = 1;
@@ -1157,8 +1249,15 @@ static void test_stacktrace_build_id(void)
previous_key = key;
} while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
- CHECK(build_id_matches < 1, "build id match",
- "Didn't find expected build ID from the map");
+ if (CHECK(build_id_matches < 1, "build id match",
+ "Didn't find expected build ID from the map\n"))
+ goto disable_pmu;
+
+ stack_trace_len = PERF_MAX_STACK_DEPTH
+ * sizeof(struct bpf_stack_build_id);
+ err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
+ CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
+ "err %d errno %d\n", err, errno);
disable_pmu:
ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
@@ -1173,10 +1272,439 @@ out:
return;
}
+static void test_stacktrace_build_id_nmi(void)
+{
+ int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
+ const char *file = "./test_stacktrace_build_id.o";
+ int err, pmu_fd, prog_fd;
+ struct perf_event_attr attr = {
+ .sample_freq = 5000,
+ .freq = 1,
+ .type = PERF_TYPE_HARDWARE,
+ .config = PERF_COUNT_HW_CPU_CYCLES,
+ };
+ __u32 key, previous_key, val, duration = 0;
+ struct bpf_object *obj;
+ char buf[256];
+ int i, j;
+ struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
+ int build_id_matches = 0;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+ return;
+
+ pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+ 0 /* cpu 0 */, -1 /* group id */,
+ 0 /* flags */);
+ if (CHECK(pmu_fd < 0, "perf_event_open",
+ "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+ pmu_fd, errno))
+ goto close_prog;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n",
+ err, errno))
+ goto close_pmu;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+ if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n",
+ err, errno))
+ goto disable_pmu;
+
+ /* find map fds */
+ control_map_fd = bpf_find_map(__func__, obj, "control_map");
+ if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
+ if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
+ if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
+ err, errno))
+ goto disable_pmu;
+
+ stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
+ if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")
+ == 0);
+ assert(system("taskset 0x1 ./urandom_read 100000") == 0);
+ /* disable stack trace collection */
+ key = 0;
+ val = 1;
+ bpf_map_update_elem(control_map_fd, &key, &val, 0);
+
+ /* for every element in stackid_hmap, we can find a corresponding one
+ * in stackmap, and vise versa.
+ */
+ err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
+ if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
+ if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ err = extract_build_id(buf, 256);
+
+ if (CHECK(err, "get build_id with readelf",
+ "err %d errno %d\n", err, errno))
+ goto disable_pmu;
+
+ err = bpf_map_get_next_key(stackmap_fd, NULL, &key);
+ if (CHECK(err, "get_next_key from stackmap",
+ "err %d, errno %d\n", err, errno))
+ goto disable_pmu;
+
+ do {
+ char build_id[64];
+
+ err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs);
+ if (CHECK(err, "lookup_elem from stackmap",
+ "err %d, errno %d\n", err, errno))
+ goto disable_pmu;
+ for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
+ if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
+ id_offs[i].offset != 0) {
+ for (j = 0; j < 20; ++j)
+ sprintf(build_id + 2 * j, "%02x",
+ id_offs[i].build_id[j] & 0xff);
+ if (strstr(buf, build_id) != NULL)
+ build_id_matches = 1;
+ }
+ previous_key = key;
+ } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0);
+
+ if (CHECK(build_id_matches < 1, "build id match",
+ "Didn't find expected build ID from the map\n"))
+ goto disable_pmu;
+
+ /*
+ * We intentionally skip compare_stack_ips(). This is because we
+ * only support one in_nmi() ips-to-build_id translation per cpu
+ * at any time, thus stack_amap here will always fallback to
+ * BPF_STACK_BUILD_ID_IP;
+ */
+
+disable_pmu:
+ ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE);
+
+close_pmu:
+ close(pmu_fd);
+
+close_prog:
+ bpf_object__close(obj);
+}
+
+#define MAX_CNT_RAWTP 10ull
+#define MAX_STACK_RAWTP 100
+struct get_stack_trace_t {
+ int pid;
+ int kern_stack_size;
+ int user_stack_size;
+ int user_stack_buildid_size;
+ __u64 kern_stack[MAX_STACK_RAWTP];
+ __u64 user_stack[MAX_STACK_RAWTP];
+ struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP];
+};
+
+static int get_stack_print_output(void *data, int size)
+{
+ bool good_kern_stack = false, good_user_stack = false;
+ const char *nonjit_func = "___bpf_prog_run";
+ struct get_stack_trace_t *e = data;
+ int i, num_stack;
+ static __u64 cnt;
+ struct ksym *ks;
+
+ cnt++;
+
+ if (size < sizeof(struct get_stack_trace_t)) {
+ __u64 *raw_data = data;
+ bool found = false;
+
+ num_stack = size / sizeof(__u64);
+ /* If jit is enabled, we do not have a good way to
+ * verify the sanity of the kernel stack. So we
+ * just assume it is good if the stack is not empty.
+ * This could be improved in the future.
+ */
+ if (jit_enabled) {
+ found = num_stack > 0;
+ } else {
+ for (i = 0; i < num_stack; i++) {
+ ks = ksym_search(raw_data[i]);
+ if (strcmp(ks->name, nonjit_func) == 0) {
+ found = true;
+ break;
+ }
+ }
+ }
+ if (found) {
+ good_kern_stack = true;
+ good_user_stack = true;
+ }
+ } else {
+ num_stack = e->kern_stack_size / sizeof(__u64);
+ if (jit_enabled) {
+ good_kern_stack = num_stack > 0;
+ } else {
+ for (i = 0; i < num_stack; i++) {
+ ks = ksym_search(e->kern_stack[i]);
+ if (strcmp(ks->name, nonjit_func) == 0) {
+ good_kern_stack = true;
+ break;
+ }
+ }
+ }
+ if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0)
+ good_user_stack = true;
+ }
+ if (!good_kern_stack || !good_user_stack)
+ return LIBBPF_PERF_EVENT_ERROR;
+
+ if (cnt == MAX_CNT_RAWTP)
+ return LIBBPF_PERF_EVENT_DONE;
+
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void test_get_stack_raw_tp(void)
+{
+ const char *file = "./test_get_stack_rawtp.o";
+ int i, efd, err, prog_fd, pmu_fd, perfmap_fd;
+ struct perf_event_attr attr = {};
+ struct timespec tv = {0, 10};
+ __u32 key = 0, duration = 0;
+ struct bpf_object *obj;
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+ return;
+
+ efd = bpf_raw_tracepoint_open("sys_enter", prog_fd);
+ if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+
+ perfmap_fd = bpf_find_map(__func__, obj, "perfmap");
+ if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n",
+ perfmap_fd, errno))
+ goto close_prog;
+
+ err = load_kallsyms();
+ if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ attr.sample_type = PERF_SAMPLE_RAW;
+ attr.type = PERF_TYPE_SOFTWARE;
+ attr.config = PERF_COUNT_SW_BPF_OUTPUT;
+ pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/,
+ -1/*group_fd*/, 0);
+ if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd,
+ errno))
+ goto close_prog;
+
+ err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY);
+ if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err,
+ errno))
+ goto close_prog;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n",
+ err, errno))
+ goto close_prog;
+
+ err = perf_event_mmap(pmu_fd);
+ if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ /* trigger some syscall action */
+ for (i = 0; i < MAX_CNT_RAWTP; i++)
+ nanosleep(&tv, NULL);
+
+ err = perf_event_poller(pmu_fd, get_stack_print_output);
+ if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ goto close_prog_noerr;
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
+}
+
+static void test_task_fd_query_rawtp(void)
+{
+ const char *file = "./test_get_stack_rawtp.o";
+ __u64 probe_offset, probe_addr;
+ __u32 len, prog_id, fd_type;
+ struct bpf_object *obj;
+ int efd, err, prog_fd;
+ __u32 duration = 0;
+ char buf[256];
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno))
+ return;
+
+ efd = bpf_raw_tracepoint_open("sys_enter", prog_fd);
+ if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+
+ /* query (getpid(), efd) */
+ len = sizeof(buf);
+ err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id,
+ &fd_type, &probe_offset, &probe_addr);
+ if (CHECK(err < 0, "bpf_task_fd_query", "err %d errno %d\n", err,
+ errno))
+ goto close_prog;
+
+ err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT &&
+ strcmp(buf, "sys_enter") == 0;
+ if (CHECK(!err, "check_results", "fd_type %d tp_name %s\n",
+ fd_type, buf))
+ goto close_prog;
+
+ /* test zero len */
+ len = 0;
+ err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id,
+ &fd_type, &probe_offset, &probe_addr);
+ if (CHECK(err < 0, "bpf_task_fd_query (len = 0)", "err %d errno %d\n",
+ err, errno))
+ goto close_prog;
+ err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT &&
+ len == strlen("sys_enter");
+ if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len))
+ goto close_prog;
+
+ /* test empty buffer */
+ len = sizeof(buf);
+ err = bpf_task_fd_query(getpid(), efd, 0, 0, &len, &prog_id,
+ &fd_type, &probe_offset, &probe_addr);
+ if (CHECK(err < 0, "bpf_task_fd_query (buf = 0)", "err %d errno %d\n",
+ err, errno))
+ goto close_prog;
+ err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT &&
+ len == strlen("sys_enter");
+ if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len))
+ goto close_prog;
+
+ /* test smaller buffer */
+ len = 3;
+ err = bpf_task_fd_query(getpid(), efd, 0, buf, &len, &prog_id,
+ &fd_type, &probe_offset, &probe_addr);
+ if (CHECK(err >= 0 || errno != ENOSPC, "bpf_task_fd_query (len = 3)",
+ "err %d errno %d\n", err, errno))
+ goto close_prog;
+ err = fd_type == BPF_FD_TYPE_RAW_TRACEPOINT &&
+ len == strlen("sys_enter") &&
+ strcmp(buf, "sy") == 0;
+ if (CHECK(!err, "check_results", "fd_type %d len %u\n", fd_type, len))
+ goto close_prog;
+
+ goto close_prog_noerr;
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
+}
+
+static void test_task_fd_query_tp_core(const char *probe_name,
+ const char *tp_name)
+{
+ const char *file = "./test_tracepoint.o";
+ int err, bytes, efd, prog_fd, pmu_fd;
+ struct perf_event_attr attr = {};
+ __u64 probe_offset, probe_addr;
+ __u32 len, prog_id, fd_type;
+ struct bpf_object *obj;
+ __u32 duration = 0;
+ char buf[256];
+
+ err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
+ if (CHECK(err, "bpf_prog_load", "err %d errno %d\n", err, errno))
+ goto close_prog;
+
+ snprintf(buf, sizeof(buf),
+ "/sys/kernel/debug/tracing/events/%s/id", probe_name);
+ efd = open(buf, O_RDONLY, 0);
+ if (CHECK(efd < 0, "open", "err %d errno %d\n", efd, errno))
+ goto close_prog;
+ bytes = read(efd, buf, sizeof(buf));
+ close(efd);
+ if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "read",
+ "bytes %d errno %d\n", bytes, errno))
+ goto close_prog;
+
+ attr.config = strtol(buf, NULL, 0);
+ attr.type = PERF_TYPE_TRACEPOINT;
+ attr.sample_type = PERF_SAMPLE_RAW;
+ attr.sample_period = 1;
+ attr.wakeup_events = 1;
+ pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+ 0 /* cpu 0 */, -1 /* group id */,
+ 0 /* flags */);
+ if (CHECK(err, "perf_event_open", "err %d errno %d\n", err, errno))
+ goto close_pmu;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
+ if (CHECK(err, "perf_event_ioc_enable", "err %d errno %d\n", err,
+ errno))
+ goto close_pmu;
+
+ err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
+ if (CHECK(err, "perf_event_ioc_set_bpf", "err %d errno %d\n", err,
+ errno))
+ goto close_pmu;
+
+ /* query (getpid(), pmu_fd) */
+ len = sizeof(buf);
+ err = bpf_task_fd_query(getpid(), pmu_fd, 0, buf, &len, &prog_id,
+ &fd_type, &probe_offset, &probe_addr);
+ if (CHECK(err < 0, "bpf_task_fd_query", "err %d errno %d\n", err,
+ errno))
+ goto close_pmu;
+
+ err = (fd_type == BPF_FD_TYPE_TRACEPOINT) && !strcmp(buf, tp_name);
+ if (CHECK(!err, "check_results", "fd_type %d tp_name %s\n",
+ fd_type, buf))
+ goto close_pmu;
+
+ close(pmu_fd);
+ goto close_prog_noerr;
+
+close_pmu:
+ close(pmu_fd);
+close_prog:
+ error_cnt++;
+close_prog_noerr:
+ bpf_object__close(obj);
+}
+
+static void test_task_fd_query_tp(void)
+{
+ test_task_fd_query_tp_core("sched/sched_switch",
+ "sched_switch");
+ test_task_fd_query_tp_core("syscalls/sys_enter_read",
+ "sys_enter_read");
+}
+
int main(void)
{
+ jit_enabled = is_jit_enabled();
+
test_pkt_access();
test_xdp();
+ test_xdp_adjust_tail();
test_l4lb_all();
test_xdp_noinline();
test_tcp_estats();
@@ -1186,7 +1714,11 @@ int main(void)
test_tp_attach_query();
test_stacktrace_map();
test_stacktrace_build_id();
+ test_stacktrace_build_id_nmi();
test_stacktrace_map_raw_tp();
+ test_get_stack_raw_tp();
+ test_task_fd_query_rawtp();
+ test_task_fd_query_tp();
printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt);
return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS;
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index 73bb20cfb9b7..f4d99fabc56d 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -13,6 +13,7 @@
#include <bpf/bpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index d488f20926e8..a5e76b9219b9 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -1,12 +1,16 @@
// SPDX-License-Identifier: GPL-2.0
// Copyright (c) 2018 Facebook
+#define _GNU_SOURCE
+
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <arpa/inet.h>
+#include <netinet/in.h>
#include <sys/types.h>
+#include <sys/select.h>
#include <sys/socket.h>
#include <linux/filter.h>
@@ -15,35 +19,467 @@
#include <bpf/libbpf.h>
#include "cgroup_helpers.h"
+#include "bpf_rlimit.h"
+
+#ifndef ENOTSUPP
+# define ENOTSUPP 524
+#endif
+
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
#define CG_PATH "/foo"
#define CONNECT4_PROG_PATH "./connect4_prog.o"
#define CONNECT6_PROG_PATH "./connect6_prog.o"
+#define SENDMSG4_PROG_PATH "./sendmsg4_prog.o"
+#define SENDMSG6_PROG_PATH "./sendmsg6_prog.o"
#define SERV4_IP "192.168.1.254"
#define SERV4_REWRITE_IP "127.0.0.1"
+#define SRC4_IP "172.16.0.1"
+#define SRC4_REWRITE_IP "127.0.0.4"
#define SERV4_PORT 4040
#define SERV4_REWRITE_PORT 4444
#define SERV6_IP "face:b00c:1234:5678::abcd"
#define SERV6_REWRITE_IP "::1"
+#define SERV6_V4MAPPED_IP "::ffff:192.168.0.4"
+#define SRC6_IP "::1"
+#define SRC6_REWRITE_IP "::6"
#define SERV6_PORT 6060
#define SERV6_REWRITE_PORT 6666
#define INET_NTOP_BUF 40
-typedef int (*load_fn)(enum bpf_attach_type, const char *comment);
+struct sock_addr_test;
+
+typedef int (*load_fn)(const struct sock_addr_test *test);
typedef int (*info_fn)(int, struct sockaddr *, socklen_t *);
-struct program {
- enum bpf_attach_type type;
- load_fn loadfn;
- int fd;
- const char *name;
- enum bpf_attach_type invalid_type;
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+struct sock_addr_test {
+ const char *descr;
+ /* BPF prog properties */
+ load_fn loadfn;
+ enum bpf_attach_type expected_attach_type;
+ enum bpf_attach_type attach_type;
+ /* Socket properties */
+ int domain;
+ int type;
+ /* IP:port pairs for BPF prog to override */
+ const char *requested_ip;
+ unsigned short requested_port;
+ const char *expected_ip;
+ unsigned short expected_port;
+ const char *expected_src_ip;
+ /* Expected test result */
+ enum {
+ LOAD_REJECT,
+ ATTACH_REJECT,
+ SYSCALL_EPERM,
+ SYSCALL_ENOTSUPP,
+ SUCCESS,
+ } expected_result;
};
-char bpf_log_buf[BPF_LOG_BUF_SIZE];
+static int bind4_prog_load(const struct sock_addr_test *test);
+static int bind6_prog_load(const struct sock_addr_test *test);
+static int connect4_prog_load(const struct sock_addr_test *test);
+static int connect6_prog_load(const struct sock_addr_test *test);
+static int sendmsg_deny_prog_load(const struct sock_addr_test *test);
+static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test);
+static int sendmsg4_rw_c_prog_load(const struct sock_addr_test *test);
+static int sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test);
+static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test);
+static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test);
+
+static struct sock_addr_test tests[] = {
+ /* bind */
+ {
+ "bind4: load prog with wrong expected attach type",
+ bind4_prog_load,
+ BPF_CGROUP_INET6_BIND,
+ BPF_CGROUP_INET4_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ LOAD_REJECT,
+ },
+ {
+ "bind4: attach prog with wrong attach type",
+ bind4_prog_load,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ ATTACH_REJECT,
+ },
+ {
+ "bind4: rewrite IP & TCP port in",
+ bind4_prog_load,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET4_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ NULL,
+ SUCCESS,
+ },
+ {
+ "bind4: rewrite IP & UDP port in",
+ bind4_prog_load,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET4_BIND,
+ AF_INET,
+ SOCK_DGRAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ NULL,
+ SUCCESS,
+ },
+ {
+ "bind6: load prog with wrong expected attach type",
+ bind6_prog_load,
+ BPF_CGROUP_INET4_BIND,
+ BPF_CGROUP_INET6_BIND,
+ AF_INET6,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ LOAD_REJECT,
+ },
+ {
+ "bind6: attach prog with wrong attach type",
+ bind6_prog_load,
+ BPF_CGROUP_INET6_BIND,
+ BPF_CGROUP_INET4_BIND,
+ AF_INET,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ ATTACH_REJECT,
+ },
+ {
+ "bind6: rewrite IP & TCP port in",
+ bind6_prog_load,
+ BPF_CGROUP_INET6_BIND,
+ BPF_CGROUP_INET6_BIND,
+ AF_INET6,
+ SOCK_STREAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ NULL,
+ SUCCESS,
+ },
+ {
+ "bind6: rewrite IP & UDP port in",
+ bind6_prog_load,
+ BPF_CGROUP_INET6_BIND,
+ BPF_CGROUP_INET6_BIND,
+ AF_INET6,
+ SOCK_DGRAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ NULL,
+ SUCCESS,
+ },
+
+ /* connect */
+ {
+ "connect4: load prog with wrong expected attach type",
+ connect4_prog_load,
+ BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET4_CONNECT,
+ AF_INET,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ LOAD_REJECT,
+ },
+ {
+ "connect4: attach prog with wrong attach type",
+ connect4_prog_load,
+ BPF_CGROUP_INET4_CONNECT,
+ BPF_CGROUP_INET6_CONNECT,
+ AF_INET,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ ATTACH_REJECT,
+ },
+ {
+ "connect4: rewrite IP & TCP port",
+ connect4_prog_load,
+ BPF_CGROUP_INET4_CONNECT,
+ BPF_CGROUP_INET4_CONNECT,
+ AF_INET,
+ SOCK_STREAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ SRC4_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "connect4: rewrite IP & UDP port",
+ connect4_prog_load,
+ BPF_CGROUP_INET4_CONNECT,
+ BPF_CGROUP_INET4_CONNECT,
+ AF_INET,
+ SOCK_DGRAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ SRC4_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "connect6: load prog with wrong expected attach type",
+ connect6_prog_load,
+ BPF_CGROUP_INET4_CONNECT,
+ BPF_CGROUP_INET6_CONNECT,
+ AF_INET6,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ LOAD_REJECT,
+ },
+ {
+ "connect6: attach prog with wrong attach type",
+ connect6_prog_load,
+ BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET4_CONNECT,
+ AF_INET,
+ SOCK_STREAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ ATTACH_REJECT,
+ },
+ {
+ "connect6: rewrite IP & TCP port",
+ connect6_prog_load,
+ BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET6_CONNECT,
+ AF_INET6,
+ SOCK_STREAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ SRC6_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "connect6: rewrite IP & UDP port",
+ connect6_prog_load,
+ BPF_CGROUP_INET6_CONNECT,
+ BPF_CGROUP_INET6_CONNECT,
+ AF_INET6,
+ SOCK_DGRAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ SRC6_REWRITE_IP,
+ SUCCESS,
+ },
+
+ /* sendmsg */
+ {
+ "sendmsg4: load prog with wrong expected attach type",
+ sendmsg4_rw_asm_prog_load,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_CGROUP_UDP4_SENDMSG,
+ AF_INET,
+ SOCK_DGRAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ LOAD_REJECT,
+ },
+ {
+ "sendmsg4: attach prog with wrong attach type",
+ sendmsg4_rw_asm_prog_load,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ AF_INET,
+ SOCK_DGRAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ ATTACH_REJECT,
+ },
+ {
+ "sendmsg4: rewrite IP & port (asm)",
+ sendmsg4_rw_asm_prog_load,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP4_SENDMSG,
+ AF_INET,
+ SOCK_DGRAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ SRC4_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "sendmsg4: rewrite IP & port (C)",
+ sendmsg4_rw_c_prog_load,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP4_SENDMSG,
+ AF_INET,
+ SOCK_DGRAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ SRC4_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "sendmsg4: deny call",
+ sendmsg_deny_prog_load,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP4_SENDMSG,
+ AF_INET,
+ SOCK_DGRAM,
+ SERV4_IP,
+ SERV4_PORT,
+ SERV4_REWRITE_IP,
+ SERV4_REWRITE_PORT,
+ SRC4_REWRITE_IP,
+ SYSCALL_EPERM,
+ },
+ {
+ "sendmsg6: load prog with wrong expected attach type",
+ sendmsg6_rw_asm_prog_load,
+ BPF_CGROUP_UDP4_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ AF_INET6,
+ SOCK_DGRAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ LOAD_REJECT,
+ },
+ {
+ "sendmsg6: attach prog with wrong attach type",
+ sendmsg6_rw_asm_prog_load,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_CGROUP_UDP4_SENDMSG,
+ AF_INET6,
+ SOCK_DGRAM,
+ NULL,
+ 0,
+ NULL,
+ 0,
+ NULL,
+ ATTACH_REJECT,
+ },
+ {
+ "sendmsg6: rewrite IP & port (asm)",
+ sendmsg6_rw_asm_prog_load,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ AF_INET6,
+ SOCK_DGRAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ SRC6_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "sendmsg6: rewrite IP & port (C)",
+ sendmsg6_rw_c_prog_load,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ AF_INET6,
+ SOCK_DGRAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ SRC6_REWRITE_IP,
+ SUCCESS,
+ },
+ {
+ "sendmsg6: IPv4-mapped IPv6",
+ sendmsg6_rw_v4mapped_prog_load,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ AF_INET6,
+ SOCK_DGRAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ SRC6_REWRITE_IP,
+ SYSCALL_ENOTSUPP,
+ },
+ {
+ "sendmsg6: deny call",
+ sendmsg_deny_prog_load,
+ BPF_CGROUP_UDP6_SENDMSG,
+ BPF_CGROUP_UDP6_SENDMSG,
+ AF_INET6,
+ SOCK_DGRAM,
+ SERV6_IP,
+ SERV6_PORT,
+ SERV6_REWRITE_IP,
+ SERV6_REWRITE_PORT,
+ SRC6_REWRITE_IP,
+ SYSCALL_EPERM,
+ },
+};
static int mk_sockaddr(int domain, const char *ip, unsigned short port,
struct sockaddr *addr, socklen_t addr_len)
@@ -83,25 +519,23 @@ static int mk_sockaddr(int domain, const char *ip, unsigned short port,
return 0;
}
-static int load_insns(enum bpf_attach_type attach_type,
- const struct bpf_insn *insns, size_t insns_cnt,
- const char *comment)
+static int load_insns(const struct sock_addr_test *test,
+ const struct bpf_insn *insns, size_t insns_cnt)
{
struct bpf_load_program_attr load_attr;
int ret;
memset(&load_attr, 0, sizeof(struct bpf_load_program_attr));
load_attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
- load_attr.expected_attach_type = attach_type;
+ load_attr.expected_attach_type = test->expected_attach_type;
load_attr.insns = insns;
load_attr.insns_cnt = insns_cnt;
load_attr.license = "GPL";
ret = bpf_load_program_xattr(&load_attr, bpf_log_buf, BPF_LOG_BUF_SIZE);
- if (ret < 0 && comment) {
- log_err(">>> Loading %s program error.\n"
- ">>> Output from verifier:\n%s\n-------\n",
- comment, bpf_log_buf);
+ if (ret < 0 && test->expected_result != LOAD_REJECT) {
+ log_err(">>> Loading program error.\n"
+ ">>> Verifier output:\n%s\n-------\n", bpf_log_buf);
}
return ret;
@@ -118,8 +552,7 @@ static int load_insns(enum bpf_attach_type attach_type,
* to count jumps properly.
*/
-static int bind4_prog_load(enum bpf_attach_type attach_type,
- const char *comment)
+static int bind4_prog_load(const struct sock_addr_test *test)
{
union {
uint8_t u4_addr8[4];
@@ -185,12 +618,10 @@ static int bind4_prog_load(enum bpf_attach_type attach_type,
BPF_EXIT_INSN(),
};
- return load_insns(attach_type, insns,
- sizeof(insns) / sizeof(struct bpf_insn), comment);
+ return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
}
-static int bind6_prog_load(enum bpf_attach_type attach_type,
- const char *comment)
+static int bind6_prog_load(const struct sock_addr_test *test)
{
struct sockaddr_in6 addr6_rw;
struct in6_addr ip6;
@@ -253,13 +684,10 @@ static int bind6_prog_load(enum bpf_attach_type attach_type,
BPF_EXIT_INSN(),
};
- return load_insns(attach_type, insns,
- sizeof(insns) / sizeof(struct bpf_insn), comment);
+ return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
}
-static int connect_prog_load_path(const char *path,
- enum bpf_attach_type attach_type,
- const char *comment)
+static int load_path(const struct sock_addr_test *test, const char *path)
{
struct bpf_prog_load_attr attr;
struct bpf_object *obj;
@@ -268,75 +696,218 @@ static int connect_prog_load_path(const char *path,
memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
attr.file = path;
attr.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR;
- attr.expected_attach_type = attach_type;
+ attr.expected_attach_type = test->expected_attach_type;
if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
- if (comment)
- log_err(">>> Loading %s program at %s error.\n",
- comment, path);
+ if (test->expected_result != LOAD_REJECT)
+ log_err(">>> Loading program (%s) error.\n", path);
return -1;
}
return prog_fd;
}
-static int connect4_prog_load(enum bpf_attach_type attach_type,
- const char *comment)
+static int connect4_prog_load(const struct sock_addr_test *test)
{
- return connect_prog_load_path(CONNECT4_PROG_PATH, attach_type, comment);
+ return load_path(test, CONNECT4_PROG_PATH);
}
-static int connect6_prog_load(enum bpf_attach_type attach_type,
- const char *comment)
+static int connect6_prog_load(const struct sock_addr_test *test)
{
- return connect_prog_load_path(CONNECT6_PROG_PATH, attach_type, comment);
+ return load_path(test, CONNECT6_PROG_PATH);
}
-static void print_ip_port(int sockfd, info_fn fn, const char *fmt)
+static int sendmsg_deny_prog_load(const struct sock_addr_test *test)
{
- char addr_buf[INET_NTOP_BUF];
- struct sockaddr_storage addr;
- struct sockaddr_in6 *addr6;
- struct sockaddr_in *addr4;
- socklen_t addr_len;
- unsigned short port;
- void *nip;
-
- addr_len = sizeof(struct sockaddr_storage);
- memset(&addr, 0, addr_len);
-
- if (fn(sockfd, (struct sockaddr *)&addr, (socklen_t *)&addr_len) == 0) {
- if (addr.ss_family == AF_INET) {
- addr4 = (struct sockaddr_in *)&addr;
- nip = (void *)&addr4->sin_addr;
- port = ntohs(addr4->sin_port);
- } else if (addr.ss_family == AF_INET6) {
- addr6 = (struct sockaddr_in6 *)&addr;
- nip = (void *)&addr6->sin6_addr;
- port = ntohs(addr6->sin6_port);
- } else {
- return;
- }
- const char *addr_str =
- inet_ntop(addr.ss_family, nip, addr_buf, INET_NTOP_BUF);
- printf(fmt, addr_str ? addr_str : "??", port);
+ struct bpf_insn insns[] = {
+ /* return 0 */
+ BPF_MOV64_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ };
+ return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn));
+}
+
+static int sendmsg4_rw_asm_prog_load(const struct sock_addr_test *test)
+{
+ struct sockaddr_in dst4_rw_addr;
+ struct in_addr src4_rw_ip;
+
+ if (inet_pton(AF_INET, SRC4_REWRITE_IP, (void *)&src4_rw_ip) != 1) {
+ log_err("Invalid IPv4: %s", SRC4_REWRITE_IP);
+ return -1;
+ }
+
+ if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT,
+ (struct sockaddr *)&dst4_rw_addr,
+ sizeof(dst4_rw_addr)) == -1)
+ return -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, 8),
+
+ /* sk.type == SOCK_DGRAM) { */
+ 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, 6),
+
+ /* msg_src_ip4 = src4_rw_ip */
+ BPF_MOV32_IMM(BPF_REG_7, src4_rw_ip.s_addr),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, msg_src_ip4)),
+
+ /* user_ip4 = dst4_rw_addr.sin_addr */
+ BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.sin_addr.s_addr),
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7,
+ offsetof(struct bpf_sock_addr, user_ip4)),
+
+ /* user_port = dst4_rw_addr.sin_port */
+ BPF_MOV32_IMM(BPF_REG_7, dst4_rw_addr.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 sendmsg4_rw_c_prog_load(const struct sock_addr_test *test)
+{
+ return load_path(test, SENDMSG4_PROG_PATH);
+}
+
+static int sendmsg6_rw_dst_asm_prog_load(const struct sock_addr_test *test,
+ const char *rw_dst_ip)
+{
+ struct sockaddr_in6 dst6_rw_addr;
+ struct in6_addr src6_rw_ip;
+
+ if (inet_pton(AF_INET6, SRC6_REWRITE_IP, (void *)&src6_rw_ip) != 1) {
+ log_err("Invalid IPv6: %s", SRC6_REWRITE_IP);
+ return -1;
+ }
+
+ if (mk_sockaddr(AF_INET6, rw_dst_ip, SERV6_REWRITE_PORT,
+ (struct sockaddr *)&dst6_rw_addr,
+ sizeof(dst6_rw_addr)) == -1)
+ return -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),
+
+#define STORE_IPV6_WORD_N(DST, SRC, N) \
+ BPF_MOV32_IMM(BPF_REG_7, SRC[N]), \
+ BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \
+ offsetof(struct bpf_sock_addr, DST[N]))
+
+#define STORE_IPV6(DST, SRC) \
+ STORE_IPV6_WORD_N(DST, SRC, 0), \
+ STORE_IPV6_WORD_N(DST, SRC, 1), \
+ STORE_IPV6_WORD_N(DST, SRC, 2), \
+ STORE_IPV6_WORD_N(DST, SRC, 3)
+
+ STORE_IPV6(msg_src_ip6, src6_rw_ip.s6_addr32),
+ STORE_IPV6(user_ip6, dst6_rw_addr.sin6_addr.s6_addr32),
+
+ /* user_port = dst6_rw_addr.sin6_port */
+ BPF_MOV32_IMM(BPF_REG_7, dst6_rw_addr.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 sendmsg6_rw_asm_prog_load(const struct sock_addr_test *test)
+{
+ return sendmsg6_rw_dst_asm_prog_load(test, SERV6_REWRITE_IP);
+}
+
+static int sendmsg6_rw_v4mapped_prog_load(const struct sock_addr_test *test)
+{
+ return sendmsg6_rw_dst_asm_prog_load(test, SERV6_V4MAPPED_IP);
+}
+
+static int sendmsg6_rw_c_prog_load(const struct sock_addr_test *test)
+{
+ return load_path(test, SENDMSG6_PROG_PATH);
+}
+
+static int cmp_addr(const struct sockaddr_storage *addr1,
+ const struct sockaddr_storage *addr2, int cmp_port)
+{
+ const struct sockaddr_in *four1, *four2;
+ const struct sockaddr_in6 *six1, *six2;
+
+ if (addr1->ss_family != addr2->ss_family)
+ return -1;
+
+ if (addr1->ss_family == AF_INET) {
+ four1 = (const struct sockaddr_in *)addr1;
+ four2 = (const struct sockaddr_in *)addr2;
+ return !((four1->sin_port == four2->sin_port || !cmp_port) &&
+ four1->sin_addr.s_addr == four2->sin_addr.s_addr);
+ } else if (addr1->ss_family == AF_INET6) {
+ six1 = (const struct sockaddr_in6 *)addr1;
+ six2 = (const struct sockaddr_in6 *)addr2;
+ return !((six1->sin6_port == six2->sin6_port || !cmp_port) &&
+ !memcmp(&six1->sin6_addr, &six2->sin6_addr,
+ sizeof(struct in6_addr)));
}
+
+ return -1;
}
-static void print_local_ip_port(int sockfd, const char *fmt)
+static int cmp_sock_addr(info_fn fn, int sock1,
+ const struct sockaddr_storage *addr2, int cmp_port)
{
- print_ip_port(sockfd, getsockname, fmt);
+ struct sockaddr_storage addr1;
+ socklen_t len1 = sizeof(addr1);
+
+ memset(&addr1, 0, len1);
+ if (fn(sock1, (struct sockaddr *)&addr1, (socklen_t *)&len1) != 0)
+ return -1;
+
+ return cmp_addr(&addr1, addr2, cmp_port);
+}
+
+static int cmp_local_ip(int sock1, const struct sockaddr_storage *addr2)
+{
+ return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 0);
}
-static void print_remote_ip_port(int sockfd, const char *fmt)
+static int cmp_local_addr(int sock1, const struct sockaddr_storage *addr2)
{
- print_ip_port(sockfd, getpeername, fmt);
+ return cmp_sock_addr(getsockname, sock1, addr2, /*cmp_port*/ 1);
+}
+
+static int cmp_peer_addr(int sock1, const struct sockaddr_storage *addr2)
+{
+ return cmp_sock_addr(getpeername, sock1, addr2, /*cmp_port*/ 1);
}
static int start_server(int type, const struct sockaddr_storage *addr,
socklen_t addr_len)
{
-
int fd;
fd = socket(addr->ss_family, type, 0);
@@ -357,8 +928,6 @@ static int start_server(int type, const struct sockaddr_storage *addr,
}
}
- print_local_ip_port(fd, "\t Actual: bind(%s, %d)\n");
-
goto out;
close_out:
close(fd);
@@ -371,19 +940,19 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr,
socklen_t addr_len)
{
int domain;
- int fd;
+ int fd = -1;
domain = addr->ss_family;
if (domain != AF_INET && domain != AF_INET6) {
log_err("Unsupported address family");
- return -1;
+ goto err;
}
fd = socket(domain, type, 0);
if (fd == -1) {
- log_err("Failed to creating client socket");
- return -1;
+ log_err("Failed to create client socket");
+ goto err;
}
if (connect(fd, (const struct sockaddr *)addr, addr_len) == -1) {
@@ -391,162 +960,394 @@ static int connect_to_server(int type, const struct sockaddr_storage *addr,
goto err;
}
- print_remote_ip_port(fd, "\t Actual: connect(%s, %d)");
- print_local_ip_port(fd, " from (%s, %d)\n");
+ goto out;
+err:
+ close(fd);
+ fd = -1;
+out:
+ return fd;
+}
+
+int init_pktinfo(int domain, struct cmsghdr *cmsg)
+{
+ struct in6_pktinfo *pktinfo6;
+ struct in_pktinfo *pktinfo4;
+
+ if (domain == AF_INET) {
+ cmsg->cmsg_level = SOL_IP;
+ cmsg->cmsg_type = IP_PKTINFO;
+ cmsg->cmsg_len = CMSG_LEN(sizeof(struct in_pktinfo));
+ pktinfo4 = (struct in_pktinfo *)CMSG_DATA(cmsg);
+ memset(pktinfo4, 0, sizeof(struct in_pktinfo));
+ if (inet_pton(domain, SRC4_IP,
+ (void *)&pktinfo4->ipi_spec_dst) != 1)
+ return -1;
+ } else if (domain == AF_INET6) {
+ cmsg->cmsg_level = SOL_IPV6;
+ cmsg->cmsg_type = IPV6_PKTINFO;
+ cmsg->cmsg_len = CMSG_LEN(sizeof(struct in6_pktinfo));
+ pktinfo6 = (struct in6_pktinfo *)CMSG_DATA(cmsg);
+ memset(pktinfo6, 0, sizeof(struct in6_pktinfo));
+ if (inet_pton(domain, SRC6_IP,
+ (void *)&pktinfo6->ipi6_addr) != 1)
+ return -1;
+ } else {
+ return -1;
+ }
return 0;
+}
+
+static int sendmsg_to_server(const struct sockaddr_storage *addr,
+ socklen_t addr_len, int set_cmsg, int *syscall_err)
+{
+ union {
+ char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))];
+ struct cmsghdr align;
+ } control6;
+ union {
+ char buf[CMSG_SPACE(sizeof(struct in_pktinfo))];
+ struct cmsghdr align;
+ } control4;
+ struct msghdr hdr;
+ struct iovec iov;
+ char data = 'a';
+ int domain;
+ int fd = -1;
+
+ domain = addr->ss_family;
+
+ if (domain != AF_INET && domain != AF_INET6) {
+ log_err("Unsupported address family");
+ goto err;
+ }
+
+ fd = socket(domain, SOCK_DGRAM, 0);
+ if (fd == -1) {
+ log_err("Failed to create client socket");
+ goto err;
+ }
+
+ memset(&iov, 0, sizeof(iov));
+ iov.iov_base = &data;
+ iov.iov_len = sizeof(data);
+
+ memset(&hdr, 0, sizeof(hdr));
+ hdr.msg_name = (void *)addr;
+ hdr.msg_namelen = addr_len;
+ hdr.msg_iov = &iov;
+ hdr.msg_iovlen = 1;
+
+ if (set_cmsg) {
+ if (domain == AF_INET) {
+ hdr.msg_control = &control4;
+ hdr.msg_controllen = sizeof(control4.buf);
+ } else if (domain == AF_INET6) {
+ hdr.msg_control = &control6;
+ hdr.msg_controllen = sizeof(control6.buf);
+ }
+ if (init_pktinfo(domain, CMSG_FIRSTHDR(&hdr))) {
+ log_err("Fail to init pktinfo");
+ goto err;
+ }
+ }
+
+ if (sendmsg(fd, &hdr, 0) != sizeof(data)) {
+ log_err("Fail to send message to server");
+ *syscall_err = errno;
+ goto err;
+ }
+
+ goto out;
err:
close(fd);
- return -1;
+ fd = -1;
+out:
+ return fd;
}
-static void print_test_case_num(int domain, int type)
+static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr)
{
- static int test_num;
-
- printf("Test case #%d (%s/%s):\n", ++test_num,
- (domain == AF_INET ? "IPv4" :
- domain == AF_INET6 ? "IPv6" :
- "unknown_domain"),
- (type == SOCK_STREAM ? "TCP" :
- type == SOCK_DGRAM ? "UDP" :
- "unknown_type"));
+ struct timeval tv;
+ struct msghdr hdr;
+ struct iovec iov;
+ char data[64];
+ fd_set rfds;
+
+ FD_ZERO(&rfds);
+ FD_SET(sockfd, &rfds);
+
+ tv.tv_sec = 2;
+ tv.tv_usec = 0;
+
+ if (select(sockfd + 1, &rfds, NULL, NULL, &tv) <= 0 ||
+ !FD_ISSET(sockfd, &rfds))
+ return -1;
+
+ memset(&iov, 0, sizeof(iov));
+ iov.iov_base = data;
+ iov.iov_len = sizeof(data);
+
+ memset(&hdr, 0, sizeof(hdr));
+ hdr.msg_name = src_addr;
+ hdr.msg_namelen = sizeof(struct sockaddr_storage);
+ hdr.msg_iov = &iov;
+ hdr.msg_iovlen = 1;
+
+ return recvmsg(sockfd, &hdr, 0);
}
-static int run_test_case(int domain, int type, const char *ip,
- unsigned short port)
+static int init_addrs(const struct sock_addr_test *test,
+ struct sockaddr_storage *requested_addr,
+ struct sockaddr_storage *expected_addr,
+ struct sockaddr_storage *expected_src_addr)
{
- struct sockaddr_storage addr;
- socklen_t addr_len = sizeof(addr);
+ socklen_t addr_len = sizeof(struct sockaddr_storage);
+
+ if (mk_sockaddr(test->domain, test->expected_ip, test->expected_port,
+ (struct sockaddr *)expected_addr, addr_len) == -1)
+ goto err;
+
+ if (mk_sockaddr(test->domain, test->requested_ip, test->requested_port,
+ (struct sockaddr *)requested_addr, addr_len) == -1)
+ goto err;
+
+ if (test->expected_src_ip &&
+ mk_sockaddr(test->domain, test->expected_src_ip, 0,
+ (struct sockaddr *)expected_src_addr, addr_len) == -1)
+ goto err;
+
+ return 0;
+err:
+ return -1;
+}
+
+static int run_bind_test_case(const struct sock_addr_test *test)
+{
+ socklen_t addr_len = sizeof(struct sockaddr_storage);
+ struct sockaddr_storage requested_addr;
+ struct sockaddr_storage expected_addr;
+ int clientfd = -1;
int servfd = -1;
int err = 0;
- print_test_case_num(domain, type);
-
- if (mk_sockaddr(domain, ip, port, (struct sockaddr *)&addr,
- addr_len) == -1)
- return -1;
+ if (init_addrs(test, &requested_addr, &expected_addr, NULL))
+ goto err;
- printf("\tRequested: bind(%s, %d) ..\n", ip, port);
- servfd = start_server(type, &addr, addr_len);
+ servfd = start_server(test->type, &requested_addr, addr_len);
if (servfd == -1)
goto err;
- printf("\tRequested: connect(%s, %d) from (*, *) ..\n", ip, port);
- if (connect_to_server(type, &addr, addr_len))
+ if (cmp_local_addr(servfd, &expected_addr))
+ goto err;
+
+ /* Try to connect to server just in case */
+ clientfd = connect_to_server(test->type, &expected_addr, addr_len);
+ if (clientfd == -1)
goto err;
goto out;
err:
err = -1;
out:
+ close(clientfd);
close(servfd);
return err;
}
-static void close_progs_fds(struct program *progs, size_t prog_cnt)
+static int run_connect_test_case(const struct sock_addr_test *test)
{
- size_t i;
+ socklen_t addr_len = sizeof(struct sockaddr_storage);
+ struct sockaddr_storage expected_src_addr;
+ struct sockaddr_storage requested_addr;
+ struct sockaddr_storage expected_addr;
+ int clientfd = -1;
+ int servfd = -1;
+ int err = 0;
- for (i = 0; i < prog_cnt; ++i) {
- close(progs[i].fd);
- progs[i].fd = -1;
- }
+ if (init_addrs(test, &requested_addr, &expected_addr,
+ &expected_src_addr))
+ goto err;
+
+ /* Prepare server to connect to */
+ servfd = start_server(test->type, &expected_addr, addr_len);
+ if (servfd == -1)
+ goto err;
+
+ clientfd = connect_to_server(test->type, &requested_addr, addr_len);
+ if (clientfd == -1)
+ goto err;
+
+ /* Make sure src and dst addrs were overridden properly */
+ if (cmp_peer_addr(clientfd, &expected_addr))
+ goto err;
+
+ if (cmp_local_ip(clientfd, &expected_src_addr))
+ goto err;
+
+ goto out;
+err:
+ err = -1;
+out:
+ close(clientfd);
+ close(servfd);
+ return err;
}
-static int load_and_attach_progs(int cgfd, struct program *progs,
- size_t prog_cnt)
+static int run_sendmsg_test_case(const struct sock_addr_test *test)
{
- size_t i;
-
- for (i = 0; i < prog_cnt; ++i) {
- printf("Load %s with invalid type (can pollute stderr) ",
- progs[i].name);
- fflush(stdout);
- progs[i].fd = progs[i].loadfn(progs[i].invalid_type, NULL);
- if (progs[i].fd != -1) {
- log_err("Load with invalid type accepted for %s",
- progs[i].name);
- goto err;
- }
- printf("... REJECTED\n");
+ socklen_t addr_len = sizeof(struct sockaddr_storage);
+ struct sockaddr_storage expected_src_addr;
+ struct sockaddr_storage requested_addr;
+ struct sockaddr_storage expected_addr;
+ struct sockaddr_storage real_src_addr;
+ int clientfd = -1;
+ int servfd = -1;
+ int set_cmsg;
+ int err = 0;
+
+ if (test->type != SOCK_DGRAM)
+ goto err;
- printf("Load %s with valid type", progs[i].name);
- progs[i].fd = progs[i].loadfn(progs[i].type, progs[i].name);
- if (progs[i].fd == -1) {
- log_err("Failed to load program %s", progs[i].name);
+ if (init_addrs(test, &requested_addr, &expected_addr,
+ &expected_src_addr))
+ goto err;
+
+ /* Prepare server to sendmsg to */
+ servfd = start_server(test->type, &expected_addr, addr_len);
+ if (servfd == -1)
+ goto err;
+
+ for (set_cmsg = 0; set_cmsg <= 1; ++set_cmsg) {
+ if (clientfd >= 0)
+ close(clientfd);
+
+ clientfd = sendmsg_to_server(&requested_addr, addr_len,
+ set_cmsg, &err);
+ if (err)
+ goto out;
+ else if (clientfd == -1)
goto err;
- }
- printf(" ... OK\n");
- printf("Attach %s with invalid type", progs[i].name);
- if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].invalid_type,
- BPF_F_ALLOW_OVERRIDE) != -1) {
- log_err("Attach with invalid type accepted for %s",
- progs[i].name);
+ /* Try to receive message on server instead of using
+ * getpeername(2) on client socket, to check that client's
+ * destination address was rewritten properly, since
+ * getpeername(2) doesn't work with unconnected datagram
+ * sockets.
+ *
+ * Get source address from recvmsg(2) as well to make sure
+ * source was rewritten properly: getsockname(2) can't be used
+ * since socket is unconnected and source defined for one
+ * specific packet may differ from the one used by default and
+ * returned by getsockname(2).
+ */
+ if (recvmsg_from_client(servfd, &real_src_addr) == -1)
goto err;
- }
- printf(" ... REJECTED\n");
- printf("Attach %s with valid type", progs[i].name);
- if (bpf_prog_attach(progs[i].fd, cgfd, progs[i].type,
- BPF_F_ALLOW_OVERRIDE) == -1) {
- log_err("Failed to attach program %s", progs[i].name);
+ if (cmp_addr(&real_src_addr, &expected_src_addr, /*cmp_port*/0))
goto err;
- }
- printf(" ... OK\n");
}
- return 0;
+ goto out;
err:
- close_progs_fds(progs, prog_cnt);
- return -1;
+ err = -1;
+out:
+ close(clientfd);
+ close(servfd);
+ return err;
}
-static int run_domain_test(int domain, int cgfd, struct program *progs,
- size_t prog_cnt, const char *ip, unsigned short port)
+static int run_test_case(int cgfd, const struct sock_addr_test *test)
{
+ int progfd = -1;
int err = 0;
- if (load_and_attach_progs(cgfd, progs, prog_cnt) == -1)
+ printf("Test case: %s .. ", test->descr);
+
+ progfd = test->loadfn(test);
+ if (test->expected_result == LOAD_REJECT && progfd < 0)
+ goto out;
+ else if (test->expected_result == LOAD_REJECT || progfd < 0)
+ goto err;
+
+ err = bpf_prog_attach(progfd, cgfd, test->attach_type,
+ BPF_F_ALLOW_OVERRIDE);
+ if (test->expected_result == ATTACH_REJECT && err) {
+ err = 0; /* error was expected, reset it */
+ goto out;
+ } else if (test->expected_result == ATTACH_REJECT || err) {
goto err;
+ }
- if (run_test_case(domain, SOCK_STREAM, ip, port) == -1)
+ switch (test->attach_type) {
+ case BPF_CGROUP_INET4_BIND:
+ case BPF_CGROUP_INET6_BIND:
+ err = run_bind_test_case(test);
+ break;
+ case BPF_CGROUP_INET4_CONNECT:
+ case BPF_CGROUP_INET6_CONNECT:
+ err = run_connect_test_case(test);
+ break;
+ case BPF_CGROUP_UDP4_SENDMSG:
+ case BPF_CGROUP_UDP6_SENDMSG:
+ err = run_sendmsg_test_case(test);
+ break;
+ default:
goto err;
+ }
+
+ if (test->expected_result == SYSCALL_EPERM && err == EPERM) {
+ err = 0; /* error was expected, reset it */
+ goto out;
+ }
+
+ if (test->expected_result == SYSCALL_ENOTSUPP && err == ENOTSUPP) {
+ err = 0; /* error was expected, reset it */
+ goto out;
+ }
- if (run_test_case(domain, SOCK_DGRAM, ip, port) == -1)
+ if (err || test->expected_result != SUCCESS)
goto err;
goto out;
err:
err = -1;
out:
- close_progs_fds(progs, prog_cnt);
+ /* Detaching w/o checking return code: best effort attempt. */
+ if (progfd != -1)
+ bpf_prog_detach(cgfd, test->attach_type);
+ close(progfd);
+ printf("[%s]\n", err ? "FAIL" : "PASS");
return err;
}
-static int run_test(void)
+static int run_tests(int cgfd)
+{
+ int passes = 0;
+ int fails = 0;
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(tests); ++i) {
+ if (run_test_case(cgfd, &tests[i]))
+ ++fails;
+ else
+ ++passes;
+ }
+ printf("Summary: %d PASSED, %d FAILED\n", passes, fails);
+ return fails ? -1 : 0;
+}
+
+int main(int argc, char **argv)
{
- size_t inet6_prog_cnt;
- size_t inet_prog_cnt;
int cgfd = -1;
int err = 0;
- struct program inet6_progs[] = {
- {BPF_CGROUP_INET6_BIND, bind6_prog_load, -1, "bind6",
- BPF_CGROUP_INET4_BIND},
- {BPF_CGROUP_INET6_CONNECT, connect6_prog_load, -1, "connect6",
- BPF_CGROUP_INET4_CONNECT},
- };
- inet6_prog_cnt = sizeof(inet6_progs) / sizeof(struct program);
-
- struct program inet_progs[] = {
- {BPF_CGROUP_INET4_BIND, bind4_prog_load, -1, "bind4",
- BPF_CGROUP_INET6_BIND},
- {BPF_CGROUP_INET4_CONNECT, connect4_prog_load, -1, "connect4",
- BPF_CGROUP_INET6_CONNECT},
- };
- inet_prog_cnt = sizeof(inet_progs) / sizeof(struct program);
+ if (argc < 2) {
+ fprintf(stderr,
+ "%s has to be run via %s.sh. Skip direct run.\n",
+ argv[0], argv[0]);
+ exit(err);
+ }
if (setup_cgroup_environment())
goto err;
@@ -558,12 +1359,7 @@ static int run_test(void)
if (join_cgroup(CG_PATH))
goto err;
- if (run_domain_test(AF_INET, cgfd, inet_progs, inet_prog_cnt, SERV4_IP,
- SERV4_PORT) == -1)
- goto err;
-
- if (run_domain_test(AF_INET6, cgfd, inet6_progs, inet6_prog_cnt,
- SERV6_IP, SERV6_PORT) == -1)
+ if (run_tests(cgfd))
goto err;
goto out;
@@ -572,17 +1368,5 @@ err:
out:
close(cgfd);
cleanup_cgroup_environment();
- printf(err ? "### FAIL\n" : "### SUCCESS\n");
return err;
}
-
-int main(int argc, char **argv)
-{
- if (argc < 2) {
- fprintf(stderr,
- "%s has to be run via %s.sh. Skip direct run.\n",
- argv[0], argv[0]);
- exit(0);
- }
- return run_test();
-}
diff --git a/tools/testing/selftests/bpf/test_sock_addr.sh b/tools/testing/selftests/bpf/test_sock_addr.sh
index c6e1dcf992c4..9832a875a828 100755
--- a/tools/testing/selftests/bpf/test_sock_addr.sh
+++ b/tools/testing/selftests/bpf/test_sock_addr.sh
@@ -4,7 +4,7 @@ set -eu
ping_once()
{
- ping -q -c 1 -W 1 ${1%%/*} >/dev/null 2>&1
+ ping -${1} -q -c 1 -W 1 ${2%%/*} >/dev/null 2>&1
}
wait_for_ip()
@@ -13,7 +13,7 @@ wait_for_ip()
echo -n "Wait for testing IPv4/IPv6 to become available "
for _i in $(seq ${MAX_PING_TRIES}); do
echo -n "."
- if ping_once ${TEST_IPv4} && ping_once ${TEST_IPv6}; then
+ if ping_once 4 ${TEST_IPv4} && ping_once 6 ${TEST_IPv6}; then
echo " OK"
return
fi
diff --git a/tools/testing/selftests/bpf/test_sockhash_kern.c b/tools/testing/selftests/bpf/test_sockhash_kern.c
new file mode 100644
index 000000000000..e6755916442a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockhash_kern.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+#undef SOCKMAP
+#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKHASH
+#include "./test_sockmap_kern.h"
diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
new file mode 100644
index 000000000000..05c8cb71724a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -0,0 +1,1524 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <sys/select.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <unistd.h>
+#include <string.h>
+#include <errno.h>
+#include <sys/ioctl.h>
+#include <stdbool.h>
+#include <signal.h>
+#include <fcntl.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <sched.h>
+
+#include <sys/time.h>
+#include <sys/resource.h>
+#include <sys/types.h>
+#include <sys/sendfile.h>
+
+#include <linux/netlink.h>
+#include <linux/socket.h>
+#include <linux/sock_diag.h>
+#include <linux/bpf.h>
+#include <linux/if_link.h>
+#include <assert.h>
+#include <libgen.h>
+
+#include <getopt.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_util.h"
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+int running;
+static void running_handler(int a);
+
+/* randomly selected ports for testing on lo */
+#define S1_PORT 10000
+#define S2_PORT 10001
+
+#define BPF_SOCKMAP_FILENAME "test_sockmap_kern.o"
+#define BPF_SOCKHASH_FILENAME "test_sockhash_kern.o"
+#define CG_PATH "/sockmap"
+
+/* global sockets */
+int s1, s2, c1, c2, p1, p2;
+int test_cnt;
+int passed;
+int failed;
+int map_fd[8];
+struct bpf_map *maps[8];
+int prog_fd[11];
+
+int txmsg_pass;
+int txmsg_noisy;
+int txmsg_redir;
+int txmsg_redir_noisy;
+int txmsg_drop;
+int txmsg_apply;
+int txmsg_cork;
+int txmsg_start;
+int txmsg_end;
+int txmsg_ingress;
+int txmsg_skb;
+
+static const struct option long_options[] = {
+ {"help", no_argument, NULL, 'h' },
+ {"cgroup", required_argument, NULL, 'c' },
+ {"rate", required_argument, NULL, 'r' },
+ {"verbose", no_argument, NULL, 'v' },
+ {"iov_count", required_argument, NULL, 'i' },
+ {"length", required_argument, NULL, 'l' },
+ {"test", required_argument, NULL, 't' },
+ {"data_test", no_argument, NULL, 'd' },
+ {"txmsg", no_argument, &txmsg_pass, 1 },
+ {"txmsg_noisy", no_argument, &txmsg_noisy, 1 },
+ {"txmsg_redir", no_argument, &txmsg_redir, 1 },
+ {"txmsg_redir_noisy", no_argument, &txmsg_redir_noisy, 1},
+ {"txmsg_drop", no_argument, &txmsg_drop, 1 },
+ {"txmsg_apply", required_argument, NULL, 'a'},
+ {"txmsg_cork", required_argument, NULL, 'k'},
+ {"txmsg_start", required_argument, NULL, 's'},
+ {"txmsg_end", required_argument, NULL, 'e'},
+ {"txmsg_ingress", no_argument, &txmsg_ingress, 1 },
+ {"txmsg_skb", no_argument, &txmsg_skb, 1 },
+ {0, 0, NULL, 0 }
+};
+
+static void usage(char *argv[])
+{
+ int i;
+
+ printf(" Usage: %s --cgroup <cgroup_path>\n", argv[0]);
+ printf(" options:\n");
+ for (i = 0; long_options[i].name != 0; i++) {
+ printf(" --%-12s", long_options[i].name);
+ if (long_options[i].flag != NULL)
+ printf(" flag (internal value:%d)\n",
+ *long_options[i].flag);
+ else
+ printf(" -%c\n", long_options[i].val);
+ }
+ printf("\n");
+}
+
+static int sockmap_init_sockets(int verbose)
+{
+ int i, err, one = 1;
+ struct sockaddr_in addr;
+ int *fds[4] = {&s1, &s2, &c1, &c2};
+
+ s1 = s2 = p1 = p2 = c1 = c2 = 0;
+
+ /* Init sockets */
+ for (i = 0; i < 4; i++) {
+ *fds[i] = socket(AF_INET, SOCK_STREAM, 0);
+ if (*fds[i] < 0) {
+ perror("socket s1 failed()");
+ return errno;
+ }
+ }
+
+ /* Allow reuse */
+ for (i = 0; i < 2; i++) {
+ err = setsockopt(*fds[i], SOL_SOCKET, SO_REUSEADDR,
+ (char *)&one, sizeof(one));
+ if (err) {
+ perror("setsockopt failed()");
+ return errno;
+ }
+ }
+
+ /* Non-blocking sockets */
+ for (i = 0; i < 2; i++) {
+ err = ioctl(*fds[i], FIONBIO, (char *)&one);
+ if (err < 0) {
+ perror("ioctl s1 failed()");
+ return errno;
+ }
+ }
+
+ /* Bind server sockets */
+ memset(&addr, 0, sizeof(struct sockaddr_in));
+ addr.sin_family = AF_INET;
+ addr.sin_addr.s_addr = inet_addr("127.0.0.1");
+
+ addr.sin_port = htons(S1_PORT);
+ err = bind(s1, (struct sockaddr *)&addr, sizeof(addr));
+ if (err < 0) {
+ perror("bind s1 failed()\n");
+ return errno;
+ }
+
+ addr.sin_port = htons(S2_PORT);
+ err = bind(s2, (struct sockaddr *)&addr, sizeof(addr));
+ if (err < 0) {
+ perror("bind s2 failed()\n");
+ return errno;
+ }
+
+ /* Listen server sockets */
+ addr.sin_port = htons(S1_PORT);
+ err = listen(s1, 32);
+ if (err < 0) {
+ perror("listen s1 failed()\n");
+ return errno;
+ }
+
+ addr.sin_port = htons(S2_PORT);
+ err = listen(s2, 32);
+ if (err < 0) {
+ perror("listen s1 failed()\n");
+ return errno;
+ }
+
+ /* Initiate Connect */
+ addr.sin_port = htons(S1_PORT);
+ err = connect(c1, (struct sockaddr *)&addr, sizeof(addr));
+ if (err < 0 && errno != EINPROGRESS) {
+ perror("connect c1 failed()\n");
+ return errno;
+ }
+
+ addr.sin_port = htons(S2_PORT);
+ err = connect(c2, (struct sockaddr *)&addr, sizeof(addr));
+ if (err < 0 && errno != EINPROGRESS) {
+ perror("connect c2 failed()\n");
+ return errno;
+ } else if (err < 0) {
+ err = 0;
+ }
+
+ /* Accept Connecrtions */
+ p1 = accept(s1, NULL, NULL);
+ if (p1 < 0) {
+ perror("accept s1 failed()\n");
+ return errno;
+ }
+
+ p2 = accept(s2, NULL, NULL);
+ if (p2 < 0) {
+ perror("accept s1 failed()\n");
+ return errno;
+ }
+
+ if (verbose) {
+ printf("connected sockets: c1 <-> p1, c2 <-> p2\n");
+ printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n",
+ c1, s1, c2, s2);
+ }
+ return 0;
+}
+
+struct msg_stats {
+ size_t bytes_sent;
+ size_t bytes_recvd;
+ struct timespec start;
+ struct timespec end;
+};
+
+struct sockmap_options {
+ int verbose;
+ bool base;
+ bool sendpage;
+ bool data_test;
+ bool drop_expected;
+ int iov_count;
+ int iov_length;
+ int rate;
+};
+
+static int msg_loop_sendpage(int fd, int iov_length, int cnt,
+ struct msg_stats *s,
+ struct sockmap_options *opt)
+{
+ bool drop = opt->drop_expected;
+ unsigned char k = 0;
+ FILE *file;
+ int i, fp;
+
+ file = fopen(".sendpage_tst.tmp", "w+");
+ for (i = 0; i < iov_length * cnt; i++, k++)
+ fwrite(&k, sizeof(char), 1, file);
+ fflush(file);
+ fseek(file, 0, SEEK_SET);
+ fclose(file);
+
+ fp = open(".sendpage_tst.tmp", O_RDONLY);
+ clock_gettime(CLOCK_MONOTONIC, &s->start);
+ for (i = 0; i < cnt; i++) {
+ int sent = sendfile(fd, fp, NULL, iov_length);
+
+ if (!drop && sent < 0) {
+ perror("send loop error:");
+ close(fp);
+ return sent;
+ } else if (drop && sent >= 0) {
+ printf("sendpage loop error expected: %i\n", sent);
+ close(fp);
+ return -EIO;
+ }
+
+ if (sent > 0)
+ s->bytes_sent += sent;
+ }
+ clock_gettime(CLOCK_MONOTONIC, &s->end);
+ close(fp);
+ return 0;
+}
+
+static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+ struct msg_stats *s, bool tx,
+ struct sockmap_options *opt)
+{
+ struct msghdr msg = {0};
+ int err, i, flags = MSG_NOSIGNAL;
+ struct iovec *iov;
+ unsigned char k;
+ bool data_test = opt->data_test;
+ bool drop = opt->drop_expected;
+
+ iov = calloc(iov_count, sizeof(struct iovec));
+ if (!iov)
+ return errno;
+
+ k = 0;
+ for (i = 0; i < iov_count; i++) {
+ unsigned char *d = calloc(iov_length, sizeof(char));
+
+ if (!d) {
+ fprintf(stderr, "iov_count %i/%i OOM\n", i, iov_count);
+ goto out_errno;
+ }
+ iov[i].iov_base = d;
+ iov[i].iov_len = iov_length;
+
+ if (data_test && tx) {
+ int j;
+
+ for (j = 0; j < iov_length; j++)
+ d[j] = k++;
+ }
+ }
+
+ msg.msg_iov = iov;
+ msg.msg_iovlen = iov_count;
+ k = 0;
+
+ if (tx) {
+ clock_gettime(CLOCK_MONOTONIC, &s->start);
+ for (i = 0; i < cnt; i++) {
+ int sent = sendmsg(fd, &msg, flags);
+
+ if (!drop && sent < 0) {
+ perror("send loop error:");
+ goto out_errno;
+ } else if (drop && sent >= 0) {
+ printf("send loop error expected: %i\n", sent);
+ errno = -EIO;
+ goto out_errno;
+ }
+ if (sent > 0)
+ s->bytes_sent += sent;
+ }
+ clock_gettime(CLOCK_MONOTONIC, &s->end);
+ } else {
+ int slct, recv, max_fd = fd;
+ int fd_flags = O_NONBLOCK;
+ struct timeval timeout;
+ float total_bytes;
+ int bytes_cnt = 0;
+ int chunk_sz;
+ fd_set w;
+
+ if (opt->sendpage)
+ chunk_sz = iov_length * cnt;
+ else
+ chunk_sz = iov_length * iov_count;
+
+ fcntl(fd, fd_flags);
+ total_bytes = (float)iov_count * (float)iov_length * (float)cnt;
+ err = clock_gettime(CLOCK_MONOTONIC, &s->start);
+ if (err < 0)
+ perror("recv start time: ");
+ while (s->bytes_recvd < total_bytes) {
+ if (txmsg_cork) {
+ timeout.tv_sec = 0;
+ timeout.tv_usec = 1000;
+ } else {
+ timeout.tv_sec = 1;
+ timeout.tv_usec = 0;
+ }
+
+ /* FD sets */
+ FD_ZERO(&w);
+ FD_SET(fd, &w);
+
+ slct = select(max_fd + 1, &w, NULL, NULL, &timeout);
+ if (slct == -1) {
+ perror("select()");
+ clock_gettime(CLOCK_MONOTONIC, &s->end);
+ goto out_errno;
+ } else if (!slct) {
+ if (opt->verbose)
+ fprintf(stderr, "unexpected timeout\n");
+ errno = -EIO;
+ clock_gettime(CLOCK_MONOTONIC, &s->end);
+ goto out_errno;
+ }
+
+ recv = recvmsg(fd, &msg, flags);
+ if (recv < 0) {
+ if (errno != EWOULDBLOCK) {
+ clock_gettime(CLOCK_MONOTONIC, &s->end);
+ perror("recv failed()\n");
+ goto out_errno;
+ }
+ }
+
+ s->bytes_recvd += recv;
+
+ if (data_test) {
+ int j;
+
+ for (i = 0; i < msg.msg_iovlen; i++) {
+ unsigned char *d = iov[i].iov_base;
+
+ for (j = 0;
+ j < iov[i].iov_len && recv; j++) {
+ if (d[j] != k++) {
+ errno = -EIO;
+ fprintf(stderr,
+ "detected data corruption @iov[%i]:%i %02x != %02x, %02x ?= %02x\n",
+ i, j, d[j], k - 1, d[j+1], k);
+ goto out_errno;
+ }
+ bytes_cnt++;
+ if (bytes_cnt == chunk_sz) {
+ k = 0;
+ bytes_cnt = 0;
+ }
+ recv--;
+ }
+ }
+ }
+ }
+ clock_gettime(CLOCK_MONOTONIC, &s->end);
+ }
+
+ for (i = 0; i < iov_count; i++)
+ free(iov[i].iov_base);
+ free(iov);
+ return 0;
+out_errno:
+ for (i = 0; i < iov_count; i++)
+ free(iov[i].iov_base);
+ free(iov);
+ return errno;
+}
+
+static float giga = 1000000000;
+
+static inline float sentBps(struct msg_stats s)
+{
+ return s.bytes_sent / (s.end.tv_sec - s.start.tv_sec);
+}
+
+static inline float recvdBps(struct msg_stats s)
+{
+ return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec);
+}
+
+static int sendmsg_test(struct sockmap_options *opt)
+{
+ float sent_Bps = 0, recvd_Bps = 0;
+ int rx_fd, txpid, rxpid, err = 0;
+ struct msg_stats s = {0};
+ int iov_count = opt->iov_count;
+ int iov_buf = opt->iov_length;
+ int rx_status, tx_status;
+ int cnt = opt->rate;
+
+ errno = 0;
+
+ if (opt->base)
+ rx_fd = p1;
+ else
+ rx_fd = p2;
+
+ rxpid = fork();
+ if (rxpid == 0) {
+ if (opt->drop_expected)
+ exit(0);
+
+ if (opt->sendpage)
+ iov_count = 1;
+ err = msg_loop(rx_fd, iov_count, iov_buf,
+ cnt, &s, false, opt);
+ if (err && opt->verbose)
+ fprintf(stderr,
+ "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n",
+ iov_count, iov_buf, cnt, err);
+ shutdown(p2, SHUT_RDWR);
+ shutdown(p1, SHUT_RDWR);
+ if (s.end.tv_sec - s.start.tv_sec) {
+ sent_Bps = sentBps(s);
+ recvd_Bps = recvdBps(s);
+ }
+ if (opt->verbose)
+ fprintf(stdout,
+ "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n",
+ s.bytes_sent, sent_Bps, sent_Bps/giga,
+ s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+ if (err && txmsg_cork)
+ err = 0;
+ exit(err ? 1 : 0);
+ } else if (rxpid == -1) {
+ perror("msg_loop_rx: ");
+ return errno;
+ }
+
+ txpid = fork();
+ if (txpid == 0) {
+ if (opt->sendpage)
+ err = msg_loop_sendpage(c1, iov_buf, cnt, &s, opt);
+ else
+ err = msg_loop(c1, iov_count, iov_buf,
+ cnt, &s, true, opt);
+
+ if (err)
+ fprintf(stderr,
+ "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n",
+ iov_count, iov_buf, cnt, err);
+ shutdown(c1, SHUT_RDWR);
+ if (s.end.tv_sec - s.start.tv_sec) {
+ sent_Bps = sentBps(s);
+ recvd_Bps = recvdBps(s);
+ }
+ if (opt->verbose)
+ fprintf(stdout,
+ "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n",
+ s.bytes_sent, sent_Bps, sent_Bps/giga,
+ s.bytes_recvd, recvd_Bps, recvd_Bps/giga);
+ exit(err ? 1 : 0);
+ } else if (txpid == -1) {
+ perror("msg_loop_tx: ");
+ return errno;
+ }
+
+ assert(waitpid(rxpid, &rx_status, 0) == rxpid);
+ assert(waitpid(txpid, &tx_status, 0) == txpid);
+ if (WIFEXITED(rx_status)) {
+ err = WEXITSTATUS(rx_status);
+ if (err) {
+ fprintf(stderr, "rx thread exited with err %d. ", err);
+ goto out;
+ }
+ }
+ if (WIFEXITED(tx_status)) {
+ err = WEXITSTATUS(tx_status);
+ if (err)
+ fprintf(stderr, "tx thread exited with err %d. ", err);
+ }
+out:
+ return err;
+}
+
+static int forever_ping_pong(int rate, struct sockmap_options *opt)
+{
+ struct timeval timeout;
+ char buf[1024] = {0};
+ int sc;
+
+ timeout.tv_sec = 10;
+ timeout.tv_usec = 0;
+
+ /* Ping/Pong data from client to server */
+ sc = send(c1, buf, sizeof(buf), 0);
+ if (sc < 0) {
+ perror("send failed()\n");
+ return sc;
+ }
+
+ do {
+ int s, rc, i, max_fd = p2;
+ fd_set w;
+
+ /* FD sets */
+ FD_ZERO(&w);
+ FD_SET(c1, &w);
+ FD_SET(c2, &w);
+ FD_SET(p1, &w);
+ FD_SET(p2, &w);
+
+ s = select(max_fd + 1, &w, NULL, NULL, &timeout);
+ if (s == -1) {
+ perror("select()");
+ break;
+ } else if (!s) {
+ fprintf(stderr, "unexpected timeout\n");
+ break;
+ }
+
+ for (i = 0; i <= max_fd && s > 0; ++i) {
+ if (!FD_ISSET(i, &w))
+ continue;
+
+ s--;
+
+ rc = recv(i, buf, sizeof(buf), 0);
+ if (rc < 0) {
+ if (errno != EWOULDBLOCK) {
+ perror("recv failed()\n");
+ return rc;
+ }
+ }
+
+ if (rc == 0) {
+ close(i);
+ break;
+ }
+
+ sc = send(i, buf, rc, 0);
+ if (sc < 0) {
+ perror("send failed()\n");
+ return sc;
+ }
+ }
+
+ if (rate)
+ sleep(rate);
+
+ if (opt->verbose) {
+ printf(".");
+ fflush(stdout);
+
+ }
+ } while (running);
+
+ return 0;
+}
+
+enum {
+ PING_PONG,
+ SENDMSG,
+ BASE,
+ BASE_SENDPAGE,
+ SENDPAGE,
+};
+
+static int run_options(struct sockmap_options *options, int cg_fd, int test)
+{
+ int i, key, next_key, err, tx_prog_fd = -1, zero = 0;
+
+ /* If base test skip BPF setup */
+ if (test == BASE || test == BASE_SENDPAGE)
+ goto run;
+
+ /* Attach programs to sockmap */
+ err = bpf_prog_attach(prog_fd[0], map_fd[0],
+ BPF_SK_SKB_STREAM_PARSER, 0);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n",
+ prog_fd[0], map_fd[0], err, strerror(errno));
+ return err;
+ }
+
+ err = bpf_prog_attach(prog_fd[1], map_fd[0],
+ BPF_SK_SKB_STREAM_VERDICT, 0);
+ if (err) {
+ fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n",
+ err, strerror(errno));
+ return err;
+ }
+
+ /* Attach to cgroups */
+ err = bpf_prog_attach(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS, 0);
+ if (err) {
+ fprintf(stderr, "ERROR: bpf_prog_attach (groups): %d (%s)\n",
+ err, strerror(errno));
+ return err;
+ }
+
+run:
+ err = sockmap_init_sockets(options->verbose);
+ if (err) {
+ fprintf(stderr, "ERROR: test socket failed: %d\n", err);
+ goto out;
+ }
+
+ /* Attach txmsg program to sockmap */
+ if (txmsg_pass)
+ tx_prog_fd = prog_fd[3];
+ else if (txmsg_noisy)
+ tx_prog_fd = prog_fd[4];
+ else if (txmsg_redir)
+ tx_prog_fd = prog_fd[5];
+ else if (txmsg_redir_noisy)
+ tx_prog_fd = prog_fd[6];
+ else if (txmsg_drop)
+ tx_prog_fd = prog_fd[9];
+ /* apply and cork must be last */
+ else if (txmsg_apply)
+ tx_prog_fd = prog_fd[7];
+ else if (txmsg_cork)
+ tx_prog_fd = prog_fd[8];
+ else
+ tx_prog_fd = 0;
+
+ if (tx_prog_fd) {
+ int redir_fd, i = 0;
+
+ err = bpf_prog_attach(tx_prog_fd,
+ map_fd[1], BPF_SK_MSG_VERDICT, 0);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_prog_attach (txmsg): %d (%s)\n",
+ err, strerror(errno));
+ goto out;
+ }
+
+ err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg): %d (%s\n",
+ err, strerror(errno));
+ goto out;
+ }
+
+ if (txmsg_redir || txmsg_redir_noisy)
+ redir_fd = c2;
+ else
+ redir_fd = c1;
+
+ err = bpf_map_update_elem(map_fd[2], &i, &redir_fd, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg): %d (%s\n",
+ err, strerror(errno));
+ goto out;
+ }
+
+ if (txmsg_apply) {
+ err = bpf_map_update_elem(map_fd[3],
+ &i, &txmsg_apply, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n",
+ err, strerror(errno));
+ goto out;
+ }
+ }
+
+ if (txmsg_cork) {
+ err = bpf_map_update_elem(map_fd[4],
+ &i, &txmsg_cork, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n",
+ err, strerror(errno));
+ goto out;
+ }
+ }
+
+ if (txmsg_start) {
+ err = bpf_map_update_elem(map_fd[5],
+ &i, &txmsg_start, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n",
+ err, strerror(errno));
+ goto out;
+ }
+ }
+
+ if (txmsg_end) {
+ i = 1;
+ err = bpf_map_update_elem(map_fd[5],
+ &i, &txmsg_end, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n",
+ err, strerror(errno));
+ goto out;
+ }
+ }
+
+ if (txmsg_ingress) {
+ int in = BPF_F_INGRESS;
+
+ i = 0;
+ err = bpf_map_update_elem(map_fd[6], &i, &in, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n",
+ err, strerror(errno));
+ }
+ i = 1;
+ err = bpf_map_update_elem(map_fd[1], &i, &p1, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (p1 txmsg): %d (%s)\n",
+ err, strerror(errno));
+ }
+ err = bpf_map_update_elem(map_fd[2], &i, &p1, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (p1 redir): %d (%s)\n",
+ err, strerror(errno));
+ }
+
+ i = 2;
+ err = bpf_map_update_elem(map_fd[2], &i, &p2, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (p2 txmsg): %d (%s)\n",
+ err, strerror(errno));
+ }
+ }
+
+ if (txmsg_skb) {
+ int skb_fd = (test == SENDMSG || test == SENDPAGE) ?
+ p2 : p1;
+ int ingress = BPF_F_INGRESS;
+
+ i = 0;
+ err = bpf_map_update_elem(map_fd[7],
+ &i, &ingress, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n",
+ err, strerror(errno));
+ }
+
+ i = 3;
+ err = bpf_map_update_elem(map_fd[0],
+ &i, &skb_fd, BPF_ANY);
+ if (err) {
+ fprintf(stderr,
+ "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n",
+ err, strerror(errno));
+ }
+ }
+ }
+
+ if (txmsg_drop)
+ options->drop_expected = true;
+
+ if (test == PING_PONG)
+ err = forever_ping_pong(options->rate, options);
+ else if (test == SENDMSG) {
+ options->base = false;
+ options->sendpage = false;
+ err = sendmsg_test(options);
+ } else if (test == SENDPAGE) {
+ options->base = false;
+ options->sendpage = true;
+ err = sendmsg_test(options);
+ } else if (test == BASE) {
+ options->base = true;
+ options->sendpage = false;
+ err = sendmsg_test(options);
+ } else if (test == BASE_SENDPAGE) {
+ options->base = true;
+ options->sendpage = true;
+ err = sendmsg_test(options);
+ } else
+ fprintf(stderr, "unknown test\n");
+out:
+ /* Detatch and zero all the maps */
+ bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS);
+ bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER);
+ bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT);
+ if (tx_prog_fd >= 0)
+ bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT);
+
+ for (i = 0; i < 8; i++) {
+ key = next_key = 0;
+ bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
+ while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) {
+ bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY);
+ key = next_key;
+ }
+ }
+
+ close(s1);
+ close(s2);
+ close(p1);
+ close(p2);
+ close(c1);
+ close(c2);
+ return err;
+}
+
+static char *test_to_str(int test)
+{
+ switch (test) {
+ case SENDMSG:
+ return "sendmsg";
+ case SENDPAGE:
+ return "sendpage";
+ }
+ return "unknown";
+}
+
+#define OPTSTRING 60
+static void test_options(char *options)
+{
+ char tstr[OPTSTRING];
+
+ memset(options, 0, OPTSTRING);
+
+ if (txmsg_pass)
+ strncat(options, "pass,", OPTSTRING);
+ if (txmsg_noisy)
+ strncat(options, "pass_noisy,", OPTSTRING);
+ if (txmsg_redir)
+ strncat(options, "redir,", OPTSTRING);
+ if (txmsg_redir_noisy)
+ strncat(options, "redir_noisy,", OPTSTRING);
+ if (txmsg_drop)
+ strncat(options, "drop,", OPTSTRING);
+ if (txmsg_apply) {
+ snprintf(tstr, OPTSTRING, "apply %d,", txmsg_apply);
+ strncat(options, tstr, OPTSTRING);
+ }
+ if (txmsg_cork) {
+ snprintf(tstr, OPTSTRING, "cork %d,", txmsg_cork);
+ strncat(options, tstr, OPTSTRING);
+ }
+ if (txmsg_start) {
+ snprintf(tstr, OPTSTRING, "start %d,", txmsg_start);
+ strncat(options, tstr, OPTSTRING);
+ }
+ if (txmsg_end) {
+ snprintf(tstr, OPTSTRING, "end %d,", txmsg_end);
+ strncat(options, tstr, OPTSTRING);
+ }
+ if (txmsg_ingress)
+ strncat(options, "ingress,", OPTSTRING);
+ if (txmsg_skb)
+ strncat(options, "skb,", OPTSTRING);
+}
+
+static int __test_exec(int cgrp, int test, struct sockmap_options *opt)
+{
+ char *options = calloc(OPTSTRING, sizeof(char));
+ int err;
+
+ if (test == SENDPAGE)
+ opt->sendpage = true;
+ else
+ opt->sendpage = false;
+
+ if (txmsg_drop)
+ opt->drop_expected = true;
+ else
+ opt->drop_expected = false;
+
+ test_options(options);
+
+ fprintf(stdout,
+ "[TEST %i]: (%i, %i, %i, %s, %s): ",
+ test_cnt, opt->rate, opt->iov_count, opt->iov_length,
+ test_to_str(test), options);
+ fflush(stdout);
+ err = run_options(opt, cgrp, test);
+ fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED");
+ test_cnt++;
+ !err ? passed++ : failed++;
+ free(options);
+ return err;
+}
+
+static int test_exec(int cgrp, struct sockmap_options *opt)
+{
+ int err = __test_exec(cgrp, SENDMSG, opt);
+
+ if (err)
+ goto out;
+
+ err = __test_exec(cgrp, SENDPAGE, opt);
+out:
+ return err;
+}
+
+static int test_loop(int cgrp)
+{
+ struct sockmap_options opt;
+
+ int err, i, l, r;
+
+ opt.verbose = 0;
+ opt.base = false;
+ opt.sendpage = false;
+ opt.data_test = false;
+ opt.drop_expected = false;
+ opt.iov_count = 0;
+ opt.iov_length = 0;
+ opt.rate = 0;
+
+ r = 1;
+ for (i = 1; i < 100; i += 33) {
+ for (l = 1; l < 100; l += 33) {
+ opt.rate = r;
+ opt.iov_count = i;
+ opt.iov_length = l;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+ }
+ sched_yield();
+out:
+ return err;
+}
+
+static int test_txmsg(int cgrp)
+{
+ int err;
+
+ txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
+ txmsg_apply = txmsg_cork = 0;
+ txmsg_ingress = txmsg_skb = 0;
+
+ txmsg_pass = 1;
+ err = test_loop(cgrp);
+ txmsg_pass = 0;
+ if (err)
+ goto out;
+
+ txmsg_redir = 1;
+ err = test_loop(cgrp);
+ txmsg_redir = 0;
+ if (err)
+ goto out;
+
+ txmsg_drop = 1;
+ err = test_loop(cgrp);
+ txmsg_drop = 0;
+ if (err)
+ goto out;
+
+ txmsg_redir = 1;
+ txmsg_ingress = 1;
+ err = test_loop(cgrp);
+ txmsg_redir = 0;
+ txmsg_ingress = 0;
+ if (err)
+ goto out;
+out:
+ txmsg_pass = 0;
+ txmsg_redir = 0;
+ txmsg_drop = 0;
+ return err;
+}
+
+static int test_send(struct sockmap_options *opt, int cgrp)
+{
+ int err;
+
+ opt->iov_length = 1;
+ opt->iov_count = 1;
+ opt->rate = 1;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 1;
+ opt->iov_count = 1024;
+ opt->rate = 1;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 1024;
+ opt->iov_count = 1;
+ opt->rate = 1;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 1;
+ opt->iov_count = 1;
+ opt->rate = 512;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->iov_length = 256;
+ opt->iov_count = 1024;
+ opt->rate = 2;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+
+ opt->rate = 100;
+ opt->iov_count = 1;
+ opt->iov_length = 5;
+ err = test_exec(cgrp, opt);
+ if (err)
+ goto out;
+out:
+ sched_yield();
+ return err;
+}
+
+static int test_mixed(int cgrp)
+{
+ struct sockmap_options opt = {0};
+ int err;
+
+ txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0;
+ txmsg_apply = txmsg_cork = 0;
+ txmsg_start = txmsg_end = 0;
+ /* Test small and large iov_count values with pass/redir/apply/cork */
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 0;
+ txmsg_cork = 1;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1;
+ txmsg_cork = 1;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1024;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 0;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_apply = 1024;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 1;
+ txmsg_redir = 0;
+ txmsg_cork = 4096;
+ txmsg_apply = 4096;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 0;
+ txmsg_cork = 1;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1024;
+ txmsg_cork = 0;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 0;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_apply = 1024;
+ txmsg_cork = 1024;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+
+ txmsg_pass = 0;
+ txmsg_redir = 1;
+ txmsg_cork = 4096;
+ txmsg_apply = 4096;
+ err = test_send(&opt, cgrp);
+ if (err)
+ goto out;
+out:
+ return err;
+}
+
+static int test_start_end(int cgrp)
+{
+ struct sockmap_options opt = {0};
+ int err, i;
+
+ /* Test basic start/end with lots of iov_count and iov_lengths */
+ txmsg_start = 1;
+ txmsg_end = 2;
+ err = test_txmsg(cgrp);
+ if (err)
+ goto out;
+
+ /* Test start/end with cork */
+ opt.rate = 16;
+ opt.iov_count = 1;
+ opt.iov_length = 100;
+ txmsg_cork = 1600;
+
+ for (i = 99; i <= 1600; i += 500) {
+ txmsg_start = 0;
+ txmsg_end = i;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+
+ /* Test start/end with cork but pull data in middle */
+ for (i = 199; i <= 1600; i += 500) {
+ txmsg_start = 100;
+ txmsg_end = i;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+ }
+
+ /* Test start/end with cork pulling last sg entry */
+ txmsg_start = 1500;
+ txmsg_end = 1600;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end pull of single byte in last page */
+ txmsg_start = 1111;
+ txmsg_end = 1112;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end with end < start */
+ txmsg_start = 1111;
+ txmsg_end = 0;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end with end > data */
+ txmsg_start = 0;
+ txmsg_end = 1601;
+ err = test_exec(cgrp, &opt);
+ if (err)
+ goto out;
+
+ /* Test start/end with start > data */
+ txmsg_start = 1601;
+ txmsg_end = 1600;
+ err = test_exec(cgrp, &opt);
+
+out:
+ txmsg_start = 0;
+ txmsg_end = 0;
+ sched_yield();
+ return err;
+}
+
+char *map_names[] = {
+ "sock_map",
+ "sock_map_txmsg",
+ "sock_map_redir",
+ "sock_apply_bytes",
+ "sock_cork_bytes",
+ "sock_pull_bytes",
+ "sock_redir_flags",
+ "sock_skb_opts",
+};
+
+int prog_attach_type[] = {
+ BPF_SK_SKB_STREAM_PARSER,
+ BPF_SK_SKB_STREAM_VERDICT,
+ BPF_CGROUP_SOCK_OPS,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+};
+
+int prog_type[] = {
+ BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_SK_SKB,
+ BPF_PROG_TYPE_SOCK_OPS,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+};
+
+static int populate_progs(char *bpf_file)
+{
+ struct bpf_program *prog;
+ struct bpf_object *obj;
+ int i = 0;
+ long err;
+
+ obj = bpf_object__open(bpf_file);
+ err = libbpf_get_error(obj);
+ if (err) {
+ char err_buf[256];
+
+ libbpf_strerror(err, err_buf, sizeof(err_buf));
+ printf("Unable to load eBPF objects in file '%s' : %s\n",
+ bpf_file, err_buf);
+ return -1;
+ }
+
+ bpf_object__for_each_program(prog, obj) {
+ bpf_program__set_type(prog, prog_type[i]);
+ bpf_program__set_expected_attach_type(prog,
+ prog_attach_type[i]);
+ i++;
+ }
+
+ i = bpf_object__load(obj);
+ i = 0;
+ bpf_object__for_each_program(prog, obj) {
+ prog_fd[i] = bpf_program__fd(prog);
+ i++;
+ }
+
+ for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) {
+ maps[i] = bpf_object__find_map_by_name(obj, map_names[i]);
+ map_fd[i] = bpf_map__fd(maps[i]);
+ if (map_fd[i] < 0) {
+ fprintf(stderr, "load_bpf_file: (%i) %s\n",
+ map_fd[i], strerror(errno));
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int __test_suite(char *bpf_file)
+{
+ int cg_fd, err;
+
+ err = populate_progs(bpf_file);
+ if (err < 0) {
+ fprintf(stderr, "ERROR: (%i) load bpf failed\n", err);
+ return err;
+ }
+
+ if (setup_cgroup_environment()) {
+ fprintf(stderr, "ERROR: cgroup env failed\n");
+ return -EINVAL;
+ }
+
+ cg_fd = create_and_get_cgroup(CG_PATH);
+ if (cg_fd < 0) {
+ fprintf(stderr,
+ "ERROR: (%i) open cg path failed: %s\n",
+ cg_fd, optarg);
+ return cg_fd;
+ }
+
+ if (join_cgroup(CG_PATH)) {
+ fprintf(stderr, "ERROR: failed to join cgroup\n");
+ return -EINVAL;
+ }
+
+ /* Tests basic commands and APIs with range of iov values */
+ txmsg_start = txmsg_end = 0;
+ err = test_txmsg(cg_fd);
+ if (err)
+ goto out;
+
+ /* Tests interesting combinations of APIs used together */
+ err = test_mixed(cg_fd);
+ if (err)
+ goto out;
+
+ /* Tests pull_data API using start/end API */
+ err = test_start_end(cg_fd);
+ if (err)
+ goto out;
+
+out:
+ printf("Summary: %i PASSED %i FAILED\n", passed, failed);
+ cleanup_cgroup_environment();
+ close(cg_fd);
+ return err;
+}
+
+static int test_suite(void)
+{
+ int err;
+
+ err = __test_suite(BPF_SOCKMAP_FILENAME);
+ if (err)
+ goto out;
+ err = __test_suite(BPF_SOCKHASH_FILENAME);
+out:
+ return err;
+}
+
+int main(int argc, char **argv)
+{
+ struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
+ int iov_count = 1, length = 1024, rate = 1;
+ struct sockmap_options options = {0};
+ int opt, longindex, err, cg_fd = 0;
+ char *bpf_file = BPF_SOCKMAP_FILENAME;
+ int test = PING_PONG;
+
+ if (setrlimit(RLIMIT_MEMLOCK, &r)) {
+ perror("setrlimit(RLIMIT_MEMLOCK)");
+ return 1;
+ }
+
+ if (argc < 2)
+ return test_suite();
+
+ while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:",
+ long_options, &longindex)) != -1) {
+ switch (opt) {
+ case 's':
+ txmsg_start = atoi(optarg);
+ break;
+ case 'e':
+ txmsg_end = atoi(optarg);
+ break;
+ case 'a':
+ txmsg_apply = atoi(optarg);
+ break;
+ case 'k':
+ txmsg_cork = atoi(optarg);
+ break;
+ case 'c':
+ cg_fd = open(optarg, O_DIRECTORY, O_RDONLY);
+ if (cg_fd < 0) {
+ fprintf(stderr,
+ "ERROR: (%i) open cg path failed: %s\n",
+ cg_fd, optarg);
+ return cg_fd;
+ }
+ break;
+ case 'r':
+ rate = atoi(optarg);
+ break;
+ case 'v':
+ options.verbose = 1;
+ break;
+ case 'i':
+ iov_count = atoi(optarg);
+ break;
+ case 'l':
+ length = atoi(optarg);
+ break;
+ case 'd':
+ options.data_test = true;
+ break;
+ case 't':
+ if (strcmp(optarg, "ping") == 0) {
+ test = PING_PONG;
+ } else if (strcmp(optarg, "sendmsg") == 0) {
+ test = SENDMSG;
+ } else if (strcmp(optarg, "base") == 0) {
+ test = BASE;
+ } else if (strcmp(optarg, "base_sendpage") == 0) {
+ test = BASE_SENDPAGE;
+ } else if (strcmp(optarg, "sendpage") == 0) {
+ test = SENDPAGE;
+ } else {
+ usage(argv);
+ return -1;
+ }
+ break;
+ case 0:
+ break;
+ case 'h':
+ default:
+ usage(argv);
+ return -1;
+ }
+ }
+
+ if (!cg_fd) {
+ fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n",
+ argv[0]);
+ return -1;
+ }
+
+ err = populate_progs(bpf_file);
+ if (err) {
+ fprintf(stderr, "populate program: (%s) %s\n",
+ bpf_file, strerror(errno));
+ return 1;
+ }
+ running = 1;
+
+ /* catch SIGINT */
+ signal(SIGINT, running_handler);
+
+ options.iov_count = iov_count;
+ options.iov_length = length;
+ options.rate = rate;
+
+ err = run_options(&options, cg_fd, test);
+ close(cg_fd);
+ return err;
+}
+
+void running_handler(int a)
+{
+ running = 0;
+}
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.c b/tools/testing/selftests/bpf/test_sockmap_kern.c
new file mode 100644
index 000000000000..677b2ed1cc1e
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.c
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
+#define SOCKMAP
+#define TEST_MAP_TYPE BPF_MAP_TYPE_SOCKMAP
+#include "./test_sockmap_kern.h"
diff --git a/tools/testing/selftests/bpf/test_sockmap_kern.h b/tools/testing/selftests/bpf/test_sockmap_kern.h
new file mode 100644
index 000000000000..8e8e41780bb9
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_sockmap_kern.h
@@ -0,0 +1,363 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io */
+#include <stddef.h>
+#include <string.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/in.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/pkt_cls.h>
+#include <sys/socket.h>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+/* Sockmap sample program connects a client and a backend together
+ * using cgroups.
+ *
+ * client:X <---> frontend:80 client:X <---> backend:80
+ *
+ * For simplicity we hard code values here and bind 1:1. The hard
+ * coded values are part of the setup in sockmap.sh script that
+ * is associated with this BPF program.
+ *
+ * The bpf_printk is verbose and prints information as connections
+ * are established and verdicts are decided.
+ */
+
+#define bpf_printk(fmt, ...) \
+({ \
+ char ____fmt[] = fmt; \
+ bpf_trace_printk(____fmt, sizeof(____fmt), \
+ ##__VA_ARGS__); \
+})
+
+struct bpf_map_def SEC("maps") sock_map = {
+ .type = TEST_MAP_TYPE,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_txmsg = {
+ .type = TEST_MAP_TYPE,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_map_redir = {
+ .type = TEST_MAP_TYPE,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 20,
+};
+
+struct bpf_map_def SEC("maps") sock_apply_bytes = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1
+};
+
+struct bpf_map_def SEC("maps") sock_cork_bytes = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1
+};
+
+struct bpf_map_def SEC("maps") sock_pull_bytes = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 2
+};
+
+struct bpf_map_def SEC("maps") sock_redir_flags = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1
+};
+
+struct bpf_map_def SEC("maps") sock_skb_opts = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(int),
+ .value_size = sizeof(int),
+ .max_entries = 1
+};
+
+SEC("sk_skb1")
+int bpf_prog1(struct __sk_buff *skb)
+{
+ return skb->len;
+}
+
+SEC("sk_skb2")
+int bpf_prog2(struct __sk_buff *skb)
+{
+ __u32 lport = skb->local_port;
+ __u32 rport = skb->remote_port;
+ int len, *f, ret, zero = 0;
+ __u64 flags = 0;
+
+ if (lport == 10000)
+ ret = 10;
+ else
+ ret = 1;
+
+ len = (__u32)skb->data_end - (__u32)skb->data;
+ f = bpf_map_lookup_elem(&sock_skb_opts, &zero);
+ if (f && *f) {
+ ret = 3;
+ flags = *f;
+ }
+
+ bpf_printk("sk_skb2: redirect(%iB) flags=%i\n",
+ len, flags);
+#ifdef SOCKMAP
+ return bpf_sk_redirect_map(skb, &sock_map, ret, flags);
+#else
+ return bpf_sk_redirect_hash(skb, &sock_map, &ret, flags);
+#endif
+
+}
+
+SEC("sockops")
+int bpf_sockmap(struct bpf_sock_ops *skops)
+{
+ __u32 lport, rport;
+ int op, err = 0, index, key, ret;
+
+
+ op = (int) skops->op;
+
+ switch (op) {
+ case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB:
+ lport = skops->local_port;
+ rport = skops->remote_port;
+
+ if (lport == 10000) {
+ ret = 1;
+#ifdef SOCKMAP
+ err = bpf_sock_map_update(skops, &sock_map, &ret,
+ BPF_NOEXIST);
+#else
+ err = bpf_sock_hash_update(skops, &sock_map, &ret,
+ BPF_NOEXIST);
+#endif
+ bpf_printk("passive(%i -> %i) map ctx update err: %d\n",
+ lport, bpf_ntohl(rport), err);
+ }
+ break;
+ case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+ lport = skops->local_port;
+ rport = skops->remote_port;
+
+ if (bpf_ntohl(rport) == 10001) {
+ ret = 10;
+#ifdef SOCKMAP
+ err = bpf_sock_map_update(skops, &sock_map, &ret,
+ BPF_NOEXIST);
+#else
+ err = bpf_sock_hash_update(skops, &sock_map, &ret,
+ BPF_NOEXIST);
+#endif
+ bpf_printk("active(%i -> %i) map ctx update err: %d\n",
+ lport, bpf_ntohl(rport), err);
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+SEC("sk_msg1")
+int bpf_prog4(struct sk_msg_md *msg)
+{
+ int *bytes, zero = 0, one = 1;
+ int *start, *end;
+
+ bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+ if (bytes)
+ bpf_msg_apply_bytes(msg, *bytes);
+ bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+ if (bytes)
+ bpf_msg_cork_bytes(msg, *bytes);
+ start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+ end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+ if (start && end)
+ bpf_msg_pull_data(msg, *start, *end, 0);
+ return SK_PASS;
+}
+
+SEC("sk_msg2")
+int bpf_prog5(struct sk_msg_md *msg)
+{
+ int err1 = -1, err2 = -1, zero = 0, one = 1;
+ int *bytes, *start, *end, len1, len2;
+
+ bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+ if (bytes)
+ err1 = bpf_msg_apply_bytes(msg, *bytes);
+ bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+ if (bytes)
+ err2 = bpf_msg_cork_bytes(msg, *bytes);
+ len1 = (__u64)msg->data_end - (__u64)msg->data;
+ start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+ end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+ if (start && end) {
+ int err;
+
+ bpf_printk("sk_msg2: pull(%i:%i)\n",
+ start ? *start : 0, end ? *end : 0);
+ err = bpf_msg_pull_data(msg, *start, *end, 0);
+ if (err)
+ bpf_printk("sk_msg2: pull_data err %i\n",
+ err);
+ len2 = (__u64)msg->data_end - (__u64)msg->data;
+ bpf_printk("sk_msg2: length update %i->%i\n",
+ len1, len2);
+ }
+ bpf_printk("sk_msg2: data length %i err1 %i err2 %i\n",
+ len1, err1, err2);
+ return SK_PASS;
+}
+
+SEC("sk_msg3")
+int bpf_prog6(struct sk_msg_md *msg)
+{
+ int *bytes, zero = 0, one = 1, key = 0;
+ int *start, *end, *f;
+ __u64 flags = 0;
+
+ bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+ if (bytes)
+ bpf_msg_apply_bytes(msg, *bytes);
+ bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+ if (bytes)
+ bpf_msg_cork_bytes(msg, *bytes);
+ start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+ end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+ if (start && end)
+ bpf_msg_pull_data(msg, *start, *end, 0);
+ f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
+ if (f && *f) {
+ key = 2;
+ flags = *f;
+ }
+#ifdef SOCKMAP
+ return bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
+#else
+ return bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
+#endif
+}
+
+SEC("sk_msg4")
+int bpf_prog7(struct sk_msg_md *msg)
+{
+ int err1 = 0, err2 = 0, zero = 0, one = 1, key = 0;
+ int *f, *bytes, *start, *end, len1, len2;
+ __u64 flags = 0;
+
+ int err;
+ bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+ if (bytes)
+ err1 = bpf_msg_apply_bytes(msg, *bytes);
+ bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+ if (bytes)
+ err2 = bpf_msg_cork_bytes(msg, *bytes);
+ len1 = (__u64)msg->data_end - (__u64)msg->data;
+ start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+ end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+ if (start && end) {
+
+ bpf_printk("sk_msg2: pull(%i:%i)\n",
+ start ? *start : 0, end ? *end : 0);
+ err = bpf_msg_pull_data(msg, *start, *end, 0);
+ if (err)
+ bpf_printk("sk_msg2: pull_data err %i\n",
+ err);
+ len2 = (__u64)msg->data_end - (__u64)msg->data;
+ bpf_printk("sk_msg2: length update %i->%i\n",
+ len1, len2);
+ }
+ f = bpf_map_lookup_elem(&sock_redir_flags, &zero);
+ if (f && *f) {
+ key = 2;
+ flags = *f;
+ }
+ bpf_printk("sk_msg3: redirect(%iB) flags=%i err=%i\n",
+ len1, flags, err1 ? err1 : err2);
+#ifdef SOCKMAP
+ err = bpf_msg_redirect_map(msg, &sock_map_redir, key, flags);
+#else
+ err = bpf_msg_redirect_hash(msg, &sock_map_redir, &key, flags);
+#endif
+ bpf_printk("sk_msg3: err %i\n", err);
+ return err;
+}
+
+SEC("sk_msg5")
+int bpf_prog8(struct sk_msg_md *msg)
+{
+ void *data_end = (void *)(long) msg->data_end;
+ void *data = (void *)(long) msg->data;
+ int ret = 0, *bytes, zero = 0;
+
+ bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+ if (bytes) {
+ ret = bpf_msg_apply_bytes(msg, *bytes);
+ if (ret)
+ return SK_DROP;
+ } else {
+ return SK_DROP;
+ }
+ return SK_PASS;
+}
+SEC("sk_msg6")
+int bpf_prog9(struct sk_msg_md *msg)
+{
+ void *data_end = (void *)(long) msg->data_end;
+ void *data = (void *)(long) msg->data;
+ int ret = 0, *bytes, zero = 0;
+
+ bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+ if (bytes) {
+ if (((__u64)data_end - (__u64)data) >= *bytes)
+ return SK_PASS;
+ ret = bpf_msg_cork_bytes(msg, *bytes);
+ if (ret)
+ return SK_DROP;
+ }
+ return SK_PASS;
+}
+
+SEC("sk_msg7")
+int bpf_prog10(struct sk_msg_md *msg)
+{
+ int *bytes, zero = 0, one = 1;
+ int *start, *end;
+
+ bytes = bpf_map_lookup_elem(&sock_apply_bytes, &zero);
+ if (bytes)
+ bpf_msg_apply_bytes(msg, *bytes);
+ bytes = bpf_map_lookup_elem(&sock_cork_bytes, &zero);
+ if (bytes)
+ bpf_msg_cork_bytes(msg, *bytes);
+ start = bpf_map_lookup_elem(&sock_pull_bytes, &zero);
+ end = bpf_map_lookup_elem(&sock_pull_bytes, &one);
+ if (start && end)
+ bpf_msg_pull_data(msg, *start, *end, 0);
+
+ return SK_DROP;
+}
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/test_stacktrace_build_id.c
index b755bd783ce5..d86c281e957f 100644
--- a/tools/testing/selftests/bpf/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/test_stacktrace_build_id.c
@@ -19,7 +19,7 @@ struct bpf_map_def SEC("maps") stackid_hmap = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
- .max_entries = 10000,
+ .max_entries = 16384,
};
struct bpf_map_def SEC("maps") stackmap = {
@@ -31,6 +31,14 @@ struct bpf_map_def SEC("maps") stackmap = {
.map_flags = BPF_F_STACK_BUILD_ID,
};
+struct bpf_map_def SEC("maps") stack_amap = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(struct bpf_stack_build_id)
+ * PERF_MAX_STACK_DEPTH,
+ .max_entries = 128,
+};
+
/* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */
struct random_urandom_args {
unsigned long long pad;
@@ -42,7 +50,10 @@ struct random_urandom_args {
SEC("tracepoint/random/urandom_read")
int oncpu(struct random_urandom_args *args)
{
+ __u32 max_len = sizeof(struct bpf_stack_build_id)
+ * PERF_MAX_STACK_DEPTH;
__u32 key = 0, val = 0, *value_p;
+ void *stack_p;
value_p = bpf_map_lookup_elem(&control_map, &key);
if (value_p && *value_p)
@@ -50,8 +61,13 @@ int oncpu(struct random_urandom_args *args)
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK);
- if ((int)key >= 0)
+ if ((int)key >= 0) {
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
+ stack_p = bpf_map_lookup_elem(&stack_amap, &key);
+ if (stack_p)
+ bpf_get_stack(args, stack_p, max_len,
+ BPF_F_USER_STACK | BPF_F_USER_BUILD_ID);
+ }
return 0;
}
diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/test_stacktrace_map.c
index 76d85c5d08bd..af111af7ca1a 100644
--- a/tools/testing/selftests/bpf/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/test_stacktrace_map.c
@@ -19,14 +19,21 @@ struct bpf_map_def SEC("maps") stackid_hmap = {
.type = BPF_MAP_TYPE_HASH,
.key_size = sizeof(__u32),
.value_size = sizeof(__u32),
- .max_entries = 10000,
+ .max_entries = 16384,
};
struct bpf_map_def SEC("maps") stackmap = {
.type = BPF_MAP_TYPE_STACK_TRACE,
.key_size = sizeof(__u32),
.value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
- .max_entries = 10000,
+ .max_entries = 16384,
+};
+
+struct bpf_map_def SEC("maps") stack_amap = {
+ .type = BPF_MAP_TYPE_ARRAY,
+ .key_size = sizeof(__u32),
+ .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH,
+ .max_entries = 16384,
};
/* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */
@@ -44,7 +51,9 @@ struct sched_switch_args {
SEC("tracepoint/sched/sched_switch")
int oncpu(struct sched_switch_args *ctx)
{
+ __u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64);
__u32 key = 0, val = 0, *value_p;
+ void *stack_p;
value_p = bpf_map_lookup_elem(&control_map, &key);
if (value_p && *value_p)
@@ -52,8 +61,12 @@ int oncpu(struct sched_switch_args *ctx)
/* The size of stackmap and stackid_hmap should be the same */
key = bpf_get_stackid(ctx, &stackmap, 0);
- if ((int)key >= 0)
+ if ((int)key >= 0) {
bpf_map_update_elem(&stackid_hmap, &key, &val, 0);
+ stack_p = bpf_map_lookup_elem(&stack_amap, &key);
+ if (stack_p)
+ bpf_get_stack(ctx, stack_p, max_len, 0);
+ }
return 0;
}
diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
new file mode 100755
index 000000000000..aeb2901f21f4
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -0,0 +1,729 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# End-to-end eBPF tunnel test suite
+# The script tests BPF network tunnel implementation.
+#
+# Topology:
+# ---------
+# root namespace | at_ns0 namespace
+# |
+# ----------- | -----------
+# | tnl dev | | | tnl dev | (overlay network)
+# ----------- | -----------
+# metadata-mode | native-mode
+# with bpf |
+# |
+# ---------- | ----------
+# | veth1 | --------- | veth0 | (underlay network)
+# ---------- peer ----------
+#
+#
+# Device Configuration
+# --------------------
+# 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)
+#
+# 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)
+#
+#
+# End-to-end ping packet flow
+# ---------------------------
+# Most of the tests start by namespace creation, device configuration,
+# then ping the underlay and overlay network. When doing 'ping 10.1.1.100'
+# from root namespace, the following operations happen:
+# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev.
+# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata,
+# with remote_ip=172.16.1.200 and others.
+# 3) Outer tunnel header is prepended and route the packet to veth1's egress
+# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0
+# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet
+# 6) Forward the packet to the overlay tnl dev
+
+PING_ARG="-c 3 -w 10 -q"
+ret=0
+GREEN='\033[0;92m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+
+config_device()
+{
+ ip netns add at_ns0
+ ip link add veth0 type veth peer name veth1
+ ip link set veth0 netns at_ns0
+ ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip link set dev veth1 up mtu 1500
+ ip addr add dev veth1 172.16.1.200/24
+}
+
+add_gre_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE key 2 external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6gretap_tunnel()
+{
+
+ # assign ipv6 address
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \
+ 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 fc80::100/96
+ 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 fc80::200/24
+ ip link set dev $DEV up
+}
+
+add_erspan_tunnel()
+{
+ # at_ns0 namespace
+ if [ "$1" == "v1" ]; then
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200 \
+ erspan_ver 1 erspan 123
+ else
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local 172.16.1.100 remote 172.16.1.200 \
+ erspan_ver 2 erspan_dir egress erspan_hwid 3
+ fi
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6erspan_tunnel()
+{
+
+ # assign ipv6 address
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ if [ "$1" == "v1" ]; then
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local ::11 remote ::22 \
+ erspan_ver 1 erspan 123
+ else
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE seq key 2 \
+ local ::11 remote ::22 \
+ erspan_ver 2 erspan_dir egress erspan_hwid 7
+ fi
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ 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 link set dev $DEV up
+}
+
+add_vxlan_tunnel()
+{
+ # Set static ARP entry here because iptables set-mark works
+ # on L3 packet, as a result not applying to ARP packets,
+ # causing errors at get_tunnel_{key/opt}.
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ id 2 dstport 4789 gbp remote 172.16.1.200
+ ip netns exec at_ns0 \
+ ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
+ ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external gbp dstport 4789
+ ip link set dev $DEV address 52:54:00:d9:02:00 up
+ ip addr add dev $DEV 10.1.1.200/24
+ arp -s 10.1.1.100 52:54:00:d9:01:00
+}
+
+add_ip6vxlan_tunnel()
+{
+ #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0
+ ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ #ip -4 addr del 172.16.1.200 dev veth1
+ ip -6 addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \
+ 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 link set dev $DEV_NS up
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external dstport 4789
+ ip addr add dev $DEV 10.1.1.200/24
+ ip link set dev $DEV up
+}
+
+add_geneve_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ id 2 dstport 6081 remote 172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE dstport 6081 external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ip6geneve_tunnel()
+{
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE id 22 \
+ remote ::22 # geneve has no local option
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+ 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 link set dev $DEV up
+}
+
+add_ipip_tunnel()
+{
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ ip link add dev $DEV_NS type $TYPE \
+ local 172.16.1.100 remote 172.16.1.200
+ ip netns exec at_ns0 ip link set dev $DEV_NS up
+ ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
+
+ # root namespace
+ ip link add dev $DEV type $TYPE external
+ ip link set dev $DEV up
+ ip addr add dev $DEV 10.1.1.200/24
+}
+
+add_ipip6tnl_tunnel()
+{
+ ip netns exec at_ns0 ip addr add ::11/96 dev veth0
+ ip netns exec at_ns0 ip link set dev veth0 up
+ ip addr add dev veth1 ::22/96
+ ip link set dev veth1 up
+
+ # at_ns0 namespace
+ ip netns exec at_ns0 \
+ 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 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 link set dev $DEV up
+}
+
+test_gre()
+{
+ TYPE=gretap
+ DEV_NS=gretap00
+ DEV=gretap11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_gre_tunnel
+ attach_bpf $DEV gre_set_tunnel gre_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6gre()
+{
+ TYPE=ip6gre
+ DEV_NS=ip6gre00
+ DEV=ip6gre11
+ ret=0
+
+ check $TYPE
+ config_device
+ # reuse the ip6gretap function
+ add_ip6gretap_tunnel
+ attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # overlay: ipv4 over ipv6
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ # overlay: ipv6 over ipv6
+ ip netns exec at_ns0 ping6 $PING_ARG fc80::200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6gretap()
+{
+ TYPE=ip6gretap
+ DEV_NS=ip6gretap00
+ DEV=ip6gretap11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6gretap_tunnel
+ attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # overlay: ipv4 over ipv6
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ # overlay: ipv6 over ipv6
+ ip netns exec at_ns0 ping6 $PING_ARG fc80::200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_erspan()
+{
+ TYPE=erspan
+ DEV_NS=erspan00
+ DEV=erspan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_erspan_tunnel $1
+ attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6erspan()
+{
+ TYPE=ip6erspan
+ DEV_NS=ip6erspan00
+ DEV=ip6erspan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6erspan_tunnel $1
+ attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel
+ ping6 $PING_ARG ::11
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_vxlan()
+{
+ TYPE=vxlan
+ DEV_NS=vxlan00
+ DEV=vxlan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_vxlan_tunnel
+ attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6vxlan()
+{
+ TYPE=vxlan
+ DEV_NS=ip6vxlan00
+ DEV=ip6vxlan11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6vxlan_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip4 over ip6
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ 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}
+}
+
+test_geneve()
+{
+ TYPE=geneve
+ DEV_NS=geneve00
+ DEV=geneve11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_geneve_tunnel
+ attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ip6geneve()
+{
+ TYPE=geneve
+ DEV_NS=ip6geneve00
+ DEV=ip6geneve11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ip6geneve_tunnel
+ attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ 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}
+}
+
+test_ipip()
+{
+ TYPE=ipip
+ DEV_NS=ipip00
+ DEV=ipip11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ipip_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+test_ipip6()
+{
+ TYPE=ip6tnl
+ DEV_NS=ipip6tnl00
+ DEV=ipip6tnl11
+ ret=0
+
+ check $TYPE
+ config_device
+ add_ipip6tnl_tunnel
+ ip link set dev veth1 mtu 1500
+ attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel
+ # underlay
+ ping6 $PING_ARG ::11
+ # ip4 over ip6
+ ping $PING_ARG 10.1.1.100
+ check_err $?
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: $TYPE"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: $TYPE"${NC}
+}
+
+setup_xfrm_tunnel()
+{
+ auth=0x$(printf '1%.0s' {1..40})
+ enc=0x$(printf '2%.0s' {1..32})
+ spi_in_to_out=0x1
+ spi_out_to_in=0x2
+ # at_ns0 namespace
+ # at_ns0 -> root
+ ip netns exec at_ns0 \
+ ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
+ spi $spi_in_to_out reqid 1 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip netns exec at_ns0 \
+ ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
+ tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
+ mode tunnel
+ # root -> at_ns0
+ ip netns exec at_ns0 \
+ ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
+ spi $spi_out_to_in reqid 2 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip netns exec at_ns0 \
+ ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
+ tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
+ mode tunnel
+ # address & route
+ ip netns exec at_ns0 \
+ ip addr add dev veth0 10.1.1.100/32
+ ip netns exec at_ns0 \
+ ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
+ src 10.1.1.100
+
+ # root namespace
+ # at_ns0 -> root
+ ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
+ spi $spi_in_to_out reqid 1 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
+ tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
+ mode tunnel
+ # root -> at_ns0
+ ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
+ spi $spi_out_to_in reqid 2 mode tunnel \
+ auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+ ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
+ tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
+ mode tunnel
+ # address & route
+ ip addr add dev veth1 10.1.1.200/32
+ ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
+}
+
+test_xfrm_tunnel()
+{
+ config_device
+ #tcpdump -nei veth1 ip &
+ output=$(mktemp)
+ cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
+ setup_xfrm_tunnel
+ tc qdisc add dev veth1 clsact
+ tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \
+ sec xfrm_get_state
+ ip netns exec at_ns0 ping $PING_ARG 10.1.1.200
+ sleep 1
+ grep "reqid 1" $output
+ check_err $?
+ grep "spi 0x1" $output
+ check_err $?
+ grep "remote ip 0xac100164" $output
+ check_err $?
+ cleanup
+
+ if [ $ret -ne 0 ]; then
+ echo -e ${RED}"FAIL: xfrm tunnel"${NC}
+ return 1
+ fi
+ echo -e ${GREEN}"PASS: xfrm tunnel"${NC}
+}
+
+attach_bpf()
+{
+ DEV=$1
+ SET=$2
+ GET=$3
+ tc qdisc add dev $DEV clsact
+ tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET
+ tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET
+}
+
+cleanup()
+{
+ ip netns delete at_ns0 2> /dev/null
+ ip link del veth1 2> /dev/null
+ ip link del ipip11 2> /dev/null
+ ip link del ipip6tnl11 2> /dev/null
+ ip link del gretap11 2> /dev/null
+ ip link del ip6gre11 2> /dev/null
+ ip link del ip6gretap11 2> /dev/null
+ ip link del vxlan11 2> /dev/null
+ ip link del ip6vxlan11 2> /dev/null
+ ip link del geneve11 2> /dev/null
+ ip link del ip6geneve11 2> /dev/null
+ ip link del erspan11 2> /dev/null
+ ip link del ip6erspan11 2> /dev/null
+}
+
+cleanup_exit()
+{
+ echo "CATCH SIGKILL or SIGINT, cleanup and exit"
+ cleanup
+ exit 0
+}
+
+check()
+{
+ ip link help $1 2>&1 | grep -q "^Usage:"
+ if [ $? -ne 0 ];then
+ echo "SKIP $1: iproute2 not support"
+ cleanup
+ return 1
+ fi
+}
+
+enable_debug()
+{
+ echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control
+ echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control
+}
+
+check_err()
+{
+ if [ $ret -eq 0 ]; then
+ ret=$1
+ fi
+}
+
+bpf_tunnel_test()
+{
+ echo "Testing GRE tunnel..."
+ test_gre
+ echo "Testing IP6GRE tunnel..."
+ test_ip6gre
+ echo "Testing IP6GRETAP tunnel..."
+ test_ip6gretap
+ echo "Testing ERSPAN tunnel..."
+ test_erspan v2
+ echo "Testing IP6ERSPAN tunnel..."
+ test_ip6erspan v2
+ echo "Testing VXLAN tunnel..."
+ test_vxlan
+ echo "Testing IP6VXLAN tunnel..."
+ test_ip6vxlan
+ echo "Testing GENEVE tunnel..."
+ test_geneve
+ echo "Testing IP6GENEVE tunnel..."
+ test_ip6geneve
+ echo "Testing IPIP tunnel..."
+ test_ipip
+ echo "Testing IPIP6 tunnel..."
+ test_ipip6
+ echo "Testing IPSec tunnel..."
+ test_xfrm_tunnel
+}
+
+trap cleanup 0 3 6
+trap cleanup_exit 2 9
+
+cleanup
+bpf_tunnel_test
+
+exit 0
diff --git a/tools/testing/selftests/bpf/test_tunnel_kern.c b/tools/testing/selftests/bpf/test_tunnel_kern.c
new file mode 100644
index 000000000000..504df69c83df
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_tunnel_kern.c
@@ -0,0 +1,713 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016 VMware
+ * Copyright (c) 2016 Facebook
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+#include <stddef.h>
+#include <string.h>
+#include <arpa/inet.h>
+#include <linux/bpf.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#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>
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+#define ERROR(ret) do {\
+ char fmt[] = "ERROR line:%d ret:%d\n";\
+ bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
+ } while (0)
+
+int _version SEC("version") = 1;
+
+struct geneve_opt {
+ __be16 opt_class;
+ __u8 type;
+ __u8 length:5;
+ __u8 r3:1;
+ __u8 r2:1;
+ __u8 r1:1;
+ __u8 opt_data[8]; /* hard-coded to 8 byte */
+};
+
+struct vxlan_metadata {
+ __u32 gbp;
+};
+
+SEC("gre_set_tunnel")
+int _gre_set_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX | BPF_F_SEQ_NUMBER);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("gre_get_tunnel")
+int _gre_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "key %d remote ip 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), key.tunnel_id, key.remote_ipv4);
+ return TC_ACT_OK;
+}
+
+SEC("ip6gretap_set_tunnel")
+int _ip6gretap_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+ key.tunnel_label = 0xabcde;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6 | BPF_F_ZERO_CSUM_TX |
+ BPF_F_SEQ_NUMBER);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6gretap_get_tunnel")
+int _ip6gretap_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip6 ::%x label %x\n";
+ struct bpf_tunnel_key key;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
+
+ return TC_ACT_OK;
+}
+
+SEC("erspan_set_tunnel")
+int _erspan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&md, 0, sizeof(md));
+#ifdef ERSPAN_V1
+ md.version = 1;
+ md.u.index = bpf_htonl(123);
+#else
+ __u8 direction = 1;
+ __u8 hwid = 7;
+
+ md.version = 2;
+ md.u.md2.dir = direction;
+ md.u.md2.hwid = hwid & 0xf;
+ md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+#endif
+
+ ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("erspan_get_tunnel")
+int _erspan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip 0x%x erspan version %d\n";
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ __u32 index;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, md.version);
+
+#ifdef ERSPAN_V1
+ char fmt2[] = "\tindex %x\n";
+
+ index = bpf_ntohl(md.u.index);
+ bpf_trace_printk(fmt2, sizeof(fmt2), index);
+#else
+ char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
+
+ bpf_trace_printk(fmt2, sizeof(fmt2),
+ md.u.md2.dir,
+ (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+ bpf_ntohl(md.u.md2.timestamp));
+#endif
+
+ return TC_ACT_OK;
+}
+
+SEC("ip4ip6erspan_set_tunnel")
+int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11);
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&md, 0, sizeof(md));
+
+#ifdef ERSPAN_V1
+ md.u.index = bpf_htonl(123);
+ md.version = 1;
+#else
+ __u8 direction = 0;
+ __u8 hwid = 17;
+
+ md.version = 2;
+ md.u.md2.dir = direction;
+ md.u.md2.hwid = hwid & 0xf;
+ md.u.md2.hwid_upper = (hwid >> 4) & 0x3;
+#endif
+
+ ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip4ip6erspan_get_tunnel")
+int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n";
+ struct bpf_tunnel_key key;
+ struct erspan_metadata md;
+ __u32 index;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, md.version);
+
+#ifdef ERSPAN_V1
+ char fmt2[] = "\tindex %x\n";
+
+ index = bpf_ntohl(md.u.index);
+ bpf_trace_printk(fmt2, sizeof(fmt2), index);
+#else
+ char fmt2[] = "\tdirection %d hwid %x timestamp %u\n";
+
+ bpf_trace_printk(fmt2, sizeof(fmt2),
+ md.u.md2.dir,
+ (md.u.md2.hwid_upper << 4) + md.u.md2.hwid,
+ bpf_ntohl(md.u.md2.timestamp));
+#endif
+
+ return TC_ACT_OK;
+}
+
+SEC("vxlan_set_tunnel")
+int _vxlan_set_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct vxlan_metadata md;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ md.gbp = 0x800FF; /* Set VXLAN Group Policy extension */
+ ret = bpf_skb_set_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("vxlan_get_tunnel")
+int _vxlan_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct vxlan_metadata md;
+ char fmt[] = "key %d remote ip 0x%x vxlan gbp 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &md, sizeof(md));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, md.gbp);
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6vxlan_set_tunnel")
+int _ip6vxlan_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 22;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6vxlan_get_tunnel")
+int _ip6vxlan_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip6 ::%x label %x\n";
+ struct bpf_tunnel_key key;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv6[3], key.tunnel_label);
+
+ return TC_ACT_OK;
+}
+
+SEC("geneve_set_tunnel")
+int _geneve_set_tunnel(struct __sk_buff *skb)
+{
+ int ret, ret2;
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */
+ key.tunnel_id = 2;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ __builtin_memset(&gopt, 0x0, sizeof(gopt));
+ gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+ gopt.type = 0x08;
+ gopt.r1 = 0;
+ gopt.r2 = 0;
+ gopt.r3 = 0;
+ gopt.length = 2; /* 4-byte multiple */
+ *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef);
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_ZERO_CSUM_TX);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("geneve_get_tunnel")
+int _geneve_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, gopt.opt_class);
+ return TC_ACT_OK;
+}
+
+SEC("ip6geneve_set_tunnel")
+int _ip6geneve_set_tunnel(struct __sk_buff *skb)
+{
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ int ret;
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_id = 22;
+ key.tunnel_tos = 0;
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&gopt, 0x0, sizeof(gopt));
+ gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */
+ gopt.type = 0x08;
+ gopt.r1 = 0;
+ gopt.r2 = 0;
+ gopt.r3 = 0;
+ gopt.length = 2; /* 4-byte multiple */
+ *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef);
+
+ ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6geneve_get_tunnel")
+int _ip6geneve_get_tunnel(struct __sk_buff *skb)
+{
+ char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n";
+ struct bpf_tunnel_key key;
+ struct geneve_opt gopt;
+ int ret;
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt));
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt),
+ key.tunnel_id, key.remote_ipv4, gopt.opt_class);
+
+ return TC_ACT_OK;
+}
+
+SEC("ipip_set_tunnel")
+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) {
+ ERROR(1);
+ return TC_ACT_SHOT;
+ }
+
+ 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);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ipip_get_tunnel")
+int _ipip_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "remote ip 0x%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), key.remote_ipv4);
+ return TC_ACT_OK;
+}
+
+SEC("ipip6_set_tunnel")
+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) {
+ ERROR(1);
+ return TC_ACT_SHOT;
+ }
+
+ __builtin_memset(&key, 0x0, sizeof(key));
+ key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */
+ key.tunnel_ttl = 64;
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ipip6_get_tunnel")
+int _ipip6_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "remote ip6 %x::%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
+ bpf_htonl(key.remote_ipv6[3]));
+ return TC_ACT_OK;
+}
+
+SEC("ip6ip6_set_tunnel")
+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) {
+ 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;
+ }
+ }
+
+ ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ return TC_ACT_OK;
+}
+
+SEC("ip6ip6_get_tunnel")
+int _ip6ip6_get_tunnel(struct __sk_buff *skb)
+{
+ int ret;
+ struct bpf_tunnel_key key;
+ char fmt[] = "remote ip6 %x::%x\n";
+
+ ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key),
+ BPF_F_TUNINFO_IPV6);
+ if (ret < 0) {
+ ERROR(ret);
+ return TC_ACT_SHOT;
+ }
+
+ bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]),
+ bpf_htonl(key.remote_ipv6[3]));
+ return TC_ACT_OK;
+}
+
+SEC("xfrm_get_state")
+int _xfrm_get_state(struct __sk_buff *skb)
+{
+ struct bpf_xfrm_state x;
+ char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n";
+ int ret;
+
+ ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
+ if (ret < 0)
+ return TC_ACT_OK;
+
+ bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi),
+ bpf_ntohl(x.remote_ipv4));
+ return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3e7718b1a9ae..7cb1d74057ce 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -41,15 +41,16 @@
# endif
#endif
#include "bpf_rlimit.h"
+#include "bpf_rand.h"
#include "../../../include/linux/filter.h"
#ifndef ARRAY_SIZE
# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
#endif
-#define MAX_INSNS 512
+#define MAX_INSNS BPF_MAXINSNS
#define MAX_FIXUPS 8
-#define MAX_NR_MAPS 4
+#define MAX_NR_MAPS 7
#define POINTER_VALUE 0xcafe4all
#define TEST_DATA_LEN 64
@@ -64,7 +65,10 @@ struct bpf_test {
struct bpf_insn insns[MAX_INSNS];
int fixup_map1[MAX_FIXUPS];
int fixup_map2[MAX_FIXUPS];
- int fixup_prog[MAX_FIXUPS];
+ int fixup_map3[MAX_FIXUPS];
+ int fixup_map4[MAX_FIXUPS];
+ int fixup_prog1[MAX_FIXUPS];
+ int fixup_prog2[MAX_FIXUPS];
int fixup_map_in_map[MAX_FIXUPS];
const char *errstr;
const char *errstr_unpriv;
@@ -76,6 +80,8 @@ struct bpf_test {
} result, result_unpriv;
enum bpf_prog_type prog_type;
uint8_t flags;
+ __u8 data[TEST_DATA_LEN];
+ void (*fill_helper)(struct bpf_test *self);
};
/* Note we want this to be 64 bit aligned so that the end of our array is
@@ -88,6 +94,91 @@ struct test_val {
int foo[MAX_ENTRIES];
};
+struct other_val {
+ long long foo;
+ long long bar;
+};
+
+static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
+{
+ /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+#define PUSH_CNT 51
+ unsigned int len = BPF_MAXINSNS;
+ struct bpf_insn *insn = self->insns;
+ int i = 0, j, k = 0;
+
+ insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+loop:
+ for (j = 0; j < PUSH_CNT; j++) {
+ insn[i++] = BPF_LD_ABS(BPF_B, 0);
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+ i++;
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+ insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1);
+ insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2);
+ insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_vlan_push),
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+ i++;
+ }
+
+ for (j = 0; j < PUSH_CNT; j++) {
+ insn[i++] = BPF_LD_ABS(BPF_B, 0);
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2);
+ i++;
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6);
+ insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_vlan_pop),
+ insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2);
+ i++;
+ }
+ if (++k < 5)
+ goto loop;
+
+ for (; i < len - 1; i++)
+ insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
+ insn[len - 1] = BPF_EXIT_INSN();
+}
+
+static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
+{
+ struct bpf_insn *insn = self->insns;
+ unsigned int len = BPF_MAXINSNS;
+ int i = 0;
+
+ insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
+ insn[i++] = BPF_LD_ABS(BPF_B, 0);
+ insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2);
+ i++;
+ while (i < len - 1)
+ insn[i++] = BPF_LD_ABS(BPF_B, 1);
+ insn[i] = BPF_EXIT_INSN();
+}
+
+static void bpf_fill_rand_ld_dw(struct bpf_test *self)
+{
+ struct bpf_insn *insn = self->insns;
+ uint64_t res = 0;
+ int i = 0;
+
+ insn[i++] = BPF_MOV32_IMM(BPF_REG_0, 0);
+ while (i < self->retval) {
+ uint64_t val = bpf_semi_rand_get();
+ struct bpf_insn tmp[2] = { BPF_LD_IMM64(BPF_REG_1, val) };
+
+ res ^= val;
+ insn[i++] = tmp[0];
+ insn[i++] = tmp[1];
+ insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
+ }
+ insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_0);
+ insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32);
+ insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
+ insn[i] = BPF_EXIT_INSN();
+ res ^= (res >> 32);
+ self->retval = (uint32_t)res;
+}
+
static struct bpf_test tests[] = {
{
"add+sub+mul",
@@ -1597,6 +1688,121 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_SK_SKB,
},
{
+ "valid access family in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, family)),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "valid access remote_ip4 in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, remote_ip4)),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "valid access local_ip4 in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_ip4)),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "valid access remote_port in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, remote_port)),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "valid access local_port in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_port)),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "valid access remote_ip6 in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, remote_ip6[0])),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, remote_ip6[1])),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, remote_ip6[2])),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, remote_ip6[3])),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+ },
+ {
+ "valid access local_ip6 in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_ip6[0])),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_ip6[1])),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_ip6[2])),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_ip6[3])),
+ BPF_EXIT_INSN(),
+ },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_SK_SKB,
+ },
+ {
+ "invalid 64B read of family in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
+ offsetof(struct sk_msg_md, family)),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "invalid bpf_context access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "invalid read past end of SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct sk_msg_md, local_port) + 4),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "R0 !read_ok",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
+ "invalid read offset in SK_MSG",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ offsetof(struct sk_msg_md, family) + 1),
+ BPF_EXIT_INSN(),
+ },
+ .errstr = "invalid bpf_context access",
+ .result = REJECT,
+ .prog_type = BPF_PROG_TYPE_SK_MSG,
+ },
+ {
"direct packet read for SK_MSG",
.insns = {
BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1,
@@ -2565,7 +2771,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 0),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 1 },
+ .fixup_prog1 = { 1 },
.errstr_unpriv = "R3 leaks addr into helper",
.result_unpriv = REJECT,
.result = ACCEPT,
@@ -2652,7 +2858,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 1 },
+ .fixup_prog1 = { 1 },
.result = ACCEPT,
.retval = 42,
},
@@ -2666,7 +2872,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 1 },
+ .fixup_prog1 = { 1 },
.result = ACCEPT,
.retval = 41,
},
@@ -2680,7 +2886,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 1),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 1 },
+ .fixup_prog1 = { 1 },
.result = ACCEPT,
.retval = 1,
},
@@ -2694,7 +2900,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 2),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 1 },
+ .fixup_prog1 = { 1 },
.result = ACCEPT,
.retval = 2,
},
@@ -2708,7 +2914,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 2),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 1 },
+ .fixup_prog1 = { 1 },
.result = ACCEPT,
.retval = 2,
},
@@ -2722,7 +2928,7 @@ static struct bpf_test tests[] = {
BPF_MOV64_IMM(BPF_REG_0, 2),
BPF_EXIT_INSN(),
},
- .fixup_prog = { 2 },
+ .fixup_prog1 = { 2 },
.result = ACCEPT,
.retval = 42,
},
@@ -5594,6 +5800,257 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_TRACEPOINT,
},
{
+ "map lookup helper access to map",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 8 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map update helper access to map",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map update helper access to map: wrong size",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_update_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map1 = { 3 },
+ .fixup_map3 = { 10 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=8 off=0 size=16",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const imm)",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
+ offsetof(struct other_val, bar)),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 9 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const imm): out-of-bound 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2,
+ sizeof(struct other_val) - 4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 9 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=12 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const imm): out-of-bound 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 9 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=-4 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const reg)",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3,
+ offsetof(struct other_val, bar)),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const reg): out-of-bound 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3,
+ sizeof(struct other_val) - 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=12 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via const reg): out-of-bound 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_3, -4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=-4 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via variable)",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+ offsetof(struct other_val, bar), 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 11 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via variable): no max check",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 10 },
+ .result = REJECT,
+ .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "map helper access to adjusted map (via variable): wrong max check",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+ BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+ BPF_JMP_IMM(BPF_JGT, BPF_REG_3,
+ offsetof(struct other_val, bar) + 1, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3),
+ BPF_LD_MAP_FD(BPF_REG_1, 0),
+ BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map3 = { 3, 11 },
+ .result = REJECT,
+ .errstr = "invalid access to map value, value_size=16 off=9 size=8",
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
"map element value is preserved across register spilling",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -11227,6 +11684,112 @@ static struct bpf_test tests[] = {
.prog_type = BPF_PROG_TYPE_XDP,
},
{
+ "calls: two calls returning different map pointers for lookup (hash, array)",
+ .insns = {
+ /* main prog */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+ BPF_CALL_REL(11),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_CALL_REL(12),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ 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_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0,
+ offsetof(struct test_val, foo)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ /* subprog 1 */
+ BPF_LD_MAP_FD(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ /* subprog 2 */
+ BPF_LD_MAP_FD(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_map2 = { 13 },
+ .fixup_map4 = { 16 },
+ .result = ACCEPT,
+ .retval = 1,
+ },
+ {
+ "calls: two calls returning different map pointers for lookup (hash, map in map)",
+ .insns = {
+ /* main prog */
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+ BPF_CALL_REL(11),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ BPF_CALL_REL(12),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ 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_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0,
+ offsetof(struct test_val, foo)),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ /* subprog 1 */
+ BPF_LD_MAP_FD(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ /* subprog 2 */
+ BPF_LD_MAP_FD(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .fixup_map_in_map = { 16 },
+ .fixup_map4 = { 13 },
+ .result = REJECT,
+ .errstr = "R0 invalid mem access 'map_ptr'",
+ },
+ {
+ "cond: two branches returning different map pointers for lookup (tail, tail)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct __sk_buff, mark)),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 0, 3),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_tail_call),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_prog1 = { 5 },
+ .fixup_prog2 = { 2 },
+ .result_unpriv = REJECT,
+ .errstr_unpriv = "tail_call abusing map_ptr",
+ .result = ACCEPT,
+ .retval = 42,
+ },
+ {
+ "cond: two branches returning same map pointers for lookup (tail, tail)",
+ .insns = {
+ BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ offsetof(struct __sk_buff, mark)),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 3),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ BPF_LD_MAP_FD(BPF_REG_2, 0),
+ BPF_MOV64_IMM(BPF_REG_3, 7),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_tail_call),
+ BPF_MOV64_IMM(BPF_REG_0, 1),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_prog2 = { 2, 5 },
+ .result_unpriv = ACCEPT,
+ .result = ACCEPT,
+ .retval = 42,
+ },
+ {
"search pruning: all branches should be verified (nop operation)",
.insns = {
BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
@@ -11423,6 +11986,278 @@ static struct bpf_test tests[] = {
.errstr = "BPF_XADD stores into R2 packet",
.prog_type = BPF_PROG_TYPE_XDP,
},
+ {
+ "bpf_get_stack return R0 within range",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 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, 28),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)),
+ BPF_MOV64_IMM(BPF_REG_4, 256),
+ BPF_EMIT_CALL(BPF_FUNC_get_stack),
+ BPF_MOV64_IMM(BPF_REG_1, 0),
+ BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32),
+ BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16),
+ BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8),
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_7),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_9),
+ BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32),
+ BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 32),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_2),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5),
+ BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_9),
+ BPF_MOV64_IMM(BPF_REG_4, 0),
+ BPF_EMIT_CALL(BPF_FUNC_get_stack),
+ BPF_EXIT_INSN(),
+ },
+ .fixup_map2 = { 4 },
+ .result = ACCEPT,
+ .prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ },
+ {
+ "ld_abs: invalid op 1",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_DW, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "unknown opcode",
+ },
+ {
+ "ld_abs: invalid op 2",
+ .insns = {
+ BPF_MOV32_IMM(BPF_REG_0, 256),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_IND(BPF_DW, BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = REJECT,
+ .errstr = "unknown opcode",
+ },
+ {
+ "ld_abs: nmap reduced",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_H, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28),
+ BPF_LD_ABS(BPF_H, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26),
+ BPF_MOV32_IMM(BPF_REG_0, 18),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64),
+ BPF_LD_IND(BPF_W, BPF_REG_7, 14),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60),
+ BPF_MOV32_IMM(BPF_REG_0, 280971478),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60),
+ BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15),
+ BPF_LD_ABS(BPF_H, 12),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13),
+ BPF_MOV32_IMM(BPF_REG_0, 22),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56),
+ BPF_LD_IND(BPF_H, BPF_REG_7, 14),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52),
+ BPF_MOV32_IMM(BPF_REG_0, 17366),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48),
+ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48),
+ BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52),
+ BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7),
+ BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ BPF_MOV32_IMM(BPF_REG_0, 256),
+ BPF_EXIT_INSN(),
+ BPF_MOV32_IMM(BPF_REG_0, 0),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0,
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+ 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 256,
+ },
+ {
+ "ld_abs: div + abs, test 1",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 3),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+ BPF_LD_ABS(BPF_B, 4),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+ BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 10,
+ },
+ {
+ "ld_abs: div + abs, test 2",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 3),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0),
+ BPF_LD_ABS(BPF_B, 128),
+ BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+ BPF_LD_IND(BPF_B, BPF_REG_8, -70),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "ld_abs: div + abs, test 3",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+ BPF_LD_ABS(BPF_B, 3),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "ld_abs: div + abs, test 4",
+ .insns = {
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0),
+ BPF_LD_ABS(BPF_B, 256),
+ BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 10, 20, 30, 40, 50,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0,
+ },
+ {
+ "ld_abs: vlan + abs, test 1",
+ .insns = { },
+ .data = {
+ 0x34,
+ },
+ .fill_helper = bpf_fill_ld_abs_vlan_push_pop,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 0xbef,
+ },
+ {
+ "ld_abs: vlan + abs, test 2",
+ .insns = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 0),
+ BPF_LD_ABS(BPF_H, 0),
+ BPF_LD_ABS(BPF_W, 0),
+ BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+ BPF_MOV64_IMM(BPF_REG_6, 0),
+ BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ BPF_MOV64_IMM(BPF_REG_2, 1),
+ BPF_MOV64_IMM(BPF_REG_3, 2),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ BPF_FUNC_skb_vlan_push),
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+ BPF_LD_ABS(BPF_B, 0),
+ BPF_LD_ABS(BPF_H, 0),
+ BPF_LD_ABS(BPF_W, 0),
+ BPF_MOV64_IMM(BPF_REG_0, 42),
+ BPF_EXIT_INSN(),
+ },
+ .data = {
+ 0x34,
+ },
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 42,
+ },
+ {
+ "ld_abs: jump around ld_abs",
+ .insns = { },
+ .data = {
+ 10, 11,
+ },
+ .fill_helper = bpf_fill_jump_around_ld_abs,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 10,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 1",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 4090,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 2",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 2047,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 3",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 511,
+ },
+ {
+ "ld_dw: xor semi-random 64 bit imms, test 4",
+ .insns = { },
+ .data = { },
+ .fill_helper = bpf_fill_rand_ld_dw,
+ .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ .result = ACCEPT,
+ .retval = 5,
+ },
};
static int probe_filter_length(const struct bpf_insn *fp)
@@ -11435,12 +12270,13 @@ static int probe_filter_length(const struct bpf_insn *fp)
return len + 1;
}
-static int create_map(uint32_t size_value, uint32_t max_elem)
+static int create_map(uint32_t type, uint32_t size_key,
+ uint32_t size_value, uint32_t max_elem)
{
int fd;
- fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
- size_value, max_elem, BPF_F_NO_PREALLOC);
+ fd = bpf_create_map(type, size_key, size_value, max_elem,
+ type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0);
if (fd < 0)
printf("Failed to create hash map '%s'!\n", strerror(errno));
@@ -11473,13 +12309,13 @@ static int create_prog_dummy2(int mfd, int idx)
ARRAY_SIZE(prog), "GPL", 0, NULL, 0);
}
-static int create_prog_array(void)
+static int create_prog_array(uint32_t max_elem, int p1key)
{
- int p1key = 0, p2key = 1;
+ int p2key = 1;
int mfd, p1fd, p2fd;
mfd = bpf_create_map(BPF_MAP_TYPE_PROG_ARRAY, sizeof(int),
- sizeof(int), 4, 0);
+ sizeof(int), max_elem, 0);
if (mfd < 0) {
printf("Failed to create prog array '%s'!\n", strerror(errno));
return -1;
@@ -11526,22 +12362,29 @@ static int create_map_in_map(void)
return outer_map_fd;
}
-static char bpf_vlog[32768];
+static char bpf_vlog[UINT_MAX >> 8];
static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
int *map_fds)
{
int *fixup_map1 = test->fixup_map1;
int *fixup_map2 = test->fixup_map2;
- int *fixup_prog = test->fixup_prog;
+ int *fixup_map3 = test->fixup_map3;
+ int *fixup_map4 = test->fixup_map4;
+ int *fixup_prog1 = test->fixup_prog1;
+ int *fixup_prog2 = test->fixup_prog2;
int *fixup_map_in_map = test->fixup_map_in_map;
+ if (test->fill_helper)
+ test->fill_helper(test);
+
/* Allocating HTs with 1 elem is fine here, since we only test
* for verifier and not do a runtime lookup, so the only thing
* that really matters is value size in this case.
*/
if (*fixup_map1) {
- map_fds[0] = create_map(sizeof(long long), 1);
+ map_fds[0] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
+ sizeof(long long), 1);
do {
prog[*fixup_map1].imm = map_fds[0];
fixup_map1++;
@@ -11549,25 +12392,52 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
}
if (*fixup_map2) {
- map_fds[1] = create_map(sizeof(struct test_val), 1);
+ map_fds[1] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
+ sizeof(struct test_val), 1);
do {
prog[*fixup_map2].imm = map_fds[1];
fixup_map2++;
} while (*fixup_map2);
}
- if (*fixup_prog) {
- map_fds[2] = create_prog_array();
+ if (*fixup_map3) {
+ map_fds[2] = create_map(BPF_MAP_TYPE_HASH, sizeof(long long),
+ sizeof(struct other_val), 1);
+ do {
+ prog[*fixup_map3].imm = map_fds[2];
+ fixup_map3++;
+ } while (*fixup_map3);
+ }
+
+ if (*fixup_map4) {
+ map_fds[3] = create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+ sizeof(struct test_val), 1);
do {
- prog[*fixup_prog].imm = map_fds[2];
- fixup_prog++;
- } while (*fixup_prog);
+ prog[*fixup_map4].imm = map_fds[3];
+ fixup_map4++;
+ } while (*fixup_map4);
+ }
+
+ if (*fixup_prog1) {
+ map_fds[4] = create_prog_array(4, 0);
+ do {
+ prog[*fixup_prog1].imm = map_fds[4];
+ fixup_prog1++;
+ } while (*fixup_prog1);
+ }
+
+ if (*fixup_prog2) {
+ map_fds[5] = create_prog_array(8, 7);
+ do {
+ prog[*fixup_prog2].imm = map_fds[5];
+ fixup_prog2++;
+ } while (*fixup_prog2);
}
if (*fixup_map_in_map) {
- map_fds[3] = create_map_in_map();
+ map_fds[6] = create_map_in_map();
do {
- prog[*fixup_map_in_map].imm = map_fds[3];
+ prog[*fixup_map_in_map].imm = map_fds[6];
fixup_map_in_map++;
} while (*fixup_map_in_map);
}
@@ -11577,10 +12447,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
int *passes, int *errors)
{
int fd_prog, expected_ret, reject_from_alignment;
+ int prog_len, prog_type = test->prog_type;
struct bpf_insn *prog = test->insns;
- int prog_len = probe_filter_length(prog);
- char data_in[TEST_DATA_LEN] = {};
- int prog_type = test->prog_type;
int map_fds[MAX_NR_MAPS];
const char *expected_err;
uint32_t retval;
@@ -11590,6 +12458,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
map_fds[i] = -1;
do_test_fixup(test, prog, map_fds);
+ prog_len = probe_filter_length(prog);
fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER,
prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT,
@@ -11629,8 +12498,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
}
if (fd_prog >= 0) {
- err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in),
- NULL, NULL, &retval, NULL);
+ err = bpf_prog_test_run(fd_prog, 1, test->data,
+ sizeof(test->data), NULL, NULL,
+ &retval, NULL);
if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) {
printf("Unexpected bpf_prog_test_run error\n");
goto fail_log;
@@ -11713,6 +12583,11 @@ static void get_unpriv_disabled()
FILE *fd;
fd = fopen("/proc/sys/"UNPRIV_SYSCTL, "r");
+ if (!fd) {
+ perror("fopen /proc/sys/"UNPRIV_SYSCTL);
+ unpriv_disabled = true;
+ return;
+ }
if (fgets(buf, 2, fd) == buf && atoi(buf))
unpriv_disabled = true;
fclose(fd);
@@ -11783,5 +12658,6 @@ int main(int argc, char **argv)
return EXIT_FAILURE;
}
+ bpf_semi_rand_init();
return do_test(unpriv, from, to);
}
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
new file mode 100644
index 000000000000..3868dcb63420
--- /dev/null
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <assert.h>
+#include <errno.h>
+#include <poll.h>
+#include <unistd.h>
+#include <linux/perf_event.h>
+#include <sys/mman.h>
+#include "trace_helpers.h"
+
+#define MAX_SYMS 300000
+static struct ksym syms[MAX_SYMS];
+static int sym_cnt;
+
+static int ksym_cmp(const void *p1, const void *p2)
+{
+ return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr;
+}
+
+int load_kallsyms(void)
+{
+ FILE *f = fopen("/proc/kallsyms", "r");
+ char func[256], buf[256];
+ char symbol;
+ void *addr;
+ int i = 0;
+
+ if (!f)
+ return -ENOENT;
+
+ while (!feof(f)) {
+ if (!fgets(buf, sizeof(buf), f))
+ break;
+ if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
+ break;
+ if (!addr)
+ continue;
+ syms[i].addr = (long) addr;
+ syms[i].name = strdup(func);
+ i++;
+ }
+ sym_cnt = i;
+ qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp);
+ return 0;
+}
+
+struct ksym *ksym_search(long key)
+{
+ int start = 0, end = sym_cnt;
+ int result;
+
+ while (start < end) {
+ size_t mid = start + (end - start) / 2;
+
+ result = key - syms[mid].addr;
+ if (result < 0)
+ end = mid;
+ else if (result > 0)
+ start = mid + 1;
+ else
+ return &syms[mid];
+ }
+
+ if (start >= 1 && syms[start - 1].addr < key &&
+ key < syms[start].addr)
+ /* valid ksym */
+ return &syms[start - 1];
+
+ /* out of range. return _stext */
+ return &syms[0];
+}
+
+long ksym_get_addr(const char *name)
+{
+ int i;
+
+ for (i = 0; i < sym_cnt; i++) {
+ if (strcmp(syms[i].name, name) == 0)
+ return syms[i].addr;
+ }
+
+ return 0;
+}
+
+static int page_size;
+static int page_cnt = 8;
+static struct perf_event_mmap_page *header;
+
+int perf_event_mmap(int fd)
+{
+ void *base;
+ int mmap_size;
+
+ page_size = getpagesize();
+ mmap_size = page_size * (page_cnt + 1);
+
+ base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);
+ if (base == MAP_FAILED) {
+ printf("mmap err\n");
+ return -1;
+ }
+
+ header = base;
+ return 0;
+}
+
+static int perf_event_poll(int fd)
+{
+ struct pollfd pfd = { .fd = fd, .events = POLLIN };
+
+ return poll(&pfd, 1, 1000);
+}
+
+struct perf_event_sample {
+ struct perf_event_header header;
+ __u32 size;
+ char data[];
+};
+
+static enum bpf_perf_event_ret bpf_perf_event_print(void *event, void *priv)
+{
+ struct perf_event_sample *e = event;
+ perf_event_print_fn fn = priv;
+ int ret;
+
+ if (e->header.type == PERF_RECORD_SAMPLE) {
+ ret = fn(e->data, e->size);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ return ret;
+ } else if (e->header.type == PERF_RECORD_LOST) {
+ struct {
+ struct perf_event_header header;
+ __u64 id;
+ __u64 lost;
+ } *lost = (void *) e;
+ printf("lost %lld events\n", lost->lost);
+ } else {
+ printf("unknown event type=%d size=%d\n",
+ e->header.type, e->header.size);
+ }
+
+ return LIBBPF_PERF_EVENT_CONT;
+}
+
+int perf_event_poller(int fd, perf_event_print_fn output_fn)
+{
+ enum bpf_perf_event_ret ret;
+ void *buf = NULL;
+ size_t len = 0;
+
+ for (;;) {
+ perf_event_poll(fd);
+ ret = bpf_perf_event_read_simple(header, page_cnt * page_size,
+ page_size, &buf, &len,
+ bpf_perf_event_print,
+ output_fn);
+ if (ret != LIBBPF_PERF_EVENT_CONT)
+ break;
+ }
+ free(buf);
+
+ return ret;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
new file mode 100644
index 000000000000..3b4bcf7f5084
--- /dev/null
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __TRACE_HELPER_H
+#define __TRACE_HELPER_H
+
+#include <libbpf.h>
+
+struct ksym {
+ long addr;
+ char *name;
+};
+
+int load_kallsyms(void);
+struct ksym *ksym_search(long key);
+long ksym_get_addr(const char *name);
+
+typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size);
+
+int perf_event_mmap(int fd);
+/* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */
+int perf_event_poller(int fd, perf_event_print_fn output_fn);
+#endif
diff --git a/tools/testing/selftests/bpf/urandom_read.c b/tools/testing/selftests/bpf/urandom_read.c
index 4acfdebf36fa..9de8b7cb4e6d 100644
--- a/tools/testing/selftests/bpf/urandom_read.c
+++ b/tools/testing/selftests/bpf/urandom_read.c
@@ -6,15 +6,21 @@
#include <stdlib.h>
#define BUF_SIZE 256
-int main(void)
+
+int main(int argc, char *argv[])
{
int fd = open("/dev/urandom", O_RDONLY);
int i;
char buf[BUF_SIZE];
+ int count = 4;
if (fd < 0)
return 1;
- for (i = 0; i < 4; ++i)
+
+ if (argc == 2)
+ count = atoi(argv[1]);
+
+ for (i = 0; i < count; ++i)
read(fd, buf, BUF_SIZE);
close(fd);
diff --git a/tools/testing/selftests/breakpoints/step_after_suspend_test.c b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
index 3fece06e9f64..f82dcc1f8841 100644
--- a/tools/testing/selftests/breakpoints/step_after_suspend_test.c
+++ b/tools/testing/selftests/breakpoints/step_after_suspend_test.c
@@ -143,10 +143,14 @@ void suspend(void)
int err;
struct itimerspec spec = {};
+ if (getuid() != 0)
+ ksft_exit_skip("Please run the test as root - Exiting.\n");
+
power_state_fd = open("/sys/power/state", O_RDWR);
if (power_state_fd < 0)
ksft_exit_fail_msg(
- "open(\"/sys/power/state\") failed (is this test running as root?)\n");
+ "open(\"/sys/power/state\") failed %s)\n",
+ strerror(errno));
timerfd = timerfd_create(CLOCK_BOOTTIME_ALARM, 0);
if (timerfd < 0)
diff --git a/tools/testing/selftests/cgroup/Makefile b/tools/testing/selftests/cgroup/Makefile
new file mode 100644
index 000000000000..f7a31392eb2f
--- /dev/null
+++ b/tools/testing/selftests/cgroup/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -Wall
+
+all:
+
+TEST_GEN_PROGS = test_memcontrol
+
+include ../lib.mk
+
+$(OUTPUT)/test_memcontrol: cgroup_util.c
diff --git a/tools/testing/selftests/cgroup/cgroup_util.c b/tools/testing/selftests/cgroup/cgroup_util.c
new file mode 100644
index 000000000000..b69bdeb4b9fe
--- /dev/null
+++ b/tools/testing/selftests/cgroup/cgroup_util.c
@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define _GNU_SOURCE
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/limits.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "cgroup_util.h"
+
+static ssize_t read_text(const char *path, char *buf, size_t max_len)
+{
+ ssize_t len;
+ int fd;
+
+ fd = open(path, O_RDONLY);
+ if (fd < 0)
+ return fd;
+
+ len = read(fd, buf, max_len - 1);
+ if (len < 0)
+ goto out;
+
+ buf[len] = 0;
+out:
+ close(fd);
+ return len;
+}
+
+static ssize_t write_text(const char *path, char *buf, size_t len)
+{
+ int fd;
+
+ fd = open(path, O_WRONLY | O_APPEND);
+ if (fd < 0)
+ return fd;
+
+ len = write(fd, buf, len);
+ if (len < 0) {
+ close(fd);
+ return len;
+ }
+
+ close(fd);
+
+ return len;
+}
+
+char *cg_name(const char *root, const char *name)
+{
+ size_t len = strlen(root) + strlen(name) + 2;
+ char *ret = malloc(len);
+
+ snprintf(ret, len, "%s/%s", root, name);
+
+ return ret;
+}
+
+char *cg_name_indexed(const char *root, const char *name, int index)
+{
+ size_t len = strlen(root) + strlen(name) + 10;
+ char *ret = malloc(len);
+
+ snprintf(ret, len, "%s/%s_%d", root, name, index);
+
+ return ret;
+}
+
+int cg_read(const char *cgroup, const char *control, char *buf, size_t len)
+{
+ char path[PATH_MAX];
+
+ snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+ if (read_text(path, buf, len) >= 0)
+ return 0;
+
+ return -1;
+}
+
+int cg_read_strcmp(const char *cgroup, const char *control,
+ const char *expected)
+{
+ size_t size = strlen(expected) + 1;
+ char *buf;
+
+ buf = malloc(size);
+ if (!buf)
+ return -1;
+
+ if (cg_read(cgroup, control, buf, size))
+ return -1;
+
+ return strcmp(expected, buf);
+}
+
+int cg_read_strstr(const char *cgroup, const char *control, const char *needle)
+{
+ char buf[PAGE_SIZE];
+
+ if (cg_read(cgroup, control, buf, sizeof(buf)))
+ return -1;
+
+ return strstr(buf, needle) ? 0 : -1;
+}
+
+long cg_read_long(const char *cgroup, const char *control)
+{
+ char buf[128];
+
+ if (cg_read(cgroup, control, buf, sizeof(buf)))
+ return -1;
+
+ return atol(buf);
+}
+
+long cg_read_key_long(const char *cgroup, const char *control, const char *key)
+{
+ char buf[PAGE_SIZE];
+ char *ptr;
+
+ if (cg_read(cgroup, control, buf, sizeof(buf)))
+ return -1;
+
+ ptr = strstr(buf, key);
+ if (!ptr)
+ return -1;
+
+ return atol(ptr + strlen(key));
+}
+
+int cg_write(const char *cgroup, const char *control, char *buf)
+{
+ char path[PATH_MAX];
+ size_t len = strlen(buf);
+
+ snprintf(path, sizeof(path), "%s/%s", cgroup, control);
+
+ if (write_text(path, buf, len) == len)
+ return 0;
+
+ return -1;
+}
+
+int cg_find_unified_root(char *root, size_t len)
+{
+ char buf[10 * PAGE_SIZE];
+ char *fs, *mount, *type;
+ const char delim[] = "\n\t ";
+
+ if (read_text("/proc/self/mounts", buf, sizeof(buf)) <= 0)
+ return -1;
+
+ /*
+ * Example:
+ * cgroup /sys/fs/cgroup cgroup2 rw,seclabel,noexec,relatime 0 0
+ */
+ for (fs = strtok(buf, delim); fs; fs = strtok(NULL, delim)) {
+ mount = strtok(NULL, delim);
+ type = strtok(NULL, delim);
+ strtok(NULL, delim);
+ strtok(NULL, delim);
+ strtok(NULL, delim);
+
+ if (strcmp(fs, "cgroup") == 0 &&
+ strcmp(type, "cgroup2") == 0) {
+ strncpy(root, mount, len);
+ return 0;
+ }
+ }
+
+ return -1;
+}
+
+int cg_create(const char *cgroup)
+{
+ return mkdir(cgroup, 0644);
+}
+
+static int cg_killall(const char *cgroup)
+{
+ char buf[PAGE_SIZE];
+ char *ptr = buf;
+
+ if (cg_read(cgroup, "cgroup.procs", buf, sizeof(buf)))
+ return -1;
+
+ while (ptr < buf + sizeof(buf)) {
+ int pid = strtol(ptr, &ptr, 10);
+
+ if (pid == 0)
+ break;
+ if (*ptr)
+ ptr++;
+ else
+ break;
+ if (kill(pid, SIGKILL))
+ return -1;
+ }
+
+ return 0;
+}
+
+int cg_destroy(const char *cgroup)
+{
+ int ret;
+
+retry:
+ ret = rmdir(cgroup);
+ if (ret && errno == EBUSY) {
+ ret = cg_killall(cgroup);
+ if (ret)
+ return ret;
+ usleep(100);
+ goto retry;
+ }
+
+ if (ret && errno == ENOENT)
+ ret = 0;
+
+ return ret;
+}
+
+int cg_run(const char *cgroup,
+ int (*fn)(const char *cgroup, void *arg),
+ void *arg)
+{
+ int pid, retcode;
+
+ pid = fork();
+ if (pid < 0) {
+ return pid;
+ } else if (pid == 0) {
+ char buf[64];
+
+ snprintf(buf, sizeof(buf), "%d", getpid());
+ if (cg_write(cgroup, "cgroup.procs", buf))
+ exit(EXIT_FAILURE);
+ exit(fn(cgroup, arg));
+ } else {
+ waitpid(pid, &retcode, 0);
+ if (WIFEXITED(retcode))
+ return WEXITSTATUS(retcode);
+ else
+ return -1;
+ }
+}
+
+int cg_run_nowait(const char *cgroup,
+ int (*fn)(const char *cgroup, void *arg),
+ void *arg)
+{
+ int pid;
+
+ pid = fork();
+ if (pid == 0) {
+ char buf[64];
+
+ snprintf(buf, sizeof(buf), "%d", getpid());
+ if (cg_write(cgroup, "cgroup.procs", buf))
+ exit(EXIT_FAILURE);
+ exit(fn(cgroup, arg));
+ }
+
+ return pid;
+}
+
+int get_temp_fd(void)
+{
+ return open(".", O_TMPFILE | O_RDWR | O_EXCL);
+}
+
+int alloc_pagecache(int fd, size_t size)
+{
+ char buf[PAGE_SIZE];
+ struct stat st;
+ int i;
+
+ if (fstat(fd, &st))
+ goto cleanup;
+
+ size += st.st_size;
+
+ if (ftruncate(fd, size))
+ goto cleanup;
+
+ for (i = 0; i < size; i += sizeof(buf))
+ read(fd, buf, sizeof(buf));
+
+ return 0;
+
+cleanup:
+ return -1;
+}
+
+int alloc_anon(const char *cgroup, void *arg)
+{
+ size_t size = (unsigned long)arg;
+ char *buf, *ptr;
+
+ buf = malloc(size);
+ for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+ *ptr = 0;
+
+ free(buf);
+ return 0;
+}
+
+int is_swap_enabled(void)
+{
+ char buf[PAGE_SIZE];
+ const char delim[] = "\n";
+ int cnt = 0;
+ char *line;
+
+ if (read_text("/proc/swaps", buf, sizeof(buf)) <= 0)
+ return -1;
+
+ for (line = strtok(buf, delim); line; line = strtok(NULL, delim))
+ cnt++;
+
+ return cnt > 1;
+}
diff --git a/tools/testing/selftests/cgroup/cgroup_util.h b/tools/testing/selftests/cgroup/cgroup_util.h
new file mode 100644
index 000000000000..fe82a297d4e0
--- /dev/null
+++ b/tools/testing/selftests/cgroup/cgroup_util.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <stdlib.h>
+
+#define PAGE_SIZE 4096
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define MB(x) (x << 20)
+
+/*
+ * Checks if two given values differ by less than err% of their sum.
+ */
+static inline int values_close(long a, long b, int err)
+{
+ return abs(a - b) <= (a + b) / 100 * err;
+}
+
+extern int cg_find_unified_root(char *root, size_t len);
+extern char *cg_name(const char *root, const char *name);
+extern char *cg_name_indexed(const char *root, const char *name, int index);
+extern int cg_create(const char *cgroup);
+extern int cg_destroy(const char *cgroup);
+extern int cg_read(const char *cgroup, const char *control,
+ char *buf, size_t len);
+extern int cg_read_strcmp(const char *cgroup, const char *control,
+ const char *expected);
+extern int cg_read_strstr(const char *cgroup, const char *control,
+ const char *needle);
+extern long cg_read_long(const char *cgroup, const char *control);
+long cg_read_key_long(const char *cgroup, const char *control, const char *key);
+extern int cg_write(const char *cgroup, const char *control, char *buf);
+extern int cg_run(const char *cgroup,
+ int (*fn)(const char *cgroup, void *arg),
+ void *arg);
+extern int cg_run_nowait(const char *cgroup,
+ int (*fn)(const char *cgroup, void *arg),
+ void *arg);
+extern int get_temp_fd(void);
+extern int alloc_pagecache(int fd, size_t size);
+extern int alloc_anon(const char *cgroup, void *arg);
+extern int is_swap_enabled(void);
diff --git a/tools/testing/selftests/cgroup/test_memcontrol.c b/tools/testing/selftests/cgroup/test_memcontrol.c
new file mode 100644
index 000000000000..cf0bddc9d271
--- /dev/null
+++ b/tools/testing/selftests/cgroup/test_memcontrol.c
@@ -0,0 +1,1015 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#define _GNU_SOURCE
+
+#include <linux/limits.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+#include <sys/socket.h>
+#include <sys/wait.h>
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <netdb.h>
+#include <errno.h>
+
+#include "../kselftest.h"
+#include "cgroup_util.h"
+
+/*
+ * This test creates two nested cgroups with and without enabling
+ * the memory controller.
+ */
+static int test_memcg_subtree_control(const char *root)
+{
+ char *parent, *child, *parent2, *child2;
+ int ret = KSFT_FAIL;
+ char buf[PAGE_SIZE];
+
+ /* Create two nested cgroups with the memory controller enabled */
+ parent = cg_name(root, "memcg_test_0");
+ child = cg_name(root, "memcg_test_0/memcg_test_1");
+ if (!parent || !child)
+ goto cleanup;
+
+ if (cg_create(parent))
+ goto cleanup;
+
+ if (cg_write(parent, "cgroup.subtree_control", "+memory"))
+ goto cleanup;
+
+ if (cg_create(child))
+ goto cleanup;
+
+ if (cg_read_strstr(child, "cgroup.controllers", "memory"))
+ goto cleanup;
+
+ /* Create two nested cgroups without enabling memory controller */
+ parent2 = cg_name(root, "memcg_test_1");
+ child2 = cg_name(root, "memcg_test_1/memcg_test_1");
+ if (!parent2 || !child2)
+ goto cleanup;
+
+ if (cg_create(parent2))
+ goto cleanup;
+
+ if (cg_create(child2))
+ goto cleanup;
+
+ if (cg_read(child2, "cgroup.controllers", buf, sizeof(buf)))
+ goto cleanup;
+
+ if (!cg_read_strstr(child2, "cgroup.controllers", "memory"))
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(child);
+ cg_destroy(parent);
+ free(parent);
+ free(child);
+
+ cg_destroy(child2);
+ cg_destroy(parent2);
+ free(parent2);
+ free(child2);
+
+ return ret;
+}
+
+static int alloc_anon_50M_check(const char *cgroup, void *arg)
+{
+ size_t size = MB(50);
+ char *buf, *ptr;
+ long anon, current;
+ int ret = -1;
+
+ buf = malloc(size);
+ for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+ *ptr = 0;
+
+ current = cg_read_long(cgroup, "memory.current");
+ if (current < size)
+ goto cleanup;
+
+ if (!values_close(size, current, 3))
+ goto cleanup;
+
+ anon = cg_read_key_long(cgroup, "memory.stat", "anon ");
+ if (anon < 0)
+ goto cleanup;
+
+ if (!values_close(anon, current, 3))
+ goto cleanup;
+
+ ret = 0;
+cleanup:
+ free(buf);
+ return ret;
+}
+
+static int alloc_pagecache_50M_check(const char *cgroup, void *arg)
+{
+ size_t size = MB(50);
+ int ret = -1;
+ long current, file;
+ int fd;
+
+ fd = get_temp_fd();
+ if (fd < 0)
+ return -1;
+
+ if (alloc_pagecache(fd, size))
+ goto cleanup;
+
+ current = cg_read_long(cgroup, "memory.current");
+ if (current < size)
+ goto cleanup;
+
+ file = cg_read_key_long(cgroup, "memory.stat", "file ");
+ if (file < 0)
+ goto cleanup;
+
+ if (!values_close(file, current, 10))
+ goto cleanup;
+
+ ret = 0;
+
+cleanup:
+ close(fd);
+ return ret;
+}
+
+/*
+ * This test create a memory cgroup, allocates
+ * some anonymous memory and some pagecache
+ * and check memory.current and some memory.stat values.
+ */
+static int test_memcg_current(const char *root)
+{
+ int ret = KSFT_FAIL;
+ long current;
+ char *memcg;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ current = cg_read_long(memcg, "memory.current");
+ if (current != 0)
+ goto cleanup;
+
+ if (cg_run(memcg, alloc_anon_50M_check, NULL))
+ goto cleanup;
+
+ if (cg_run(memcg, alloc_pagecache_50M_check, NULL))
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+static int alloc_pagecache_50M(const char *cgroup, void *arg)
+{
+ int fd = (long)arg;
+
+ return alloc_pagecache(fd, MB(50));
+}
+
+static int alloc_pagecache_50M_noexit(const char *cgroup, void *arg)
+{
+ int fd = (long)arg;
+ int ppid = getppid();
+
+ if (alloc_pagecache(fd, MB(50)))
+ return -1;
+
+ while (getppid() == ppid)
+ sleep(1);
+
+ return 0;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A memory.min = 50M, memory.max = 200M
+ * A/B memory.min = 50M, memory.current = 50M
+ * A/B/C memory.min = 75M, memory.current = 50M
+ * A/B/D memory.min = 25M, memory.current = 50M
+ * A/B/E memory.min = 500M, memory.current = 0
+ * A/B/F memory.min = 0, memory.current = 50M
+ *
+ * Usages are pagecache, but the test keeps a running
+ * process in every leaf cgroup.
+ * Then it creates A/G and creates a significant
+ * memory pressure in it.
+ *
+ * A/B memory.current ~= 50M
+ * A/B/C memory.current ~= 33M
+ * A/B/D memory.current ~= 17M
+ * A/B/E memory.current ~= 0
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available, and checks
+ * checks that memory.min protects pagecache even
+ * in this case.
+ */
+static int test_memcg_min(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *parent[3] = {NULL};
+ char *children[4] = {NULL};
+ long c[4];
+ int i, attempts;
+ int fd;
+
+ fd = get_temp_fd();
+ if (fd < 0)
+ goto cleanup;
+
+ parent[0] = cg_name(root, "memcg_test_0");
+ if (!parent[0])
+ goto cleanup;
+
+ parent[1] = cg_name(parent[0], "memcg_test_1");
+ if (!parent[1])
+ goto cleanup;
+
+ parent[2] = cg_name(parent[0], "memcg_test_2");
+ if (!parent[2])
+ goto cleanup;
+
+ if (cg_create(parent[0]))
+ goto cleanup;
+
+ if (cg_read_long(parent[0], "memory.min")) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (cg_write(parent[0], "cgroup.subtree_control", "+memory"))
+ goto cleanup;
+
+ if (cg_write(parent[0], "memory.max", "200M"))
+ goto cleanup;
+
+ if (cg_write(parent[0], "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (cg_create(parent[1]))
+ goto cleanup;
+
+ if (cg_write(parent[1], "cgroup.subtree_control", "+memory"))
+ goto cleanup;
+
+ if (cg_create(parent[2]))
+ goto cleanup;
+
+ for (i = 0; i < ARRAY_SIZE(children); i++) {
+ children[i] = cg_name_indexed(parent[1], "child_memcg", i);
+ if (!children[i])
+ goto cleanup;
+
+ if (cg_create(children[i]))
+ goto cleanup;
+
+ if (i == 2)
+ continue;
+
+ cg_run_nowait(children[i], alloc_pagecache_50M_noexit,
+ (void *)(long)fd);
+ }
+
+ if (cg_write(parent[0], "memory.min", "50M"))
+ goto cleanup;
+ if (cg_write(parent[1], "memory.min", "50M"))
+ goto cleanup;
+ if (cg_write(children[0], "memory.min", "75M"))
+ goto cleanup;
+ if (cg_write(children[1], "memory.min", "25M"))
+ goto cleanup;
+ if (cg_write(children[2], "memory.min", "500M"))
+ goto cleanup;
+ if (cg_write(children[3], "memory.min", "0"))
+ goto cleanup;
+
+ attempts = 0;
+ while (!values_close(cg_read_long(parent[1], "memory.current"),
+ MB(150), 3)) {
+ if (attempts++ > 5)
+ break;
+ sleep(1);
+ }
+
+ if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
+ goto cleanup;
+
+ if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+ goto cleanup;
+
+ for (i = 0; i < ARRAY_SIZE(children); i++)
+ c[i] = cg_read_long(children[i], "memory.current");
+
+ if (!values_close(c[0], MB(33), 10))
+ goto cleanup;
+
+ if (!values_close(c[1], MB(17), 10))
+ goto cleanup;
+
+ if (!values_close(c[2], 0, 1))
+ goto cleanup;
+
+ if (!cg_run(parent[2], alloc_anon, (void *)MB(170)))
+ goto cleanup;
+
+ if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ for (i = ARRAY_SIZE(children) - 1; i >= 0; i--) {
+ if (!children[i])
+ continue;
+
+ cg_destroy(children[i]);
+ free(children[i]);
+ }
+
+ for (i = ARRAY_SIZE(parent) - 1; i >= 0; i--) {
+ if (!parent[i])
+ continue;
+
+ cg_destroy(parent[i]);
+ free(parent[i]);
+ }
+ close(fd);
+ return ret;
+}
+
+/*
+ * First, this test creates the following hierarchy:
+ * A memory.low = 50M, memory.max = 200M
+ * A/B memory.low = 50M, memory.current = 50M
+ * A/B/C memory.low = 75M, memory.current = 50M
+ * A/B/D memory.low = 25M, memory.current = 50M
+ * A/B/E memory.low = 500M, memory.current = 0
+ * A/B/F memory.low = 0, memory.current = 50M
+ *
+ * Usages are pagecache.
+ * Then it creates A/G an creates a significant
+ * memory pressure in it.
+ *
+ * Then it checks actual memory usages and expects that:
+ * A/B memory.current ~= 50M
+ * A/B/ memory.current ~= 33M
+ * A/B/D memory.current ~= 17M
+ * A/B/E memory.current ~= 0
+ *
+ * After that it tries to allocate more than there is
+ * unprotected memory in A available,
+ * and checks low and oom events in memory.events.
+ */
+static int test_memcg_low(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *parent[3] = {NULL};
+ char *children[4] = {NULL};
+ long low, oom;
+ long c[4];
+ int i;
+ int fd;
+
+ fd = get_temp_fd();
+ if (fd < 0)
+ goto cleanup;
+
+ parent[0] = cg_name(root, "memcg_test_0");
+ if (!parent[0])
+ goto cleanup;
+
+ parent[1] = cg_name(parent[0], "memcg_test_1");
+ if (!parent[1])
+ goto cleanup;
+
+ parent[2] = cg_name(parent[0], "memcg_test_2");
+ if (!parent[2])
+ goto cleanup;
+
+ if (cg_create(parent[0]))
+ goto cleanup;
+
+ if (cg_read_long(parent[0], "memory.low"))
+ goto cleanup;
+
+ if (cg_write(parent[0], "cgroup.subtree_control", "+memory"))
+ goto cleanup;
+
+ if (cg_write(parent[0], "memory.max", "200M"))
+ goto cleanup;
+
+ if (cg_write(parent[0], "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (cg_create(parent[1]))
+ goto cleanup;
+
+ if (cg_write(parent[1], "cgroup.subtree_control", "+memory"))
+ goto cleanup;
+
+ if (cg_create(parent[2]))
+ goto cleanup;
+
+ for (i = 0; i < ARRAY_SIZE(children); i++) {
+ children[i] = cg_name_indexed(parent[1], "child_memcg", i);
+ if (!children[i])
+ goto cleanup;
+
+ if (cg_create(children[i]))
+ goto cleanup;
+
+ if (i == 2)
+ continue;
+
+ if (cg_run(children[i], alloc_pagecache_50M, (void *)(long)fd))
+ goto cleanup;
+ }
+
+ if (cg_write(parent[0], "memory.low", "50M"))
+ goto cleanup;
+ if (cg_write(parent[1], "memory.low", "50M"))
+ goto cleanup;
+ if (cg_write(children[0], "memory.low", "75M"))
+ goto cleanup;
+ if (cg_write(children[1], "memory.low", "25M"))
+ goto cleanup;
+ if (cg_write(children[2], "memory.low", "500M"))
+ goto cleanup;
+ if (cg_write(children[3], "memory.low", "0"))
+ goto cleanup;
+
+ if (cg_run(parent[2], alloc_anon, (void *)MB(148)))
+ goto cleanup;
+
+ if (!values_close(cg_read_long(parent[1], "memory.current"), MB(50), 3))
+ goto cleanup;
+
+ for (i = 0; i < ARRAY_SIZE(children); i++)
+ c[i] = cg_read_long(children[i], "memory.current");
+
+ if (!values_close(c[0], MB(33), 10))
+ goto cleanup;
+
+ if (!values_close(c[1], MB(17), 10))
+ goto cleanup;
+
+ if (!values_close(c[2], 0, 1))
+ goto cleanup;
+
+ if (cg_run(parent[2], alloc_anon, (void *)MB(166))) {
+ fprintf(stderr,
+ "memory.low prevents from allocating anon memory\n");
+ goto cleanup;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(children); i++) {
+ oom = cg_read_key_long(children[i], "memory.events", "oom ");
+ low = cg_read_key_long(children[i], "memory.events", "low ");
+
+ if (oom)
+ goto cleanup;
+ if (i < 2 && low <= 0)
+ goto cleanup;
+ if (i >= 2 && low)
+ goto cleanup;
+ }
+
+ ret = KSFT_PASS;
+
+cleanup:
+ for (i = ARRAY_SIZE(children) - 1; i >= 0; i--) {
+ if (!children[i])
+ continue;
+
+ cg_destroy(children[i]);
+ free(children[i]);
+ }
+
+ for (i = ARRAY_SIZE(parent) - 1; i >= 0; i--) {
+ if (!parent[i])
+ continue;
+
+ cg_destroy(parent[i]);
+ free(parent[i]);
+ }
+ close(fd);
+ return ret;
+}
+
+static int alloc_pagecache_max_30M(const char *cgroup, void *arg)
+{
+ size_t size = MB(50);
+ int ret = -1;
+ long current;
+ int fd;
+
+ fd = get_temp_fd();
+ if (fd < 0)
+ return -1;
+
+ if (alloc_pagecache(fd, size))
+ goto cleanup;
+
+ current = cg_read_long(cgroup, "memory.current");
+ if (current <= MB(29) || current > MB(30))
+ goto cleanup;
+
+ ret = 0;
+
+cleanup:
+ close(fd);
+ return ret;
+
+}
+
+/*
+ * This test checks that memory.high limits the amount of
+ * memory which can be consumed by either anonymous memory
+ * or pagecache.
+ */
+static int test_memcg_high(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *memcg;
+ long high;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ if (cg_read_strcmp(memcg, "memory.high", "max\n"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.high", "30M"))
+ goto cleanup;
+
+ if (cg_run(memcg, alloc_anon, (void *)MB(100)))
+ goto cleanup;
+
+ if (!cg_run(memcg, alloc_pagecache_50M_check, NULL))
+ goto cleanup;
+
+ if (cg_run(memcg, alloc_pagecache_max_30M, NULL))
+ goto cleanup;
+
+ high = cg_read_key_long(memcg, "memory.events", "high ");
+ if (high <= 0)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+/*
+ * This test checks that memory.max limits the amount of
+ * memory which can be consumed by either anonymous memory
+ * or pagecache.
+ */
+static int test_memcg_max(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *memcg;
+ long current, max;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ if (cg_read_strcmp(memcg, "memory.max", "max\n"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.max", "30M"))
+ goto cleanup;
+
+ /* Should be killed by OOM killer */
+ if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+ goto cleanup;
+
+ if (cg_run(memcg, alloc_pagecache_max_30M, NULL))
+ goto cleanup;
+
+ current = cg_read_long(memcg, "memory.current");
+ if (current > MB(30) || !current)
+ goto cleanup;
+
+ max = cg_read_key_long(memcg, "memory.events", "max ");
+ if (max <= 0)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+static int alloc_anon_50M_check_swap(const char *cgroup, void *arg)
+{
+ long mem_max = (long)arg;
+ size_t size = MB(50);
+ char *buf, *ptr;
+ long mem_current, swap_current;
+ int ret = -1;
+
+ buf = malloc(size);
+ for (ptr = buf; ptr < buf + size; ptr += PAGE_SIZE)
+ *ptr = 0;
+
+ mem_current = cg_read_long(cgroup, "memory.current");
+ if (!mem_current || !values_close(mem_current, mem_max, 3))
+ goto cleanup;
+
+ swap_current = cg_read_long(cgroup, "memory.swap.current");
+ if (!swap_current ||
+ !values_close(mem_current + swap_current, size, 3))
+ goto cleanup;
+
+ ret = 0;
+cleanup:
+ free(buf);
+ return ret;
+}
+
+/*
+ * This test checks that memory.swap.max limits the amount of
+ * anonymous memory which can be swapped out.
+ */
+static int test_memcg_swap_max(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *memcg;
+ long max;
+
+ if (!is_swap_enabled())
+ return KSFT_SKIP;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ if (cg_read_long(memcg, "memory.swap.current")) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (cg_read_strcmp(memcg, "memory.max", "max\n"))
+ goto cleanup;
+
+ if (cg_read_strcmp(memcg, "memory.swap.max", "max\n"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.swap.max", "30M"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.max", "30M"))
+ goto cleanup;
+
+ /* Should be killed by OOM killer */
+ if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+ goto cleanup;
+
+ if (cg_read_key_long(memcg, "memory.events", "oom ") != 1)
+ goto cleanup;
+
+ if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
+ goto cleanup;
+
+ if (cg_run(memcg, alloc_anon_50M_check_swap, (void *)MB(30)))
+ goto cleanup;
+
+ max = cg_read_key_long(memcg, "memory.events", "max ");
+ if (max <= 0)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+/*
+ * This test disables swapping and tries to allocate anonymous memory
+ * up to OOM. Then it checks for oom and oom_kill events in
+ * memory.events.
+ */
+static int test_memcg_oom_events(const char *root)
+{
+ int ret = KSFT_FAIL;
+ char *memcg;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.max", "30M"))
+ goto cleanup;
+
+ if (cg_write(memcg, "memory.swap.max", "0"))
+ goto cleanup;
+
+ if (!cg_run(memcg, alloc_anon, (void *)MB(100)))
+ goto cleanup;
+
+ if (cg_read_strcmp(memcg, "cgroup.procs", ""))
+ goto cleanup;
+
+ if (cg_read_key_long(memcg, "memory.events", "oom ") != 1)
+ goto cleanup;
+
+ if (cg_read_key_long(memcg, "memory.events", "oom_kill ") != 1)
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+struct tcp_server_args {
+ unsigned short port;
+ int ctl[2];
+};
+
+static int tcp_server(const char *cgroup, void *arg)
+{
+ struct tcp_server_args *srv_args = arg;
+ struct sockaddr_in6 saddr = { 0 };
+ socklen_t slen = sizeof(saddr);
+ int sk, client_sk, ctl_fd, yes = 1, ret = -1;
+
+ close(srv_args->ctl[0]);
+ ctl_fd = srv_args->ctl[1];
+
+ saddr.sin6_family = AF_INET6;
+ saddr.sin6_addr = in6addr_any;
+ saddr.sin6_port = htons(srv_args->port);
+
+ sk = socket(AF_INET6, SOCK_STREAM, 0);
+ if (sk < 0)
+ return ret;
+
+ if (setsockopt(sk, SOL_SOCKET, SO_REUSEADDR, &yes, sizeof(yes)) < 0)
+ goto cleanup;
+
+ if (bind(sk, (struct sockaddr *)&saddr, slen)) {
+ write(ctl_fd, &errno, sizeof(errno));
+ goto cleanup;
+ }
+
+ if (listen(sk, 1))
+ goto cleanup;
+
+ ret = 0;
+ if (write(ctl_fd, &ret, sizeof(ret)) != sizeof(ret)) {
+ ret = -1;
+ goto cleanup;
+ }
+
+ client_sk = accept(sk, NULL, NULL);
+ if (client_sk < 0)
+ goto cleanup;
+
+ ret = -1;
+ for (;;) {
+ uint8_t buf[0x100000];
+
+ if (write(client_sk, buf, sizeof(buf)) <= 0) {
+ if (errno == ECONNRESET)
+ ret = 0;
+ break;
+ }
+ }
+
+ close(client_sk);
+
+cleanup:
+ close(sk);
+ return ret;
+}
+
+static int tcp_client(const char *cgroup, unsigned short port)
+{
+ const char server[] = "localhost";
+ struct addrinfo *ai;
+ char servport[6];
+ int retries = 0x10; /* nice round number */
+ int sk, ret;
+
+ snprintf(servport, sizeof(servport), "%hd", port);
+ ret = getaddrinfo(server, servport, NULL, &ai);
+ if (ret)
+ return ret;
+
+ sk = socket(ai->ai_family, ai->ai_socktype, ai->ai_protocol);
+ if (sk < 0)
+ goto free_ainfo;
+
+ ret = connect(sk, ai->ai_addr, ai->ai_addrlen);
+ if (ret < 0)
+ goto close_sk;
+
+ ret = KSFT_FAIL;
+ while (retries--) {
+ uint8_t buf[0x100000];
+ long current, sock;
+
+ if (read(sk, buf, sizeof(buf)) <= 0)
+ goto close_sk;
+
+ current = cg_read_long(cgroup, "memory.current");
+ sock = cg_read_key_long(cgroup, "memory.stat", "sock ");
+
+ if (current < 0 || sock < 0)
+ goto close_sk;
+
+ if (current < sock)
+ goto close_sk;
+
+ if (values_close(current, sock, 10)) {
+ ret = KSFT_PASS;
+ break;
+ }
+ }
+
+close_sk:
+ close(sk);
+free_ainfo:
+ freeaddrinfo(ai);
+ return ret;
+}
+
+/*
+ * This test checks socket memory accounting.
+ * The test forks a TCP server listens on a random port between 1000
+ * and 61000. Once it gets a client connection, it starts writing to
+ * its socket.
+ * The TCP client interleaves reads from the socket with check whether
+ * memory.current and memory.stat.sock are similar.
+ */
+static int test_memcg_sock(const char *root)
+{
+ int bind_retries = 5, ret = KSFT_FAIL, pid, err;
+ unsigned short port;
+ char *memcg;
+
+ memcg = cg_name(root, "memcg_test");
+ if (!memcg)
+ goto cleanup;
+
+ if (cg_create(memcg))
+ goto cleanup;
+
+ while (bind_retries--) {
+ struct tcp_server_args args;
+
+ if (pipe(args.ctl))
+ goto cleanup;
+
+ port = args.port = 1000 + rand() % 60000;
+
+ pid = cg_run_nowait(memcg, tcp_server, &args);
+ if (pid < 0)
+ goto cleanup;
+
+ close(args.ctl[1]);
+ if (read(args.ctl[0], &err, sizeof(err)) != sizeof(err))
+ goto cleanup;
+ close(args.ctl[0]);
+
+ if (!err)
+ break;
+ if (err != EADDRINUSE)
+ goto cleanup;
+
+ waitpid(pid, NULL, 0);
+ }
+
+ if (err == EADDRINUSE) {
+ ret = KSFT_SKIP;
+ goto cleanup;
+ }
+
+ if (tcp_client(memcg, port) != KSFT_PASS)
+ goto cleanup;
+
+ waitpid(pid, &err, 0);
+ if (WEXITSTATUS(err))
+ goto cleanup;
+
+ if (cg_read_long(memcg, "memory.current") < 0)
+ goto cleanup;
+
+ if (cg_read_key_long(memcg, "memory.stat", "sock "))
+ goto cleanup;
+
+ ret = KSFT_PASS;
+
+cleanup:
+ cg_destroy(memcg);
+ free(memcg);
+
+ return ret;
+}
+
+#define T(x) { x, #x }
+struct memcg_test {
+ int (*fn)(const char *root);
+ const char *name;
+} tests[] = {
+ T(test_memcg_subtree_control),
+ T(test_memcg_current),
+ T(test_memcg_min),
+ T(test_memcg_low),
+ T(test_memcg_high),
+ T(test_memcg_max),
+ T(test_memcg_oom_events),
+ T(test_memcg_swap_max),
+ T(test_memcg_sock),
+};
+#undef T
+
+int main(int argc, char **argv)
+{
+ char root[PATH_MAX];
+ int i, ret = EXIT_SUCCESS;
+
+ if (cg_find_unified_root(root, sizeof(root)))
+ ksft_exit_skip("cgroup v2 isn't mounted\n");
+
+ /*
+ * Check that memory controller is available:
+ * memory is listed in cgroup.controllers
+ */
+ if (cg_read_strstr(root, "cgroup.controllers", "memory"))
+ ksft_exit_skip("memory controller isn't available\n");
+
+ for (i = 0; i < ARRAY_SIZE(tests); i++) {
+ switch (tests[i].fn(root)) {
+ case KSFT_PASS:
+ ksft_test_result_pass("%s\n", tests[i].name);
+ break;
+ case KSFT_SKIP:
+ ksft_test_result_skip("%s\n", tests[i].name);
+ break;
+ default:
+ ret = EXIT_FAILURE;
+ ksft_test_result_fail("%s\n", tests[i].name);
+ break;
+ }
+ }
+
+ return ret;
+}
diff --git a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
index f3a8933c1275..bab13dd025a6 100755
--- a/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
+++ b/tools/testing/selftests/cpu-hotplug/cpu-on-off-test.sh
@@ -2,6 +2,8 @@
# SPDX-License-Identifier: GPL-2.0
SYSFS=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
prerequisite()
{
@@ -9,7 +11,7 @@ prerequisite()
if [ $UID != 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
taskset -p 01 $$
@@ -18,12 +20,12 @@ prerequisite()
if [ ! -d "$SYSFS" ]; then
echo $msg sysfs is not mounted >&2
- exit 0
+ exit $ksft_skip
fi
if ! ls $SYSFS/devices/system/cpu/cpu* > /dev/null 2>&1; then
echo $msg cpu hotplug is not supported >&2
- exit 0
+ exit $ksft_skip
fi
echo "CPU online/offline summary:"
@@ -32,7 +34,7 @@ prerequisite()
if [[ "$online_cpus" = "$online_max" ]]; then
echo "$msg: since there is only one cpu: $online_cpus"
- exit 0
+ exit $ksft_skip
fi
echo -e "\t Cpus in online state: $online_cpus"
@@ -237,12 +239,12 @@ prerequisite_extra()
if [ ! -d "$DEBUGFS" ]; then
echo $msg debugfs is not mounted >&2
- exit 0
+ exit $ksft_skip
fi
if [ ! -d $NOTIFIER_ERR_INJECT_DIR ]; then
echo $msg cpu-notifier-error-inject module is not available >&2
- exit 0
+ exit $ksft_skip
fi
}
diff --git a/tools/testing/selftests/cpufreq/main.sh b/tools/testing/selftests/cpufreq/main.sh
index d83922de9d89..31f8c9a76c5f 100755
--- a/tools/testing/selftests/cpufreq/main.sh
+++ b/tools/testing/selftests/cpufreq/main.sh
@@ -13,6 +13,9 @@ SYSFS=
CPUROOT=
CPUFREQROOT=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
helpme()
{
printf "Usage: $0 [-h] [-todg args]
@@ -38,7 +41,7 @@ prerequisite()
if [ $UID != 0 ]; then
echo $msg must be run as root >&2
- exit 2
+ exit $ksft_skip
fi
taskset -p 01 $$
diff --git a/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
new file mode 100755
index 000000000000..1893d0f59ad7
--- /dev/null
+++ b/tools/testing/selftests/drivers/usb/usbip/usbip_test.sh
@@ -0,0 +1,198 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+usage() { echo "usbip_test.sh -b <busid> -p <usbip tools path>"; exit 1; }
+
+while getopts "h:b:p:" arg; do
+ case "${arg}" in
+ h)
+ usage
+ ;;
+ b)
+ busid=${OPTARG}
+ ;;
+ p)
+ tools_path=${OPTARG}
+ ;;
+ *)
+ usage
+ ;;
+ esac
+done
+shift $((OPTIND-1))
+
+if [ -z "${busid}" ]; then
+ usage
+fi
+
+echo "Running USB over IP Testing on $busid";
+
+test_end_msg="End of USB over IP Testing on $busid"
+
+if [ $UID != 0 ]; then
+ echo "Please run usbip_test as root [SKIP]"
+ echo $test_end_msg
+ exit $ksft_skip
+fi
+
+echo "Load usbip_host module"
+if ! /sbin/modprobe -q -n usbip_host; then
+ echo "usbip_test: module usbip_host is not found [SKIP]"
+ echo $test_end_msg
+ exit $ksft_skip
+fi
+
+if /sbin/modprobe -q usbip_host; then
+ /sbin/modprobe -q -r test_bitmap
+ echo "usbip_test: module usbip_host is loaded [OK]"
+else
+ echo "usbip_test: module usbip_host failed to load [FAIL]"
+ echo $test_end_msg
+ exit 1
+fi
+
+echo "Load vhci_hcd module"
+if /sbin/modprobe -q vhci_hcd; then
+ /sbin/modprobe -q -r test_bitmap
+ echo "usbip_test: module vhci_hcd is loaded [OK]"
+else
+ echo "usbip_test: module vhci_hcd failed to load [FAIL]"
+ echo $test_end_msg
+ exit 1
+fi
+echo "=============================================================="
+
+cd $tools_path;
+
+if [ ! -f src/usbip ]; then
+ echo "Please build usbip tools"
+ echo $test_end_msg
+ exit $ksft_skip
+fi
+
+echo "Expect to see export-able devices";
+src/usbip list -l;
+echo "=============================================================="
+
+echo "Run lsusb to see all usb devices"
+lsusb -t;
+echo "=============================================================="
+
+src/usbipd -D;
+
+echo "Get exported devices from localhost - expect to see none";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "bind devices";
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "Run lsusb - bound devices should be under usbip_host control"
+lsusb -t;
+echo "=============================================================="
+
+echo "bind devices - expect already bound messages"
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "Get exported devices from localhost - expect to see exported devices";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "unbind devices";
+src/usbip unbind -b $busid;
+echo "=============================================================="
+
+echo "Run lsusb - bound devices should be rebound to original drivers"
+lsusb -t;
+echo "=============================================================="
+
+echo "unbind devices - expect no devices bound message";
+src/usbip unbind -b $busid;
+echo "=============================================================="
+
+echo "Get exported devices from localhost - expect to see none";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "List imported devices - expect to see none";
+src/usbip port;
+echo "=============================================================="
+
+echo "Import devices from localhost - should fail with no devices"
+src/usbip attach -r localhost -b $busid;
+echo "=============================================================="
+
+echo "bind devices";
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "List imported devices - expect to see exported devices";
+src/usbip list -r localhost;
+echo "=============================================================="
+
+echo "List imported devices - expect to see none";
+src/usbip port;
+echo "=============================================================="
+
+echo "Import devices from localhost - should work"
+src/usbip attach -r localhost -b $busid;
+echo "=============================================================="
+
+echo "List imported devices - expect to see imported devices";
+src/usbip port;
+echo "=============================================================="
+
+echo "Import devices from localhost - expect already imported messages"
+src/usbip attach -r localhost -b $busid;
+echo "=============================================================="
+
+echo "Un-import devices";
+src/usbip detach -p 00;
+src/usbip detach -p 01;
+echo "=============================================================="
+
+echo "List imported devices - expect to see none";
+src/usbip port;
+echo "=============================================================="
+
+echo "Un-import devices - expect no devices to detach messages";
+src/usbip detach -p 00;
+src/usbip detach -p 01;
+echo "=============================================================="
+
+echo "Detach invalid port tests - expect invalid port error message";
+src/usbip detach -p 100;
+echo "=============================================================="
+
+echo "Expect to see export-able devices";
+src/usbip list -l;
+echo "=============================================================="
+
+echo "Remove usbip_host module";
+rmmod usbip_host;
+
+echo "Run lsusb - bound devices should be rebound to original drivers"
+lsusb -t;
+echo "=============================================================="
+
+echo "Run bind without usbip_host - expect fail"
+src/usbip bind -b $busid;
+echo "=============================================================="
+
+echo "Run lsusb - devices that failed to bind aren't bound to any driver"
+lsusb -t;
+echo "=============================================================="
+
+echo "modprobe usbip_host - does it work?"
+/sbin/modprobe usbip_host
+echo "Should see -busid- is not in match_busid table... skip! dmesg"
+echo "=============================================================="
+dmesg | grep "is not in match_busid table"
+echo "=============================================================="
+
+echo $test_end_msg
diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh
index c6d5790575ae..a47029a799d2 100755
--- a/tools/testing/selftests/efivarfs/efivarfs.sh
+++ b/tools/testing/selftests/efivarfs/efivarfs.sh
@@ -4,18 +4,21 @@
efivarfs_mount=/sys/firmware/efi/efivars
test_guid=210be57c-9849-4fc7-a635-e6382d1aec27
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
check_prereqs()
{
local msg="skip all tests:"
if [ $UID != 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
if ! grep -q "^\S\+ $efivarfs_mount efivarfs" /proc/mounts; then
echo $msg efivarfs is not mounted on $efivarfs_mount >&2
- exit 0
+ exit $ksft_skip
fi
}
diff --git a/tools/testing/selftests/exec/execveat.c b/tools/testing/selftests/exec/execveat.c
index 67cd4597db2b..47cbf54d0801 100644
--- a/tools/testing/selftests/exec/execveat.c
+++ b/tools/testing/selftests/exec/execveat.c
@@ -20,6 +20,8 @@
#include <string.h>
#include <unistd.h>
+#include "../kselftest.h"
+
static char longpath[2 * PATH_MAX] = "";
static char *envp[] = { "IN_TEST=yes", NULL, NULL };
static char *argv[] = { "execveat", "99", NULL };
@@ -249,8 +251,8 @@ static int run_tests(void)
errno = 0;
execveat_(-1, NULL, NULL, NULL, 0);
if (errno == ENOSYS) {
- printf("[FAIL] ENOSYS calling execveat - no kernel support?\n");
- return 1;
+ ksft_exit_skip(
+ "ENOSYS calling execveat - no kernel support?\n");
}
/* Change file position to confirm it doesn't affect anything */
diff --git a/tools/testing/selftests/filesystems/Makefile b/tools/testing/selftests/filesystems/Makefile
index 4e6d09fb166f..129880fb42d3 100644
--- a/tools/testing/selftests/filesystems/Makefile
+++ b/tools/testing/selftests/filesystems/Makefile
@@ -1,8 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
-TEST_PROGS := dnotify_test devpts_pts
-all: $(TEST_PROGS)
-include ../lib.mk
+CFLAGS += -I../../../../usr/include/
+TEST_GEN_PROGS := devpts_pts
+TEST_GEN_PROGS_EXTENDED := dnotify_test
-clean:
- rm -fr $(TEST_PROGS)
+include ../lib.mk
diff --git a/tools/testing/selftests/filesystems/devpts_pts.c b/tools/testing/selftests/filesystems/devpts_pts.c
index b9055e974289..b1fc9b916ace 100644
--- a/tools/testing/selftests/filesystems/devpts_pts.c
+++ b/tools/testing/selftests/filesystems/devpts_pts.c
@@ -8,9 +8,10 @@
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
-#include <sys/ioctl.h>
+#include <asm/ioctls.h>
#include <sys/mount.h>
#include <sys/wait.h>
+#include "../kselftest.h"
static bool terminal_dup2(int duplicate, int original)
{
@@ -125,10 +126,12 @@ static int do_tiocgptpeer(char *ptmx, char *expected_procfd_contents)
if (errno == EINVAL) {
fprintf(stderr, "TIOCGPTPEER is not supported. "
"Skipping test.\n");
- fret = EXIT_SUCCESS;
+ fret = KSFT_SKIP;
+ } else {
+ fprintf(stderr,
+ "Failed to perform TIOCGPTPEER ioctl\n");
+ fret = EXIT_FAILURE;
}
-
- fprintf(stderr, "Failed to perform TIOCGPTPEER ioctl\n");
goto do_cleanup;
}
@@ -279,9 +282,9 @@ int main(int argc, char *argv[])
int ret;
if (!isatty(STDIN_FILENO)) {
- fprintf(stderr, "Standard input file desciptor is not attached "
+ fprintf(stderr, "Standard input file descriptor is not attached "
"to a terminal. Skipping test\n");
- exit(EXIT_FAILURE);
+ exit(KSFT_SKIP);
}
ret = unshare(CLONE_NEWNS);
diff --git a/tools/testing/selftests/firmware/Makefile b/tools/testing/selftests/firmware/Makefile
index 826f38d5dd19..261c81f08606 100644
--- a/tools/testing/selftests/firmware/Makefile
+++ b/tools/testing/selftests/firmware/Makefile
@@ -4,6 +4,7 @@
all:
TEST_PROGS := fw_run_tests.sh
+TEST_FILES := fw_fallback.sh fw_filesystem.sh fw_lib.sh
include ../lib.mk
diff --git a/tools/testing/selftests/firmware/fw_fallback.sh b/tools/testing/selftests/firmware/fw_fallback.sh
index 8e2e34a2ca69..70d18be46af5 100755
--- a/tools/testing/selftests/firmware/fw_fallback.sh
+++ b/tools/testing/selftests/firmware/fw_fallback.sh
@@ -74,7 +74,7 @@ load_fw_custom()
{
if [ ! -e "$DIR"/trigger_custom_fallback ]; then
echo "$0: custom fallback trigger not present, ignoring test" >&2
- return 1
+ exit $ksft_skip
fi
local name="$1"
@@ -107,7 +107,7 @@ load_fw_custom_cancel()
{
if [ ! -e "$DIR"/trigger_custom_fallback ]; then
echo "$0: canceling custom fallback trigger not present, ignoring test" >&2
- return 1
+ exit $ksft_skip
fi
local name="$1"
diff --git a/tools/testing/selftests/firmware/fw_filesystem.sh b/tools/testing/selftests/firmware/fw_filesystem.sh
index 6452d2129cd9..a4320c4b44dc 100755
--- a/tools/testing/selftests/firmware/fw_filesystem.sh
+++ b/tools/testing/selftests/firmware/fw_filesystem.sh
@@ -30,6 +30,7 @@ fi
if [ ! -e "$DIR"/trigger_async_request ]; then
echo "$0: empty filename: async trigger not present, ignoring test" >&2
+ exit $ksft_skip
else
if printf '\000' >"$DIR"/trigger_async_request 2> /dev/null; then
echo "$0: empty filename should not succeed (async)" >&2
@@ -69,6 +70,7 @@ fi
# Try the asynchronous version too
if [ ! -e "$DIR"/trigger_async_request ]; then
echo "$0: firmware loading: async trigger not present, ignoring test" >&2
+ exit $ksft_skip
else
if ! echo -n "$NAME" >"$DIR"/trigger_async_request ; then
echo "$0: could not trigger async request" >&2
@@ -89,7 +91,7 @@ test_config_present()
{
if [ ! -f $DIR/reset ]; then
echo "Configuration triggers not present, ignoring test"
- exit 0
+ exit $ksft_skip
fi
}
diff --git a/tools/testing/selftests/firmware/fw_lib.sh b/tools/testing/selftests/firmware/fw_lib.sh
index 9ea31b57d71a..6c5f1b2ffb74 100755
--- a/tools/testing/selftests/firmware/fw_lib.sh
+++ b/tools/testing/selftests/firmware/fw_lib.sh
@@ -9,11 +9,14 @@ DIR=/sys/devices/virtual/misc/test_firmware
PROC_CONFIG="/proc/config.gz"
TEST_DIR=$(dirname $0)
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
print_reqs_exit()
{
echo "You must have the following enabled in your kernel:" >&2
cat $TEST_DIR/config >&2
- exit 1
+ exit $ksft_skip
}
test_modprobe()
@@ -88,7 +91,7 @@ verify_reqs()
if [ "$TEST_REQS_FW_SYSFS_FALLBACK" = "yes" ]; then
if [ ! "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
echo "usermode helper disabled so ignoring test"
- exit 0
+ exit $ksft_skip
fi
fi
}
@@ -154,11 +157,13 @@ test_finish()
if [ "$HAS_FW_LOADER_USER_HELPER" = "yes" ]; then
echo "$OLD_TIMEOUT" >/sys/class/firmware/timeout
fi
- if [ "$OLD_FWPATH" = "" ]; then
- OLD_FWPATH=" "
- fi
if [ "$TEST_REQS_FW_SET_CUSTOM_PATH" = "yes" ]; then
- echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+ if [ "$OLD_FWPATH" = "" ]; then
+ # A zero-length write won't work; write a null byte
+ printf '\000' >/sys/module/firmware_class/parameters/path
+ else
+ echo -n "$OLD_FWPATH" >/sys/module/firmware_class/parameters/path
+ fi
fi
if [ -f $FW ]; then
rm -f "$FW"
diff --git a/tools/testing/selftests/firmware/fw_run_tests.sh b/tools/testing/selftests/firmware/fw_run_tests.sh
index 06d638e9dc62..cffdd4eb0a57 100755
--- a/tools/testing/selftests/firmware/fw_run_tests.sh
+++ b/tools/testing/selftests/firmware/fw_run_tests.sh
@@ -66,5 +66,5 @@ if [ -f $FW_FORCE_SYSFS_FALLBACK ]; then
run_test_config_0003
else
echo "Running basic kernel configuration, working with your config"
- run_test
+ run_tests
fi
diff --git a/tools/testing/selftests/ftrace/test.d/functions b/tools/testing/selftests/ftrace/test.d/functions
index df3dd7fe5f9b..e4645d5e3126 100644
--- a/tools/testing/selftests/ftrace/test.d/functions
+++ b/tools/testing/selftests/ftrace/test.d/functions
@@ -15,14 +15,29 @@ reset_tracer() { # reset the current tracer
echo nop > current_tracer
}
-reset_trigger() { # reset all current setting triggers
- grep -v ^# events/*/*/trigger |
+reset_trigger_file() {
+ # remove action triggers first
+ grep -H ':on[^:]*(' $@ |
+ while read line; do
+ cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["`
+ file=`echo $line | cut -f1 -d:`
+ echo "!$cmd" >> $file
+ done
+ grep -Hv ^# $@ |
while read line; do
- cmd=`echo $line | cut -f2- -d: | cut -f1 -d" "`
- echo "!$cmd" > `echo $line | cut -f1 -d:`
+ cmd=`echo $line | cut -f2- -d: | cut -f1 -d"["`
+ file=`echo $line | cut -f1 -d:`
+ echo "!$cmd" > $file
done
}
+reset_trigger() { # reset all current setting triggers
+ if [ -d events/synthetic ]; then
+ reset_trigger_file events/synthetic/*/trigger
+ fi
+ reset_trigger_file events/*/*/trigger
+}
+
reset_events_filter() { # reset all current setting filters
grep -v ^none events/*/*/filter |
while read line; do
@@ -59,6 +74,13 @@ disable_events() {
echo 0 > events/enable
}
+clear_synthetic_events() { # reset all current synthetic events
+ grep -v ^# synthetic_events |
+ while read line; do
+ echo "!$line" >> synthetic_events
+ done
+}
+
initialize_ftrace() { # Reset ftrace to initial-state
# As the initial state, ftrace will be set to nop tracer,
# no events, no triggers, no filters, no function filters,
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
new file mode 100644
index 000000000000..2aabab363cfb
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc
@@ -0,0 +1,39 @@
+#!/bin/sh
+# description: event trigger - test extended error support
+
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+reset_tracer
+do_reset
+
+echo "Test extended error support"
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
+! echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger 2> /dev/null
+if ! grep -q "ERROR:" events/sched/sched_wakeup/hist; then
+ fail "Failed to generate extended error in histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
new file mode 100644
index 000000000000..7fd5b4a8f060
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc
@@ -0,0 +1,54 @@
+#!/bin/sh
+# description: event trigger - test field variable support
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test field variable support"
+
+echo 'wakeup_latency u64 lat; pid_t pid; int prio; char comm[16]' > synthetic_events
+echo 'hist:keys=comm:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_waking/trigger
+echo 'hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
+echo 'hist:keys=pid,prio,comm:vals=lat:sort=pid,prio' > events/synthetic/wakeup_latency/trigger
+
+ping localhost -c 3
+if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
+ fail "Failed to create inter-event histogram"
+fi
+
+if ! grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then
+ fail "Failed to create histogram with field variable"
+fi
+
+echo '!hist:keys=next_comm:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,next_pid,sched.sched_waking.prio,next_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
+
+if grep -q "synthetic_prio=prio" events/sched/sched_waking/hist; then
+ fail "Failed to remove histogram with field variable"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
new file mode 100644
index 000000000000..c93dbe38b5df
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc
@@ -0,0 +1,58 @@
+#!/bin/sh
+# description: event trigger - test inter-event combined histogram trigger
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+reset_tracer
+do_reset
+clear_synthetic_events
+
+echo "Test create synthetic event"
+
+echo 'waking_latency u64 lat pid_t pid' > synthetic_events
+if [ ! -d events/synthetic/waking_latency ]; then
+ fail "Failed to create waking_latency synthetic event"
+fi
+
+echo "Test combined histogram"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_waking/trigger
+echo 'hist:keys=pid:waking_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).waking_latency($waking_lat,pid) if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=pid,lat:sort=pid,lat' > events/synthetic/waking_latency/trigger
+
+echo 'wakeup_latency u64 lat pid_t pid' >> synthetic_events
+echo 'hist:keys=pid:ts1=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_wakeup/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts1:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid) if next_comm=="ping"' > events/sched/sched_switch/trigger
+
+echo 'waking+wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+echo 'hist:keys=pid,lat:sort=pid,lat:ww_lat=$waking_lat+$wakeup_lat:onmatch(synthetic.wakeup_latency).waking+wakeup_latency($ww_lat,pid)' >> events/synthetic/wakeup_latency/trigger
+echo 'hist:keys=pid,lat:sort=pid,lat' >> events/synthetic/waking+wakeup_latency/trigger
+
+ping localhost -c 3
+if ! grep -q "pid:" events/synthetic/waking+wakeup_latency/hist; then
+ fail "Failed to create combined histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
new file mode 100644
index 000000000000..c193dce611a2
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-multi-actions-accept.tc
@@ -0,0 +1,44 @@
+#!/bin/sh
+# description: event trigger - test multiple actions on hist trigger
+
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test multiple actions on hist trigger"
+echo 'wakeup_latency u64 lat; pid_t pid' >> synthetic_events
+TRIGGER1=events/sched/sched_wakeup/trigger
+TRIGGER2=events/sched/sched_switch/trigger
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="cyclictest"' > $TRIGGER1
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0 if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,next_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid:onmatch(sched.sched_wakeup).wakeup_latency(sched.sched_switch.$wakeup_lat,prev_pid) if next_comm=="cyclictest"' >> $TRIGGER2
+echo 'hist:keys=next_pid if next_comm=="cyclictest"' >> $TRIGGER2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
new file mode 100644
index 000000000000..e84e7d048566
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc
@@ -0,0 +1,50 @@
+#!/bin/sh
+# description: event trigger - test inter-event histogram trigger onmatch action
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+ fail "Failed to create wakeup_latency synthetic event"
+fi
+
+echo "Test create histogram for synthetic event"
+echo "Test histogram variables,simple expression support and onmatch action"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm) if next_comm=="ping"' > events/sched/sched_switch/trigger
+echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
+ping localhost -c 5
+if ! grep -q "ping" events/synthetic/wakeup_latency/hist; then
+ fail "Failed to create onmatch action inter-event histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
new file mode 100644
index 000000000000..7907d8aacde3
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc
@@ -0,0 +1,50 @@
+#!/bin/sh
+# description: event trigger - test inter-event histogram trigger onmatch-onmax action
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+ fail "Failed to create wakeup_latency synthetic event"
+fi
+
+echo "Test create histogram for synthetic event"
+echo "Test histogram variables,simple expression support and onmatch-onmax action"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' > events/sched/sched_wakeup/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_wakeup).wakeup_latency($wakeup_lat,next_pid,next_comm):onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
+echo 'hist:keys=comm,pid,lat:wakeup_lat=lat:sort=lat' > events/synthetic/wakeup_latency/trigger
+ping localhost -c 5
+if [ ! grep -q "ping" events/synthetic/wakeup_latency/hist -o ! grep -q "max:" events/sched/sched_switch/hist]; then
+ fail "Failed to create onmatch-onmax action inter-event histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
new file mode 100644
index 000000000000..38b7ed6242b2
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc
@@ -0,0 +1,48 @@
+#!/bin/sh
+# description: event trigger - test inter-event histogram trigger onmax action
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+ fail "Failed to create wakeup_latency synthetic event"
+fi
+
+echo "Test onmax action"
+
+echo 'hist:keys=pid:ts0=common_timestamp.usecs if comm=="ping"' >> events/sched/sched_waking/trigger
+echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) if next_comm=="ping"' >> events/sched/sched_switch/trigger
+ping localhost -c 3
+if ! grep -q "max:" events/sched/sched_switch/hist; then
+ fail "Failed to create onmax action inter-event histogram"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
new file mode 100644
index 000000000000..cef11377dcbd
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc
@@ -0,0 +1,54 @@
+#!/bin/sh
+# description: event trigger - test synthetic event create remove
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic event is not supported"
+ exit_unsupported
+fi
+
+clear_synthetic_events
+reset_tracer
+do_reset
+
+echo "Test create synthetic event"
+
+echo 'wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ ! -d events/synthetic/wakeup_latency ]; then
+ fail "Failed to create wakeup_latency synthetic event"
+fi
+
+reset_trigger
+
+echo "Test create synthetic event with an error"
+echo 'wakeup_latency u64 lat pid_t pid char' > synthetic_events > /dev/null
+if [ -d events/synthetic/wakeup_latency ]; then
+ fail "Created wakeup_latency synthetic event with an invalid format"
+fi
+
+reset_trigger
+
+echo "Test remove synthetic event"
+echo '!wakeup_latency u64 lat pid_t pid char comm[16]' > synthetic_events
+if [ -d events/synthetic/wakeup_latency ]; then
+ fail "Failed to delete wakeup_latency synthetic event"
+fi
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
new file mode 100644
index 000000000000..2acbfe2c0c0c
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-hist.tc
@@ -0,0 +1,49 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: trace_marker trigger - test histogram trigger
+# flags: instance
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -d events/ftrace/print ]; then
+ echo "event trace_marker is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/trigger ]; then
+ echo "event trigger is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
+do_reset
+
+echo "Test histogram trace_marker tigger"
+
+echo 'hist:keys=common_pid' > events/ftrace/print/trigger
+for i in `seq 1 10` ; do echo "hello" > trace_marker; done
+grep 'hitcount: *10$' events/ftrace/print/hist > /dev/null || \
+ fail "hist trigger did not trigger correct times on trace_marker"
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
new file mode 100644
index 000000000000..6748e8cb42d0
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-snapshot.tc
@@ -0,0 +1,74 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: trace_marker trigger - test snapshot trigger
+# flags: instance
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ echo 0 > snapshot
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f snapshot ]; then
+ echo "snapshot is not supported"
+ exit_unsupported
+fi
+
+if [ ! -d events/ftrace/print ]; then
+ echo "event trace_marker is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/trigger ]; then
+ echo "event trigger is not supported"
+ exit_unsupported
+fi
+
+test_trace() {
+ file=$1
+ x=$2
+
+ cat $file | while read line; do
+ comment=`echo $line | sed -e 's/^#//'`
+ if [ "$line" != "$comment" ]; then
+ continue
+ fi
+ echo "testing $line for >$x<"
+ match=`echo $line | sed -e "s/>$x<//"`
+ if [ "$line" == "$match" ]; then
+ fail "$line does not have >$x< in it"
+ fi
+ let x=$x+2
+ done
+}
+
+do_reset
+
+echo "Test snapshot trace_marker tigger"
+
+echo 'snapshot' > events/ftrace/print/trigger
+
+# make sure the snapshot is allocated
+
+grep -q 'Snapshot is allocated' snapshot
+
+for i in `seq 1 10` ; do echo "hello >$i<" > trace_marker; done
+
+test_trace trace 1
+test_trace snapshot 2
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
new file mode 100644
index 000000000000..0a69c5d1cda8
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic-kernel.tc
@@ -0,0 +1,68 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: trace_marker trigger - test histogram with synthetic event against kernel event
+# flags:
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ echo > synthetic_events
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic events not supported"
+ exit_unsupported
+fi
+
+if [ ! -d events/ftrace/print ]; then
+ echo "event trace_marker is not supported"
+ exit_unsupported
+fi
+
+if [ ! -d events/sched/sched_waking ]; then
+ echo "event sched_waking is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/trigger ]; then
+ echo "event trigger is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
+do_reset
+
+echo "Test histogram kernel event to trace_marker latency histogram trigger"
+
+echo 'latency u64 lat' > synthetic_events
+echo 'hist:keys=pid:ts0=common_timestamp.usecs' > events/sched/sched_waking/trigger
+echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).latency($lat)' > events/ftrace/print/trigger
+echo 'hist:keys=common_pid,lat:sort=lat' > events/synthetic/latency/trigger
+sleep 1
+echo "hello" > trace_marker
+
+grep 'hitcount: *1$' events/ftrace/print/hist > /dev/null || \
+ fail "hist trigger did not trigger correct times on trace_marker"
+
+grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \
+ fail "hist trigger did not trigger "
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
new file mode 100644
index 000000000000..3666dd6ab02a
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-trace-marker-synthetic.tc
@@ -0,0 +1,66 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: trace_marker trigger - test histogram with synthetic event
+# flags:
+
+do_reset() {
+ reset_trigger
+ echo > set_event
+ echo > synthetic_events
+ clear_trace
+}
+
+fail() { #msg
+ do_reset
+ echo $1
+ exit_fail
+}
+
+if [ ! -f set_event ]; then
+ echo "event tracing is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f synthetic_events ]; then
+ echo "synthetic events not supported"
+ exit_unsupported
+fi
+
+if [ ! -d events/ftrace/print ]; then
+ echo "event trace_marker is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/trigger ]; then
+ echo "event trigger is not supported"
+ exit_unsupported
+fi
+
+if [ ! -f events/ftrace/print/hist ]; then
+ echo "hist trigger is not supported"
+ exit_unsupported
+fi
+
+do_reset
+
+echo "Test histogram trace_marker to trace_marker latency histogram trigger"
+
+echo 'latency u64 lat' > synthetic_events
+echo 'hist:keys=common_pid:ts0=common_timestamp.usecs if buf == "start"' > events/ftrace/print/trigger
+echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(ftrace.print).latency($lat) if buf == "end"' >> events/ftrace/print/trigger
+echo 'hist:keys=common_pid,lat:sort=lat' > events/synthetic/latency/trigger
+echo -n "start" > trace_marker
+echo -n "end" > trace_marker
+
+cnt=`grep 'hitcount: *1$' events/ftrace/print/hist | wc -l`
+
+if [ $cnt -ne 2 ]; then
+ fail "hist trace_marker trigger did not trigger correctly"
+fi
+
+grep 'hitcount: *1$' events/synthetic/latency/hist > /dev/null || \
+ fail "hist trigger did not trigger "
+
+do_reset
+
+exit 0
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index 8497a376ef9d..12631f0076a1 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -17,14 +17,6 @@ all:
fi \
done
-override define RUN_TESTS
- @export KSFT_TAP_LEVEL=`echo 1`;
- @echo "TAP version 13";
- @echo "selftests: futex";
- @echo "========================================";
- @cd $(OUTPUT); ./run.sh
-endef
-
override define INSTALL_RULE
mkdir -p $(INSTALL_PATH)
install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)
@@ -36,10 +28,6 @@ override define INSTALL_RULE
done;
endef
-override define EMIT_TESTS
- echo "./run.sh"
-endef
-
override define CLEAN
@for DIR in $(SUBDIRS); do \
BUILD_TARGET=$(OUTPUT)/$$DIR; \
diff --git a/tools/testing/selftests/gpio/gpio-mockup.sh b/tools/testing/selftests/gpio/gpio-mockup.sh
index 183fb932edbd..7f35b9880485 100755
--- a/tools/testing/selftests/gpio/gpio-mockup.sh
+++ b/tools/testing/selftests/gpio/gpio-mockup.sh
@@ -2,10 +2,11 @@
# SPDX-License-Identifier: GPL-2.0
#exit status
-#1: run as non-root user
+#1: Internal error
#2: sysfs/debugfs not mount
#3: insert module fail when gpio-mockup is a module.
-#4: other reason.
+#4: Skip test including run as non-root user.
+#5: other reason.
SYSFS=
GPIO_SYSFS=
@@ -15,6 +16,9 @@ GPIO_DEBUGFS=
dev_type=
module=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
usage()
{
echo "Usage:"
@@ -34,7 +38,7 @@ prerequisite()
msg="skip all tests:"
if [ $UID != 0 ]; then
echo $msg must be run as root >&2
- exit 1
+ exit $ksft_skip
fi
SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
if [ ! -d "$SYSFS" ]; then
@@ -73,7 +77,7 @@ remove_module()
die()
{
remove_module
- exit 4
+ exit 5
}
test_chips()
diff --git a/tools/testing/selftests/intel_pstate/aperf.c b/tools/testing/selftests/intel_pstate/aperf.c
index d21edea9c560..f6cd03a87493 100644
--- a/tools/testing/selftests/intel_pstate/aperf.c
+++ b/tools/testing/selftests/intel_pstate/aperf.c
@@ -9,6 +9,8 @@
#include <sys/timeb.h>
#include <sched.h>
#include <errno.h>
+#include <string.h>
+#include "../kselftest.h"
void usage(char *name) {
printf ("Usage: %s cpunum\n", name);
@@ -41,8 +43,8 @@ int main(int argc, char **argv) {
fd = open(msr_file_name, O_RDONLY);
if (fd == -1) {
- perror("Failed to open");
- return 1;
+ printf("/dev/cpu/%d/msr: %s\n", cpu, strerror(errno));
+ return KSFT_SKIP;
}
CPU_ZERO(&cpuset);
diff --git a/tools/testing/selftests/intel_pstate/run.sh b/tools/testing/selftests/intel_pstate/run.sh
index c670359becc6..e7008f614ad7 100755
--- a/tools/testing/selftests/intel_pstate/run.sh
+++ b/tools/testing/selftests/intel_pstate/run.sh
@@ -30,9 +30,18 @@
EVALUATE_ONLY=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
if ! uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ | grep -q x86; then
echo "$0 # Skipped: Test can only run on x86 architectures."
- exit 0
+ exit $ksft_skip
+fi
+
+msg="skip all tests:"
+if [ $UID != 0 ] && [ $EVALUATE_ONLY == 0 ]; then
+ echo $msg please run this as root >&2
+ exit $ksft_skip
fi
max_cpus=$(($(nproc)-1))
@@ -48,11 +57,12 @@ function run_test () {
echo "sleeping for 5 seconds"
sleep 5
- num_freqs=$(cat /proc/cpuinfo | grep MHz | sort -u | wc -l)
- if [ $num_freqs -le 2 ]; then
- cat /proc/cpuinfo | grep MHz | sort -u | tail -1 > /tmp/result.$1
+ grep MHz /proc/cpuinfo | sort -u > /tmp/result.freqs
+ num_freqs=$(wc -l /tmp/result.freqs | awk ' { print $1 } ')
+ if [ $num_freqs -ge 2 ]; then
+ tail -n 1 /tmp/result.freqs > /tmp/result.$1
else
- cat /proc/cpuinfo | grep MHz | sort -u > /tmp/result.$1
+ cp /tmp/result.freqs /tmp/result.$1
fi
./msr 0 >> /tmp/result.$1
@@ -82,32 +92,37 @@ _max_freq=$(cpupower frequency-info -l | tail -1 | awk ' { print $2 } ')
max_freq=$(($_max_freq / 1000))
-for freq in `seq $max_freq -100 $min_freq`
+[ $EVALUATE_ONLY -eq 0 ] && for freq in `seq $max_freq -100 $min_freq`
do
echo "Setting maximum frequency to $freq"
cpupower frequency-set -g powersave --max=${freq}MHz >& /dev/null
- [ $EVALUATE_ONLY -eq 0 ] && run_test $freq
+ run_test $freq
done
-echo "=============================================================================="
+[ $EVALUATE_ONLY -eq 0 ] && cpupower frequency-set -g powersave --max=${max_freq}MHz >& /dev/null
+echo "========================================================================"
echo "The marketing frequency of the cpu is $mkt_freq MHz"
echo "The maximum frequency of the cpu is $max_freq MHz"
echo "The minimum frequency of the cpu is $min_freq MHz"
-cpupower frequency-set -g powersave --max=${max_freq}MHz >& /dev/null
-
# make a pretty table
-echo "Target Actual Difference MSR(0x199) max_perf_pct"
+echo "Target Actual Difference MSR(0x199) max_perf_pct" | tr " " "\n" > /tmp/result.tab
for freq in `seq $max_freq -100 $min_freq`
do
result_freq=$(cat /tmp/result.${freq} | grep "cpu MHz" | awk ' { print $4 } ' | awk -F "." ' { print $1 } ')
msr=$(cat /tmp/result.${freq} | grep "msr" | awk ' { print $3 } ')
max_perf_pct=$(cat /tmp/result.${freq} | grep "max_perf_pct" | awk ' { print $2 } ' )
- if [ $result_freq -eq $freq ]; then
- echo " $freq $result_freq 0 $msr $(($max_perf_pct*3300))"
- else
- echo " $freq $result_freq $(($result_freq-$freq)) $msr $(($max_perf_pct*$max_freq))"
- fi
+ cat >> /tmp/result.tab << EOF
+$freq
+$result_freq
+$((result_freq - freq))
+$msr
+$((max_perf_pct * max_freq))
+EOF
done
+
+# print the table
+pr -aTt -5 < /tmp/result.tab
+
exit 0
diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c
index ee9382bdfadc..dac927e82336 100644
--- a/tools/testing/selftests/ipc/msgque.c
+++ b/tools/testing/selftests/ipc/msgque.c
@@ -196,10 +196,9 @@ int main(int argc, char **argv)
int msg, pid, err;
struct msgque_data msgque;
- if (getuid() != 0) {
- printf("Please run the test as root - Exiting.\n");
- return ksft_exit_fail();
- }
+ if (getuid() != 0)
+ return ksft_exit_skip(
+ "Please run the test as root - Exiting.\n");
msgque.key = ftok(argv[0], 822155650);
if (msgque.key == -1) {
diff --git a/tools/testing/selftests/kmod/kmod.sh b/tools/testing/selftests/kmod/kmod.sh
index 7956ea3be667..0a76314b4414 100755
--- a/tools/testing/selftests/kmod/kmod.sh
+++ b/tools/testing/selftests/kmod/kmod.sh
@@ -62,13 +62,16 @@ ALL_TESTS="$ALL_TESTS 0007:5:1"
ALL_TESTS="$ALL_TESTS 0008:150:1"
ALL_TESTS="$ALL_TESTS 0009:150:1"
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
test_modprobe()
{
if [ ! -d $DIR ]; then
echo "$0: $DIR not present" >&2
echo "You must have the following enabled in your kernel:" >&2
cat $TEST_DIR/config >&2
- exit 1
+ exit $ksft_skip
fi
}
@@ -105,12 +108,12 @@ test_reqs()
{
if ! which modprobe 2> /dev/null > /dev/null; then
echo "$0: You need modprobe installed" >&2
- exit 1
+ exit $ksft_skip
fi
if ! which kmod 2> /dev/null > /dev/null; then
echo "$0: You need kmod installed" >&2
- exit 1
+ exit $ksft_skip
fi
# kmod 19 has a bad bug where it returns 0 when modprobe
@@ -124,13 +127,13 @@ test_reqs()
echo "$0: You need at least kmod 20" >&2
echo "kmod <= 19 is buggy, for details see:" >&2
echo "http://git.kernel.org/cgit/utils/kernel/kmod/kmod.git/commit/libkmod/libkmod-module.c?id=fd44a98ae2eb5eb32161088954ab21e58e19dfc4" >&2
- exit 1
+ exit $ksft_skip
fi
uid=$(id -u)
if [ $uid -ne 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
}
diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
index 1b9d8ecdebce..15e6b75fc3a5 100644
--- a/tools/testing/selftests/kselftest.h
+++ b/tools/testing/selftests/kselftest.h
@@ -20,7 +20,7 @@
#define KSFT_XFAIL 2
#define KSFT_XPASS 3
/* Treat skip as pass */
-#define KSFT_SKIP KSFT_PASS
+#define KSFT_SKIP 4
/* counters */
struct ksft_count {
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
new file mode 100644
index 000000000000..63fc1ab9248f
--- /dev/null
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -0,0 +1,3 @@
+set_sregs_test
+sync_regs_test
+vmx_tsc_adjust_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
new file mode 100644
index 000000000000..d9d00319b07c
--- /dev/null
+++ b/tools/testing/selftests/kvm/Makefile
@@ -0,0 +1,40 @@
+all:
+
+top_srcdir = ../../../../
+UNAME_M := $(shell uname -m)
+
+LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
+LIBKVM_x86_64 = lib/x86.c lib/vmx.c
+
+TEST_GEN_PROGS_x86_64 = set_sregs_test
+TEST_GEN_PROGS_x86_64 += sync_regs_test
+TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
+
+TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
+LIBKVM += $(LIBKVM_$(UNAME_M))
+
+INSTALL_HDR_PATH = $(top_srcdir)/usr
+LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -I..
+
+# After inclusion, $(OUTPUT) is defined and
+# $(TEST_GEN_PROGS) starts with $(OUTPUT)/
+include ../lib.mk
+
+STATIC_LIBS := $(OUTPUT)/libkvm.a
+LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
+EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS)
+
+x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
+$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
+ $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
+
+$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
+ $(AR) crs $@ $^
+
+$(LINUX_HDR_PATH):
+ make -C $(top_srcdir) headers_install
+
+all: $(STATIC_LIBS) $(LINUX_HDR_PATH)
+$(TEST_GEN_PROGS): $(STATIC_LIBS)
+$(TEST_GEN_PROGS) $(LIBKVM_OBJ): | $(LINUX_HDR_PATH)
diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h
new file mode 100644
index 000000000000..637b7017b6ee
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/kvm_util.h
@@ -0,0 +1,145 @@
+/*
+ * tools/testing/selftests/kvm/include/kvm_util.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+#ifndef SELFTEST_KVM_UTIL_H
+#define SELFTEST_KVM_UTIL_H 1
+
+#include "test_util.h"
+
+#include "asm/kvm.h"
+#include "linux/kvm.h"
+#include <sys/ioctl.h>
+
+#include "sparsebit.h"
+
+/*
+ * Memslots can't cover the gfn starting at this gpa otherwise vCPUs can't be
+ * created. Only applies to VMs using EPT.
+ */
+#define KVM_DEFAULT_IDENTITY_MAP_ADDRESS 0xfffbc000ul
+
+
+/* Callers of kvm_util only have an incomplete/opaque description of the
+ * structure kvm_util is using to maintain the state of a VM.
+ */
+struct kvm_vm;
+
+typedef uint64_t vm_paddr_t; /* Virtual Machine (Guest) physical address */
+typedef uint64_t vm_vaddr_t; /* Virtual Machine (Guest) virtual address */
+
+/* Minimum allocated guest virtual and physical addresses */
+#define KVM_UTIL_MIN_VADDR 0x2000
+
+#define DEFAULT_GUEST_PHY_PAGES 512
+#define DEFAULT_GUEST_STACK_VADDR_MIN 0xab6000
+#define DEFAULT_STACK_PGS 5
+
+enum vm_guest_mode {
+ VM_MODE_FLAT48PG,
+};
+
+enum vm_mem_backing_src_type {
+ VM_MEM_SRC_ANONYMOUS,
+ VM_MEM_SRC_ANONYMOUS_THP,
+ VM_MEM_SRC_ANONYMOUS_HUGETLB,
+};
+
+int kvm_check_cap(long cap);
+
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
+void kvm_vm_free(struct kvm_vm *vmp);
+
+int kvm_memcmp_hva_gva(void *hva,
+ struct kvm_vm *vm, const vm_vaddr_t gva, size_t len);
+
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
+ uint32_t data_memslot, uint32_t pgd_memslot);
+
+void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+void vcpu_dump(FILE *stream, struct kvm_vm *vm,
+ uint32_t vcpuid, uint8_t indent);
+
+void vm_create_irqchip(struct kvm_vm *vm);
+
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+ enum vm_mem_backing_src_type src_type,
+ uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+ uint32_t flags);
+
+void vcpu_ioctl(struct kvm_vm *vm,
+ uint32_t vcpuid, unsigned long ioctl, void *arg);
+void vm_ioctl(struct kvm_vm *vm, unsigned long ioctl, void *arg);
+void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags);
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid);
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+ uint32_t data_memslot, uint32_t pgd_memslot);
+void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa);
+void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva);
+vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva);
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
+
+struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_mp_state *mp_state);
+void vcpu_regs_get(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_regs_set(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_regs *regs);
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...);
+void vcpu_sregs_get(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_sregs *sregs);
+void vcpu_sregs_set(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_sregs *sregs);
+int _vcpu_sregs_set(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_sregs *sregs);
+void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events);
+void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events);
+
+const char *exit_reason_str(unsigned int exit_reason);
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot);
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint32_t pgd_memslot);
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
+ vm_paddr_t paddr_min, uint32_t memslot);
+
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
+void vcpu_set_cpuid(
+ struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
+
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
+
+static inline struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_entry(uint32_t function)
+{
+ return kvm_get_supported_cpuid_index(function, 0);
+}
+
+struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code);
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
+
+typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
+ vm_paddr_t vmxon_paddr,
+ vm_vaddr_t vmcs_vaddr,
+ vm_paddr_t vmcs_paddr);
+
+struct kvm_userspace_memory_region *
+kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
+ uint64_t end);
+
+struct kvm_dirty_log *
+allocate_kvm_dirty_log(struct kvm_userspace_memory_region *region);
+
+int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
+
+#endif /* SELFTEST_KVM_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/sparsebit.h b/tools/testing/selftests/kvm/include/sparsebit.h
new file mode 100644
index 000000000000..54cfeb6568d3
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/sparsebit.h
@@ -0,0 +1,75 @@
+/*
+ * tools/testing/selftests/kvm/include/sparsebit.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * Header file that describes API to the sparsebit library.
+ * This library provides a memory efficient means of storing
+ * the settings of bits indexed via a uint64_t. Memory usage
+ * is reasonable, significantly less than (2^64 / 8) bytes, as
+ * long as bits that are mostly set or mostly cleared are close
+ * to each other. This library is efficient in memory usage
+ * even in the case where most bits are set.
+ */
+
+#ifndef _TEST_SPARSEBIT_H_
+#define _TEST_SPARSEBIT_H_
+
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct sparsebit;
+typedef uint64_t sparsebit_idx_t;
+typedef uint64_t sparsebit_num_t;
+
+struct sparsebit *sparsebit_alloc(void);
+void sparsebit_free(struct sparsebit **sbitp);
+void sparsebit_copy(struct sparsebit *dstp, struct sparsebit *src);
+
+bool sparsebit_is_set(struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_set_num(struct sparsebit *sbit,
+ sparsebit_idx_t idx, sparsebit_num_t num);
+bool sparsebit_is_clear(struct sparsebit *sbit, sparsebit_idx_t idx);
+bool sparsebit_is_clear_num(struct sparsebit *sbit,
+ sparsebit_idx_t idx, sparsebit_num_t num);
+sparsebit_num_t sparsebit_num_set(struct sparsebit *sbit);
+bool sparsebit_any_set(struct sparsebit *sbit);
+bool sparsebit_any_clear(struct sparsebit *sbit);
+bool sparsebit_all_set(struct sparsebit *sbit);
+bool sparsebit_all_clear(struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_set(struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_first_clear(struct sparsebit *sbit);
+sparsebit_idx_t sparsebit_next_set(struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_clear(struct sparsebit *sbit, sparsebit_idx_t prev);
+sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *sbit,
+ sparsebit_idx_t start, sparsebit_num_t num);
+sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *sbit,
+ sparsebit_idx_t start, sparsebit_num_t num);
+
+void sparsebit_set(struct sparsebit *sbitp, sparsebit_idx_t idx);
+void sparsebit_set_num(struct sparsebit *sbitp, sparsebit_idx_t start,
+ sparsebit_num_t num);
+void sparsebit_set_all(struct sparsebit *sbitp);
+
+void sparsebit_clear(struct sparsebit *sbitp, sparsebit_idx_t idx);
+void sparsebit_clear_num(struct sparsebit *sbitp,
+ sparsebit_idx_t start, sparsebit_num_t num);
+void sparsebit_clear_all(struct sparsebit *sbitp);
+
+void sparsebit_dump(FILE *stream, struct sparsebit *sbit,
+ unsigned int indent);
+void sparsebit_validate_internal(struct sparsebit *sbit);
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _TEST_SPARSEBIT_H_ */
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
new file mode 100644
index 000000000000..ac53730b30aa
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -0,0 +1,46 @@
+/*
+ * tools/testing/selftests/kvm/include/test_util.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef TEST_UTIL_H
+#define TEST_UTIL_H 1
+
+#include <stdlib.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+#include <inttypes.h>
+#include <errno.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include "kselftest.h"
+
+ssize_t test_write(int fd, const void *buf, size_t count);
+ssize_t test_read(int fd, void *buf, size_t count);
+int test_seq_read(const char *path, char **bufp, size_t *sizep);
+
+void test_assert(bool exp, const char *exp_str,
+ const char *file, unsigned int line, const char *fmt, ...);
+
+#define ARRAY_SIZE(array) (sizeof(array) / sizeof((array)[0]))
+
+#define TEST_ASSERT(e, fmt, ...) \
+ test_assert((e), #e, __FILE__, __LINE__, fmt, ##__VA_ARGS__)
+
+#define ASSERT_EQ(a, b) do { \
+ typeof(a) __a = (a); \
+ typeof(b) __b = (b); \
+ TEST_ASSERT(__a == __b, \
+ "ASSERT_EQ(%s, %s) failed.\n" \
+ "\t%s is %#lx\n" \
+ "\t%s is %#lx", \
+ #a, #b, #a, (unsigned long) __a, #b, (unsigned long) __b); \
+} while (0)
+
+#endif /* TEST_UTIL_H */
diff --git a/tools/testing/selftests/kvm/include/vmx.h b/tools/testing/selftests/kvm/include/vmx.h
new file mode 100644
index 000000000000..6ed8499807fd
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/vmx.h
@@ -0,0 +1,494 @@
+/*
+ * tools/testing/selftests/kvm/include/vmx.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_VMX_H
+#define SELFTEST_KVM_VMX_H
+
+#include <stdint.h>
+#include "x86.h"
+
+#define CPUID_VMX_BIT 5
+
+#define CPUID_VMX (1 << 5)
+
+/*
+ * Definitions of Primary Processor-Based VM-Execution Controls.
+ */
+#define CPU_BASED_VIRTUAL_INTR_PENDING 0x00000004
+#define CPU_BASED_USE_TSC_OFFSETING 0x00000008
+#define CPU_BASED_HLT_EXITING 0x00000080
+#define CPU_BASED_INVLPG_EXITING 0x00000200
+#define CPU_BASED_MWAIT_EXITING 0x00000400
+#define CPU_BASED_RDPMC_EXITING 0x00000800
+#define CPU_BASED_RDTSC_EXITING 0x00001000
+#define CPU_BASED_CR3_LOAD_EXITING 0x00008000
+#define CPU_BASED_CR3_STORE_EXITING 0x00010000
+#define CPU_BASED_CR8_LOAD_EXITING 0x00080000
+#define CPU_BASED_CR8_STORE_EXITING 0x00100000
+#define CPU_BASED_TPR_SHADOW 0x00200000
+#define CPU_BASED_VIRTUAL_NMI_PENDING 0x00400000
+#define CPU_BASED_MOV_DR_EXITING 0x00800000
+#define CPU_BASED_UNCOND_IO_EXITING 0x01000000
+#define CPU_BASED_USE_IO_BITMAPS 0x02000000
+#define CPU_BASED_MONITOR_TRAP 0x08000000
+#define CPU_BASED_USE_MSR_BITMAPS 0x10000000
+#define CPU_BASED_MONITOR_EXITING 0x20000000
+#define CPU_BASED_PAUSE_EXITING 0x40000000
+#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS 0x80000000
+
+#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x0401e172
+
+/*
+ * Definitions of Secondary Processor-Based VM-Execution Controls.
+ */
+#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
+#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
+#define SECONDARY_EXEC_DESC 0x00000004
+#define SECONDARY_EXEC_RDTSCP 0x00000008
+#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE 0x00000010
+#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
+#define SECONDARY_EXEC_WBINVD_EXITING 0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST 0x00000080
+#define SECONDARY_EXEC_APIC_REGISTER_VIRT 0x00000100
+#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY 0x00000200
+#define SECONDARY_EXEC_PAUSE_LOOP_EXITING 0x00000400
+#define SECONDARY_EXEC_RDRAND_EXITING 0x00000800
+#define SECONDARY_EXEC_ENABLE_INVPCID 0x00001000
+#define SECONDARY_EXEC_ENABLE_VMFUNC 0x00002000
+#define SECONDARY_EXEC_SHADOW_VMCS 0x00004000
+#define SECONDARY_EXEC_RDSEED_EXITING 0x00010000
+#define SECONDARY_EXEC_ENABLE_PML 0x00020000
+#define SECONDARY_EPT_VE 0x00040000
+#define SECONDARY_ENABLE_XSAV_RESTORE 0x00100000
+#define SECONDARY_EXEC_TSC_SCALING 0x02000000
+
+#define PIN_BASED_EXT_INTR_MASK 0x00000001
+#define PIN_BASED_NMI_EXITING 0x00000008
+#define PIN_BASED_VIRTUAL_NMIS 0x00000020
+#define PIN_BASED_VMX_PREEMPTION_TIMER 0x00000040
+#define PIN_BASED_POSTED_INTR 0x00000080
+
+#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x00000016
+
+#define VM_EXIT_SAVE_DEBUG_CONTROLS 0x00000004
+#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200
+#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL 0x00001000
+#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000
+#define VM_EXIT_SAVE_IA32_PAT 0x00040000
+#define VM_EXIT_LOAD_IA32_PAT 0x00080000
+#define VM_EXIT_SAVE_IA32_EFER 0x00100000
+#define VM_EXIT_LOAD_IA32_EFER 0x00200000
+#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000
+
+#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff
+
+#define VM_ENTRY_LOAD_DEBUG_CONTROLS 0x00000004
+#define VM_ENTRY_IA32E_MODE 0x00000200
+#define VM_ENTRY_SMM 0x00000400
+#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800
+#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL 0x00002000
+#define VM_ENTRY_LOAD_IA32_PAT 0x00004000
+#define VM_ENTRY_LOAD_IA32_EFER 0x00008000
+
+#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff
+
+#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
+#define VMX_MISC_SAVE_EFER_LMA 0x00000020
+
+#define EXIT_REASON_FAILED_VMENTRY 0x80000000
+#define EXIT_REASON_EXCEPTION_NMI 0
+#define EXIT_REASON_EXTERNAL_INTERRUPT 1
+#define EXIT_REASON_TRIPLE_FAULT 2
+#define EXIT_REASON_PENDING_INTERRUPT 7
+#define EXIT_REASON_NMI_WINDOW 8
+#define EXIT_REASON_TASK_SWITCH 9
+#define EXIT_REASON_CPUID 10
+#define EXIT_REASON_HLT 12
+#define EXIT_REASON_INVD 13
+#define EXIT_REASON_INVLPG 14
+#define EXIT_REASON_RDPMC 15
+#define EXIT_REASON_RDTSC 16
+#define EXIT_REASON_VMCALL 18
+#define EXIT_REASON_VMCLEAR 19
+#define EXIT_REASON_VMLAUNCH 20
+#define EXIT_REASON_VMPTRLD 21
+#define EXIT_REASON_VMPTRST 22
+#define EXIT_REASON_VMREAD 23
+#define EXIT_REASON_VMRESUME 24
+#define EXIT_REASON_VMWRITE 25
+#define EXIT_REASON_VMOFF 26
+#define EXIT_REASON_VMON 27
+#define EXIT_REASON_CR_ACCESS 28
+#define EXIT_REASON_DR_ACCESS 29
+#define EXIT_REASON_IO_INSTRUCTION 30
+#define EXIT_REASON_MSR_READ 31
+#define EXIT_REASON_MSR_WRITE 32
+#define EXIT_REASON_INVALID_STATE 33
+#define EXIT_REASON_MWAIT_INSTRUCTION 36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
+#define EXIT_REASON_PAUSE_INSTRUCTION 40
+#define EXIT_REASON_MCE_DURING_VMENTRY 41
+#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
+#define EXIT_REASON_APIC_ACCESS 44
+#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_EPT_VIOLATION 48
+#define EXIT_REASON_EPT_MISCONFIG 49
+#define EXIT_REASON_INVEPT 50
+#define EXIT_REASON_RDTSCP 51
+#define EXIT_REASON_PREEMPTION_TIMER 52
+#define EXIT_REASON_INVVPID 53
+#define EXIT_REASON_WBINVD 54
+#define EXIT_REASON_XSETBV 55
+#define EXIT_REASON_APIC_WRITE 56
+#define EXIT_REASON_INVPCID 58
+#define EXIT_REASON_PML_FULL 62
+#define EXIT_REASON_XSAVES 63
+#define EXIT_REASON_XRSTORS 64
+#define LAST_EXIT_REASON 64
+
+enum vmcs_field {
+ VIRTUAL_PROCESSOR_ID = 0x00000000,
+ POSTED_INTR_NV = 0x00000002,
+ GUEST_ES_SELECTOR = 0x00000800,
+ GUEST_CS_SELECTOR = 0x00000802,
+ GUEST_SS_SELECTOR = 0x00000804,
+ GUEST_DS_SELECTOR = 0x00000806,
+ GUEST_FS_SELECTOR = 0x00000808,
+ GUEST_GS_SELECTOR = 0x0000080a,
+ GUEST_LDTR_SELECTOR = 0x0000080c,
+ GUEST_TR_SELECTOR = 0x0000080e,
+ GUEST_INTR_STATUS = 0x00000810,
+ GUEST_PML_INDEX = 0x00000812,
+ HOST_ES_SELECTOR = 0x00000c00,
+ HOST_CS_SELECTOR = 0x00000c02,
+ HOST_SS_SELECTOR = 0x00000c04,
+ HOST_DS_SELECTOR = 0x00000c06,
+ HOST_FS_SELECTOR = 0x00000c08,
+ HOST_GS_SELECTOR = 0x00000c0a,
+ HOST_TR_SELECTOR = 0x00000c0c,
+ IO_BITMAP_A = 0x00002000,
+ IO_BITMAP_A_HIGH = 0x00002001,
+ IO_BITMAP_B = 0x00002002,
+ IO_BITMAP_B_HIGH = 0x00002003,
+ MSR_BITMAP = 0x00002004,
+ MSR_BITMAP_HIGH = 0x00002005,
+ VM_EXIT_MSR_STORE_ADDR = 0x00002006,
+ VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007,
+ VM_EXIT_MSR_LOAD_ADDR = 0x00002008,
+ VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009,
+ VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a,
+ VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b,
+ PML_ADDRESS = 0x0000200e,
+ PML_ADDRESS_HIGH = 0x0000200f,
+ TSC_OFFSET = 0x00002010,
+ TSC_OFFSET_HIGH = 0x00002011,
+ VIRTUAL_APIC_PAGE_ADDR = 0x00002012,
+ VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013,
+ APIC_ACCESS_ADDR = 0x00002014,
+ APIC_ACCESS_ADDR_HIGH = 0x00002015,
+ POSTED_INTR_DESC_ADDR = 0x00002016,
+ POSTED_INTR_DESC_ADDR_HIGH = 0x00002017,
+ EPT_POINTER = 0x0000201a,
+ EPT_POINTER_HIGH = 0x0000201b,
+ EOI_EXIT_BITMAP0 = 0x0000201c,
+ EOI_EXIT_BITMAP0_HIGH = 0x0000201d,
+ EOI_EXIT_BITMAP1 = 0x0000201e,
+ EOI_EXIT_BITMAP1_HIGH = 0x0000201f,
+ EOI_EXIT_BITMAP2 = 0x00002020,
+ EOI_EXIT_BITMAP2_HIGH = 0x00002021,
+ EOI_EXIT_BITMAP3 = 0x00002022,
+ EOI_EXIT_BITMAP3_HIGH = 0x00002023,
+ VMREAD_BITMAP = 0x00002026,
+ VMREAD_BITMAP_HIGH = 0x00002027,
+ VMWRITE_BITMAP = 0x00002028,
+ VMWRITE_BITMAP_HIGH = 0x00002029,
+ XSS_EXIT_BITMAP = 0x0000202C,
+ XSS_EXIT_BITMAP_HIGH = 0x0000202D,
+ TSC_MULTIPLIER = 0x00002032,
+ TSC_MULTIPLIER_HIGH = 0x00002033,
+ GUEST_PHYSICAL_ADDRESS = 0x00002400,
+ GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
+ VMCS_LINK_POINTER = 0x00002800,
+ VMCS_LINK_POINTER_HIGH = 0x00002801,
+ GUEST_IA32_DEBUGCTL = 0x00002802,
+ GUEST_IA32_DEBUGCTL_HIGH = 0x00002803,
+ GUEST_IA32_PAT = 0x00002804,
+ GUEST_IA32_PAT_HIGH = 0x00002805,
+ GUEST_IA32_EFER = 0x00002806,
+ GUEST_IA32_EFER_HIGH = 0x00002807,
+ GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808,
+ GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809,
+ GUEST_PDPTR0 = 0x0000280a,
+ GUEST_PDPTR0_HIGH = 0x0000280b,
+ GUEST_PDPTR1 = 0x0000280c,
+ GUEST_PDPTR1_HIGH = 0x0000280d,
+ GUEST_PDPTR2 = 0x0000280e,
+ GUEST_PDPTR2_HIGH = 0x0000280f,
+ GUEST_PDPTR3 = 0x00002810,
+ GUEST_PDPTR3_HIGH = 0x00002811,
+ GUEST_BNDCFGS = 0x00002812,
+ GUEST_BNDCFGS_HIGH = 0x00002813,
+ HOST_IA32_PAT = 0x00002c00,
+ HOST_IA32_PAT_HIGH = 0x00002c01,
+ HOST_IA32_EFER = 0x00002c02,
+ HOST_IA32_EFER_HIGH = 0x00002c03,
+ HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04,
+ HOST_IA32_PERF_GLOBAL_CTRL_HIGH = 0x00002c05,
+ PIN_BASED_VM_EXEC_CONTROL = 0x00004000,
+ CPU_BASED_VM_EXEC_CONTROL = 0x00004002,
+ EXCEPTION_BITMAP = 0x00004004,
+ PAGE_FAULT_ERROR_CODE_MASK = 0x00004006,
+ PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008,
+ CR3_TARGET_COUNT = 0x0000400a,
+ VM_EXIT_CONTROLS = 0x0000400c,
+ VM_EXIT_MSR_STORE_COUNT = 0x0000400e,
+ VM_EXIT_MSR_LOAD_COUNT = 0x00004010,
+ VM_ENTRY_CONTROLS = 0x00004012,
+ VM_ENTRY_MSR_LOAD_COUNT = 0x00004014,
+ VM_ENTRY_INTR_INFO_FIELD = 0x00004016,
+ VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018,
+ VM_ENTRY_INSTRUCTION_LEN = 0x0000401a,
+ TPR_THRESHOLD = 0x0000401c,
+ SECONDARY_VM_EXEC_CONTROL = 0x0000401e,
+ PLE_GAP = 0x00004020,
+ PLE_WINDOW = 0x00004022,
+ VM_INSTRUCTION_ERROR = 0x00004400,
+ VM_EXIT_REASON = 0x00004402,
+ VM_EXIT_INTR_INFO = 0x00004404,
+ VM_EXIT_INTR_ERROR_CODE = 0x00004406,
+ IDT_VECTORING_INFO_FIELD = 0x00004408,
+ IDT_VECTORING_ERROR_CODE = 0x0000440a,
+ VM_EXIT_INSTRUCTION_LEN = 0x0000440c,
+ VMX_INSTRUCTION_INFO = 0x0000440e,
+ GUEST_ES_LIMIT = 0x00004800,
+ GUEST_CS_LIMIT = 0x00004802,
+ GUEST_SS_LIMIT = 0x00004804,
+ GUEST_DS_LIMIT = 0x00004806,
+ GUEST_FS_LIMIT = 0x00004808,
+ GUEST_GS_LIMIT = 0x0000480a,
+ GUEST_LDTR_LIMIT = 0x0000480c,
+ GUEST_TR_LIMIT = 0x0000480e,
+ GUEST_GDTR_LIMIT = 0x00004810,
+ GUEST_IDTR_LIMIT = 0x00004812,
+ GUEST_ES_AR_BYTES = 0x00004814,
+ GUEST_CS_AR_BYTES = 0x00004816,
+ GUEST_SS_AR_BYTES = 0x00004818,
+ GUEST_DS_AR_BYTES = 0x0000481a,
+ GUEST_FS_AR_BYTES = 0x0000481c,
+ GUEST_GS_AR_BYTES = 0x0000481e,
+ GUEST_LDTR_AR_BYTES = 0x00004820,
+ GUEST_TR_AR_BYTES = 0x00004822,
+ GUEST_INTERRUPTIBILITY_INFO = 0x00004824,
+ GUEST_ACTIVITY_STATE = 0X00004826,
+ GUEST_SYSENTER_CS = 0x0000482A,
+ VMX_PREEMPTION_TIMER_VALUE = 0x0000482E,
+ HOST_IA32_SYSENTER_CS = 0x00004c00,
+ CR0_GUEST_HOST_MASK = 0x00006000,
+ CR4_GUEST_HOST_MASK = 0x00006002,
+ CR0_READ_SHADOW = 0x00006004,
+ CR4_READ_SHADOW = 0x00006006,
+ CR3_TARGET_VALUE0 = 0x00006008,
+ CR3_TARGET_VALUE1 = 0x0000600a,
+ CR3_TARGET_VALUE2 = 0x0000600c,
+ CR3_TARGET_VALUE3 = 0x0000600e,
+ EXIT_QUALIFICATION = 0x00006400,
+ GUEST_LINEAR_ADDRESS = 0x0000640a,
+ GUEST_CR0 = 0x00006800,
+ GUEST_CR3 = 0x00006802,
+ GUEST_CR4 = 0x00006804,
+ GUEST_ES_BASE = 0x00006806,
+ GUEST_CS_BASE = 0x00006808,
+ GUEST_SS_BASE = 0x0000680a,
+ GUEST_DS_BASE = 0x0000680c,
+ GUEST_FS_BASE = 0x0000680e,
+ GUEST_GS_BASE = 0x00006810,
+ GUEST_LDTR_BASE = 0x00006812,
+ GUEST_TR_BASE = 0x00006814,
+ GUEST_GDTR_BASE = 0x00006816,
+ GUEST_IDTR_BASE = 0x00006818,
+ GUEST_DR7 = 0x0000681a,
+ GUEST_RSP = 0x0000681c,
+ GUEST_RIP = 0x0000681e,
+ GUEST_RFLAGS = 0x00006820,
+ GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822,
+ GUEST_SYSENTER_ESP = 0x00006824,
+ GUEST_SYSENTER_EIP = 0x00006826,
+ HOST_CR0 = 0x00006c00,
+ HOST_CR3 = 0x00006c02,
+ HOST_CR4 = 0x00006c04,
+ HOST_FS_BASE = 0x00006c06,
+ HOST_GS_BASE = 0x00006c08,
+ HOST_TR_BASE = 0x00006c0a,
+ HOST_GDTR_BASE = 0x00006c0c,
+ HOST_IDTR_BASE = 0x00006c0e,
+ HOST_IA32_SYSENTER_ESP = 0x00006c10,
+ HOST_IA32_SYSENTER_EIP = 0x00006c12,
+ HOST_RSP = 0x00006c14,
+ HOST_RIP = 0x00006c16,
+};
+
+struct vmx_msr_entry {
+ uint32_t index;
+ uint32_t reserved;
+ uint64_t value;
+} __attribute__ ((aligned(16)));
+
+static inline int vmxon(uint64_t phys)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmxon %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(phys)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline void vmxoff(void)
+{
+ __asm__ __volatile__("vmxoff");
+}
+
+static inline int vmclear(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmclear %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline int vmptrld(uint64_t vmcs_pa)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmptrld %[pa]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [pa]"m"(vmcs_pa)
+ : "cc", "memory");
+
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmlaunch.
+ */
+static inline int vmlaunch(void)
+{
+ int ret;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmlaunch;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+/*
+ * No guest state (e.g. GPRs) is established by this vmresume.
+ */
+static inline int vmresume(void)
+{
+ int ret;
+
+ __asm__ __volatile__("push %%rbp;"
+ "push %%rcx;"
+ "push %%rdx;"
+ "push %%rsi;"
+ "push %%rdi;"
+ "push $0;"
+ "vmwrite %%rsp, %[host_rsp];"
+ "lea 1f(%%rip), %%rax;"
+ "vmwrite %%rax, %[host_rip];"
+ "vmresume;"
+ "incq (%%rsp);"
+ "1: pop %%rax;"
+ "pop %%rdi;"
+ "pop %%rsi;"
+ "pop %%rdx;"
+ "pop %%rcx;"
+ "pop %%rbp;"
+ : [ret]"=&a"(ret)
+ : [host_rsp]"r"((uint64_t)HOST_RSP),
+ [host_rip]"r"((uint64_t)HOST_RIP)
+ : "memory", "cc", "rbx", "r8", "r9", "r10",
+ "r11", "r12", "r13", "r14", "r15");
+ return ret;
+}
+
+static inline int vmread(uint64_t encoding, uint64_t *value)
+{
+ uint64_t tmp;
+ uint8_t ret;
+
+ __asm__ __volatile__("vmread %[encoding], %[value]; setna %[ret]"
+ : [value]"=rm"(tmp), [ret]"=rm"(ret)
+ : [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ *value = tmp;
+ return ret;
+}
+
+/*
+ * A wrapper around vmread that ignores errors and returns zero if the
+ * vmread instruction fails.
+ */
+static inline uint64_t vmreadz(uint64_t encoding)
+{
+ uint64_t value = 0;
+ vmread(encoding, &value);
+ return value;
+}
+
+static inline int vmwrite(uint64_t encoding, uint64_t value)
+{
+ uint8_t ret;
+
+ __asm__ __volatile__ ("vmwrite %[value], %[encoding]; setna %[ret]"
+ : [ret]"=rm"(ret)
+ : [value]"rm"(value), [encoding]"r"(encoding)
+ : "cc", "memory");
+
+ return ret;
+}
+
+static inline uint32_t vmcs_revision(void)
+{
+ return rdmsr(MSR_IA32_VMX_BASIC);
+}
+
+void prepare_for_vmx_operation(void);
+void prepare_vmcs(void *guest_rip, void *guest_rsp);
+struct kvm_vm *vm_create_default_vmx(uint32_t vcpuid,
+ vmx_guest_code_t guest_code);
+
+#endif /* !SELFTEST_KVM_VMX_H */
diff --git a/tools/testing/selftests/kvm/include/x86.h b/tools/testing/selftests/kvm/include/x86.h
new file mode 100644
index 000000000000..4a5b2c4c1a0f
--- /dev/null
+++ b/tools/testing/selftests/kvm/include/x86.h
@@ -0,0 +1,1043 @@
+/*
+ * tools/testing/selftests/kvm/include/x86.h
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ */
+
+#ifndef SELFTEST_KVM_X86_H
+#define SELFTEST_KVM_X86_H
+
+#include <assert.h>
+#include <stdint.h>
+
+#define X86_EFLAGS_FIXED (1u << 1)
+
+#define X86_CR4_VME (1ul << 0)
+#define X86_CR4_PVI (1ul << 1)
+#define X86_CR4_TSD (1ul << 2)
+#define X86_CR4_DE (1ul << 3)
+#define X86_CR4_PSE (1ul << 4)
+#define X86_CR4_PAE (1ul << 5)
+#define X86_CR4_MCE (1ul << 6)
+#define X86_CR4_PGE (1ul << 7)
+#define X86_CR4_PCE (1ul << 8)
+#define X86_CR4_OSFXSR (1ul << 9)
+#define X86_CR4_OSXMMEXCPT (1ul << 10)
+#define X86_CR4_UMIP (1ul << 11)
+#define X86_CR4_VMXE (1ul << 13)
+#define X86_CR4_SMXE (1ul << 14)
+#define X86_CR4_FSGSBASE (1ul << 16)
+#define X86_CR4_PCIDE (1ul << 17)
+#define X86_CR4_OSXSAVE (1ul << 18)
+#define X86_CR4_SMEP (1ul << 20)
+#define X86_CR4_SMAP (1ul << 21)
+#define X86_CR4_PKE (1ul << 22)
+
+/* The enum values match the intruction encoding of each register */
+enum x86_register {
+ RAX = 0,
+ RCX,
+ RDX,
+ RBX,
+ RSP,
+ RBP,
+ RSI,
+ RDI,
+ R8,
+ R9,
+ R10,
+ R11,
+ R12,
+ R13,
+ R14,
+ R15,
+};
+
+struct desc64 {
+ uint16_t limit0;
+ uint16_t base0;
+ unsigned base1:8, type:5, dpl:2, p:1;
+ unsigned limit1:4, zero0:3, g:1, base2:8;
+ uint32_t base3;
+ uint32_t zero1;
+} __attribute__((packed));
+
+struct desc_ptr {
+ uint16_t size;
+ uint64_t address;
+} __attribute__((packed));
+
+static inline uint64_t get_desc64_base(const struct desc64 *desc)
+{
+ return ((uint64_t)desc->base3 << 32) |
+ (desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
+}
+
+static inline uint64_t rdtsc(void)
+{
+ uint32_t eax, edx;
+
+ /*
+ * The lfence is to wait (on Intel CPUs) until all previous
+ * instructions have been executed.
+ */
+ __asm__ __volatile__("lfence; rdtsc" : "=a"(eax), "=d"(edx));
+ return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdtscp(uint32_t *aux)
+{
+ uint32_t eax, edx;
+
+ __asm__ __volatile__("rdtscp" : "=a"(eax), "=d"(edx), "=c"(*aux));
+ return ((uint64_t)edx) << 32 | eax;
+}
+
+static inline uint64_t rdmsr(uint32_t msr)
+{
+ uint32_t a, d;
+
+ __asm__ __volatile__("rdmsr" : "=a"(a), "=d"(d) : "c"(msr) : "memory");
+
+ return a | ((uint64_t) d << 32);
+}
+
+static inline void wrmsr(uint32_t msr, uint64_t value)
+{
+ uint32_t a = value;
+ uint32_t d = value >> 32;
+
+ __asm__ __volatile__("wrmsr" :: "a"(a), "d"(d), "c"(msr) : "memory");
+}
+
+
+static inline uint16_t inw(uint16_t port)
+{
+ uint16_t tmp;
+
+ __asm__ __volatile__("in %%dx, %%ax"
+ : /* output */ "=a" (tmp)
+ : /* input */ "d" (port));
+
+ return tmp;
+}
+
+static inline uint16_t get_es(void)
+{
+ uint16_t es;
+
+ __asm__ __volatile__("mov %%es, %[es]"
+ : /* output */ [es]"=rm"(es));
+ return es;
+}
+
+static inline uint16_t get_cs(void)
+{
+ uint16_t cs;
+
+ __asm__ __volatile__("mov %%cs, %[cs]"
+ : /* output */ [cs]"=rm"(cs));
+ return cs;
+}
+
+static inline uint16_t get_ss(void)
+{
+ uint16_t ss;
+
+ __asm__ __volatile__("mov %%ss, %[ss]"
+ : /* output */ [ss]"=rm"(ss));
+ return ss;
+}
+
+static inline uint16_t get_ds(void)
+{
+ uint16_t ds;
+
+ __asm__ __volatile__("mov %%ds, %[ds]"
+ : /* output */ [ds]"=rm"(ds));
+ return ds;
+}
+
+static inline uint16_t get_fs(void)
+{
+ uint16_t fs;
+
+ __asm__ __volatile__("mov %%fs, %[fs]"
+ : /* output */ [fs]"=rm"(fs));
+ return fs;
+}
+
+static inline uint16_t get_gs(void)
+{
+ uint16_t gs;
+
+ __asm__ __volatile__("mov %%gs, %[gs]"
+ : /* output */ [gs]"=rm"(gs));
+ return gs;
+}
+
+static inline uint16_t get_tr(void)
+{
+ uint16_t tr;
+
+ __asm__ __volatile__("str %[tr]"
+ : /* output */ [tr]"=rm"(tr));
+ return tr;
+}
+
+static inline uint64_t get_cr0(void)
+{
+ uint64_t cr0;
+
+ __asm__ __volatile__("mov %%cr0, %[cr0]"
+ : /* output */ [cr0]"=r"(cr0));
+ return cr0;
+}
+
+static inline uint64_t get_cr3(void)
+{
+ uint64_t cr3;
+
+ __asm__ __volatile__("mov %%cr3, %[cr3]"
+ : /* output */ [cr3]"=r"(cr3));
+ return cr3;
+}
+
+static inline uint64_t get_cr4(void)
+{
+ uint64_t cr4;
+
+ __asm__ __volatile__("mov %%cr4, %[cr4]"
+ : /* output */ [cr4]"=r"(cr4));
+ return cr4;
+}
+
+static inline void set_cr4(uint64_t val)
+{
+ __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory");
+}
+
+static inline uint64_t get_gdt_base(void)
+{
+ struct desc_ptr gdt;
+ __asm__ __volatile__("sgdt %[gdt]"
+ : /* output */ [gdt]"=m"(gdt));
+ return gdt.address;
+}
+
+static inline uint64_t get_idt_base(void)
+{
+ struct desc_ptr idt;
+ __asm__ __volatile__("sidt %[idt]"
+ : /* output */ [idt]"=m"(idt));
+ return idt.address;
+}
+
+#define SET_XMM(__var, __xmm) \
+ asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
+
+static inline void set_xmm(int n, unsigned long val)
+{
+ switch (n) {
+ case 0:
+ SET_XMM(val, xmm0);
+ break;
+ case 1:
+ SET_XMM(val, xmm1);
+ break;
+ case 2:
+ SET_XMM(val, xmm2);
+ break;
+ case 3:
+ SET_XMM(val, xmm3);
+ break;
+ case 4:
+ SET_XMM(val, xmm4);
+ break;
+ case 5:
+ SET_XMM(val, xmm5);
+ break;
+ case 6:
+ SET_XMM(val, xmm6);
+ break;
+ case 7:
+ SET_XMM(val, xmm7);
+ break;
+ }
+}
+
+typedef unsigned long v1di __attribute__ ((vector_size (8)));
+static inline unsigned long get_xmm(int n)
+{
+ assert(n >= 0 && n <= 7);
+
+ register v1di xmm0 __asm__("%xmm0");
+ register v1di xmm1 __asm__("%xmm1");
+ register v1di xmm2 __asm__("%xmm2");
+ register v1di xmm3 __asm__("%xmm3");
+ register v1di xmm4 __asm__("%xmm4");
+ register v1di xmm5 __asm__("%xmm5");
+ register v1di xmm6 __asm__("%xmm6");
+ register v1di xmm7 __asm__("%xmm7");
+ switch (n) {
+ case 0:
+ return (unsigned long)xmm0;
+ case 1:
+ return (unsigned long)xmm1;
+ case 2:
+ return (unsigned long)xmm2;
+ case 3:
+ return (unsigned long)xmm3;
+ case 4:
+ return (unsigned long)xmm4;
+ case 5:
+ return (unsigned long)xmm5;
+ case 6:
+ return (unsigned long)xmm6;
+ case 7:
+ return (unsigned long)xmm7;
+ }
+ return 0;
+}
+
+/*
+ * Basic CPU control in CR0
+ */
+#define X86_CR0_PE (1UL<<0) /* Protection Enable */
+#define X86_CR0_MP (1UL<<1) /* Monitor Coprocessor */
+#define X86_CR0_EM (1UL<<2) /* Emulation */
+#define X86_CR0_TS (1UL<<3) /* Task Switched */
+#define X86_CR0_ET (1UL<<4) /* Extension Type */
+#define X86_CR0_NE (1UL<<5) /* Numeric Error */
+#define X86_CR0_WP (1UL<<16) /* Write Protect */
+#define X86_CR0_AM (1UL<<18) /* Alignment Mask */
+#define X86_CR0_NW (1UL<<29) /* Not Write-through */
+#define X86_CR0_CD (1UL<<30) /* Cache Disable */
+#define X86_CR0_PG (1UL<<31) /* Paging */
+
+/*
+ * CPU model specific register (MSR) numbers.
+ */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER 0xc0000080 /* extended feature register */
+#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */
+#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */
+
+/* EFER bits: */
+#define EFER_SCE (1<<0) /* SYSCALL/SYSRET */
+#define EFER_LME (1<<8) /* Long mode enable */
+#define EFER_LMA (1<<10) /* Long mode active (read-only) */
+#define EFER_NX (1<<11) /* No execute enable */
+#define EFER_SVME (1<<12) /* Enable virtualization */
+#define EFER_LMSLE (1<<13) /* Long Mode Segment Limit Enable */
+#define EFER_FFXSR (1<<14) /* Enable Fast FXSAVE/FXRSTOR */
+
+/* Intel MSRs. Some also available on other CPUs */
+
+#define MSR_PPIN_CTL 0x0000004e
+#define MSR_PPIN 0x0000004f
+
+#define MSR_IA32_PERFCTR0 0x000000c1
+#define MSR_IA32_PERFCTR1 0x000000c2
+#define MSR_FSB_FREQ 0x000000cd
+#define MSR_PLATFORM_INFO 0x000000ce
+#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31
+#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
+
+#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2
+#define NHM_C3_AUTO_DEMOTE (1UL << 25)
+#define NHM_C1_AUTO_DEMOTE (1UL << 26)
+#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25)
+#define SNB_C1_AUTO_UNDEMOTE (1UL << 27)
+#define SNB_C3_AUTO_UNDEMOTE (1UL << 28)
+
+#define MSR_MTRRcap 0x000000fe
+#define MSR_IA32_BBL_CR_CTL 0x00000119
+#define MSR_IA32_BBL_CR_CTL3 0x0000011e
+
+#define MSR_IA32_SYSENTER_CS 0x00000174
+#define MSR_IA32_SYSENTER_ESP 0x00000175
+#define MSR_IA32_SYSENTER_EIP 0x00000176
+
+#define MSR_IA32_MCG_CAP 0x00000179
+#define MSR_IA32_MCG_STATUS 0x0000017a
+#define MSR_IA32_MCG_CTL 0x0000017b
+#define MSR_IA32_MCG_EXT_CTL 0x000004d0
+
+#define MSR_OFFCORE_RSP_0 0x000001a6
+#define MSR_OFFCORE_RSP_1 0x000001a7
+#define MSR_TURBO_RATIO_LIMIT 0x000001ad
+#define MSR_TURBO_RATIO_LIMIT1 0x000001ae
+#define MSR_TURBO_RATIO_LIMIT2 0x000001af
+
+#define MSR_LBR_SELECT 0x000001c8
+#define MSR_LBR_TOS 0x000001c9
+#define MSR_LBR_NHM_FROM 0x00000680
+#define MSR_LBR_NHM_TO 0x000006c0
+#define MSR_LBR_CORE_FROM 0x00000040
+#define MSR_LBR_CORE_TO 0x00000060
+
+#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */
+#define LBR_INFO_MISPRED BIT_ULL(63)
+#define LBR_INFO_IN_TX BIT_ULL(62)
+#define LBR_INFO_ABORT BIT_ULL(61)
+#define LBR_INFO_CYCLES 0xffff
+
+#define MSR_IA32_PEBS_ENABLE 0x000003f1
+#define MSR_IA32_DS_AREA 0x00000600
+#define MSR_IA32_PERF_CAPABILITIES 0x00000345
+#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6
+
+#define MSR_IA32_RTIT_CTL 0x00000570
+#define MSR_IA32_RTIT_STATUS 0x00000571
+#define MSR_IA32_RTIT_ADDR0_A 0x00000580
+#define MSR_IA32_RTIT_ADDR0_B 0x00000581
+#define MSR_IA32_RTIT_ADDR1_A 0x00000582
+#define MSR_IA32_RTIT_ADDR1_B 0x00000583
+#define MSR_IA32_RTIT_ADDR2_A 0x00000584
+#define MSR_IA32_RTIT_ADDR2_B 0x00000585
+#define MSR_IA32_RTIT_ADDR3_A 0x00000586
+#define MSR_IA32_RTIT_ADDR3_B 0x00000587
+#define MSR_IA32_RTIT_CR3_MATCH 0x00000572
+#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560
+#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561
+
+#define MSR_MTRRfix64K_00000 0x00000250
+#define MSR_MTRRfix16K_80000 0x00000258
+#define MSR_MTRRfix16K_A0000 0x00000259
+#define MSR_MTRRfix4K_C0000 0x00000268
+#define MSR_MTRRfix4K_C8000 0x00000269
+#define MSR_MTRRfix4K_D0000 0x0000026a
+#define MSR_MTRRfix4K_D8000 0x0000026b
+#define MSR_MTRRfix4K_E0000 0x0000026c
+#define MSR_MTRRfix4K_E8000 0x0000026d
+#define MSR_MTRRfix4K_F0000 0x0000026e
+#define MSR_MTRRfix4K_F8000 0x0000026f
+#define MSR_MTRRdefType 0x000002ff
+
+#define MSR_IA32_CR_PAT 0x00000277
+
+#define MSR_IA32_DEBUGCTLMSR 0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP 0x000001db
+#define MSR_IA32_LASTBRANCHTOIP 0x000001dc
+#define MSR_IA32_LASTINTFROMIP 0x000001dd
+#define MSR_IA32_LASTINTTOIP 0x000001de
+
+/* DEBUGCTLMSR bits (others vary by model): */
+#define DEBUGCTLMSR_LBR (1UL << 0) /* last branch recording */
+#define DEBUGCTLMSR_BTF_SHIFT 1
+#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */
+#define DEBUGCTLMSR_TR (1UL << 6)
+#define DEBUGCTLMSR_BTS (1UL << 7)
+#define DEBUGCTLMSR_BTINT (1UL << 8)
+#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9)
+#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
+#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
+#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14
+#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+
+#define MSR_PEBS_FRONTEND 0x000003f7
+
+#define MSR_IA32_POWER_CTL 0x000001fc
+
+#define MSR_IA32_MC0_CTL 0x00000400
+#define MSR_IA32_MC0_STATUS 0x00000401
+#define MSR_IA32_MC0_ADDR 0x00000402
+#define MSR_IA32_MC0_MISC 0x00000403
+
+/* C-state Residency Counters */
+#define MSR_PKG_C3_RESIDENCY 0x000003f8
+#define MSR_PKG_C6_RESIDENCY 0x000003f9
+#define MSR_ATOM_PKG_C6_RESIDENCY 0x000003fa
+#define MSR_PKG_C7_RESIDENCY 0x000003fa
+#define MSR_CORE_C3_RESIDENCY 0x000003fc
+#define MSR_CORE_C6_RESIDENCY 0x000003fd
+#define MSR_CORE_C7_RESIDENCY 0x000003fe
+#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff
+#define MSR_PKG_C2_RESIDENCY 0x0000060d
+#define MSR_PKG_C8_RESIDENCY 0x00000630
+#define MSR_PKG_C9_RESIDENCY 0x00000631
+#define MSR_PKG_C10_RESIDENCY 0x00000632
+
+/* Interrupt Response Limit */
+#define MSR_PKGC3_IRTL 0x0000060a
+#define MSR_PKGC6_IRTL 0x0000060b
+#define MSR_PKGC7_IRTL 0x0000060c
+#define MSR_PKGC8_IRTL 0x00000633
+#define MSR_PKGC9_IRTL 0x00000634
+#define MSR_PKGC10_IRTL 0x00000635
+
+/* Run Time Average Power Limiting (RAPL) Interface */
+
+#define MSR_RAPL_POWER_UNIT 0x00000606
+
+#define MSR_PKG_POWER_LIMIT 0x00000610
+#define MSR_PKG_ENERGY_STATUS 0x00000611
+#define MSR_PKG_PERF_STATUS 0x00000613
+#define MSR_PKG_POWER_INFO 0x00000614
+
+#define MSR_DRAM_POWER_LIMIT 0x00000618
+#define MSR_DRAM_ENERGY_STATUS 0x00000619
+#define MSR_DRAM_PERF_STATUS 0x0000061b
+#define MSR_DRAM_POWER_INFO 0x0000061c
+
+#define MSR_PP0_POWER_LIMIT 0x00000638
+#define MSR_PP0_ENERGY_STATUS 0x00000639
+#define MSR_PP0_POLICY 0x0000063a
+#define MSR_PP0_PERF_STATUS 0x0000063b
+
+#define MSR_PP1_POWER_LIMIT 0x00000640
+#define MSR_PP1_ENERGY_STATUS 0x00000641
+#define MSR_PP1_POLICY 0x00000642
+
+/* Config TDP MSRs */
+#define MSR_CONFIG_TDP_NOMINAL 0x00000648
+#define MSR_CONFIG_TDP_LEVEL_1 0x00000649
+#define MSR_CONFIG_TDP_LEVEL_2 0x0000064A
+#define MSR_CONFIG_TDP_CONTROL 0x0000064B
+#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C
+
+#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D
+
+#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658
+#define MSR_PKG_ANY_CORE_C0_RES 0x00000659
+#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A
+#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B
+
+#define MSR_CORE_C1_RES 0x00000660
+#define MSR_MODULE_C6_RES_MS 0x00000664
+
+#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668
+#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669
+
+#define MSR_ATOM_CORE_RATIOS 0x0000066a
+#define MSR_ATOM_CORE_VIDS 0x0000066b
+#define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c
+#define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d
+
+
+#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690
+#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0
+#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1
+
+/* Hardware P state interface */
+#define MSR_PPERF 0x0000064e
+#define MSR_PERF_LIMIT_REASONS 0x0000064f
+#define MSR_PM_ENABLE 0x00000770
+#define MSR_HWP_CAPABILITIES 0x00000771
+#define MSR_HWP_REQUEST_PKG 0x00000772
+#define MSR_HWP_INTERRUPT 0x00000773
+#define MSR_HWP_REQUEST 0x00000774
+#define MSR_HWP_STATUS 0x00000777
+
+/* CPUID.6.EAX */
+#define HWP_BASE_BIT (1<<7)
+#define HWP_NOTIFICATIONS_BIT (1<<8)
+#define HWP_ACTIVITY_WINDOW_BIT (1<<9)
+#define HWP_ENERGY_PERF_PREFERENCE_BIT (1<<10)
+#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11)
+
+/* IA32_HWP_CAPABILITIES */
+#define HWP_HIGHEST_PERF(x) (((x) >> 0) & 0xff)
+#define HWP_GUARANTEED_PERF(x) (((x) >> 8) & 0xff)
+#define HWP_MOSTEFFICIENT_PERF(x) (((x) >> 16) & 0xff)
+#define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff)
+
+/* IA32_HWP_REQUEST */
+#define HWP_MIN_PERF(x) (x & 0xff)
+#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
+#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16)
+#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24)
+#define HWP_EPP_PERFORMANCE 0x00
+#define HWP_EPP_BALANCE_PERFORMANCE 0x80
+#define HWP_EPP_BALANCE_POWERSAVE 0xC0
+#define HWP_EPP_POWERSAVE 0xFF
+#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42)
+
+/* IA32_HWP_STATUS */
+#define HWP_GUARANTEED_CHANGE(x) (x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM(x) (x & 0x4)
+
+/* IA32_HWP_INTERRUPT */
+#define HWP_CHANGE_TO_GUARANTEED_INT(x) (x & 0x1)
+#define HWP_EXCURSION_TO_MINIMUM_INT(x) (x & 0x2)
+
+#define MSR_AMD64_MC0_MASK 0xc0010044
+
+#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x))
+#define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x))
+#define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x))
+#define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x))
+
+#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x))
+
+/* These are consecutive and not in the normal 4er MCE bank block */
+#define MSR_IA32_MC0_CTL2 0x00000280
+#define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x))
+
+#define MSR_P6_PERFCTR0 0x000000c1
+#define MSR_P6_PERFCTR1 0x000000c2
+#define MSR_P6_EVNTSEL0 0x00000186
+#define MSR_P6_EVNTSEL1 0x00000187
+
+#define MSR_KNC_PERFCTR0 0x00000020
+#define MSR_KNC_PERFCTR1 0x00000021
+#define MSR_KNC_EVNTSEL0 0x00000028
+#define MSR_KNC_EVNTSEL1 0x00000029
+
+/* Alternative perfctr range with full access. */
+#define MSR_IA32_PMC0 0x000004c1
+
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
+ complete list. */
+
+#define MSR_AMD64_PATCH_LEVEL 0x0000008b
+#define MSR_AMD64_TSC_RATIO 0xc0000104
+#define MSR_AMD64_NB_CFG 0xc001001f
+#define MSR_AMD64_PATCH_LOADER 0xc0010020
+#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140
+#define MSR_AMD64_OSVW_STATUS 0xc0010141
+#define MSR_AMD64_LS_CFG 0xc0011020
+#define MSR_AMD64_DC_CFG 0xc0011022
+#define MSR_AMD64_BU_CFG2 0xc001102a
+#define MSR_AMD64_IBSFETCHCTL 0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD 0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032
+#define MSR_AMD64_IBSFETCH_REG_COUNT 3
+#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<<MSR_AMD64_IBSFETCH_REG_COUNT)-1)
+#define MSR_AMD64_IBSOPCTL 0xc0011033
+#define MSR_AMD64_IBSOPRIP 0xc0011034
+#define MSR_AMD64_IBSOPDATA 0xc0011035
+#define MSR_AMD64_IBSOPDATA2 0xc0011036
+#define MSR_AMD64_IBSOPDATA3 0xc0011037
+#define MSR_AMD64_IBSDCLINAD 0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD 0xc0011039
+#define MSR_AMD64_IBSOP_REG_COUNT 7
+#define MSR_AMD64_IBSOP_REG_MASK ((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
+#define MSR_AMD64_IBSCTL 0xc001103a
+#define MSR_AMD64_IBSBRTARGET 0xc001103b
+#define MSR_AMD64_IBSOPDATA4 0xc001103d
+#define MSR_AMD64_IBS_REG_COUNT_MAX 8 /* includes MSR_AMD64_IBSBRTARGET */
+#define MSR_AMD64_SEV 0xc0010131
+#define MSR_AMD64_SEV_ENABLED_BIT 0
+#define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT)
+
+/* Fam 17h MSRs */
+#define MSR_F17H_IRPERF 0xc00000e9
+
+/* Fam 16h MSRs */
+#define MSR_F16H_L2I_PERF_CTL 0xc0010230
+#define MSR_F16H_L2I_PERF_CTR 0xc0010231
+#define MSR_F16H_DR1_ADDR_MASK 0xc0011019
+#define MSR_F16H_DR2_ADDR_MASK 0xc001101a
+#define MSR_F16H_DR3_ADDR_MASK 0xc001101b
+#define MSR_F16H_DR0_ADDR_MASK 0xc0011027
+
+/* Fam 15h MSRs */
+#define MSR_F15H_PERF_CTL 0xc0010200
+#define MSR_F15H_PERF_CTR 0xc0010201
+#define MSR_F15H_NB_PERF_CTL 0xc0010240
+#define MSR_F15H_NB_PERF_CTR 0xc0010241
+#define MSR_F15H_PTSC 0xc0010280
+#define MSR_F15H_IC_CFG 0xc0011021
+
+/* Fam 10h MSRs */
+#define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058
+#define FAM10H_MMIO_CONF_ENABLE (1<<0)
+#define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf
+#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
+#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL
+#define FAM10H_MMIO_CONF_BASE_SHIFT 20
+#define MSR_FAM10H_NODE_ID 0xc001100c
+#define MSR_F10H_DECFG 0xc0011029
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT 1
+#define MSR_F10H_DECFG_LFENCE_SERIALIZE BIT_ULL(MSR_F10H_DECFG_LFENCE_SERIALIZE_BIT)
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1 0xc001001a
+#define MSR_K8_TOP_MEM2 0xc001001d
+#define MSR_K8_SYSCFG 0xc0010010
+#define MSR_K8_SYSCFG_MEM_ENCRYPT_BIT 23
+#define MSR_K8_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_K8_SYSCFG_MEM_ENCRYPT_BIT)
+#define MSR_K8_INT_PENDING_MSG 0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK 0x18000000
+#define MSR_K8_TSEG_ADDR 0xc0010112
+#define MSR_K8_TSEG_MASK 0xc0010113
+#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */
+
+/* K7 MSRs */
+#define MSR_K7_EVNTSEL0 0xc0010000
+#define MSR_K7_PERFCTR0 0xc0010004
+#define MSR_K7_EVNTSEL1 0xc0010001
+#define MSR_K7_PERFCTR1 0xc0010005
+#define MSR_K7_EVNTSEL2 0xc0010002
+#define MSR_K7_PERFCTR2 0xc0010006
+#define MSR_K7_EVNTSEL3 0xc0010003
+#define MSR_K7_PERFCTR3 0xc0010007
+#define MSR_K7_CLK_CTL 0xc001001b
+#define MSR_K7_HWCR 0xc0010015
+#define MSR_K7_HWCR_SMMLOCK_BIT 0
+#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
+#define MSR_K7_FID_VID_CTL 0xc0010041
+#define MSR_K7_FID_VID_STATUS 0xc0010042
+
+/* K6 MSRs */
+#define MSR_K6_WHCR 0xc0000082
+#define MSR_K6_UWCCR 0xc0000085
+#define MSR_K6_EPMR 0xc0000086
+#define MSR_K6_PSOR 0xc0000087
+#define MSR_K6_PFIR 0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1 0x00000107
+#define MSR_IDT_FCR2 0x00000108
+#define MSR_IDT_FCR3 0x00000109
+#define MSR_IDT_FCR4 0x0000010a
+
+#define MSR_IDT_MCR0 0x00000110
+#define MSR_IDT_MCR1 0x00000111
+#define MSR_IDT_MCR2 0x00000112
+#define MSR_IDT_MCR3 0x00000113
+#define MSR_IDT_MCR4 0x00000114
+#define MSR_IDT_MCR5 0x00000115
+#define MSR_IDT_MCR6 0x00000116
+#define MSR_IDT_MCR7 0x00000117
+#define MSR_IDT_MCR_CTRL 0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR 0x00001107
+#define MSR_VIA_LONGHAUL 0x0000110a
+#define MSR_VIA_RNG 0x0000110b
+#define MSR_VIA_BCR2 0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL 0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS 0x80868011
+#define MSR_TMTA_LRTI_READOUT 0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR 0x00000000
+#define MSR_IA32_P5_MC_TYPE 0x00000001
+#define MSR_IA32_TSC 0x00000010
+#define MSR_IA32_PLATFORM_ID 0x00000017
+#define MSR_IA32_EBL_CR_POWERON 0x0000002a
+#define MSR_EBC_FREQUENCY_ID 0x0000002c
+#define MSR_SMI_COUNT 0x00000034
+#define MSR_IA32_FEATURE_CONTROL 0x0000003a
+#define MSR_IA32_TSC_ADJUST 0x0000003b
+#define MSR_IA32_BNDCFGS 0x00000d90
+
+#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc
+
+#define MSR_IA32_XSS 0x00000da0
+
+#define FEATURE_CONTROL_LOCKED (1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED_INSIDE_SMX (1<<1)
+#define FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX (1<<2)
+#define FEATURE_CONTROL_LMCE (1<<20)
+
+#define MSR_IA32_APICBASE 0x0000001b
+#define MSR_IA32_APICBASE_BSP (1<<8)
+#define MSR_IA32_APICBASE_ENABLE (1<<11)
+#define MSR_IA32_APICBASE_BASE (0xfffff<<12)
+
+#define MSR_IA32_TSCDEADLINE 0x000006e0
+
+#define MSR_IA32_UCODE_WRITE 0x00000079
+#define MSR_IA32_UCODE_REV 0x0000008b
+
+#define MSR_IA32_SMM_MONITOR_CTL 0x0000009b
+#define MSR_IA32_SMBASE 0x0000009e
+
+#define MSR_IA32_PERF_STATUS 0x00000198
+#define MSR_IA32_PERF_CTL 0x00000199
+#define INTEL_PERF_CTL_MASK 0xffff
+#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064
+#define MSR_AMD_PERF_STATUS 0xc0010063
+#define MSR_AMD_PERF_CTL 0xc0010062
+
+#define MSR_IA32_MPERF 0x000000e7
+#define MSR_IA32_APERF 0x000000e8
+
+#define MSR_IA32_THERM_CONTROL 0x0000019a
+#define MSR_IA32_THERM_INTERRUPT 0x0000019b
+
+#define THERM_INT_HIGH_ENABLE (1 << 0)
+#define THERM_INT_LOW_ENABLE (1 << 1)
+#define THERM_INT_PLN_ENABLE (1 << 24)
+
+#define MSR_IA32_THERM_STATUS 0x0000019c
+
+#define THERM_STATUS_PROCHOT (1 << 0)
+#define THERM_STATUS_POWER_LIMIT (1 << 10)
+
+#define MSR_THERM2_CTL 0x0000019d
+
+#define MSR_THERM2_CTL_TM_SELECT (1ULL << 16)
+
+#define MSR_IA32_MISC_ENABLE 0x000001a0
+
+#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2
+
+#define MSR_MISC_FEATURE_CONTROL 0x000001a4
+#define MSR_MISC_PWR_MGMT 0x000001aa
+
+#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0
+#define ENERGY_PERF_BIAS_PERFORMANCE 0
+#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE 4
+#define ENERGY_PERF_BIAS_NORMAL 6
+#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE 8
+#define ENERGY_PERF_BIAS_POWERSAVE 15
+
+#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1
+
+#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0)
+#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10)
+
+#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2
+
+#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0)
+#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1)
+#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24)
+
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE (1 << 15)
+#define THERM_SHIFT_THRESHOLD0 8
+#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE (1 << 23)
+#define THERM_SHIFT_THRESHOLD1 16
+#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0 (1 << 6)
+#define THERM_LOG_THRESHOLD0 (1 << 7)
+#define THERM_STATUS_THRESHOLD1 (1 << 8)
+#define THERM_LOG_THRESHOLD1 (1 << 9)
+
+/* MISC_ENABLE bits: architectural */
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT 1
+#define MSR_IA32_MISC_ENABLE_TCC (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT 7
+#define MSR_IA32_MISC_ENABLE_EMON (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT 11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT 12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT 16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18
+#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT)
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
+
+/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT 2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT 3
+#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT 4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT 6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT 8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT 9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT 10
+#define MSR_IA32_MISC_ENABLE_FERR (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT 10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT 13
+#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT 19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT 20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT 24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT 37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT 38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
+
+/* MISC_FEATURES_ENABLES non-architectural features */
+#define MSR_MISC_FEATURES_ENABLES 0x00000140
+
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0
+#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT)
+#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1
+
+#define MSR_IA32_TSC_DEADLINE 0x000006E0
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX 0x00000180
+#define MSR_IA32_MCG_EBX 0x00000181
+#define MSR_IA32_MCG_ECX 0x00000182
+#define MSR_IA32_MCG_EDX 0x00000183
+#define MSR_IA32_MCG_ESI 0x00000184
+#define MSR_IA32_MCG_EDI 0x00000185
+#define MSR_IA32_MCG_EBP 0x00000186
+#define MSR_IA32_MCG_ESP 0x00000187
+#define MSR_IA32_MCG_EFLAGS 0x00000188
+#define MSR_IA32_MCG_EIP 0x00000189
+#define MSR_IA32_MCG_RESERVED 0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0 0x00000300
+#define MSR_P4_BPU_PERFCTR1 0x00000301
+#define MSR_P4_BPU_PERFCTR2 0x00000302
+#define MSR_P4_BPU_PERFCTR3 0x00000303
+#define MSR_P4_MS_PERFCTR0 0x00000304
+#define MSR_P4_MS_PERFCTR1 0x00000305
+#define MSR_P4_MS_PERFCTR2 0x00000306
+#define MSR_P4_MS_PERFCTR3 0x00000307
+#define MSR_P4_FLAME_PERFCTR0 0x00000308
+#define MSR_P4_FLAME_PERFCTR1 0x00000309
+#define MSR_P4_FLAME_PERFCTR2 0x0000030a
+#define MSR_P4_FLAME_PERFCTR3 0x0000030b
+#define MSR_P4_IQ_PERFCTR0 0x0000030c
+#define MSR_P4_IQ_PERFCTR1 0x0000030d
+#define MSR_P4_IQ_PERFCTR2 0x0000030e
+#define MSR_P4_IQ_PERFCTR3 0x0000030f
+#define MSR_P4_IQ_PERFCTR4 0x00000310
+#define MSR_P4_IQ_PERFCTR5 0x00000311
+#define MSR_P4_BPU_CCCR0 0x00000360
+#define MSR_P4_BPU_CCCR1 0x00000361
+#define MSR_P4_BPU_CCCR2 0x00000362
+#define MSR_P4_BPU_CCCR3 0x00000363
+#define MSR_P4_MS_CCCR0 0x00000364
+#define MSR_P4_MS_CCCR1 0x00000365
+#define MSR_P4_MS_CCCR2 0x00000366
+#define MSR_P4_MS_CCCR3 0x00000367
+#define MSR_P4_FLAME_CCCR0 0x00000368
+#define MSR_P4_FLAME_CCCR1 0x00000369
+#define MSR_P4_FLAME_CCCR2 0x0000036a
+#define MSR_P4_FLAME_CCCR3 0x0000036b
+#define MSR_P4_IQ_CCCR0 0x0000036c
+#define MSR_P4_IQ_CCCR1 0x0000036d
+#define MSR_P4_IQ_CCCR2 0x0000036e
+#define MSR_P4_IQ_CCCR3 0x0000036f
+#define MSR_P4_IQ_CCCR4 0x00000370
+#define MSR_P4_IQ_CCCR5 0x00000371
+#define MSR_P4_ALF_ESCR0 0x000003ca
+#define MSR_P4_ALF_ESCR1 0x000003cb
+#define MSR_P4_BPU_ESCR0 0x000003b2
+#define MSR_P4_BPU_ESCR1 0x000003b3
+#define MSR_P4_BSU_ESCR0 0x000003a0
+#define MSR_P4_BSU_ESCR1 0x000003a1
+#define MSR_P4_CRU_ESCR0 0x000003b8
+#define MSR_P4_CRU_ESCR1 0x000003b9
+#define MSR_P4_CRU_ESCR2 0x000003cc
+#define MSR_P4_CRU_ESCR3 0x000003cd
+#define MSR_P4_CRU_ESCR4 0x000003e0
+#define MSR_P4_CRU_ESCR5 0x000003e1
+#define MSR_P4_DAC_ESCR0 0x000003a8
+#define MSR_P4_DAC_ESCR1 0x000003a9
+#define MSR_P4_FIRM_ESCR0 0x000003a4
+#define MSR_P4_FIRM_ESCR1 0x000003a5
+#define MSR_P4_FLAME_ESCR0 0x000003a6
+#define MSR_P4_FLAME_ESCR1 0x000003a7
+#define MSR_P4_FSB_ESCR0 0x000003a2
+#define MSR_P4_FSB_ESCR1 0x000003a3
+#define MSR_P4_IQ_ESCR0 0x000003ba
+#define MSR_P4_IQ_ESCR1 0x000003bb
+#define MSR_P4_IS_ESCR0 0x000003b4
+#define MSR_P4_IS_ESCR1 0x000003b5
+#define MSR_P4_ITLB_ESCR0 0x000003b6
+#define MSR_P4_ITLB_ESCR1 0x000003b7
+#define MSR_P4_IX_ESCR0 0x000003c8
+#define MSR_P4_IX_ESCR1 0x000003c9
+#define MSR_P4_MOB_ESCR0 0x000003aa
+#define MSR_P4_MOB_ESCR1 0x000003ab
+#define MSR_P4_MS_ESCR0 0x000003c0
+#define MSR_P4_MS_ESCR1 0x000003c1
+#define MSR_P4_PMH_ESCR0 0x000003ac
+#define MSR_P4_PMH_ESCR1 0x000003ad
+#define MSR_P4_RAT_ESCR0 0x000003bc
+#define MSR_P4_RAT_ESCR1 0x000003bd
+#define MSR_P4_SAAT_ESCR0 0x000003ae
+#define MSR_P4_SAAT_ESCR1 0x000003af
+#define MSR_P4_SSU_ESCR0 0x000003be
+#define MSR_P4_SSU_ESCR1 0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0 0x000003c2
+#define MSR_P4_TBPU_ESCR1 0x000003c3
+#define MSR_P4_TC_ESCR0 0x000003c4
+#define MSR_P4_TC_ESCR1 0x000003c5
+#define MSR_P4_U2L_ESCR0 0x000003b0
+#define MSR_P4_U2L_ESCR1 0x000003b1
+
+#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0 0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0 0x00001900
+
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC 0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS 0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS 0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS 0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS 0x00000484
+#define MSR_IA32_VMX_MISC 0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0 0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1 0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0 0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1 0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM 0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c
+#define MSR_IA32_VMX_TRUE_PINBASED_CTLS 0x0000048d
+#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e
+#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f
+#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490
+#define MSR_IA32_VMX_VMFUNC 0x00000491
+
+/* VMX_BASIC bits and bitmasks */
+#define VMX_BASIC_VMCS_SIZE_SHIFT 32
+#define VMX_BASIC_TRUE_CTLS (1ULL << 55)
+#define VMX_BASIC_64 0x0001000000000000LLU
+#define VMX_BASIC_MEM_TYPE_SHIFT 50
+#define VMX_BASIC_MEM_TYPE_MASK 0x003c000000000000LLU
+#define VMX_BASIC_MEM_TYPE_WB 6LLU
+#define VMX_BASIC_INOUT 0x0040000000000000LLU
+
+/* MSR_IA32_VMX_MISC bits */
+#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
+#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
+/* AMD-V MSRs */
+
+#define MSR_VM_CR 0xc0010114
+#define MSR_VM_IGNNE 0xc0010115
+#define MSR_VM_HSAVE_PA 0xc0010117
+
+#endif /* !SELFTEST_KVM_X86_H */
diff --git a/tools/testing/selftests/kvm/lib/assert.c b/tools/testing/selftests/kvm/lib/assert.c
new file mode 100644
index 000000000000..cd01144d27c8
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/assert.c
@@ -0,0 +1,92 @@
+/*
+ * tools/testing/selftests/kvm/lib/assert.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for getline(3) and strchrnul(3)*/
+
+#include "test_util.h"
+
+#include <execinfo.h>
+#include <sys/syscall.h>
+
+#include "../../kselftest.h"
+
+/* Dumps the current stack trace to stderr. */
+static void __attribute__((noinline)) test_dump_stack(void);
+static void test_dump_stack(void)
+{
+ /*
+ * Build and run this command:
+ *
+ * addr2line -s -e /proc/$PPID/exe -fpai {backtrace addresses} | \
+ * grep -v test_dump_stack | cat -n 1>&2
+ *
+ * Note that the spacing is different and there's no newline.
+ */
+ size_t i;
+ size_t n = 20;
+ void *stack[n];
+ const char *addr2line = "addr2line -s -e /proc/$PPID/exe -fpai";
+ const char *pipeline = "|cat -n 1>&2";
+ char cmd[strlen(addr2line) + strlen(pipeline) +
+ /* N bytes per addr * 2 digits per byte + 1 space per addr: */
+ n * (((sizeof(void *)) * 2) + 1) +
+ /* Null terminator: */
+ 1];
+ char *c;
+
+ n = backtrace(stack, n);
+ c = &cmd[0];
+ c += sprintf(c, "%s", addr2line);
+ /*
+ * Skip the first 3 frames: backtrace, test_dump_stack, and
+ * test_assert. We hope that backtrace isn't inlined and the other two
+ * we've declared noinline.
+ */
+ for (i = 2; i < n; i++)
+ c += sprintf(c, " %lx", ((unsigned long) stack[i]) - 1);
+ c += sprintf(c, "%s", pipeline);
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wunused-result"
+ system(cmd);
+#pragma GCC diagnostic pop
+}
+
+static pid_t gettid(void)
+{
+ return syscall(SYS_gettid);
+}
+
+void __attribute__((noinline))
+test_assert(bool exp, const char *exp_str,
+ const char *file, unsigned int line, const char *fmt, ...)
+{
+ va_list ap;
+
+ if (!(exp)) {
+ va_start(ap, fmt);
+
+ fprintf(stderr, "==== Test Assertion Failure ====\n"
+ " %s:%u: %s\n"
+ " pid=%d tid=%d - %s\n",
+ file, line, exp_str, getpid(), gettid(),
+ strerror(errno));
+ test_dump_stack();
+ if (fmt) {
+ fputs(" ", stderr);
+ vfprintf(stderr, fmt, ap);
+ fputs("\n", stderr);
+ }
+ va_end(ap);
+
+ if (errno == EACCES)
+ ksft_exit_skip("Access denied - Exiting.\n");
+ exit(254);
+ }
+
+ return;
+}
diff --git a/tools/testing/selftests/kvm/lib/elf.c b/tools/testing/selftests/kvm/lib/elf.c
new file mode 100644
index 000000000000..5eb857584aa3
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/elf.c
@@ -0,0 +1,197 @@
+/*
+ * tools/testing/selftests/kvm/lib/elf.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include "test_util.h"
+
+#include <bits/endian.h>
+#include <linux/elf.h>
+
+#include "kvm_util.h"
+#include "kvm_util_internal.h"
+
+static void elfhdr_get(const char *filename, Elf64_Ehdr *hdrp)
+{
+ off_t offset_rv;
+
+ /* Open the ELF file. */
+ int fd;
+ fd = open(filename, O_RDONLY);
+ TEST_ASSERT(fd >= 0, "Failed to open ELF file,\n"
+ " filename: %s\n"
+ " rv: %i errno: %i", filename, fd, errno);
+
+ /* Read in and validate ELF Identification Record.
+ * The ELF Identification record is the first 16 (EI_NIDENT) bytes
+ * of the ELF header, which is at the beginning of the ELF file.
+ * For now it is only safe to read the first EI_NIDENT bytes. Once
+ * read and validated, the value of e_ehsize can be used to determine
+ * the real size of the ELF header.
+ */
+ unsigned char ident[EI_NIDENT];
+ test_read(fd, ident, sizeof(ident));
+ TEST_ASSERT((ident[EI_MAG0] == ELFMAG0) && (ident[EI_MAG1] == ELFMAG1)
+ && (ident[EI_MAG2] == ELFMAG2) && (ident[EI_MAG3] == ELFMAG3),
+ "ELF MAGIC Mismatch,\n"
+ " filename: %s\n"
+ " ident[EI_MAG0 - EI_MAG3]: %02x %02x %02x %02x\n"
+ " Expected: %02x %02x %02x %02x",
+ filename,
+ ident[EI_MAG0], ident[EI_MAG1], ident[EI_MAG2], ident[EI_MAG3],
+ ELFMAG0, ELFMAG1, ELFMAG2, ELFMAG3);
+ TEST_ASSERT(ident[EI_CLASS] == ELFCLASS64,
+ "Current implementation only able to handle ELFCLASS64,\n"
+ " filename: %s\n"
+ " ident[EI_CLASS]: %02x\n"
+ " expected: %02x",
+ filename,
+ ident[EI_CLASS], ELFCLASS64);
+ TEST_ASSERT(((BYTE_ORDER == LITTLE_ENDIAN)
+ && (ident[EI_DATA] == ELFDATA2LSB))
+ || ((BYTE_ORDER == BIG_ENDIAN)
+ && (ident[EI_DATA] == ELFDATA2MSB)), "Current "
+ "implementation only able to handle\n"
+ "cases where the host and ELF file endianness\n"
+ "is the same:\n"
+ " host BYTE_ORDER: %u\n"
+ " host LITTLE_ENDIAN: %u\n"
+ " host BIG_ENDIAN: %u\n"
+ " ident[EI_DATA]: %u\n"
+ " ELFDATA2LSB: %u\n"
+ " ELFDATA2MSB: %u",
+ BYTE_ORDER, LITTLE_ENDIAN, BIG_ENDIAN,
+ ident[EI_DATA], ELFDATA2LSB, ELFDATA2MSB);
+ TEST_ASSERT(ident[EI_VERSION] == EV_CURRENT,
+ "Current implementation only able to handle current "
+ "ELF version,\n"
+ " filename: %s\n"
+ " ident[EI_VERSION]: %02x\n"
+ " expected: %02x",
+ filename, ident[EI_VERSION], EV_CURRENT);
+
+ /* Read in the ELF header.
+ * With the ELF Identification portion of the ELF header
+ * validated, especially that the value at EI_VERSION is
+ * as expected, it is now safe to read the entire ELF header.
+ */
+ offset_rv = lseek(fd, 0, SEEK_SET);
+ TEST_ASSERT(offset_rv == 0, "Seek to ELF header failed,\n"
+ " rv: %zi expected: %i", offset_rv, 0);
+ test_read(fd, hdrp, sizeof(*hdrp));
+ TEST_ASSERT(hdrp->e_phentsize == sizeof(Elf64_Phdr),
+ "Unexpected physical header size,\n"
+ " hdrp->e_phentsize: %x\n"
+ " expected: %zx",
+ hdrp->e_phentsize, sizeof(Elf64_Phdr));
+ TEST_ASSERT(hdrp->e_shentsize == sizeof(Elf64_Shdr),
+ "Unexpected section header size,\n"
+ " hdrp->e_shentsize: %x\n"
+ " expected: %zx",
+ hdrp->e_shentsize, sizeof(Elf64_Shdr));
+}
+
+/* VM ELF Load
+ *
+ * Input Args:
+ * filename - Path to ELF file
+ *
+ * Output Args: None
+ *
+ * Input/Output Args:
+ * vm - Pointer to opaque type that describes the VM.
+ *
+ * Return: None, TEST_ASSERT failures for all error conditions
+ *
+ * Loads the program image of the ELF file specified by filename,
+ * into the virtual address space of the VM pointed to by vm. On entry
+ * the VM needs to not be using any of the virtual address space used
+ * by the image and it needs to have sufficient available physical pages, to
+ * back the virtual pages used to load the image.
+ */
+void kvm_vm_elf_load(struct kvm_vm *vm, const char *filename,
+ uint32_t data_memslot, uint32_t pgd_memslot)
+{
+ off_t offset, offset_rv;
+ Elf64_Ehdr hdr;
+
+ /* Open the ELF file. */
+ int fd;
+ fd = open(filename, O_RDONLY);
+ TEST_ASSERT(fd >= 0, "Failed to open ELF file,\n"
+ " filename: %s\n"
+ " rv: %i errno: %i", filename, fd, errno);
+
+ /* Read in the ELF header. */
+ elfhdr_get(filename, &hdr);
+
+ /* For each program header.
+ * The following ELF header members specify the location
+ * and size of the program headers:
+ *
+ * e_phoff - File offset to start of program headers
+ * e_phentsize - Size of each program header
+ * e_phnum - Number of program header entries
+ */
+ for (unsigned int n1 = 0; n1 < hdr.e_phnum; n1++) {
+ /* Seek to the beginning of the program header. */
+ offset = hdr.e_phoff + (n1 * hdr.e_phentsize);
+ offset_rv = lseek(fd, offset, SEEK_SET);
+ TEST_ASSERT(offset_rv == offset,
+ "Failed to seek to begining of program header %u,\n"
+ " filename: %s\n"
+ " rv: %jd errno: %i",
+ n1, filename, (intmax_t) offset_rv, errno);
+
+ /* Read in the program header. */
+ Elf64_Phdr phdr;
+ test_read(fd, &phdr, sizeof(phdr));
+
+ /* Skip if this header doesn't describe a loadable segment. */
+ if (phdr.p_type != PT_LOAD)
+ continue;
+
+ /* Allocate memory for this segment within the VM. */
+ TEST_ASSERT(phdr.p_memsz > 0, "Unexpected loadable segment "
+ "memsize of 0,\n"
+ " phdr index: %u p_memsz: 0x%" PRIx64,
+ n1, (uint64_t) phdr.p_memsz);
+ vm_vaddr_t seg_vstart = phdr.p_vaddr;
+ seg_vstart &= ~(vm_vaddr_t)(vm->page_size - 1);
+ vm_vaddr_t seg_vend = phdr.p_vaddr + phdr.p_memsz - 1;
+ seg_vend |= vm->page_size - 1;
+ size_t seg_size = seg_vend - seg_vstart + 1;
+
+ vm_vaddr_t vaddr = vm_vaddr_alloc(vm, seg_size, seg_vstart,
+ data_memslot, pgd_memslot);
+ TEST_ASSERT(vaddr == seg_vstart, "Unable to allocate "
+ "virtual memory for segment at requested min addr,\n"
+ " segment idx: %u\n"
+ " seg_vstart: 0x%lx\n"
+ " vaddr: 0x%lx",
+ n1, seg_vstart, vaddr);
+ memset(addr_gva2hva(vm, vaddr), 0, seg_size);
+ /* TODO(lhuemill): Set permissions of each memory segment
+ * based on the least-significant 3 bits of phdr.p_flags.
+ */
+
+ /* Load portion of initial state that is contained within
+ * the ELF file.
+ */
+ if (phdr.p_filesz) {
+ offset_rv = lseek(fd, phdr.p_offset, SEEK_SET);
+ TEST_ASSERT(offset_rv == phdr.p_offset,
+ "Seek to program segment offset failed,\n"
+ " program header idx: %u errno: %i\n"
+ " offset_rv: 0x%jx\n"
+ " expected: 0x%jx\n",
+ n1, errno, (intmax_t) offset_rv,
+ (intmax_t) phdr.p_offset);
+ test_read(fd, addr_gva2hva(vm, phdr.p_vaddr),
+ phdr.p_filesz);
+ }
+ }
+}
diff --git a/tools/testing/selftests/kvm/lib/io.c b/tools/testing/selftests/kvm/lib/io.c
new file mode 100644
index 000000000000..cff869ffe6ee
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/io.c
@@ -0,0 +1,158 @@
+/*
+ * tools/testing/selftests/kvm/lib/io.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include "test_util.h"
+
+/* Test Write
+ *
+ * A wrapper for write(2), that automatically handles the following
+ * special conditions:
+ *
+ * + Interrupted system call (EINTR)
+ * + Write of less than requested amount
+ * + Non-block return (EAGAIN)
+ *
+ * For each of the above, an additional write is performed to automatically
+ * continue writing the requested data.
+ * There are also many cases where write(2) can return an unexpected
+ * error (e.g. EIO). Such errors cause a TEST_ASSERT failure.
+ *
+ * Note, for function signature compatibility with write(2), this function
+ * returns the number of bytes written, but that value will always be equal
+ * to the number of requested bytes. All other conditions in this and
+ * future enhancements to this function either automatically issue another
+ * write(2) or cause a TEST_ASSERT failure.
+ *
+ * Args:
+ * fd - Opened file descriptor to file to be written.
+ * count - Number of bytes to write.
+ *
+ * Output:
+ * buf - Starting address of data to be written.
+ *
+ * Return:
+ * On success, number of bytes written.
+ * On failure, a TEST_ASSERT failure is caused.
+ */
+ssize_t test_write(int fd, const void *buf, size_t count)
+{
+ ssize_t rc;
+ ssize_t num_written = 0;
+ size_t num_left = count;
+ const char *ptr = buf;
+
+ /* Note: Count of zero is allowed (see "RETURN VALUE" portion of
+ * write(2) manpage for details.
+ */
+ TEST_ASSERT(count >= 0, "Unexpected count, count: %li", count);
+
+ do {
+ rc = write(fd, ptr, num_left);
+
+ switch (rc) {
+ case -1:
+ TEST_ASSERT(errno == EAGAIN || errno == EINTR,
+ "Unexpected write failure,\n"
+ " rc: %zi errno: %i", rc, errno);
+ continue;
+
+ case 0:
+ TEST_ASSERT(false, "Unexpected EOF,\n"
+ " rc: %zi num_written: %zi num_left: %zu",
+ rc, num_written, num_left);
+ break;
+
+ default:
+ TEST_ASSERT(rc >= 0, "Unexpected ret from write,\n"
+ " rc: %zi errno: %i", rc, errno);
+ num_written += rc;
+ num_left -= rc;
+ ptr += rc;
+ break;
+ }
+ } while (num_written < count);
+
+ return num_written;
+}
+
+/* Test Read
+ *
+ * A wrapper for read(2), that automatically handles the following
+ * special conditions:
+ *
+ * + Interrupted system call (EINTR)
+ * + Read of less than requested amount
+ * + Non-block return (EAGAIN)
+ *
+ * For each of the above, an additional read is performed to automatically
+ * continue reading the requested data.
+ * There are also many cases where read(2) can return an unexpected
+ * error (e.g. EIO). Such errors cause a TEST_ASSERT failure. Note,
+ * it is expected that the file opened by fd at the current file position
+ * contains at least the number of requested bytes to be read. A TEST_ASSERT
+ * failure is produced if an End-Of-File condition occurs, before all the
+ * data is read. It is the callers responsibility to assure that sufficient
+ * data exists.
+ *
+ * Note, for function signature compatibility with read(2), this function
+ * returns the number of bytes read, but that value will always be equal
+ * to the number of requested bytes. All other conditions in this and
+ * future enhancements to this function either automatically issue another
+ * read(2) or cause a TEST_ASSERT failure.
+ *
+ * Args:
+ * fd - Opened file descriptor to file to be read.
+ * count - Number of bytes to read.
+ *
+ * Output:
+ * buf - Starting address of where to write the bytes read.
+ *
+ * Return:
+ * On success, number of bytes read.
+ * On failure, a TEST_ASSERT failure is caused.
+ */
+ssize_t test_read(int fd, void *buf, size_t count)
+{
+ ssize_t rc;
+ ssize_t num_read = 0;
+ size_t num_left = count;
+ char *ptr = buf;
+
+ /* Note: Count of zero is allowed (see "If count is zero" portion of
+ * read(2) manpage for details.
+ */
+ TEST_ASSERT(count >= 0, "Unexpected count, count: %li", count);
+
+ do {
+ rc = read(fd, ptr, num_left);
+
+ switch (rc) {
+ case -1:
+ TEST_ASSERT(errno == EAGAIN || errno == EINTR,
+ "Unexpected read failure,\n"
+ " rc: %zi errno: %i", rc, errno);
+ break;
+
+ case 0:
+ TEST_ASSERT(false, "Unexpected EOF,\n"
+ " rc: %zi num_read: %zi num_left: %zu",
+ rc, num_read, num_left);
+ break;
+
+ default:
+ TEST_ASSERT(rc > 0, "Unexpected ret from read,\n"
+ " rc: %zi errno: %i", rc, errno);
+ num_read += rc;
+ num_left -= rc;
+ ptr += rc;
+ break;
+ }
+ } while (num_read < count);
+
+ return num_read;
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c
new file mode 100644
index 000000000000..37e2a787d2fc
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/kvm_util.c
@@ -0,0 +1,1486 @@
+/*
+ * tools/testing/selftests/kvm/lib/kvm_util.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kvm_util_internal.h"
+
+#include <assert.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+
+#define KVM_DEV_PATH "/dev/kvm"
+
+#define KVM_UTIL_PGS_PER_HUGEPG 512
+#define KVM_UTIL_MIN_PADDR 0x2000
+
+/* Aligns x up to the next multiple of size. Size must be a power of 2. */
+static void *align(void *x, size_t size)
+{
+ size_t mask = size - 1;
+ TEST_ASSERT(size != 0 && !(size & (size - 1)),
+ "size not a power of 2: %lu", size);
+ return (void *) (((size_t) x + mask) & ~mask);
+}
+
+/* Capability
+ *
+ * Input Args:
+ * cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return:
+ * On success, the Value corresponding to the capability (KVM_CAP_*)
+ * specified by the value of cap. On failure a TEST_ASSERT failure
+ * is produced.
+ *
+ * Looks up and returns the value corresponding to the capability
+ * (KVM_CAP_*) given by cap.
+ */
+int kvm_check_cap(long cap)
+{
+ int ret;
+ int kvm_fd;
+
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ ret = ioctl(kvm_fd, KVM_CHECK_EXTENSION, cap);
+ TEST_ASSERT(ret != -1, "KVM_CHECK_EXTENSION IOCTL failed,\n"
+ " rc: %i errno: %i", ret, errno);
+
+ close(kvm_fd);
+
+ return ret;
+}
+
+/* VM Create
+ *
+ * Input Args:
+ * mode - VM Mode (e.g. VM_MODE_FLAT48PG)
+ * phy_pages - Physical memory pages
+ * perm - permission
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ *
+ * Creates a VM with the mode specified by mode (e.g. VM_MODE_FLAT48PG).
+ * When phy_pages is non-zero, a memory region of phy_pages physical pages
+ * is created and mapped starting at guest physical address 0. The file
+ * descriptor to control the created VM is created with the permissions
+ * given by perm (e.g. O_RDWR).
+ */
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+{
+ struct kvm_vm *vm;
+ int kvm_fd;
+
+ /* Allocate memory. */
+ vm = calloc(1, sizeof(*vm));
+ TEST_ASSERT(vm != NULL, "Insufficent Memory");
+
+ vm->mode = mode;
+ kvm_fd = open(KVM_DEV_PATH, perm);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ /* Create VM. */
+ vm->fd = ioctl(kvm_fd, KVM_CREATE_VM, NULL);
+ TEST_ASSERT(vm->fd >= 0, "KVM_CREATE_VM ioctl failed, "
+ "rc: %i errno: %i", vm->fd, errno);
+
+ close(kvm_fd);
+
+ /* Setup mode specific traits. */
+ switch (vm->mode) {
+ case VM_MODE_FLAT48PG:
+ vm->page_size = 0x1000;
+ vm->page_shift = 12;
+
+ /* Limit to 48-bit canonical virtual addresses. */
+ vm->vpages_valid = sparsebit_alloc();
+ sparsebit_set_num(vm->vpages_valid,
+ 0, (1ULL << (48 - 1)) >> vm->page_shift);
+ sparsebit_set_num(vm->vpages_valid,
+ (~((1ULL << (48 - 1)) - 1)) >> vm->page_shift,
+ (1ULL << (48 - 1)) >> vm->page_shift);
+
+ /* Limit physical addresses to 52-bits. */
+ vm->max_gfn = ((1ULL << 52) >> vm->page_shift) - 1;
+ break;
+
+ default:
+ TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", mode);
+ }
+
+ /* Allocate and setup memory for guest. */
+ vm->vpages_mapped = sparsebit_alloc();
+ if (phy_pages != 0)
+ vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+ 0, 0, phy_pages, 0);
+
+ return vm;
+}
+
+/* Userspace Memory Region Find
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * start - Starting VM physical address
+ * end - Ending VM physical address, inclusive.
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to overlapping region, NULL if no such region.
+ *
+ * Searches for a region with any physical memory that overlaps with
+ * any portion of the guest physical addresses from start to end
+ * inclusive. If multiple overlapping regions exist, a pointer to any
+ * of the regions is returned. Null is returned only when no overlapping
+ * region exists.
+ */
+static struct userspace_mem_region *userspace_mem_region_find(
+ struct kvm_vm *vm, uint64_t start, uint64_t end)
+{
+ struct userspace_mem_region *region;
+
+ for (region = vm->userspace_mem_region_head; region;
+ region = region->next) {
+ uint64_t existing_start = region->region.guest_phys_addr;
+ uint64_t existing_end = region->region.guest_phys_addr
+ + region->region.memory_size - 1;
+ if (start <= existing_end && end >= existing_start)
+ return region;
+ }
+
+ return NULL;
+}
+
+/* KVM Userspace Memory Region Find
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * start - Starting VM physical address
+ * end - Ending VM physical address, inclusive.
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to overlapping region, NULL if no such region.
+ *
+ * Public interface to userspace_mem_region_find. Allows tests to look up
+ * the memslot datastructure for a given range of guest physical memory.
+ */
+struct kvm_userspace_memory_region *
+kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
+ uint64_t end)
+{
+ struct userspace_mem_region *region;
+
+ region = userspace_mem_region_find(vm, start, end);
+ if (!region)
+ return NULL;
+
+ return &region->region;
+}
+
+/* VCPU Find
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to VCPU structure
+ *
+ * Locates a vcpu structure that describes the VCPU specified by vcpuid and
+ * returns a pointer to it. Returns NULL if the VM doesn't contain a VCPU
+ * for the specified vcpuid.
+ */
+struct vcpu *vcpu_find(struct kvm_vm *vm,
+ uint32_t vcpuid)
+{
+ struct vcpu *vcpup;
+
+ for (vcpup = vm->vcpu_head; vcpup; vcpup = vcpup->next) {
+ if (vcpup->id == vcpuid)
+ return vcpup;
+ }
+
+ return NULL;
+}
+
+/* VM VCPU Remove
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args: None
+ *
+ * Return: None, TEST_ASSERT failures for all error conditions
+ *
+ * Within the VM specified by vm, removes the VCPU given by vcpuid.
+ */
+static void vm_vcpu_rm(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+ int ret = close(vcpu->fd);
+ TEST_ASSERT(ret == 0, "Close of VCPU fd failed, rc: %i "
+ "errno: %i", ret, errno);
+
+ if (vcpu->next)
+ vcpu->next->prev = vcpu->prev;
+ if (vcpu->prev)
+ vcpu->prev->next = vcpu->next;
+ else
+ vm->vcpu_head = vcpu->next;
+ free(vcpu);
+}
+
+
+/* Destroys and frees the VM pointed to by vmp.
+ */
+void kvm_vm_free(struct kvm_vm *vmp)
+{
+ int ret;
+
+ if (vmp == NULL)
+ return;
+
+ /* Free userspace_mem_regions. */
+ while (vmp->userspace_mem_region_head) {
+ struct userspace_mem_region *region
+ = vmp->userspace_mem_region_head;
+
+ region->region.memory_size = 0;
+ ret = ioctl(vmp->fd, KVM_SET_USER_MEMORY_REGION,
+ &region->region);
+ TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed, "
+ "rc: %i errno: %i", ret, errno);
+
+ vmp->userspace_mem_region_head = region->next;
+ sparsebit_free(&region->unused_phy_pages);
+ ret = munmap(region->mmap_start, region->mmap_size);
+ TEST_ASSERT(ret == 0, "munmap failed, rc: %i errno: %i",
+ ret, errno);
+
+ free(region);
+ }
+
+ /* Free VCPUs. */
+ while (vmp->vcpu_head)
+ vm_vcpu_rm(vmp, vmp->vcpu_head->id);
+
+ /* Free sparsebit arrays. */
+ sparsebit_free(&vmp->vpages_valid);
+ sparsebit_free(&vmp->vpages_mapped);
+
+ /* Close file descriptor for the VM. */
+ ret = close(vmp->fd);
+ TEST_ASSERT(ret == 0, "Close of vm fd failed,\n"
+ " vmp->fd: %i rc: %i errno: %i", vmp->fd, ret, errno);
+
+ /* Free the structure describing the VM. */
+ free(vmp);
+}
+
+/* Memory Compare, host virtual to guest virtual
+ *
+ * Input Args:
+ * hva - Starting host virtual address
+ * vm - Virtual Machine
+ * gva - Starting guest virtual address
+ * len - number of bytes to compare
+ *
+ * Output Args: None
+ *
+ * Input/Output Args: None
+ *
+ * Return:
+ * Returns 0 if the bytes starting at hva for a length of len
+ * are equal the guest virtual bytes starting at gva. Returns
+ * a value < 0, if bytes at hva are less than those at gva.
+ * Otherwise a value > 0 is returned.
+ *
+ * Compares the bytes starting at the host virtual address hva, for
+ * a length of len, to the guest bytes starting at the guest virtual
+ * address given by gva.
+ */
+int kvm_memcmp_hva_gva(void *hva,
+ struct kvm_vm *vm, vm_vaddr_t gva, size_t len)
+{
+ size_t amt;
+
+ /* Compare a batch of bytes until either a match is found
+ * or all the bytes have been compared.
+ */
+ for (uintptr_t offset = 0; offset < len; offset += amt) {
+ uintptr_t ptr1 = (uintptr_t)hva + offset;
+
+ /* Determine host address for guest virtual address
+ * at offset.
+ */
+ uintptr_t ptr2 = (uintptr_t)addr_gva2hva(vm, gva + offset);
+
+ /* Determine amount to compare on this pass.
+ * Don't allow the comparsion to cross a page boundary.
+ */
+ amt = len - offset;
+ if ((ptr1 >> vm->page_shift) != ((ptr1 + amt) >> vm->page_shift))
+ amt = vm->page_size - (ptr1 % vm->page_size);
+ if ((ptr2 >> vm->page_shift) != ((ptr2 + amt) >> vm->page_shift))
+ amt = vm->page_size - (ptr2 % vm->page_size);
+
+ assert((ptr1 >> vm->page_shift) == ((ptr1 + amt - 1) >> vm->page_shift));
+ assert((ptr2 >> vm->page_shift) == ((ptr2 + amt - 1) >> vm->page_shift));
+
+ /* Perform the comparison. If there is a difference
+ * return that result to the caller, otherwise need
+ * to continue on looking for a mismatch.
+ */
+ int ret = memcmp((void *)ptr1, (void *)ptr2, amt);
+ if (ret != 0)
+ return ret;
+ }
+
+ /* No mismatch found. Let the caller know the two memory
+ * areas are equal.
+ */
+ return 0;
+}
+
+/* Allocate an instance of struct kvm_cpuid2
+ *
+ * Input Args: None
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the allocated struct. The caller is responsible
+ * for freeing this struct.
+ *
+ * Since kvm_cpuid2 uses a 0-length array to allow a the size of the
+ * array to be decided at allocation time, allocation is slightly
+ * complicated. This function uses a reasonable default length for
+ * the array and performs the appropriate allocation.
+ */
+static struct kvm_cpuid2 *allocate_kvm_cpuid2(void)
+{
+ struct kvm_cpuid2 *cpuid;
+ int nent = 100;
+ size_t size;
+
+ size = sizeof(*cpuid);
+ size += nent * sizeof(struct kvm_cpuid_entry2);
+ cpuid = malloc(size);
+ if (!cpuid) {
+ perror("malloc");
+ abort();
+ }
+
+ cpuid->nent = nent;
+
+ return cpuid;
+}
+
+/* KVM Supported CPUID Get
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ *
+ * Return: The supported KVM CPUID
+ *
+ * Get the guest CPUID supported by KVM.
+ */
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void)
+{
+ static struct kvm_cpuid2 *cpuid;
+ int ret;
+ int kvm_fd;
+
+ if (cpuid)
+ return cpuid;
+
+ cpuid = allocate_kvm_cpuid2();
+ kvm_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (kvm_fd < 0)
+ exit(KSFT_SKIP);
+
+ ret = ioctl(kvm_fd, KVM_GET_SUPPORTED_CPUID, cpuid);
+ TEST_ASSERT(ret == 0, "KVM_GET_SUPPORTED_CPUID failed %d %d\n",
+ ret, errno);
+
+ close(kvm_fd);
+ return cpuid;
+}
+
+/* Locate a cpuid entry.
+ *
+ * Input Args:
+ * cpuid: The cpuid.
+ * function: The function of the cpuid entry to find.
+ *
+ * Output Args: None
+ *
+ * Return: A pointer to the cpuid entry. Never returns NULL.
+ */
+struct kvm_cpuid_entry2 *
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index)
+{
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_cpuid_entry2 *entry = NULL;
+ int i;
+
+ cpuid = kvm_get_supported_cpuid();
+ for (i = 0; i < cpuid->nent; i++) {
+ if (cpuid->entries[i].function == function &&
+ cpuid->entries[i].index == index) {
+ entry = &cpuid->entries[i];
+ break;
+ }
+ }
+
+ TEST_ASSERT(entry, "Guest CPUID entry not found: (EAX=%x, ECX=%x).",
+ function, index);
+ return entry;
+}
+
+/* VM Userspace Memory Region Add
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * backing_src - Storage source for this region.
+ * NULL to use anonymous memory.
+ * guest_paddr - Starting guest physical address
+ * slot - KVM region slot
+ * npages - Number of physical pages
+ * flags - KVM memory region flags (e.g. KVM_MEM_LOG_DIRTY_PAGES)
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Allocates a memory area of the number of pages specified by npages
+ * and maps it to the VM specified by vm, at a starting physical address
+ * given by guest_paddr. The region is created with a KVM region slot
+ * given by slot, which must be unique and < KVM_MEM_SLOTS_NUM. The
+ * region is created with the flags given by flags.
+ */
+void vm_userspace_mem_region_add(struct kvm_vm *vm,
+ enum vm_mem_backing_src_type src_type,
+ uint64_t guest_paddr, uint32_t slot, uint64_t npages,
+ uint32_t flags)
+{
+ int ret;
+ unsigned long pmem_size = 0;
+ struct userspace_mem_region *region;
+ size_t huge_page_size = KVM_UTIL_PGS_PER_HUGEPG * vm->page_size;
+
+ TEST_ASSERT((guest_paddr % vm->page_size) == 0, "Guest physical "
+ "address not on a page boundary.\n"
+ " guest_paddr: 0x%lx vm->page_size: 0x%x",
+ guest_paddr, vm->page_size);
+ TEST_ASSERT((((guest_paddr >> vm->page_shift) + npages) - 1)
+ <= vm->max_gfn, "Physical range beyond maximum "
+ "supported physical address,\n"
+ " guest_paddr: 0x%lx npages: 0x%lx\n"
+ " vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ guest_paddr, npages, vm->max_gfn, vm->page_size);
+
+ /* Confirm a mem region with an overlapping address doesn't
+ * already exist.
+ */
+ region = (struct userspace_mem_region *) userspace_mem_region_find(
+ vm, guest_paddr, guest_paddr + npages * vm->page_size);
+ if (region != NULL)
+ TEST_ASSERT(false, "overlapping userspace_mem_region already "
+ "exists\n"
+ " requested guest_paddr: 0x%lx npages: 0x%lx "
+ "page_size: 0x%x\n"
+ " existing guest_paddr: 0x%lx size: 0x%lx",
+ guest_paddr, npages, vm->page_size,
+ (uint64_t) region->region.guest_phys_addr,
+ (uint64_t) region->region.memory_size);
+
+ /* Confirm no region with the requested slot already exists. */
+ for (region = vm->userspace_mem_region_head; region;
+ region = region->next) {
+ if (region->region.slot == slot)
+ break;
+ if ((guest_paddr <= (region->region.guest_phys_addr
+ + region->region.memory_size))
+ && ((guest_paddr + npages * vm->page_size)
+ >= region->region.guest_phys_addr))
+ break;
+ }
+ if (region != NULL)
+ TEST_ASSERT(false, "A mem region with the requested slot "
+ "or overlapping physical memory range already exists.\n"
+ " requested slot: %u paddr: 0x%lx npages: 0x%lx\n"
+ " existing slot: %u paddr: 0x%lx size: 0x%lx",
+ slot, guest_paddr, npages,
+ region->region.slot,
+ (uint64_t) region->region.guest_phys_addr,
+ (uint64_t) region->region.memory_size);
+
+ /* Allocate and initialize new mem region structure. */
+ region = calloc(1, sizeof(*region));
+ TEST_ASSERT(region != NULL, "Insufficient Memory");
+ region->mmap_size = npages * vm->page_size;
+
+ /* Enough memory to align up to a huge page. */
+ if (src_type == VM_MEM_SRC_ANONYMOUS_THP)
+ region->mmap_size += huge_page_size;
+ region->mmap_start = mmap(NULL, region->mmap_size,
+ PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS
+ | (src_type == VM_MEM_SRC_ANONYMOUS_HUGETLB ? MAP_HUGETLB : 0),
+ -1, 0);
+ TEST_ASSERT(region->mmap_start != MAP_FAILED,
+ "test_malloc failed, mmap_start: %p errno: %i",
+ region->mmap_start, errno);
+
+ /* Align THP allocation up to start of a huge page. */
+ region->host_mem = align(region->mmap_start,
+ src_type == VM_MEM_SRC_ANONYMOUS_THP ? huge_page_size : 1);
+
+ /* As needed perform madvise */
+ if (src_type == VM_MEM_SRC_ANONYMOUS || src_type == VM_MEM_SRC_ANONYMOUS_THP) {
+ ret = madvise(region->host_mem, npages * vm->page_size,
+ src_type == VM_MEM_SRC_ANONYMOUS ? MADV_NOHUGEPAGE : MADV_HUGEPAGE);
+ TEST_ASSERT(ret == 0, "madvise failed,\n"
+ " addr: %p\n"
+ " length: 0x%lx\n"
+ " src_type: %x",
+ region->host_mem, npages * vm->page_size, src_type);
+ }
+
+ region->unused_phy_pages = sparsebit_alloc();
+ sparsebit_set_num(region->unused_phy_pages,
+ guest_paddr >> vm->page_shift, npages);
+ region->region.slot = slot;
+ region->region.flags = flags;
+ region->region.guest_phys_addr = guest_paddr;
+ region->region.memory_size = npages * vm->page_size;
+ region->region.userspace_addr = (uintptr_t) region->host_mem;
+ ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
+ TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+ " rc: %i errno: %i\n"
+ " slot: %u flags: 0x%x\n"
+ " guest_phys_addr: 0x%lx size: 0x%lx",
+ ret, errno, slot, flags,
+ guest_paddr, (uint64_t) region->region.memory_size);
+
+ /* Add to linked-list of memory regions. */
+ if (vm->userspace_mem_region_head)
+ vm->userspace_mem_region_head->prev = region;
+ region->next = vm->userspace_mem_region_head;
+ vm->userspace_mem_region_head = region;
+}
+
+/* Memslot to region
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * memslot - KVM memory slot ID
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to memory region structure that describe memory region
+ * using kvm memory slot ID given by memslot. TEST_ASSERT failure
+ * on error (e.g. currently no memory region using memslot as a KVM
+ * memory slot ID).
+ */
+static struct userspace_mem_region *memslot2region(struct kvm_vm *vm,
+ uint32_t memslot)
+{
+ struct userspace_mem_region *region;
+
+ for (region = vm->userspace_mem_region_head; region;
+ region = region->next) {
+ if (region->region.slot == memslot)
+ break;
+ }
+ if (region == NULL) {
+ fprintf(stderr, "No mem region with the requested slot found,\n"
+ " requested slot: %u\n", memslot);
+ fputs("---- vm dump ----\n", stderr);
+ vm_dump(stderr, vm, 2);
+ TEST_ASSERT(false, "Mem region not found");
+ }
+
+ return region;
+}
+
+/* VM Memory Region Flags Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * flags - Starting guest physical address
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the flags of the memory region specified by the value of slot,
+ * to the values given by flags.
+ */
+void vm_mem_region_set_flags(struct kvm_vm *vm, uint32_t slot, uint32_t flags)
+{
+ int ret;
+ struct userspace_mem_region *region;
+
+ /* Locate memory region. */
+ region = memslot2region(vm, slot);
+
+ region->region.flags = flags;
+
+ ret = ioctl(vm->fd, KVM_SET_USER_MEMORY_REGION, &region->region);
+
+ TEST_ASSERT(ret == 0, "KVM_SET_USER_MEMORY_REGION IOCTL failed,\n"
+ " rc: %i errno: %i slot: %u flags: 0x%x",
+ ret, errno, slot, flags);
+}
+
+/* VCPU mmap Size
+ *
+ * Input Args: None
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Size of VCPU state
+ *
+ * Returns the size of the structure pointed to by the return value
+ * of vcpu_state().
+ */
+static int vcpu_mmap_sz(void)
+{
+ int dev_fd, ret;
+
+ dev_fd = open(KVM_DEV_PATH, O_RDONLY);
+ if (dev_fd < 0)
+ exit(KSFT_SKIP);
+
+ ret = ioctl(dev_fd, KVM_GET_VCPU_MMAP_SIZE, NULL);
+ TEST_ASSERT(ret >= sizeof(struct kvm_run),
+ "%s KVM_GET_VCPU_MMAP_SIZE ioctl failed, rc: %i errno: %i",
+ __func__, ret, errno);
+
+ close(dev_fd);
+
+ return ret;
+}
+
+/* VM VCPU Add
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Creates and adds to the VM specified by vm and virtual CPU with
+ * the ID given by vcpuid.
+ */
+void vm_vcpu_add(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu;
+
+ /* Confirm a vcpu with the specified id doesn't already exist. */
+ vcpu = vcpu_find(vm, vcpuid);
+ if (vcpu != NULL)
+ TEST_ASSERT(false, "vcpu with the specified id "
+ "already exists,\n"
+ " requested vcpuid: %u\n"
+ " existing vcpuid: %u state: %p",
+ vcpuid, vcpu->id, vcpu->state);
+
+ /* Allocate and initialize new vcpu structure. */
+ vcpu = calloc(1, sizeof(*vcpu));
+ TEST_ASSERT(vcpu != NULL, "Insufficient Memory");
+ vcpu->id = vcpuid;
+ vcpu->fd = ioctl(vm->fd, KVM_CREATE_VCPU, vcpuid);
+ TEST_ASSERT(vcpu->fd >= 0, "KVM_CREATE_VCPU failed, rc: %i errno: %i",
+ vcpu->fd, errno);
+
+ TEST_ASSERT(vcpu_mmap_sz() >= sizeof(*vcpu->state), "vcpu mmap size "
+ "smaller than expected, vcpu_mmap_sz: %i expected_min: %zi",
+ vcpu_mmap_sz(), sizeof(*vcpu->state));
+ vcpu->state = (struct kvm_run *) mmap(NULL, sizeof(*vcpu->state),
+ PROT_READ | PROT_WRITE, MAP_SHARED, vcpu->fd, 0);
+ TEST_ASSERT(vcpu->state != MAP_FAILED, "mmap vcpu_state failed, "
+ "vcpu id: %u errno: %i", vcpuid, errno);
+
+ /* Add to linked-list of VCPUs. */
+ if (vm->vcpu_head)
+ vm->vcpu_head->prev = vcpu;
+ vcpu->next = vm->vcpu_head;
+ vm->vcpu_head = vcpu;
+
+ vcpu_setup(vm, vcpuid);
+}
+
+/* VM Virtual Address Unused Gap
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * sz - Size (bytes)
+ * vaddr_min - Minimum Virtual Address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Lowest virtual address at or below vaddr_min, with at least
+ * sz unused bytes. TEST_ASSERT failure if no area of at least
+ * size sz is available.
+ *
+ * Within the VM specified by vm, locates the lowest starting virtual
+ * address >= vaddr_min, that has at least sz unallocated bytes. A
+ * TEST_ASSERT failure occurs for invalid input or no area of at least
+ * sz unallocated bytes >= vaddr_min is available.
+ */
+static vm_vaddr_t vm_vaddr_unused_gap(struct kvm_vm *vm, size_t sz,
+ vm_vaddr_t vaddr_min)
+{
+ uint64_t pages = (sz + vm->page_size - 1) >> vm->page_shift;
+
+ /* Determine lowest permitted virtual page index. */
+ uint64_t pgidx_start = (vaddr_min + vm->page_size - 1) >> vm->page_shift;
+ if ((pgidx_start * vm->page_size) < vaddr_min)
+ goto no_va_found;
+
+ /* Loop over section with enough valid virtual page indexes. */
+ if (!sparsebit_is_set_num(vm->vpages_valid,
+ pgidx_start, pages))
+ pgidx_start = sparsebit_next_set_num(vm->vpages_valid,
+ pgidx_start, pages);
+ do {
+ /*
+ * Are there enough unused virtual pages available at
+ * the currently proposed starting virtual page index.
+ * If not, adjust proposed starting index to next
+ * possible.
+ */
+ if (sparsebit_is_clear_num(vm->vpages_mapped,
+ pgidx_start, pages))
+ goto va_found;
+ pgidx_start = sparsebit_next_clear_num(vm->vpages_mapped,
+ pgidx_start, pages);
+ if (pgidx_start == 0)
+ goto no_va_found;
+
+ /*
+ * If needed, adjust proposed starting virtual address,
+ * to next range of valid virtual addresses.
+ */
+ if (!sparsebit_is_set_num(vm->vpages_valid,
+ pgidx_start, pages)) {
+ pgidx_start = sparsebit_next_set_num(
+ vm->vpages_valid, pgidx_start, pages);
+ if (pgidx_start == 0)
+ goto no_va_found;
+ }
+ } while (pgidx_start != 0);
+
+no_va_found:
+ TEST_ASSERT(false, "No vaddr of specified pages available, "
+ "pages: 0x%lx", pages);
+
+ /* NOT REACHED */
+ return -1;
+
+va_found:
+ TEST_ASSERT(sparsebit_is_set_num(vm->vpages_valid,
+ pgidx_start, pages),
+ "Unexpected, invalid virtual page index range,\n"
+ " pgidx_start: 0x%lx\n"
+ " pages: 0x%lx",
+ pgidx_start, pages);
+ TEST_ASSERT(sparsebit_is_clear_num(vm->vpages_mapped,
+ pgidx_start, pages),
+ "Unexpected, pages already mapped,\n"
+ " pgidx_start: 0x%lx\n"
+ " pages: 0x%lx",
+ pgidx_start, pages);
+
+ return pgidx_start * vm->page_size;
+}
+
+/* VM Virtual Address Allocate
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * sz - Size in bytes
+ * vaddr_min - Minimum starting virtual address
+ * data_memslot - Memory region slot for data pages
+ * pgd_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Starting guest virtual address
+ *
+ * Allocates at least sz bytes within the virtual address space of the vm
+ * given by vm. The allocated bytes are mapped to a virtual address >=
+ * the address given by vaddr_min. Note that each allocation uses a
+ * a unique set of pages, with the minimum real allocation being at least
+ * a page.
+ */
+vm_vaddr_t vm_vaddr_alloc(struct kvm_vm *vm, size_t sz, vm_vaddr_t vaddr_min,
+ uint32_t data_memslot, uint32_t pgd_memslot)
+{
+ uint64_t pages = (sz >> vm->page_shift) + ((sz % vm->page_size) != 0);
+
+ virt_pgd_alloc(vm, pgd_memslot);
+
+ /* Find an unused range of virtual page addresses of at least
+ * pages in length.
+ */
+ vm_vaddr_t vaddr_start = vm_vaddr_unused_gap(vm, sz, vaddr_min);
+
+ /* Map the virtual pages. */
+ for (vm_vaddr_t vaddr = vaddr_start; pages > 0;
+ pages--, vaddr += vm->page_size) {
+ vm_paddr_t paddr;
+
+ paddr = vm_phy_page_alloc(vm, KVM_UTIL_MIN_PADDR, data_memslot);
+
+ virt_pg_map(vm, vaddr, paddr, pgd_memslot);
+
+ sparsebit_set(vm->vpages_mapped,
+ vaddr >> vm->page_shift);
+ }
+
+ return vaddr_start;
+}
+
+/* Address VM Physical to Host Virtual
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gpa - VM physical address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent host virtual address
+ *
+ * Locates the memory region containing the VM physical address given
+ * by gpa, within the VM given by vm. When found, the host virtual
+ * address providing the memory to the vm physical address is returned.
+ * A TEST_ASSERT failure occurs if no region containing gpa exists.
+ */
+void *addr_gpa2hva(struct kvm_vm *vm, vm_paddr_t gpa)
+{
+ struct userspace_mem_region *region;
+ for (region = vm->userspace_mem_region_head; region;
+ region = region->next) {
+ if ((gpa >= region->region.guest_phys_addr)
+ && (gpa <= (region->region.guest_phys_addr
+ + region->region.memory_size - 1)))
+ return (void *) ((uintptr_t) region->host_mem
+ + (gpa - region->region.guest_phys_addr));
+ }
+
+ TEST_ASSERT(false, "No vm physical memory at 0x%lx", gpa);
+ return NULL;
+}
+
+/* Address Host Virtual to VM Physical
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * hva - Host virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent VM physical address
+ *
+ * Locates the memory region containing the host virtual address given
+ * by hva, within the VM given by vm. When found, the equivalent
+ * VM physical address is returned. A TEST_ASSERT failure occurs if no
+ * region containing hva exists.
+ */
+vm_paddr_t addr_hva2gpa(struct kvm_vm *vm, void *hva)
+{
+ struct userspace_mem_region *region;
+ for (region = vm->userspace_mem_region_head; region;
+ region = region->next) {
+ if ((hva >= region->host_mem)
+ && (hva <= (region->host_mem
+ + region->region.memory_size - 1)))
+ return (vm_paddr_t) ((uintptr_t)
+ region->region.guest_phys_addr
+ + (hva - (uintptr_t) region->host_mem));
+ }
+
+ TEST_ASSERT(false, "No mapping to a guest physical address, "
+ "hva: %p", hva);
+ return -1;
+}
+
+/* VM Create IRQ Chip
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Creates an interrupt controller chip for the VM specified by vm.
+ */
+void vm_create_irqchip(struct kvm_vm *vm)
+{
+ int ret;
+
+ ret = ioctl(vm->fd, KVM_CREATE_IRQCHIP, 0);
+ TEST_ASSERT(ret == 0, "KVM_CREATE_IRQCHIP IOCTL failed, "
+ "rc: %i errno: %i", ret, errno);
+}
+
+/* VM VCPU State
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to structure that describes the state of the VCPU.
+ *
+ * Locates and returns a pointer to a structure that describes the
+ * state of the VCPU with the given vcpuid.
+ */
+struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ return vcpu->state;
+}
+
+/* VM VCPU Run
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Switch to executing the code for the VCPU given by vcpuid, within the VM
+ * given by vm.
+ */
+void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ int ret = _vcpu_run(vm, vcpuid);
+ TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
+ "rc: %i errno: %i", ret, errno);
+}
+
+int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int rc;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+ do {
+ rc = ioctl(vcpu->fd, KVM_RUN, NULL);
+ } while (rc == -1 && errno == EINTR);
+ return rc;
+}
+
+/* VM VCPU Set MP State
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * mp_state - mp_state to be set
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the MP state of the VCPU given by vcpuid, to the state given
+ * by mp_state.
+ */
+void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_mp_state *mp_state)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ ret = ioctl(vcpu->fd, KVM_SET_MP_STATE, mp_state);
+ TEST_ASSERT(ret == 0, "KVM_SET_MP_STATE IOCTL failed, "
+ "rc: %i errno: %i", ret, errno);
+}
+
+/* VM VCPU Regs Get
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args:
+ * regs - current state of VCPU regs
+ *
+ * Return: None
+ *
+ * Obtains the current register state for the VCPU specified by vcpuid
+ * and stores it at the location given by regs.
+ */
+void vcpu_regs_get(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_regs *regs)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ /* Get the regs. */
+ ret = ioctl(vcpu->fd, KVM_GET_REGS, regs);
+ TEST_ASSERT(ret == 0, "KVM_GET_REGS failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+/* VM VCPU Regs Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * regs - Values to set VCPU regs to
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the regs of the VCPU specified by vcpuid to the values
+ * given by regs.
+ */
+void vcpu_regs_set(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_regs *regs)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ /* Set the regs. */
+ ret = ioctl(vcpu->fd, KVM_SET_REGS, regs);
+ TEST_ASSERT(ret == 0, "KVM_SET_REGS failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ /* Get the regs. */
+ ret = ioctl(vcpu->fd, KVM_GET_VCPU_EVENTS, events);
+ TEST_ASSERT(ret == 0, "KVM_GET_VCPU_EVENTS, failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+void vcpu_events_set(struct kvm_vm *vm, uint32_t vcpuid,
+ struct kvm_vcpu_events *events)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ /* Set the regs. */
+ ret = ioctl(vcpu->fd, KVM_SET_VCPU_EVENTS, events);
+ TEST_ASSERT(ret == 0, "KVM_SET_VCPU_EVENTS, failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+/* VM VCPU Args Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * num - number of arguments
+ * ... - arguments, each of type uint64_t
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the first num function input arguments to the values
+ * given as variable args. Each of the variable args is expected to
+ * be of type uint64_t.
+ */
+void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
+{
+ va_list ap;
+ struct kvm_regs regs;
+
+ TEST_ASSERT(num >= 1 && num <= 6, "Unsupported number of args,\n"
+ " num: %u\n",
+ num);
+
+ va_start(ap, num);
+ vcpu_regs_get(vm, vcpuid, &regs);
+
+ if (num >= 1)
+ regs.rdi = va_arg(ap, uint64_t);
+
+ if (num >= 2)
+ regs.rsi = va_arg(ap, uint64_t);
+
+ if (num >= 3)
+ regs.rdx = va_arg(ap, uint64_t);
+
+ if (num >= 4)
+ regs.rcx = va_arg(ap, uint64_t);
+
+ if (num >= 5)
+ regs.r8 = va_arg(ap, uint64_t);
+
+ if (num >= 6)
+ regs.r9 = va_arg(ap, uint64_t);
+
+ vcpu_regs_set(vm, vcpuid, &regs);
+ va_end(ap);
+}
+
+/* VM VCPU System Regs Get
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ *
+ * Output Args:
+ * sregs - current state of VCPU system regs
+ *
+ * Return: None
+ *
+ * Obtains the current system register state for the VCPU specified by
+ * vcpuid and stores it at the location given by sregs.
+ */
+void vcpu_sregs_get(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_sregs *sregs)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ /* Get the regs. */
+ /* Get the regs. */
+ ret = ioctl(vcpu->fd, KVM_GET_SREGS, sregs);
+ TEST_ASSERT(ret == 0, "KVM_GET_SREGS failed, rc: %i errno: %i",
+ ret, errno);
+}
+
+/* VM VCPU System Regs Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * sregs - Values to set VCPU system regs to
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Sets the system regs of the VCPU specified by vcpuid to the values
+ * given by sregs.
+ */
+void vcpu_sregs_set(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_sregs *sregs)
+{
+ int ret = _vcpu_sregs_set(vm, vcpuid, sregs);
+ TEST_ASSERT(ret == 0, "KVM_RUN IOCTL failed, "
+ "rc: %i errno: %i", ret, errno);
+}
+
+int _vcpu_sregs_set(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_sregs *sregs)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ /* Get the regs. */
+ return ioctl(vcpu->fd, KVM_SET_SREGS, sregs);
+}
+
+/* VCPU Ioctl
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * cmd - Ioctl number
+ * arg - Argument to pass to the ioctl
+ *
+ * Return: None
+ *
+ * Issues an arbitrary ioctl on a VCPU fd.
+ */
+void vcpu_ioctl(struct kvm_vm *vm,
+ uint32_t vcpuid, unsigned long cmd, void *arg)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int ret;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ ret = ioctl(vcpu->fd, cmd, arg);
+ TEST_ASSERT(ret == 0, "vcpu ioctl %lu failed, rc: %i errno: %i (%s)",
+ cmd, ret, errno, strerror(errno));
+}
+
+/* VM Ioctl
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * cmd - Ioctl number
+ * arg - Argument to pass to the ioctl
+ *
+ * Return: None
+ *
+ * Issues an arbitrary ioctl on a VM fd.
+ */
+void vm_ioctl(struct kvm_vm *vm, unsigned long cmd, void *arg)
+{
+ int ret;
+
+ ret = ioctl(vm->fd, cmd, arg);
+ TEST_ASSERT(ret == 0, "vm ioctl %lu failed, rc: %i errno: %i (%s)",
+ cmd, ret, errno, strerror(errno));
+}
+
+/* VM Dump
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * indent - Left margin indent amount
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VM given by vm, to the FILE stream
+ * given by stream.
+ */
+void vm_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ struct userspace_mem_region *region;
+ struct vcpu *vcpu;
+
+ fprintf(stream, "%*smode: 0x%x\n", indent, "", vm->mode);
+ fprintf(stream, "%*sfd: %i\n", indent, "", vm->fd);
+ fprintf(stream, "%*spage_size: 0x%x\n", indent, "", vm->page_size);
+ fprintf(stream, "%*sMem Regions:\n", indent, "");
+ for (region = vm->userspace_mem_region_head; region;
+ region = region->next) {
+ fprintf(stream, "%*sguest_phys: 0x%lx size: 0x%lx "
+ "host_virt: %p\n", indent + 2, "",
+ (uint64_t) region->region.guest_phys_addr,
+ (uint64_t) region->region.memory_size,
+ region->host_mem);
+ fprintf(stream, "%*sunused_phy_pages: ", indent + 2, "");
+ sparsebit_dump(stream, region->unused_phy_pages, 0);
+ }
+ fprintf(stream, "%*sMapped Virtual Pages:\n", indent, "");
+ sparsebit_dump(stream, vm->vpages_mapped, indent + 2);
+ fprintf(stream, "%*spgd_created: %u\n", indent, "",
+ vm->pgd_created);
+ if (vm->pgd_created) {
+ fprintf(stream, "%*sVirtual Translation Tables:\n",
+ indent + 2, "");
+ virt_dump(stream, vm, indent + 4);
+ }
+ fprintf(stream, "%*sVCPUs:\n", indent, "");
+ for (vcpu = vm->vcpu_head; vcpu; vcpu = vcpu->next)
+ vcpu_dump(stream, vm, vcpu->id, indent + 2);
+}
+
+/* VM VCPU Dump
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU ID
+ * indent - Left margin indent amount
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the current state of the VCPU specified by vcpuid, within the VM
+ * given by vm, to the FILE stream given by stream.
+ */
+void vcpu_dump(FILE *stream, struct kvm_vm *vm,
+ uint32_t vcpuid, uint8_t indent)
+{
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+
+ fprintf(stream, "%*scpuid: %u\n", indent, "", vcpuid);
+
+ fprintf(stream, "%*sregs:\n", indent + 2, "");
+ vcpu_regs_get(vm, vcpuid, &regs);
+ regs_dump(stream, &regs, indent + 4);
+
+ fprintf(stream, "%*ssregs:\n", indent + 2, "");
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+ sregs_dump(stream, &sregs, indent + 4);
+}
+
+/* Known KVM exit reasons */
+static struct exit_reason {
+ unsigned int reason;
+ const char *name;
+} exit_reasons_known[] = {
+ {KVM_EXIT_UNKNOWN, "UNKNOWN"},
+ {KVM_EXIT_EXCEPTION, "EXCEPTION"},
+ {KVM_EXIT_IO, "IO"},
+ {KVM_EXIT_HYPERCALL, "HYPERCALL"},
+ {KVM_EXIT_DEBUG, "DEBUG"},
+ {KVM_EXIT_HLT, "HLT"},
+ {KVM_EXIT_MMIO, "MMIO"},
+ {KVM_EXIT_IRQ_WINDOW_OPEN, "IRQ_WINDOW_OPEN"},
+ {KVM_EXIT_SHUTDOWN, "SHUTDOWN"},
+ {KVM_EXIT_FAIL_ENTRY, "FAIL_ENTRY"},
+ {KVM_EXIT_INTR, "INTR"},
+ {KVM_EXIT_SET_TPR, "SET_TPR"},
+ {KVM_EXIT_TPR_ACCESS, "TPR_ACCESS"},
+ {KVM_EXIT_S390_SIEIC, "S390_SIEIC"},
+ {KVM_EXIT_S390_RESET, "S390_RESET"},
+ {KVM_EXIT_DCR, "DCR"},
+ {KVM_EXIT_NMI, "NMI"},
+ {KVM_EXIT_INTERNAL_ERROR, "INTERNAL_ERROR"},
+ {KVM_EXIT_OSI, "OSI"},
+ {KVM_EXIT_PAPR_HCALL, "PAPR_HCALL"},
+#ifdef KVM_EXIT_MEMORY_NOT_PRESENT
+ {KVM_EXIT_MEMORY_NOT_PRESENT, "MEMORY_NOT_PRESENT"},
+#endif
+};
+
+/* Exit Reason String
+ *
+ * Input Args:
+ * exit_reason - Exit reason
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Constant string pointer describing the exit reason.
+ *
+ * Locates and returns a constant string that describes the KVM exit
+ * reason given by exit_reason. If no such string is found, a constant
+ * string of "Unknown" is returned.
+ */
+const char *exit_reason_str(unsigned int exit_reason)
+{
+ unsigned int n1;
+
+ for (n1 = 0; n1 < ARRAY_SIZE(exit_reasons_known); n1++) {
+ if (exit_reason == exit_reasons_known[n1].reason)
+ return exit_reasons_known[n1].name;
+ }
+
+ return "Unknown";
+}
+
+/* Physical Page Allocate
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * paddr_min - Physical address minimum
+ * memslot - Memory region to allocate page from
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Starting physical address
+ *
+ * Within the VM specified by vm, locates an available physical page
+ * at or above paddr_min. If found, the page is marked as in use
+ * and its address is returned. A TEST_ASSERT failure occurs if no
+ * page is available at or above paddr_min.
+ */
+vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
+ vm_paddr_t paddr_min, uint32_t memslot)
+{
+ struct userspace_mem_region *region;
+ sparsebit_idx_t pg;
+
+ TEST_ASSERT((paddr_min % vm->page_size) == 0, "Min physical address "
+ "not divisible by page size.\n"
+ " paddr_min: 0x%lx page_size: 0x%x",
+ paddr_min, vm->page_size);
+
+ /* Locate memory region. */
+ region = memslot2region(vm, memslot);
+
+ /* Locate next available physical page at or above paddr_min. */
+ pg = paddr_min >> vm->page_shift;
+
+ if (!sparsebit_is_set(region->unused_phy_pages, pg)) {
+ pg = sparsebit_next_set(region->unused_phy_pages, pg);
+ if (pg == 0) {
+ fprintf(stderr, "No guest physical page available, "
+ "paddr_min: 0x%lx page_size: 0x%x memslot: %u",
+ paddr_min, vm->page_size, memslot);
+ fputs("---- vm dump ----\n", stderr);
+ vm_dump(stderr, vm, 2);
+ abort();
+ }
+ }
+
+ /* Specify page as in use and return its address. */
+ sparsebit_clear(region->unused_phy_pages, pg);
+
+ return pg * vm->page_size;
+}
+
+/* Address Guest Virtual to Host Virtual
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gva - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent host virtual address
+ */
+void *addr_gva2hva(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ return addr_gpa2hva(vm, addr_gva2gpa(vm, gva));
+}
diff --git a/tools/testing/selftests/kvm/lib/kvm_util_internal.h b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
new file mode 100644
index 000000000000..a0bd1980c81c
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/kvm_util_internal.h
@@ -0,0 +1,67 @@
+/*
+ * tools/testing/selftests/kvm/lib/kvm_util.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#ifndef KVM_UTIL_INTERNAL_H
+#define KVM_UTIL_INTERNAL_H 1
+
+#include "sparsebit.h"
+
+#ifndef BITS_PER_BYTE
+#define BITS_PER_BYTE 8
+#endif
+
+#ifndef BITS_PER_LONG
+#define BITS_PER_LONG (BITS_PER_BYTE * sizeof(long))
+#endif
+
+#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_LONG)
+
+/* Concrete definition of struct kvm_vm. */
+struct userspace_mem_region {
+ struct userspace_mem_region *next, *prev;
+ struct kvm_userspace_memory_region region;
+ struct sparsebit *unused_phy_pages;
+ int fd;
+ off_t offset;
+ void *host_mem;
+ void *mmap_start;
+ size_t mmap_size;
+};
+
+struct vcpu {
+ struct vcpu *next, *prev;
+ uint32_t id;
+ int fd;
+ struct kvm_run *state;
+};
+
+struct kvm_vm {
+ int mode;
+ int fd;
+ unsigned int page_size;
+ unsigned int page_shift;
+ uint64_t max_gfn;
+ struct vcpu *vcpu_head;
+ struct userspace_mem_region *userspace_mem_region_head;
+ struct sparsebit *vpages_valid;
+ struct sparsebit *vpages_mapped;
+ bool pgd_created;
+ vm_paddr_t pgd;
+};
+
+struct vcpu *vcpu_find(struct kvm_vm *vm,
+ uint32_t vcpuid);
+void vcpu_setup(struct kvm_vm *vm, int vcpuid);
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent);
+void regs_dump(FILE *stream, struct kvm_regs *regs,
+ uint8_t indent);
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
+ uint8_t indent);
+
+#endif
diff --git a/tools/testing/selftests/kvm/lib/sparsebit.c b/tools/testing/selftests/kvm/lib/sparsebit.c
new file mode 100644
index 000000000000..b132bc95d183
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/sparsebit.c
@@ -0,0 +1,2087 @@
+/*
+ * Sparse bit array
+ *
+ * Copyright (C) 2018, Google LLC.
+ * Copyright (C) 2018, Red Hat, Inc. (code style cleanup and fuzzing driver)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * This library provides functions to support a memory efficient bit array,
+ * with an index size of 2^64. A sparsebit array is allocated through
+ * the use sparsebit_alloc() and free'd via sparsebit_free(),
+ * such as in the following:
+ *
+ * struct sparsebit *s;
+ * s = sparsebit_alloc();
+ * sparsebit_free(&s);
+ *
+ * The struct sparsebit type resolves down to a struct sparsebit.
+ * Note that, sparsebit_free() takes a pointer to the sparsebit
+ * structure. This is so that sparsebit_free() is able to poison
+ * the pointer (e.g. set it to NULL) to the struct sparsebit before
+ * returning to the caller.
+ *
+ * Between the return of sparsebit_alloc() and the call of
+ * sparsebit_free(), there are multiple query and modifying operations
+ * that can be performed on the allocated sparsebit array. All of
+ * these operations take as a parameter the value returned from
+ * sparsebit_alloc() and most also take a bit index. Frequently
+ * used routines include:
+ *
+ * ---- Query Operations
+ * sparsebit_is_set(s, idx)
+ * sparsebit_is_clear(s, idx)
+ * sparsebit_any_set(s)
+ * sparsebit_first_set(s)
+ * sparsebit_next_set(s, prev_idx)
+ *
+ * ---- Modifying Operations
+ * sparsebit_set(s, idx)
+ * sparsebit_clear(s, idx)
+ * sparsebit_set_num(s, idx, num);
+ * sparsebit_clear_num(s, idx, num);
+ *
+ * A common operation, is to itterate over all the bits set in a test
+ * sparsebit array. This can be done via code with the following structure:
+ *
+ * sparsebit_idx_t idx;
+ * if (sparsebit_any_set(s)) {
+ * idx = sparsebit_first_set(s);
+ * do {
+ * ...
+ * idx = sparsebit_next_set(s, idx);
+ * } while (idx != 0);
+ * }
+ *
+ * The index of the first bit set needs to be obtained via
+ * sparsebit_first_set(), because sparsebit_next_set(), needs
+ * the index of the previously set. The sparsebit_idx_t type is
+ * unsigned, so there is no previous index before 0 that is available.
+ * Also, the call to sparsebit_first_set() is not made unless there
+ * is at least 1 bit in the array set. This is because sparsebit_first_set()
+ * aborts if sparsebit_first_set() is called with no bits set.
+ * It is the callers responsibility to assure that the
+ * sparsebit array has at least a single bit set before calling
+ * sparsebit_first_set().
+ *
+ * ==== Implementation Overview ====
+ * For the most part the internal implementation of sparsebit is
+ * opaque to the caller. One important implementation detail that the
+ * caller may need to be aware of is the spatial complexity of the
+ * implementation. This implementation of a sparsebit array is not
+ * only sparse, in that it uses memory proportional to the number of bits
+ * set. It is also efficient in memory usage when most of the bits are
+ * set.
+ *
+ * At a high-level the state of the bit settings are maintained through
+ * the use of a binary-search tree, where each node contains at least
+ * the following members:
+ *
+ * typedef uint64_t sparsebit_idx_t;
+ * typedef uint64_t sparsebit_num_t;
+ *
+ * sparsebit_idx_t idx;
+ * uint32_t mask;
+ * sparsebit_num_t num_after;
+ *
+ * The idx member contains the bit index of the first bit described by this
+ * node, while the mask member stores the setting of the first 32-bits.
+ * The setting of the bit at idx + n, where 0 <= n < 32, is located in the
+ * mask member at 1 << n.
+ *
+ * Nodes are sorted by idx and the bits described by two nodes will never
+ * overlap. The idx member is always aligned to the mask size, i.e. a
+ * multiple of 32.
+ *
+ * Beyond a typical implementation, the nodes in this implementation also
+ * contains a member named num_after. The num_after member holds the
+ * number of bits immediately after the mask bits that are contiguously set.
+ * The use of the num_after member allows this implementation to efficiently
+ * represent cases where most bits are set. For example, the case of all
+ * but the last two bits set, is represented by the following two nodes:
+ *
+ * node 0 - idx: 0x0 mask: 0xffffffff num_after: 0xffffffffffffffc0
+ * node 1 - idx: 0xffffffffffffffe0 mask: 0x3fffffff num_after: 0
+ *
+ * ==== Invariants ====
+ * This implementation usses the following invariants:
+ *
+ * + Node are only used to represent bits that are set.
+ * Nodes with a mask of 0 and num_after of 0 are not allowed.
+ *
+ * + Sum of bits set in all the nodes is equal to the value of
+ * the struct sparsebit_pvt num_set member.
+ *
+ * + The setting of at least one bit is always described in a nodes
+ * mask (mask >= 1).
+ *
+ * + A node with all mask bits set only occurs when the last bit
+ * described by the previous node is not equal to this nodes
+ * starting index - 1. All such occurences of this condition are
+ * avoided by moving the setting of the nodes mask bits into
+ * the previous nodes num_after setting.
+ *
+ * + Node starting index is evenly divisible by the number of bits
+ * within a nodes mask member.
+ *
+ * + Nodes never represent a range of bits that wrap around the
+ * highest supported index.
+ *
+ * (idx + MASK_BITS + num_after - 1) <= ((sparsebit_idx_t) 0) - 1)
+ *
+ * As a consequence of the above, the num_after member of a node
+ * will always be <=:
+ *
+ * maximum_index - nodes_starting_index - number_of_mask_bits
+ *
+ * + Nodes within the binary search tree are sorted based on each
+ * nodes starting index.
+ *
+ * + The range of bits described by any two nodes do not overlap. The
+ * range of bits described by a single node is:
+ *
+ * start: node->idx
+ * end (inclusive): node->idx + MASK_BITS + node->num_after - 1;
+ *
+ * Note, at times these invariants are temporarily violated for a
+ * specific portion of the code. For example, when setting a mask
+ * bit, there is a small delay between when the mask bit is set and the
+ * value in the struct sparsebit_pvt num_set member is updated. Other
+ * temporary violations occur when node_split() is called with a specified
+ * index and assures that a node where its mask represents the bit
+ * at the specified index exists. At times to do this node_split()
+ * must split an existing node into two nodes or create a node that
+ * has no bits set. Such temporary violations must be corrected before
+ * returning to the caller. These corrections are typically performed
+ * by the local function node_reduce().
+ */
+
+#include "test_util.h"
+#include "sparsebit.h"
+#include <limits.h>
+#include <assert.h>
+
+#define DUMP_LINE_MAX 100 /* Does not include indent amount */
+
+typedef uint32_t mask_t;
+#define MASK_BITS (sizeof(mask_t) * CHAR_BIT)
+
+struct node {
+ struct node *parent;
+ struct node *left;
+ struct node *right;
+ sparsebit_idx_t idx; /* index of least-significant bit in mask */
+ sparsebit_num_t num_after; /* num contiguously set after mask */
+ mask_t mask;
+};
+
+struct sparsebit {
+ /*
+ * Points to root node of the binary search
+ * tree. Equal to NULL when no bits are set in
+ * the entire sparsebit array.
+ */
+ struct node *root;
+
+ /*
+ * A redundant count of the total number of bits set. Used for
+ * diagnostic purposes and to change the time complexity of
+ * sparsebit_num_set() from O(n) to O(1).
+ * Note: Due to overflow, a value of 0 means none or all set.
+ */
+ sparsebit_num_t num_set;
+};
+
+/* Returns the number of set bits described by the settings
+ * of the node pointed to by nodep.
+ */
+static sparsebit_num_t node_num_set(struct node *nodep)
+{
+ return nodep->num_after + __builtin_popcount(nodep->mask);
+}
+
+/* Returns a pointer to the node that describes the
+ * lowest bit index.
+ */
+static struct node *node_first(struct sparsebit *s)
+{
+ struct node *nodep;
+
+ for (nodep = s->root; nodep && nodep->left; nodep = nodep->left)
+ ;
+
+ return nodep;
+}
+
+/* Returns a pointer to the node that describes the
+ * lowest bit index > the index of the node pointed to by np.
+ * Returns NULL if no node with a higher index exists.
+ */
+static struct node *node_next(struct sparsebit *s, struct node *np)
+{
+ struct node *nodep = np;
+
+ /*
+ * If current node has a right child, next node is the left-most
+ * of the right child.
+ */
+ if (nodep->right) {
+ for (nodep = nodep->right; nodep->left; nodep = nodep->left)
+ ;
+ return nodep;
+ }
+
+ /*
+ * No right child. Go up until node is left child of a parent.
+ * That parent is then the next node.
+ */
+ while (nodep->parent && nodep == nodep->parent->right)
+ nodep = nodep->parent;
+
+ return nodep->parent;
+}
+
+/* Searches for and returns a pointer to the node that describes the
+ * highest index < the index of the node pointed to by np.
+ * Returns NULL if no node with a lower index exists.
+ */
+static struct node *node_prev(struct sparsebit *s, struct node *np)
+{
+ struct node *nodep = np;
+
+ /*
+ * If current node has a left child, next node is the right-most
+ * of the left child.
+ */
+ if (nodep->left) {
+ for (nodep = nodep->left; nodep->right; nodep = nodep->right)
+ ;
+ return (struct node *) nodep;
+ }
+
+ /*
+ * No left child. Go up until node is right child of a parent.
+ * That parent is then the next node.
+ */
+ while (nodep->parent && nodep == nodep->parent->left)
+ nodep = nodep->parent;
+
+ return (struct node *) nodep->parent;
+}
+
+
+/* Allocates space to hold a copy of the node sub-tree pointed to by
+ * subtree and duplicates the bit settings to the newly allocated nodes.
+ * Returns the newly allocated copy of subtree.
+ */
+static struct node *node_copy_subtree(struct node *subtree)
+{
+ struct node *root;
+
+ /* Duplicate the node at the root of the subtree */
+ root = calloc(1, sizeof(*root));
+ if (!root) {
+ perror("calloc");
+ abort();
+ }
+
+ root->idx = subtree->idx;
+ root->mask = subtree->mask;
+ root->num_after = subtree->num_after;
+
+ /* As needed, recursively duplicate the left and right subtrees */
+ if (subtree->left) {
+ root->left = node_copy_subtree(subtree->left);
+ root->left->parent = root;
+ }
+
+ if (subtree->right) {
+ root->right = node_copy_subtree(subtree->right);
+ root->right->parent = root;
+ }
+
+ return root;
+}
+
+/* Searches for and returns a pointer to the node that describes the setting
+ * of the bit given by idx. A node describes the setting of a bit if its
+ * index is within the bits described by the mask bits or the number of
+ * contiguous bits set after the mask. Returns NULL if there is no such node.
+ */
+static struct node *node_find(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ struct node *nodep;
+
+ /* Find the node that describes the setting of the bit at idx */
+ for (nodep = s->root; nodep;
+ nodep = nodep->idx > idx ? nodep->left : nodep->right) {
+ if (idx >= nodep->idx &&
+ idx <= nodep->idx + MASK_BITS + nodep->num_after - 1)
+ break;
+ }
+
+ return nodep;
+}
+
+/* Entry Requirements:
+ * + A node that describes the setting of idx is not already present.
+ *
+ * Adds a new node to describe the setting of the bit at the index given
+ * by idx. Returns a pointer to the newly added node.
+ *
+ * TODO(lhuemill): Degenerate cases causes the tree to get unbalanced.
+ */
+static struct node *node_add(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ struct node *nodep, *parentp, *prev;
+
+ /* Allocate and initialize the new node. */
+ nodep = calloc(1, sizeof(*nodep));
+ if (!nodep) {
+ perror("calloc");
+ abort();
+ }
+
+ nodep->idx = idx & -MASK_BITS;
+
+ /* If no nodes, set it up as the root node. */
+ if (!s->root) {
+ s->root = nodep;
+ return nodep;
+ }
+
+ /*
+ * Find the parent where the new node should be attached
+ * and add the node there.
+ */
+ parentp = s->root;
+ while (true) {
+ if (idx < parentp->idx) {
+ if (!parentp->left) {
+ parentp->left = nodep;
+ nodep->parent = parentp;
+ break;
+ }
+ parentp = parentp->left;
+ } else {
+ assert(idx > parentp->idx + MASK_BITS + parentp->num_after - 1);
+ if (!parentp->right) {
+ parentp->right = nodep;
+ nodep->parent = parentp;
+ break;
+ }
+ parentp = parentp->right;
+ }
+ }
+
+ /*
+ * Does num_after bits of previous node overlap with the mask
+ * of the new node? If so set the bits in the new nodes mask
+ * and reduce the previous nodes num_after.
+ */
+ prev = node_prev(s, nodep);
+ while (prev && prev->idx + MASK_BITS + prev->num_after - 1 >= nodep->idx) {
+ unsigned int n1 = (prev->idx + MASK_BITS + prev->num_after - 1)
+ - nodep->idx;
+ assert(prev->num_after > 0);
+ assert(n1 < MASK_BITS);
+ assert(!(nodep->mask & (1 << n1)));
+ nodep->mask |= (1 << n1);
+ prev->num_after--;
+ }
+
+ return nodep;
+}
+
+/* Returns whether all the bits in the sparsebit array are set. */
+bool sparsebit_all_set(struct sparsebit *s)
+{
+ /*
+ * If any nodes there must be at least one bit set. Only case
+ * where a bit is set and total num set is 0, is when all bits
+ * are set.
+ */
+ return s->root && s->num_set == 0;
+}
+
+/* Clears all bits described by the node pointed to by nodep, then
+ * removes the node.
+ */
+static void node_rm(struct sparsebit *s, struct node *nodep)
+{
+ struct node *tmp;
+ sparsebit_num_t num_set;
+
+ num_set = node_num_set(nodep);
+ assert(s->num_set >= num_set || sparsebit_all_set(s));
+ s->num_set -= node_num_set(nodep);
+
+ /* Have both left and right child */
+ if (nodep->left && nodep->right) {
+ /*
+ * Move left children to the leftmost leaf node
+ * of the right child.
+ */
+ for (tmp = nodep->right; tmp->left; tmp = tmp->left)
+ ;
+ tmp->left = nodep->left;
+ nodep->left = NULL;
+ tmp->left->parent = tmp;
+ }
+
+ /* Left only child */
+ if (nodep->left) {
+ if (!nodep->parent) {
+ s->root = nodep->left;
+ nodep->left->parent = NULL;
+ } else {
+ nodep->left->parent = nodep->parent;
+ if (nodep == nodep->parent->left)
+ nodep->parent->left = nodep->left;
+ else {
+ assert(nodep == nodep->parent->right);
+ nodep->parent->right = nodep->left;
+ }
+ }
+
+ nodep->parent = nodep->left = nodep->right = NULL;
+ free(nodep);
+
+ return;
+ }
+
+
+ /* Right only child */
+ if (nodep->right) {
+ if (!nodep->parent) {
+ s->root = nodep->right;
+ nodep->right->parent = NULL;
+ } else {
+ nodep->right->parent = nodep->parent;
+ if (nodep == nodep->parent->left)
+ nodep->parent->left = nodep->right;
+ else {
+ assert(nodep == nodep->parent->right);
+ nodep->parent->right = nodep->right;
+ }
+ }
+
+ nodep->parent = nodep->left = nodep->right = NULL;
+ free(nodep);
+
+ return;
+ }
+
+ /* Leaf Node */
+ if (!nodep->parent) {
+ s->root = NULL;
+ } else {
+ if (nodep->parent->left == nodep)
+ nodep->parent->left = NULL;
+ else {
+ assert(nodep == nodep->parent->right);
+ nodep->parent->right = NULL;
+ }
+ }
+
+ nodep->parent = nodep->left = nodep->right = NULL;
+ free(nodep);
+
+ return;
+}
+
+/* Splits the node containing the bit at idx so that there is a node
+ * that starts at the specified index. If no such node exists, a new
+ * node at the specified index is created. Returns the new node.
+ *
+ * idx must start of a mask boundary.
+ */
+static struct node *node_split(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ struct node *nodep1, *nodep2;
+ sparsebit_idx_t offset;
+ sparsebit_num_t orig_num_after;
+
+ assert(!(idx % MASK_BITS));
+
+ /*
+ * Is there a node that describes the setting of idx?
+ * If not, add it.
+ */
+ nodep1 = node_find(s, idx);
+ if (!nodep1)
+ return node_add(s, idx);
+
+ /*
+ * All done if the starting index of the node is where the
+ * split should occur.
+ */
+ if (nodep1->idx == idx)
+ return nodep1;
+
+ /*
+ * Split point not at start of mask, so it must be part of
+ * bits described by num_after.
+ */
+
+ /*
+ * Calculate offset within num_after for where the split is
+ * to occur.
+ */
+ offset = idx - (nodep1->idx + MASK_BITS);
+ orig_num_after = nodep1->num_after;
+
+ /*
+ * Add a new node to describe the bits starting at
+ * the split point.
+ */
+ nodep1->num_after = offset;
+ nodep2 = node_add(s, idx);
+
+ /* Move bits after the split point into the new node */
+ nodep2->num_after = orig_num_after - offset;
+ if (nodep2->num_after >= MASK_BITS) {
+ nodep2->mask = ~(mask_t) 0;
+ nodep2->num_after -= MASK_BITS;
+ } else {
+ nodep2->mask = (1 << nodep2->num_after) - 1;
+ nodep2->num_after = 0;
+ }
+
+ return nodep2;
+}
+
+/* Iteratively reduces the node pointed to by nodep and its adjacent
+ * nodes into a more compact form. For example, a node with a mask with
+ * all bits set adjacent to a previous node, will get combined into a
+ * single node with an increased num_after setting.
+ *
+ * After each reduction, a further check is made to see if additional
+ * reductions are possible with the new previous and next nodes. Note,
+ * a search for a reduction is only done across the nodes nearest nodep
+ * and those that became part of a reduction. Reductions beyond nodep
+ * and the adjacent nodes that are reduced are not discovered. It is the
+ * responsibility of the caller to pass a nodep that is within one node
+ * of each possible reduction.
+ *
+ * This function does not fix the temporary violation of all invariants.
+ * For example it does not fix the case where the bit settings described
+ * by two or more nodes overlap. Such a violation introduces the potential
+ * complication of a bit setting for a specific index having different settings
+ * in different nodes. This would then introduce the further complication
+ * of which node has the correct setting of the bit and thus such conditions
+ * are not allowed.
+ *
+ * This function is designed to fix invariant violations that are introduced
+ * by node_split() and by changes to the nodes mask or num_after members.
+ * For example, when setting a bit within a nodes mask, the function that
+ * sets the bit doesn't have to worry about whether the setting of that
+ * bit caused the mask to have leading only or trailing only bits set.
+ * Instead, the function can call node_reduce(), with nodep equal to the
+ * node address that it set a mask bit in, and node_reduce() will notice
+ * the cases of leading or trailing only bits and that there is an
+ * adjacent node that the bit settings could be merged into.
+ *
+ * This implementation specifically detects and corrects violation of the
+ * following invariants:
+ *
+ * + Node are only used to represent bits that are set.
+ * Nodes with a mask of 0 and num_after of 0 are not allowed.
+ *
+ * + The setting of at least one bit is always described in a nodes
+ * mask (mask >= 1).
+ *
+ * + A node with all mask bits set only occurs when the last bit
+ * described by the previous node is not equal to this nodes
+ * starting index - 1. All such occurences of this condition are
+ * avoided by moving the setting of the nodes mask bits into
+ * the previous nodes num_after setting.
+ */
+static void node_reduce(struct sparsebit *s, struct node *nodep)
+{
+ bool reduction_performed;
+
+ do {
+ reduction_performed = false;
+ struct node *prev, *next, *tmp;
+
+ /* 1) Potential reductions within the current node. */
+
+ /* Nodes with all bits cleared may be removed. */
+ if (nodep->mask == 0 && nodep->num_after == 0) {
+ /*
+ * About to remove the node pointed to by
+ * nodep, which normally would cause a problem
+ * for the next pass through the reduction loop,
+ * because the node at the starting point no longer
+ * exists. This potential problem is handled
+ * by first remembering the location of the next
+ * or previous nodes. Doesn't matter which, because
+ * once the node at nodep is removed, there will be
+ * no other nodes between prev and next.
+ *
+ * Note, the checks performed on nodep against both
+ * both prev and next both check for an adjacent
+ * node that can be reduced into a single node. As
+ * such, after removing the node at nodep, doesn't
+ * matter whether the nodep for the next pass
+ * through the loop is equal to the previous pass
+ * prev or next node. Either way, on the next pass
+ * the one not selected will become either the
+ * prev or next node.
+ */
+ tmp = node_next(s, nodep);
+ if (!tmp)
+ tmp = node_prev(s, nodep);
+
+ node_rm(s, nodep);
+ nodep = NULL;
+
+ nodep = tmp;
+ reduction_performed = true;
+ continue;
+ }
+
+ /*
+ * When the mask is 0, can reduce the amount of num_after
+ * bits by moving the initial num_after bits into the mask.
+ */
+ if (nodep->mask == 0) {
+ assert(nodep->num_after != 0);
+ assert(nodep->idx + MASK_BITS > nodep->idx);
+
+ nodep->idx += MASK_BITS;
+
+ if (nodep->num_after >= MASK_BITS) {
+ nodep->mask = ~0;
+ nodep->num_after -= MASK_BITS;
+ } else {
+ nodep->mask = (1u << nodep->num_after) - 1;
+ nodep->num_after = 0;
+ }
+
+ reduction_performed = true;
+ continue;
+ }
+
+ /*
+ * 2) Potential reductions between the current and
+ * previous nodes.
+ */
+ prev = node_prev(s, nodep);
+ if (prev) {
+ sparsebit_idx_t prev_highest_bit;
+
+ /* Nodes with no bits set can be removed. */
+ if (prev->mask == 0 && prev->num_after == 0) {
+ node_rm(s, prev);
+
+ reduction_performed = true;
+ continue;
+ }
+
+ /*
+ * All mask bits set and previous node has
+ * adjacent index.
+ */
+ if (nodep->mask + 1 == 0 &&
+ prev->idx + MASK_BITS == nodep->idx) {
+ prev->num_after += MASK_BITS + nodep->num_after;
+ nodep->mask = 0;
+ nodep->num_after = 0;
+
+ reduction_performed = true;
+ continue;
+ }
+
+ /*
+ * Is node adjacent to previous node and the node
+ * contains a single contiguous range of bits
+ * starting from the beginning of the mask?
+ */
+ prev_highest_bit = prev->idx + MASK_BITS - 1 + prev->num_after;
+ if (prev_highest_bit + 1 == nodep->idx &&
+ (nodep->mask | (nodep->mask >> 1)) == nodep->mask) {
+ /*
+ * How many contiguous bits are there?
+ * Is equal to the total number of set
+ * bits, due to an earlier check that
+ * there is a single contiguous range of
+ * set bits.
+ */
+ unsigned int num_contiguous
+ = __builtin_popcount(nodep->mask);
+ assert((num_contiguous > 0) &&
+ ((1ULL << num_contiguous) - 1) == nodep->mask);
+
+ prev->num_after += num_contiguous;
+ nodep->mask = 0;
+
+ /*
+ * For predictable performance, handle special
+ * case where all mask bits are set and there
+ * is a non-zero num_after setting. This code
+ * is functionally correct without the following
+ * conditionalized statements, but without them
+ * the value of num_after is only reduced by
+ * the number of mask bits per pass. There are
+ * cases where num_after can be close to 2^64.
+ * Without this code it could take nearly
+ * (2^64) / 32 passes to perform the full
+ * reduction.
+ */
+ if (num_contiguous == MASK_BITS) {
+ prev->num_after += nodep->num_after;
+ nodep->num_after = 0;
+ }
+
+ reduction_performed = true;
+ continue;
+ }
+ }
+
+ /*
+ * 3) Potential reductions between the current and
+ * next nodes.
+ */
+ next = node_next(s, nodep);
+ if (next) {
+ /* Nodes with no bits set can be removed. */
+ if (next->mask == 0 && next->num_after == 0) {
+ node_rm(s, next);
+ reduction_performed = true;
+ continue;
+ }
+
+ /*
+ * Is next node index adjacent to current node
+ * and has a mask with all bits set?
+ */
+ if (next->idx == nodep->idx + MASK_BITS + nodep->num_after &&
+ next->mask == ~(mask_t) 0) {
+ nodep->num_after += MASK_BITS;
+ next->mask = 0;
+ nodep->num_after += next->num_after;
+ next->num_after = 0;
+
+ node_rm(s, next);
+ next = NULL;
+
+ reduction_performed = true;
+ continue;
+ }
+ }
+ } while (nodep && reduction_performed);
+}
+
+/* Returns whether the bit at the index given by idx, within the
+ * sparsebit array is set or not.
+ */
+bool sparsebit_is_set(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ struct node *nodep;
+
+ /* Find the node that describes the setting of the bit at idx */
+ for (nodep = s->root; nodep;
+ nodep = nodep->idx > idx ? nodep->left : nodep->right)
+ if (idx >= nodep->idx &&
+ idx <= nodep->idx + MASK_BITS + nodep->num_after - 1)
+ goto have_node;
+
+ return false;
+
+have_node:
+ /* Bit is set if it is any of the bits described by num_after */
+ if (nodep->num_after && idx >= nodep->idx + MASK_BITS)
+ return true;
+
+ /* Is the corresponding mask bit set */
+ assert(idx >= nodep->idx && idx - nodep->idx < MASK_BITS);
+ return !!(nodep->mask & (1 << (idx - nodep->idx)));
+}
+
+/* Within the sparsebit array pointed to by s, sets the bit
+ * at the index given by idx.
+ */
+static void bit_set(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ struct node *nodep;
+
+ /* Skip bits that are already set */
+ if (sparsebit_is_set(s, idx))
+ return;
+
+ /*
+ * Get a node where the bit at idx is described by the mask.
+ * The node_split will also create a node, if there isn't
+ * already a node that describes the setting of bit.
+ */
+ nodep = node_split(s, idx & -MASK_BITS);
+
+ /* Set the bit within the nodes mask */
+ assert(idx >= nodep->idx && idx <= nodep->idx + MASK_BITS - 1);
+ assert(!(nodep->mask & (1 << (idx - nodep->idx))));
+ nodep->mask |= 1 << (idx - nodep->idx);
+ s->num_set++;
+
+ node_reduce(s, nodep);
+}
+
+/* Within the sparsebit array pointed to by s, clears the bit
+ * at the index given by idx.
+ */
+static void bit_clear(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ struct node *nodep;
+
+ /* Skip bits that are already cleared */
+ if (!sparsebit_is_set(s, idx))
+ return;
+
+ /* Is there a node that describes the setting of this bit? */
+ nodep = node_find(s, idx);
+ if (!nodep)
+ return;
+
+ /*
+ * If a num_after bit, split the node, so that the bit is
+ * part of a node mask.
+ */
+ if (idx >= nodep->idx + MASK_BITS)
+ nodep = node_split(s, idx & -MASK_BITS);
+
+ /*
+ * After node_split above, bit at idx should be within the mask.
+ * Clear that bit.
+ */
+ assert(idx >= nodep->idx && idx <= nodep->idx + MASK_BITS - 1);
+ assert(nodep->mask & (1 << (idx - nodep->idx)));
+ nodep->mask &= ~(1 << (idx - nodep->idx));
+ assert(s->num_set > 0 || sparsebit_all_set(s));
+ s->num_set--;
+
+ node_reduce(s, nodep);
+}
+
+/* Recursively dumps to the FILE stream given by stream the contents
+ * of the sub-tree of nodes pointed to by nodep. Each line of output
+ * is prefixed by the number of spaces given by indent. On each
+ * recursion, the indent amount is increased by 2. This causes nodes
+ * at each level deeper into the binary search tree to be displayed
+ * with a greater indent.
+ */
+static void dump_nodes(FILE *stream, struct node *nodep,
+ unsigned int indent)
+{
+ char *node_type;
+
+ /* Dump contents of node */
+ if (!nodep->parent)
+ node_type = "root";
+ else if (nodep == nodep->parent->left)
+ node_type = "left";
+ else {
+ assert(nodep == nodep->parent->right);
+ node_type = "right";
+ }
+ fprintf(stream, "%*s---- %s nodep: %p\n", indent, "", node_type, nodep);
+ fprintf(stream, "%*s parent: %p left: %p right: %p\n", indent, "",
+ nodep->parent, nodep->left, nodep->right);
+ fprintf(stream, "%*s idx: 0x%lx mask: 0x%x num_after: 0x%lx\n",
+ indent, "", nodep->idx, nodep->mask, nodep->num_after);
+
+ /* If present, dump contents of left child nodes */
+ if (nodep->left)
+ dump_nodes(stream, nodep->left, indent + 2);
+
+ /* If present, dump contents of right child nodes */
+ if (nodep->right)
+ dump_nodes(stream, nodep->right, indent + 2);
+}
+
+static inline sparsebit_idx_t node_first_set(struct node *nodep, int start)
+{
+ mask_t leading = (mask_t)1 << start;
+ int n1 = __builtin_ctz(nodep->mask & -leading);
+
+ return nodep->idx + n1;
+}
+
+static inline sparsebit_idx_t node_first_clear(struct node *nodep, int start)
+{
+ mask_t leading = (mask_t)1 << start;
+ int n1 = __builtin_ctz(~nodep->mask & -leading);
+
+ return nodep->idx + n1;
+}
+
+/* Dumps to the FILE stream specified by stream, the implementation dependent
+ * internal state of s. Each line of output is prefixed with the number
+ * of spaces given by indent. The output is completely implementation
+ * dependent and subject to change. Output from this function should only
+ * be used for diagnostic purposes. For example, this function can be
+ * used by test cases after they detect an unexpected condition, as a means
+ * to capture diagnostic information.
+ */
+static void sparsebit_dump_internal(FILE *stream, struct sparsebit *s,
+ unsigned int indent)
+{
+ /* Dump the contents of s */
+ fprintf(stream, "%*sroot: %p\n", indent, "", s->root);
+ fprintf(stream, "%*snum_set: 0x%lx\n", indent, "", s->num_set);
+
+ if (s->root)
+ dump_nodes(stream, s->root, indent);
+}
+
+/* Allocates and returns a new sparsebit array. The initial state
+ * of the newly allocated sparsebit array has all bits cleared.
+ */
+struct sparsebit *sparsebit_alloc(void)
+{
+ struct sparsebit *s;
+
+ /* Allocate top level structure. */
+ s = calloc(1, sizeof(*s));
+ if (!s) {
+ perror("calloc");
+ abort();
+ }
+
+ return s;
+}
+
+/* Frees the implementation dependent data for the sparsebit array
+ * pointed to by s and poisons the pointer to that data.
+ */
+void sparsebit_free(struct sparsebit **sbitp)
+{
+ struct sparsebit *s = *sbitp;
+
+ if (!s)
+ return;
+
+ sparsebit_clear_all(s);
+ free(s);
+ *sbitp = NULL;
+}
+
+/* Makes a copy of the sparsebit array given by s, to the sparsebit
+ * array given by d. Note, d must have already been allocated via
+ * sparsebit_alloc(). It can though already have bits set, which
+ * if different from src will be cleared.
+ */
+void sparsebit_copy(struct sparsebit *d, struct sparsebit *s)
+{
+ /* First clear any bits already set in the destination */
+ sparsebit_clear_all(d);
+
+ if (s->root) {
+ d->root = node_copy_subtree(s->root);
+ d->num_set = s->num_set;
+ }
+}
+
+/* Returns whether num consecutive bits starting at idx are all set. */
+bool sparsebit_is_set_num(struct sparsebit *s,
+ sparsebit_idx_t idx, sparsebit_num_t num)
+{
+ sparsebit_idx_t next_cleared;
+
+ assert(num > 0);
+ assert(idx + num - 1 >= idx);
+
+ /* With num > 0, the first bit must be set. */
+ if (!sparsebit_is_set(s, idx))
+ return false;
+
+ /* Find the next cleared bit */
+ next_cleared = sparsebit_next_clear(s, idx);
+
+ /*
+ * If no cleared bits beyond idx, then there are at least num
+ * set bits. idx + num doesn't wrap. Otherwise check if
+ * there are enough set bits between idx and the next cleared bit.
+ */
+ return next_cleared == 0 || next_cleared - idx >= num;
+}
+
+/* Returns whether the bit at the index given by idx. */
+bool sparsebit_is_clear(struct sparsebit *s,
+ sparsebit_idx_t idx)
+{
+ return !sparsebit_is_set(s, idx);
+}
+
+/* Returns whether num consecutive bits starting at idx are all cleared. */
+bool sparsebit_is_clear_num(struct sparsebit *s,
+ sparsebit_idx_t idx, sparsebit_num_t num)
+{
+ sparsebit_idx_t next_set;
+
+ assert(num > 0);
+ assert(idx + num - 1 >= idx);
+
+ /* With num > 0, the first bit must be cleared. */
+ if (!sparsebit_is_clear(s, idx))
+ return false;
+
+ /* Find the next set bit */
+ next_set = sparsebit_next_set(s, idx);
+
+ /*
+ * If no set bits beyond idx, then there are at least num
+ * cleared bits. idx + num doesn't wrap. Otherwise check if
+ * there are enough cleared bits between idx and the next set bit.
+ */
+ return next_set == 0 || next_set - idx >= num;
+}
+
+/* Returns the total number of bits set. Note: 0 is also returned for
+ * the case of all bits set. This is because with all bits set, there
+ * is 1 additional bit set beyond what can be represented in the return
+ * value. Use sparsebit_any_set(), instead of sparsebit_num_set() > 0,
+ * to determine if the sparsebit array has any bits set.
+ */
+sparsebit_num_t sparsebit_num_set(struct sparsebit *s)
+{
+ return s->num_set;
+}
+
+/* Returns whether any bit is set in the sparsebit array. */
+bool sparsebit_any_set(struct sparsebit *s)
+{
+ /*
+ * Nodes only describe set bits. If any nodes then there
+ * is at least 1 bit set.
+ */
+ if (!s->root)
+ return false;
+
+ /*
+ * Every node should have a non-zero mask. For now will
+ * just assure that the root node has a non-zero mask,
+ * which is a quick check that at least 1 bit is set.
+ */
+ assert(s->root->mask != 0);
+ assert(s->num_set > 0 ||
+ (s->root->num_after == ((sparsebit_num_t) 0) - MASK_BITS &&
+ s->root->mask == ~(mask_t) 0));
+
+ return true;
+}
+
+/* Returns whether all the bits in the sparsebit array are cleared. */
+bool sparsebit_all_clear(struct sparsebit *s)
+{
+ return !sparsebit_any_set(s);
+}
+
+/* Returns whether all the bits in the sparsebit array are set. */
+bool sparsebit_any_clear(struct sparsebit *s)
+{
+ return !sparsebit_all_set(s);
+}
+
+/* Returns the index of the first set bit. Abort if no bits are set.
+ */
+sparsebit_idx_t sparsebit_first_set(struct sparsebit *s)
+{
+ struct node *nodep;
+
+ /* Validate at least 1 bit is set */
+ assert(sparsebit_any_set(s));
+
+ nodep = node_first(s);
+ return node_first_set(nodep, 0);
+}
+
+/* Returns the index of the first cleared bit. Abort if
+ * no bits are cleared.
+ */
+sparsebit_idx_t sparsebit_first_clear(struct sparsebit *s)
+{
+ struct node *nodep1, *nodep2;
+
+ /* Validate at least 1 bit is cleared. */
+ assert(sparsebit_any_clear(s));
+
+ /* If no nodes or first node index > 0 then lowest cleared is 0 */
+ nodep1 = node_first(s);
+ if (!nodep1 || nodep1->idx > 0)
+ return 0;
+
+ /* Does the mask in the first node contain any cleared bits. */
+ if (nodep1->mask != ~(mask_t) 0)
+ return node_first_clear(nodep1, 0);
+
+ /*
+ * All mask bits set in first node. If there isn't a second node
+ * then the first cleared bit is the first bit after the bits
+ * described by the first node.
+ */
+ nodep2 = node_next(s, nodep1);
+ if (!nodep2) {
+ /*
+ * No second node. First cleared bit is first bit beyond
+ * bits described by first node.
+ */
+ assert(nodep1->mask == ~(mask_t) 0);
+ assert(nodep1->idx + MASK_BITS + nodep1->num_after != (sparsebit_idx_t) 0);
+ return nodep1->idx + MASK_BITS + nodep1->num_after;
+ }
+
+ /*
+ * There is a second node.
+ * If it is not adjacent to the first node, then there is a gap
+ * of cleared bits between the nodes, and the first cleared bit
+ * is the first bit within the gap.
+ */
+ if (nodep1->idx + MASK_BITS + nodep1->num_after != nodep2->idx)
+ return nodep1->idx + MASK_BITS + nodep1->num_after;
+
+ /*
+ * Second node is adjacent to the first node.
+ * Because it is adjacent, its mask should be non-zero. If all
+ * its mask bits are set, then with it being adjacent, it should
+ * have had the mask bits moved into the num_after setting of the
+ * previous node.
+ */
+ return node_first_clear(nodep2, 0);
+}
+
+/* Returns index of next bit set within s after the index given by prev.
+ * Returns 0 if there are no bits after prev that are set.
+ */
+sparsebit_idx_t sparsebit_next_set(struct sparsebit *s,
+ sparsebit_idx_t prev)
+{
+ sparsebit_idx_t lowest_possible = prev + 1;
+ sparsebit_idx_t start;
+ struct node *nodep;
+
+ /* A bit after the highest index can't be set. */
+ if (lowest_possible == 0)
+ return 0;
+
+ /*
+ * Find the leftmost 'candidate' overlapping or to the right
+ * of lowest_possible.
+ */
+ struct node *candidate = NULL;
+
+ /* True iff lowest_possible is within candidate */
+ bool contains = false;
+
+ /*
+ * Find node that describes setting of bit at lowest_possible.
+ * If such a node doesn't exist, find the node with the lowest
+ * starting index that is > lowest_possible.
+ */
+ for (nodep = s->root; nodep;) {
+ if ((nodep->idx + MASK_BITS + nodep->num_after - 1)
+ >= lowest_possible) {
+ candidate = nodep;
+ if (candidate->idx <= lowest_possible) {
+ contains = true;
+ break;
+ }
+ nodep = nodep->left;
+ } else {
+ nodep = nodep->right;
+ }
+ }
+ if (!candidate)
+ return 0;
+
+ assert(candidate->mask != 0);
+
+ /* Does the candidate node describe the setting of lowest_possible? */
+ if (!contains) {
+ /*
+ * Candidate doesn't describe setting of bit at lowest_possible.
+ * Candidate points to the first node with a starting index
+ * > lowest_possible.
+ */
+ assert(candidate->idx > lowest_possible);
+
+ return node_first_set(candidate, 0);
+ }
+
+ /*
+ * Candidate describes setting of bit at lowest_possible.
+ * Note: although the node describes the setting of the bit
+ * at lowest_possible, its possible that its setting and the
+ * setting of all latter bits described by this node are 0.
+ * For now, just handle the cases where this node describes
+ * a bit at or after an index of lowest_possible that is set.
+ */
+ start = lowest_possible - candidate->idx;
+
+ if (start < MASK_BITS && candidate->mask >= (1 << start))
+ return node_first_set(candidate, start);
+
+ if (candidate->num_after) {
+ sparsebit_idx_t first_num_after_idx = candidate->idx + MASK_BITS;
+
+ return lowest_possible < first_num_after_idx
+ ? first_num_after_idx : lowest_possible;
+ }
+
+ /*
+ * Although candidate node describes setting of bit at
+ * the index of lowest_possible, all bits at that index and
+ * latter that are described by candidate are cleared. With
+ * this, the next bit is the first bit in the next node, if
+ * such a node exists. If a next node doesn't exist, then
+ * there is no next set bit.
+ */
+ candidate = node_next(s, candidate);
+ if (!candidate)
+ return 0;
+
+ return node_first_set(candidate, 0);
+}
+
+/* Returns index of next bit cleared within s after the index given by prev.
+ * Returns 0 if there are no bits after prev that are cleared.
+ */
+sparsebit_idx_t sparsebit_next_clear(struct sparsebit *s,
+ sparsebit_idx_t prev)
+{
+ sparsebit_idx_t lowest_possible = prev + 1;
+ sparsebit_idx_t idx;
+ struct node *nodep1, *nodep2;
+
+ /* A bit after the highest index can't be set. */
+ if (lowest_possible == 0)
+ return 0;
+
+ /*
+ * Does a node describing the setting of lowest_possible exist?
+ * If not, the bit at lowest_possible is cleared.
+ */
+ nodep1 = node_find(s, lowest_possible);
+ if (!nodep1)
+ return lowest_possible;
+
+ /* Does a mask bit in node 1 describe the next cleared bit. */
+ for (idx = lowest_possible - nodep1->idx; idx < MASK_BITS; idx++)
+ if (!(nodep1->mask & (1 << idx)))
+ return nodep1->idx + idx;
+
+ /*
+ * Next cleared bit is not described by node 1. If there
+ * isn't a next node, then next cleared bit is described
+ * by bit after the bits described by the first node.
+ */
+ nodep2 = node_next(s, nodep1);
+ if (!nodep2)
+ return nodep1->idx + MASK_BITS + nodep1->num_after;
+
+ /*
+ * There is a second node.
+ * If it is not adjacent to the first node, then there is a gap
+ * of cleared bits between the nodes, and the next cleared bit
+ * is the first bit within the gap.
+ */
+ if (nodep1->idx + MASK_BITS + nodep1->num_after != nodep2->idx)
+ return nodep1->idx + MASK_BITS + nodep1->num_after;
+
+ /*
+ * Second node is adjacent to the first node.
+ * Because it is adjacent, its mask should be non-zero. If all
+ * its mask bits are set, then with it being adjacent, it should
+ * have had the mask bits moved into the num_after setting of the
+ * previous node.
+ */
+ return node_first_clear(nodep2, 0);
+}
+
+/* Starting with the index 1 greater than the index given by start, finds
+ * and returns the index of the first sequence of num consecutively set
+ * bits. Returns a value of 0 of no such sequence exists.
+ */
+sparsebit_idx_t sparsebit_next_set_num(struct sparsebit *s,
+ sparsebit_idx_t start, sparsebit_num_t num)
+{
+ sparsebit_idx_t idx;
+
+ assert(num >= 1);
+
+ for (idx = sparsebit_next_set(s, start);
+ idx != 0 && idx + num - 1 >= idx;
+ idx = sparsebit_next_set(s, idx)) {
+ assert(sparsebit_is_set(s, idx));
+
+ /*
+ * Does the sequence of bits starting at idx consist of
+ * num set bits?
+ */
+ if (sparsebit_is_set_num(s, idx, num))
+ return idx;
+
+ /*
+ * Sequence of set bits at idx isn't large enough.
+ * Skip this entire sequence of set bits.
+ */
+ idx = sparsebit_next_clear(s, idx);
+ if (idx == 0)
+ return 0;
+ }
+
+ return 0;
+}
+
+/* Starting with the index 1 greater than the index given by start, finds
+ * and returns the index of the first sequence of num consecutively cleared
+ * bits. Returns a value of 0 of no such sequence exists.
+ */
+sparsebit_idx_t sparsebit_next_clear_num(struct sparsebit *s,
+ sparsebit_idx_t start, sparsebit_num_t num)
+{
+ sparsebit_idx_t idx;
+
+ assert(num >= 1);
+
+ for (idx = sparsebit_next_clear(s, start);
+ idx != 0 && idx + num - 1 >= idx;
+ idx = sparsebit_next_clear(s, idx)) {
+ assert(sparsebit_is_clear(s, idx));
+
+ /*
+ * Does the sequence of bits starting at idx consist of
+ * num cleared bits?
+ */
+ if (sparsebit_is_clear_num(s, idx, num))
+ return idx;
+
+ /*
+ * Sequence of cleared bits at idx isn't large enough.
+ * Skip this entire sequence of cleared bits.
+ */
+ idx = sparsebit_next_set(s, idx);
+ if (idx == 0)
+ return 0;
+ }
+
+ return 0;
+}
+
+/* Sets the bits * in the inclusive range idx through idx + num - 1. */
+void sparsebit_set_num(struct sparsebit *s,
+ sparsebit_idx_t start, sparsebit_num_t num)
+{
+ struct node *nodep, *next;
+ unsigned int n1;
+ sparsebit_idx_t idx;
+ sparsebit_num_t n;
+ sparsebit_idx_t middle_start, middle_end;
+
+ assert(num > 0);
+ assert(start + num - 1 >= start);
+
+ /*
+ * Leading - bits before first mask boundary.
+ *
+ * TODO(lhuemill): With some effort it may be possible to
+ * replace the following loop with a sequential sequence
+ * of statements. High level sequence would be:
+ *
+ * 1. Use node_split() to force node that describes setting
+ * of idx to be within the mask portion of a node.
+ * 2. Form mask of bits to be set.
+ * 3. Determine number of mask bits already set in the node
+ * and store in a local variable named num_already_set.
+ * 4. Set the appropriate mask bits within the node.
+ * 5. Increment struct sparsebit_pvt num_set member
+ * by the number of bits that were actually set.
+ * Exclude from the counts bits that were already set.
+ * 6. Before returning to the caller, use node_reduce() to
+ * handle the multiple corner cases that this method
+ * introduces.
+ */
+ for (idx = start, n = num; n > 0 && idx % MASK_BITS != 0; idx++, n--)
+ bit_set(s, idx);
+
+ /* Middle - bits spanning one or more entire mask */
+ middle_start = idx;
+ middle_end = middle_start + (n & -MASK_BITS) - 1;
+ if (n >= MASK_BITS) {
+ nodep = node_split(s, middle_start);
+
+ /*
+ * As needed, split just after end of middle bits.
+ * No split needed if end of middle bits is at highest
+ * supported bit index.
+ */
+ if (middle_end + 1 > middle_end)
+ (void) node_split(s, middle_end + 1);
+
+ /* Delete nodes that only describe bits within the middle. */
+ for (next = node_next(s, nodep);
+ next && (next->idx < middle_end);
+ next = node_next(s, nodep)) {
+ assert(next->idx + MASK_BITS + next->num_after - 1 <= middle_end);
+ node_rm(s, next);
+ next = NULL;
+ }
+
+ /* As needed set each of the mask bits */
+ for (n1 = 0; n1 < MASK_BITS; n1++) {
+ if (!(nodep->mask & (1 << n1))) {
+ nodep->mask |= 1 << n1;
+ s->num_set++;
+ }
+ }
+
+ s->num_set -= nodep->num_after;
+ nodep->num_after = middle_end - middle_start + 1 - MASK_BITS;
+ s->num_set += nodep->num_after;
+
+ node_reduce(s, nodep);
+ }
+ idx = middle_end + 1;
+ n -= middle_end - middle_start + 1;
+
+ /* Trailing - bits at and beyond last mask boundary */
+ assert(n < MASK_BITS);
+ for (; n > 0; idx++, n--)
+ bit_set(s, idx);
+}
+
+/* Clears the bits * in the inclusive range idx through idx + num - 1. */
+void sparsebit_clear_num(struct sparsebit *s,
+ sparsebit_idx_t start, sparsebit_num_t num)
+{
+ struct node *nodep, *next;
+ unsigned int n1;
+ sparsebit_idx_t idx;
+ sparsebit_num_t n;
+ sparsebit_idx_t middle_start, middle_end;
+
+ assert(num > 0);
+ assert(start + num - 1 >= start);
+
+ /* Leading - bits before first mask boundary */
+ for (idx = start, n = num; n > 0 && idx % MASK_BITS != 0; idx++, n--)
+ bit_clear(s, idx);
+
+ /* Middle - bits spanning one or more entire mask */
+ middle_start = idx;
+ middle_end = middle_start + (n & -MASK_BITS) - 1;
+ if (n >= MASK_BITS) {
+ nodep = node_split(s, middle_start);
+
+ /*
+ * As needed, split just after end of middle bits.
+ * No split needed if end of middle bits is at highest
+ * supported bit index.
+ */
+ if (middle_end + 1 > middle_end)
+ (void) node_split(s, middle_end + 1);
+
+ /* Delete nodes that only describe bits within the middle. */
+ for (next = node_next(s, nodep);
+ next && (next->idx < middle_end);
+ next = node_next(s, nodep)) {
+ assert(next->idx + MASK_BITS + next->num_after - 1 <= middle_end);
+ node_rm(s, next);
+ next = NULL;
+ }
+
+ /* As needed clear each of the mask bits */
+ for (n1 = 0; n1 < MASK_BITS; n1++) {
+ if (nodep->mask & (1 << n1)) {
+ nodep->mask &= ~(1 << n1);
+ s->num_set--;
+ }
+ }
+
+ /* Clear any bits described by num_after */
+ s->num_set -= nodep->num_after;
+ nodep->num_after = 0;
+
+ /*
+ * Delete the node that describes the beginning of
+ * the middle bits and perform any allowed reductions
+ * with the nodes prev or next of nodep.
+ */
+ node_reduce(s, nodep);
+ nodep = NULL;
+ }
+ idx = middle_end + 1;
+ n -= middle_end - middle_start + 1;
+
+ /* Trailing - bits at and beyond last mask boundary */
+ assert(n < MASK_BITS);
+ for (; n > 0; idx++, n--)
+ bit_clear(s, idx);
+}
+
+/* Sets the bit at the index given by idx. */
+void sparsebit_set(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ sparsebit_set_num(s, idx, 1);
+}
+
+/* Clears the bit at the index given by idx. */
+void sparsebit_clear(struct sparsebit *s, sparsebit_idx_t idx)
+{
+ sparsebit_clear_num(s, idx, 1);
+}
+
+/* Sets the bits in the entire addressable range of the sparsebit array. */
+void sparsebit_set_all(struct sparsebit *s)
+{
+ sparsebit_set(s, 0);
+ sparsebit_set_num(s, 1, ~(sparsebit_idx_t) 0);
+ assert(sparsebit_all_set(s));
+}
+
+/* Clears the bits in the entire addressable range of the sparsebit array. */
+void sparsebit_clear_all(struct sparsebit *s)
+{
+ sparsebit_clear(s, 0);
+ sparsebit_clear_num(s, 1, ~(sparsebit_idx_t) 0);
+ assert(!sparsebit_any_set(s));
+}
+
+static size_t display_range(FILE *stream, sparsebit_idx_t low,
+ sparsebit_idx_t high, bool prepend_comma_space)
+{
+ char *fmt_str;
+ size_t sz;
+
+ /* Determine the printf format string */
+ if (low == high)
+ fmt_str = prepend_comma_space ? ", 0x%lx" : "0x%lx";
+ else
+ fmt_str = prepend_comma_space ? ", 0x%lx:0x%lx" : "0x%lx:0x%lx";
+
+ /*
+ * When stream is NULL, just determine the size of what would
+ * have been printed, else print the range.
+ */
+ if (!stream)
+ sz = snprintf(NULL, 0, fmt_str, low, high);
+ else
+ sz = fprintf(stream, fmt_str, low, high);
+
+ return sz;
+}
+
+
+/* Dumps to the FILE stream given by stream, the bit settings
+ * of s. Each line of output is prefixed with the number of
+ * spaces given by indent. The length of each line is implementation
+ * dependent and does not depend on the indent amount. The following
+ * is an example output of a sparsebit array that has bits:
+ *
+ * 0x5, 0x8, 0xa:0xe, 0x12
+ *
+ * This corresponds to a sparsebit whose bits 5, 8, 10, 11, 12, 13, 14, 18
+ * are set. Note that a ':', instead of a '-' is used to specify a range of
+ * contiguous bits. This is done because '-' is used to specify command-line
+ * options, and sometimes ranges are specified as command-line arguments.
+ */
+void sparsebit_dump(FILE *stream, struct sparsebit *s,
+ unsigned int indent)
+{
+ size_t current_line_len = 0;
+ size_t sz;
+ struct node *nodep;
+
+ if (!sparsebit_any_set(s))
+ return;
+
+ /* Display initial indent */
+ fprintf(stream, "%*s", indent, "");
+
+ /* For each node */
+ for (nodep = node_first(s); nodep; nodep = node_next(s, nodep)) {
+ unsigned int n1;
+ sparsebit_idx_t low, high;
+
+ /* For each group of bits in the mask */
+ for (n1 = 0; n1 < MASK_BITS; n1++) {
+ if (nodep->mask & (1 << n1)) {
+ low = high = nodep->idx + n1;
+
+ for (; n1 < MASK_BITS; n1++) {
+ if (nodep->mask & (1 << n1))
+ high = nodep->idx + n1;
+ else
+ break;
+ }
+
+ if ((n1 == MASK_BITS) && nodep->num_after)
+ high += nodep->num_after;
+
+ /*
+ * How much room will it take to display
+ * this range.
+ */
+ sz = display_range(NULL, low, high,
+ current_line_len != 0);
+
+ /*
+ * If there is not enough room, display
+ * a newline plus the indent of the next
+ * line.
+ */
+ if (current_line_len + sz > DUMP_LINE_MAX) {
+ fputs("\n", stream);
+ fprintf(stream, "%*s", indent, "");
+ current_line_len = 0;
+ }
+
+ /* Display the range */
+ sz = display_range(stream, low, high,
+ current_line_len != 0);
+ current_line_len += sz;
+ }
+ }
+
+ /*
+ * If num_after and most significant-bit of mask is not
+ * set, then still need to display a range for the bits
+ * described by num_after.
+ */
+ if (!(nodep->mask & (1 << (MASK_BITS - 1))) && nodep->num_after) {
+ low = nodep->idx + MASK_BITS;
+ high = nodep->idx + MASK_BITS + nodep->num_after - 1;
+
+ /*
+ * How much room will it take to display
+ * this range.
+ */
+ sz = display_range(NULL, low, high,
+ current_line_len != 0);
+
+ /*
+ * If there is not enough room, display
+ * a newline plus the indent of the next
+ * line.
+ */
+ if (current_line_len + sz > DUMP_LINE_MAX) {
+ fputs("\n", stream);
+ fprintf(stream, "%*s", indent, "");
+ current_line_len = 0;
+ }
+
+ /* Display the range */
+ sz = display_range(stream, low, high,
+ current_line_len != 0);
+ current_line_len += sz;
+ }
+ }
+ fputs("\n", stream);
+}
+
+/* Validates the internal state of the sparsebit array given by
+ * s. On error, diagnostic information is printed to stderr and
+ * abort is called.
+ */
+void sparsebit_validate_internal(struct sparsebit *s)
+{
+ bool error_detected = false;
+ struct node *nodep, *prev = NULL;
+ sparsebit_num_t total_bits_set = 0;
+ unsigned int n1;
+
+ /* For each node */
+ for (nodep = node_first(s); nodep;
+ prev = nodep, nodep = node_next(s, nodep)) {
+
+ /*
+ * Increase total bits set by the number of bits set
+ * in this node.
+ */
+ for (n1 = 0; n1 < MASK_BITS; n1++)
+ if (nodep->mask & (1 << n1))
+ total_bits_set++;
+
+ total_bits_set += nodep->num_after;
+
+ /*
+ * Arbitrary choice as to whether a mask of 0 is allowed
+ * or not. For diagnostic purposes it is beneficial to
+ * have only one valid means to represent a set of bits.
+ * To support this an arbitrary choice has been made
+ * to not allow a mask of zero.
+ */
+ if (nodep->mask == 0) {
+ fprintf(stderr, "Node mask of zero, "
+ "nodep: %p nodep->mask: 0x%x",
+ nodep, nodep->mask);
+ error_detected = true;
+ break;
+ }
+
+ /*
+ * Validate num_after is not greater than the max index
+ * - the number of mask bits. The num_after member
+ * uses 0-based indexing and thus has no value that
+ * represents all bits set. This limitation is handled
+ * by requiring a non-zero mask. With a non-zero mask,
+ * MASK_BITS worth of bits are described by the mask,
+ * which makes the largest needed num_after equal to:
+ *
+ * (~(sparsebit_num_t) 0) - MASK_BITS + 1
+ */
+ if (nodep->num_after
+ > (~(sparsebit_num_t) 0) - MASK_BITS + 1) {
+ fprintf(stderr, "num_after too large, "
+ "nodep: %p nodep->num_after: 0x%lx",
+ nodep, nodep->num_after);
+ error_detected = true;
+ break;
+ }
+
+ /* Validate node index is divisible by the mask size */
+ if (nodep->idx % MASK_BITS) {
+ fprintf(stderr, "Node index not divisible by "
+ "mask size,\n"
+ " nodep: %p nodep->idx: 0x%lx "
+ "MASK_BITS: %lu\n",
+ nodep, nodep->idx, MASK_BITS);
+ error_detected = true;
+ break;
+ }
+
+ /*
+ * Validate bits described by node don't wrap beyond the
+ * highest supported index.
+ */
+ if ((nodep->idx + MASK_BITS + nodep->num_after - 1) < nodep->idx) {
+ fprintf(stderr, "Bits described by node wrap "
+ "beyond highest supported index,\n"
+ " nodep: %p nodep->idx: 0x%lx\n"
+ " MASK_BITS: %lu nodep->num_after: 0x%lx",
+ nodep, nodep->idx, MASK_BITS, nodep->num_after);
+ error_detected = true;
+ break;
+ }
+
+ /* Check parent pointers. */
+ if (nodep->left) {
+ if (nodep->left->parent != nodep) {
+ fprintf(stderr, "Left child parent pointer "
+ "doesn't point to this node,\n"
+ " nodep: %p nodep->left: %p "
+ "nodep->left->parent: %p",
+ nodep, nodep->left,
+ nodep->left->parent);
+ error_detected = true;
+ break;
+ }
+ }
+
+ if (nodep->right) {
+ if (nodep->right->parent != nodep) {
+ fprintf(stderr, "Right child parent pointer "
+ "doesn't point to this node,\n"
+ " nodep: %p nodep->right: %p "
+ "nodep->right->parent: %p",
+ nodep, nodep->right,
+ nodep->right->parent);
+ error_detected = true;
+ break;
+ }
+ }
+
+ if (!nodep->parent) {
+ if (s->root != nodep) {
+ fprintf(stderr, "Unexpected root node, "
+ "s->root: %p nodep: %p",
+ s->root, nodep);
+ error_detected = true;
+ break;
+ }
+ }
+
+ if (prev) {
+ /*
+ * Is index of previous node before index of
+ * current node?
+ */
+ if (prev->idx >= nodep->idx) {
+ fprintf(stderr, "Previous node index "
+ ">= current node index,\n"
+ " prev: %p prev->idx: 0x%lx\n"
+ " nodep: %p nodep->idx: 0x%lx",
+ prev, prev->idx, nodep, nodep->idx);
+ error_detected = true;
+ break;
+ }
+
+ /*
+ * Nodes occur in asscending order, based on each
+ * nodes starting index.
+ */
+ if ((prev->idx + MASK_BITS + prev->num_after - 1)
+ >= nodep->idx) {
+ fprintf(stderr, "Previous node bit range "
+ "overlap with current node bit range,\n"
+ " prev: %p prev->idx: 0x%lx "
+ "prev->num_after: 0x%lx\n"
+ " nodep: %p nodep->idx: 0x%lx "
+ "nodep->num_after: 0x%lx\n"
+ " MASK_BITS: %lu",
+ prev, prev->idx, prev->num_after,
+ nodep, nodep->idx, nodep->num_after,
+ MASK_BITS);
+ error_detected = true;
+ break;
+ }
+
+ /*
+ * When the node has all mask bits set, it shouldn't
+ * be adjacent to the last bit described by the
+ * previous node.
+ */
+ if (nodep->mask == ~(mask_t) 0 &&
+ prev->idx + MASK_BITS + prev->num_after == nodep->idx) {
+ fprintf(stderr, "Current node has mask with "
+ "all bits set and is adjacent to the "
+ "previous node,\n"
+ " prev: %p prev->idx: 0x%lx "
+ "prev->num_after: 0x%lx\n"
+ " nodep: %p nodep->idx: 0x%lx "
+ "nodep->num_after: 0x%lx\n"
+ " MASK_BITS: %lu",
+ prev, prev->idx, prev->num_after,
+ nodep, nodep->idx, nodep->num_after,
+ MASK_BITS);
+
+ error_detected = true;
+ break;
+ }
+ }
+ }
+
+ if (!error_detected) {
+ /*
+ * Is sum of bits set in each node equal to the count
+ * of total bits set.
+ */
+ if (s->num_set != total_bits_set) {
+ fprintf(stderr, "Number of bits set missmatch,\n"
+ " s->num_set: 0x%lx total_bits_set: 0x%lx",
+ s->num_set, total_bits_set);
+
+ error_detected = true;
+ }
+ }
+
+ if (error_detected) {
+ fputs(" dump_internal:\n", stderr);
+ sparsebit_dump_internal(stderr, s, 4);
+ abort();
+ }
+}
+
+
+#ifdef FUZZ
+/* A simple but effective fuzzing driver. Look for bugs with the help
+ * of some invariants and of a trivial representation of sparsebit.
+ * Just use 512 bytes of /dev/zero and /dev/urandom as inputs, and let
+ * afl-fuzz do the magic. :)
+ */
+
+#include <stdlib.h>
+#include <assert.h>
+
+struct range {
+ sparsebit_idx_t first, last;
+ bool set;
+};
+
+struct sparsebit *s;
+struct range ranges[1000];
+int num_ranges;
+
+static bool get_value(sparsebit_idx_t idx)
+{
+ int i;
+
+ for (i = num_ranges; --i >= 0; )
+ if (ranges[i].first <= idx && idx <= ranges[i].last)
+ return ranges[i].set;
+
+ return false;
+}
+
+static void operate(int code, sparsebit_idx_t first, sparsebit_idx_t last)
+{
+ sparsebit_num_t num;
+ sparsebit_idx_t next;
+
+ if (first < last) {
+ num = last - first + 1;
+ } else {
+ num = first - last + 1;
+ first = last;
+ last = first + num - 1;
+ }
+
+ switch (code) {
+ case 0:
+ sparsebit_set(s, first);
+ assert(sparsebit_is_set(s, first));
+ assert(!sparsebit_is_clear(s, first));
+ assert(sparsebit_any_set(s));
+ assert(!sparsebit_all_clear(s));
+ if (get_value(first))
+ return;
+ if (num_ranges == 1000)
+ exit(0);
+ ranges[num_ranges++] = (struct range)
+ { .first = first, .last = first, .set = true };
+ break;
+ case 1:
+ sparsebit_clear(s, first);
+ assert(!sparsebit_is_set(s, first));
+ assert(sparsebit_is_clear(s, first));
+ assert(sparsebit_any_clear(s));
+ assert(!sparsebit_all_set(s));
+ if (!get_value(first))
+ return;
+ if (num_ranges == 1000)
+ exit(0);
+ ranges[num_ranges++] = (struct range)
+ { .first = first, .last = first, .set = false };
+ break;
+ case 2:
+ assert(sparsebit_is_set(s, first) == get_value(first));
+ assert(sparsebit_is_clear(s, first) == !get_value(first));
+ break;
+ case 3:
+ if (sparsebit_any_set(s))
+ assert(get_value(sparsebit_first_set(s)));
+ if (sparsebit_any_clear(s))
+ assert(!get_value(sparsebit_first_clear(s)));
+ sparsebit_set_all(s);
+ assert(!sparsebit_any_clear(s));
+ assert(sparsebit_all_set(s));
+ num_ranges = 0;
+ ranges[num_ranges++] = (struct range)
+ { .first = 0, .last = ~(sparsebit_idx_t)0, .set = true };
+ break;
+ case 4:
+ if (sparsebit_any_set(s))
+ assert(get_value(sparsebit_first_set(s)));
+ if (sparsebit_any_clear(s))
+ assert(!get_value(sparsebit_first_clear(s)));
+ sparsebit_clear_all(s);
+ assert(!sparsebit_any_set(s));
+ assert(sparsebit_all_clear(s));
+ num_ranges = 0;
+ break;
+ case 5:
+ next = sparsebit_next_set(s, first);
+ assert(next == 0 || next > first);
+ assert(next == 0 || get_value(next));
+ break;
+ case 6:
+ next = sparsebit_next_clear(s, first);
+ assert(next == 0 || next > first);
+ assert(next == 0 || !get_value(next));
+ break;
+ case 7:
+ next = sparsebit_next_clear(s, first);
+ if (sparsebit_is_set_num(s, first, num)) {
+ assert(next == 0 || next > last);
+ if (first)
+ next = sparsebit_next_set(s, first - 1);
+ else if (sparsebit_any_set(s))
+ next = sparsebit_first_set(s);
+ else
+ return;
+ assert(next == first);
+ } else {
+ assert(sparsebit_is_clear(s, first) || next <= last);
+ }
+ break;
+ case 8:
+ next = sparsebit_next_set(s, first);
+ if (sparsebit_is_clear_num(s, first, num)) {
+ assert(next == 0 || next > last);
+ if (first)
+ next = sparsebit_next_clear(s, first - 1);
+ else if (sparsebit_any_clear(s))
+ next = sparsebit_first_clear(s);
+ else
+ return;
+ assert(next == first);
+ } else {
+ assert(sparsebit_is_set(s, first) || next <= last);
+ }
+ break;
+ case 9:
+ sparsebit_set_num(s, first, num);
+ assert(sparsebit_is_set_num(s, first, num));
+ assert(!sparsebit_is_clear_num(s, first, num));
+ assert(sparsebit_any_set(s));
+ assert(!sparsebit_all_clear(s));
+ if (num_ranges == 1000)
+ exit(0);
+ ranges[num_ranges++] = (struct range)
+ { .first = first, .last = last, .set = true };
+ break;
+ case 10:
+ sparsebit_clear_num(s, first, num);
+ assert(!sparsebit_is_set_num(s, first, num));
+ assert(sparsebit_is_clear_num(s, first, num));
+ assert(sparsebit_any_clear(s));
+ assert(!sparsebit_all_set(s));
+ if (num_ranges == 1000)
+ exit(0);
+ ranges[num_ranges++] = (struct range)
+ { .first = first, .last = last, .set = false };
+ break;
+ case 11:
+ sparsebit_validate_internal(s);
+ break;
+ default:
+ break;
+ }
+}
+
+unsigned char get8(void)
+{
+ int ch;
+
+ ch = getchar();
+ if (ch == EOF)
+ exit(0);
+ return ch;
+}
+
+uint64_t get64(void)
+{
+ uint64_t x;
+
+ x = get8();
+ x = (x << 8) | get8();
+ x = (x << 8) | get8();
+ x = (x << 8) | get8();
+ x = (x << 8) | get8();
+ x = (x << 8) | get8();
+ x = (x << 8) | get8();
+ return (x << 8) | get8();
+}
+
+int main(void)
+{
+ s = sparsebit_alloc();
+ for (;;) {
+ uint8_t op = get8() & 0xf;
+ uint64_t first = get64();
+ uint64_t last = get64();
+
+ operate(op, first, last);
+ }
+}
+#endif
diff --git a/tools/testing/selftests/kvm/lib/vmx.c b/tools/testing/selftests/kvm/lib/vmx.c
new file mode 100644
index 000000000000..0231bc0aae7b
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/vmx.c
@@ -0,0 +1,243 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+/* Create a default VM for VMX tests.
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *
+vm_create_default_vmx(uint32_t vcpuid, vmx_guest_code_t guest_code)
+{
+ struct kvm_cpuid2 *cpuid;
+ struct kvm_vm *vm;
+ vm_vaddr_t vmxon_vaddr;
+ vm_paddr_t vmxon_paddr;
+ vm_vaddr_t vmcs_vaddr;
+ vm_paddr_t vmcs_paddr;
+
+ vm = vm_create_default(vcpuid, (void *) guest_code);
+
+ /* Enable nesting in CPUID */
+ vcpu_set_cpuid(vm, vcpuid, kvm_get_supported_cpuid());
+
+ /* Setup of a region of guest memory for the vmxon region. */
+ vmxon_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+ vmxon_paddr = addr_gva2gpa(vm, vmxon_vaddr);
+
+ /* Setup of a region of guest memory for a vmcs. */
+ vmcs_vaddr = vm_vaddr_alloc(vm, getpagesize(), 0, 0, 0);
+ vmcs_paddr = addr_gva2gpa(vm, vmcs_vaddr);
+
+ vcpu_args_set(vm, vcpuid, 4, vmxon_vaddr, vmxon_paddr, vmcs_vaddr,
+ vmcs_paddr);
+
+ return vm;
+}
+
+void prepare_for_vmx_operation(void)
+{
+ uint64_t feature_control;
+ uint64_t required;
+ unsigned long cr0;
+ unsigned long cr4;
+
+ /*
+ * Ensure bits in CR0 and CR4 are valid in VMX operation:
+ * - Bit X is 1 in _FIXED0: bit X is fixed to 1 in CRx.
+ * - Bit X is 0 in _FIXED1: bit X is fixed to 0 in CRx.
+ */
+ __asm__ __volatile__("mov %%cr0, %0" : "=r"(cr0) : : "memory");
+ cr0 &= rdmsr(MSR_IA32_VMX_CR0_FIXED1);
+ cr0 |= rdmsr(MSR_IA32_VMX_CR0_FIXED0);
+ __asm__ __volatile__("mov %0, %%cr0" : : "r"(cr0) : "memory");
+
+ __asm__ __volatile__("mov %%cr4, %0" : "=r"(cr4) : : "memory");
+ cr4 &= rdmsr(MSR_IA32_VMX_CR4_FIXED1);
+ cr4 |= rdmsr(MSR_IA32_VMX_CR4_FIXED0);
+ /* Enable VMX operation */
+ cr4 |= X86_CR4_VMXE;
+ __asm__ __volatile__("mov %0, %%cr4" : : "r"(cr4) : "memory");
+
+ /*
+ * Configure IA32_FEATURE_CONTROL MSR to allow VMXON:
+ * Bit 0: Lock bit. If clear, VMXON causes a #GP.
+ * Bit 2: Enables VMXON outside of SMX operation. If clear, VMXON
+ * outside of SMX causes a #GP.
+ */
+ required = FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ required |= FEATURE_CONTROL_LOCKED;
+ feature_control = rdmsr(MSR_IA32_FEATURE_CONTROL);
+ if ((feature_control & required) != required)
+ wrmsr(MSR_IA32_FEATURE_CONTROL, feature_control | required);
+}
+
+/*
+ * Initialize the control fields to the most basic settings possible.
+ */
+static inline void init_vmcs_control_fields(void)
+{
+ vmwrite(VIRTUAL_PROCESSOR_ID, 0);
+ vmwrite(POSTED_INTR_NV, 0);
+
+ vmwrite(PIN_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PINBASED_CTLS));
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, rdmsr(MSR_IA32_VMX_PROCBASED_CTLS));
+ vmwrite(EXCEPTION_BITMAP, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MASK, 0);
+ vmwrite(PAGE_FAULT_ERROR_CODE_MATCH, -1); /* Never match */
+ vmwrite(CR3_TARGET_COUNT, 0);
+ vmwrite(VM_EXIT_CONTROLS, rdmsr(MSR_IA32_VMX_EXIT_CTLS) |
+ VM_EXIT_HOST_ADDR_SPACE_SIZE); /* 64-bit host */
+ vmwrite(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmwrite(VM_EXIT_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_CONTROLS, rdmsr(MSR_IA32_VMX_ENTRY_CTLS) |
+ VM_ENTRY_IA32E_MODE); /* 64-bit guest */
+ vmwrite(VM_ENTRY_MSR_LOAD_COUNT, 0);
+ vmwrite(VM_ENTRY_INTR_INFO_FIELD, 0);
+ vmwrite(TPR_THRESHOLD, 0);
+ vmwrite(SECONDARY_VM_EXEC_CONTROL, 0);
+
+ vmwrite(CR0_GUEST_HOST_MASK, 0);
+ vmwrite(CR4_GUEST_HOST_MASK, 0);
+ vmwrite(CR0_READ_SHADOW, get_cr0());
+ vmwrite(CR4_READ_SHADOW, get_cr4());
+}
+
+/*
+ * Initialize the host state fields based on the current host state, with
+ * the exception of HOST_RSP and HOST_RIP, which should be set by vmlaunch
+ * or vmresume.
+ */
+static inline void init_vmcs_host_state(void)
+{
+ uint32_t exit_controls = vmreadz(VM_EXIT_CONTROLS);
+
+ vmwrite(HOST_ES_SELECTOR, get_es());
+ vmwrite(HOST_CS_SELECTOR, get_cs());
+ vmwrite(HOST_SS_SELECTOR, get_ss());
+ vmwrite(HOST_DS_SELECTOR, get_ds());
+ vmwrite(HOST_FS_SELECTOR, get_fs());
+ vmwrite(HOST_GS_SELECTOR, get_gs());
+ vmwrite(HOST_TR_SELECTOR, get_tr());
+
+ if (exit_controls & VM_EXIT_LOAD_IA32_PAT)
+ vmwrite(HOST_IA32_PAT, rdmsr(MSR_IA32_CR_PAT));
+ if (exit_controls & VM_EXIT_LOAD_IA32_EFER)
+ vmwrite(HOST_IA32_EFER, rdmsr(MSR_EFER));
+ if (exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
+ vmwrite(HOST_IA32_PERF_GLOBAL_CTRL,
+ rdmsr(MSR_CORE_PERF_GLOBAL_CTRL));
+
+ vmwrite(HOST_IA32_SYSENTER_CS, rdmsr(MSR_IA32_SYSENTER_CS));
+
+ vmwrite(HOST_CR0, get_cr0());
+ vmwrite(HOST_CR3, get_cr3());
+ vmwrite(HOST_CR4, get_cr4());
+ vmwrite(HOST_FS_BASE, rdmsr(MSR_FS_BASE));
+ vmwrite(HOST_GS_BASE, rdmsr(MSR_GS_BASE));
+ vmwrite(HOST_TR_BASE,
+ get_desc64_base((struct desc64 *)(get_gdt_base() + get_tr())));
+ vmwrite(HOST_GDTR_BASE, get_gdt_base());
+ vmwrite(HOST_IDTR_BASE, get_idt_base());
+ vmwrite(HOST_IA32_SYSENTER_ESP, rdmsr(MSR_IA32_SYSENTER_ESP));
+ vmwrite(HOST_IA32_SYSENTER_EIP, rdmsr(MSR_IA32_SYSENTER_EIP));
+}
+
+/*
+ * Initialize the guest state fields essentially as a clone of
+ * the host state fields. Some host state fields have fixed
+ * values, and we set the corresponding guest state fields accordingly.
+ */
+static inline void init_vmcs_guest_state(void *rip, void *rsp)
+{
+ vmwrite(GUEST_ES_SELECTOR, vmreadz(HOST_ES_SELECTOR));
+ vmwrite(GUEST_CS_SELECTOR, vmreadz(HOST_CS_SELECTOR));
+ vmwrite(GUEST_SS_SELECTOR, vmreadz(HOST_SS_SELECTOR));
+ vmwrite(GUEST_DS_SELECTOR, vmreadz(HOST_DS_SELECTOR));
+ vmwrite(GUEST_FS_SELECTOR, vmreadz(HOST_FS_SELECTOR));
+ vmwrite(GUEST_GS_SELECTOR, vmreadz(HOST_GS_SELECTOR));
+ vmwrite(GUEST_LDTR_SELECTOR, 0);
+ vmwrite(GUEST_TR_SELECTOR, vmreadz(HOST_TR_SELECTOR));
+ vmwrite(GUEST_INTR_STATUS, 0);
+ vmwrite(GUEST_PML_INDEX, 0);
+
+ vmwrite(VMCS_LINK_POINTER, -1ll);
+ vmwrite(GUEST_IA32_DEBUGCTL, 0);
+ vmwrite(GUEST_IA32_PAT, vmreadz(HOST_IA32_PAT));
+ vmwrite(GUEST_IA32_EFER, vmreadz(HOST_IA32_EFER));
+ vmwrite(GUEST_IA32_PERF_GLOBAL_CTRL,
+ vmreadz(HOST_IA32_PERF_GLOBAL_CTRL));
+
+ vmwrite(GUEST_ES_LIMIT, -1);
+ vmwrite(GUEST_CS_LIMIT, -1);
+ vmwrite(GUEST_SS_LIMIT, -1);
+ vmwrite(GUEST_DS_LIMIT, -1);
+ vmwrite(GUEST_FS_LIMIT, -1);
+ vmwrite(GUEST_GS_LIMIT, -1);
+ vmwrite(GUEST_LDTR_LIMIT, -1);
+ vmwrite(GUEST_TR_LIMIT, 0x67);
+ vmwrite(GUEST_GDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_IDTR_LIMIT, 0xffff);
+ vmwrite(GUEST_ES_AR_BYTES,
+ vmreadz(GUEST_ES_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_CS_AR_BYTES, 0xa09b);
+ vmwrite(GUEST_SS_AR_BYTES, 0xc093);
+ vmwrite(GUEST_DS_AR_BYTES,
+ vmreadz(GUEST_DS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_FS_AR_BYTES,
+ vmreadz(GUEST_FS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_GS_AR_BYTES,
+ vmreadz(GUEST_GS_SELECTOR) == 0 ? 0x10000 : 0xc093);
+ vmwrite(GUEST_LDTR_AR_BYTES, 0x10000);
+ vmwrite(GUEST_TR_AR_BYTES, 0x8b);
+ vmwrite(GUEST_INTERRUPTIBILITY_INFO, 0);
+ vmwrite(GUEST_ACTIVITY_STATE, 0);
+ vmwrite(GUEST_SYSENTER_CS, vmreadz(HOST_IA32_SYSENTER_CS));
+ vmwrite(VMX_PREEMPTION_TIMER_VALUE, 0);
+
+ vmwrite(GUEST_CR0, vmreadz(HOST_CR0));
+ vmwrite(GUEST_CR3, vmreadz(HOST_CR3));
+ vmwrite(GUEST_CR4, vmreadz(HOST_CR4));
+ vmwrite(GUEST_ES_BASE, 0);
+ vmwrite(GUEST_CS_BASE, 0);
+ vmwrite(GUEST_SS_BASE, 0);
+ vmwrite(GUEST_DS_BASE, 0);
+ vmwrite(GUEST_FS_BASE, vmreadz(HOST_FS_BASE));
+ vmwrite(GUEST_GS_BASE, vmreadz(HOST_GS_BASE));
+ vmwrite(GUEST_LDTR_BASE, 0);
+ vmwrite(GUEST_TR_BASE, vmreadz(HOST_TR_BASE));
+ vmwrite(GUEST_GDTR_BASE, vmreadz(HOST_GDTR_BASE));
+ vmwrite(GUEST_IDTR_BASE, vmreadz(HOST_IDTR_BASE));
+ vmwrite(GUEST_DR7, 0x400);
+ vmwrite(GUEST_RSP, (uint64_t)rsp);
+ vmwrite(GUEST_RIP, (uint64_t)rip);
+ vmwrite(GUEST_RFLAGS, 2);
+ vmwrite(GUEST_PENDING_DBG_EXCEPTIONS, 0);
+ vmwrite(GUEST_SYSENTER_ESP, vmreadz(HOST_IA32_SYSENTER_ESP));
+ vmwrite(GUEST_SYSENTER_EIP, vmreadz(HOST_IA32_SYSENTER_EIP));
+}
+
+void prepare_vmcs(void *guest_rip, void *guest_rsp)
+{
+ init_vmcs_control_fields();
+ init_vmcs_host_state();
+ init_vmcs_guest_state(guest_rip, guest_rsp);
+}
diff --git a/tools/testing/selftests/kvm/lib/x86.c b/tools/testing/selftests/kvm/lib/x86.c
new file mode 100644
index 000000000000..2f17675f4275
--- /dev/null
+++ b/tools/testing/selftests/kvm/lib/x86.c
@@ -0,0 +1,700 @@
+/*
+ * tools/testing/selftests/kvm/lib/x86.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_name */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "kvm_util_internal.h"
+#include "x86.h"
+
+/* Minimum physical address used for virtual translation tables. */
+#define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
+
+/* Virtual translation table structure declarations */
+struct pageMapL4Entry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t ignored_06:1;
+ uint64_t page_size:1;
+ uint64_t ignored_11_08:4;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+struct pageDirectoryPointerEntry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t ignored_06:1;
+ uint64_t page_size:1;
+ uint64_t ignored_11_08:4;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+struct pageDirectoryEntry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t ignored_06:1;
+ uint64_t page_size:1;
+ uint64_t ignored_11_08:4;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+struct pageTableEntry {
+ uint64_t present:1;
+ uint64_t writable:1;
+ uint64_t user:1;
+ uint64_t write_through:1;
+ uint64_t cache_disable:1;
+ uint64_t accessed:1;
+ uint64_t dirty:1;
+ uint64_t reserved_07:1;
+ uint64_t global:1;
+ uint64_t ignored_11_09:3;
+ uint64_t address:40;
+ uint64_t ignored_62_52:11;
+ uint64_t execute_disable:1;
+};
+
+/* Register Dump
+ *
+ * Input Args:
+ * indent - Left margin indent amount
+ * regs - register
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the registers given by regs, to the FILE stream
+ * given by steam.
+ */
+void regs_dump(FILE *stream, struct kvm_regs *regs,
+ uint8_t indent)
+{
+ fprintf(stream, "%*srax: 0x%.16llx rbx: 0x%.16llx "
+ "rcx: 0x%.16llx rdx: 0x%.16llx\n",
+ indent, "",
+ regs->rax, regs->rbx, regs->rcx, regs->rdx);
+ fprintf(stream, "%*srsi: 0x%.16llx rdi: 0x%.16llx "
+ "rsp: 0x%.16llx rbp: 0x%.16llx\n",
+ indent, "",
+ regs->rsi, regs->rdi, regs->rsp, regs->rbp);
+ fprintf(stream, "%*sr8: 0x%.16llx r9: 0x%.16llx "
+ "r10: 0x%.16llx r11: 0x%.16llx\n",
+ indent, "",
+ regs->r8, regs->r9, regs->r10, regs->r11);
+ fprintf(stream, "%*sr12: 0x%.16llx r13: 0x%.16llx "
+ "r14: 0x%.16llx r15: 0x%.16llx\n",
+ indent, "",
+ regs->r12, regs->r13, regs->r14, regs->r15);
+ fprintf(stream, "%*srip: 0x%.16llx rfl: 0x%.16llx\n",
+ indent, "",
+ regs->rip, regs->rflags);
+}
+
+/* Segment Dump
+ *
+ * Input Args:
+ * indent - Left margin indent amount
+ * segment - KVM segment
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM segment given by segment, to the FILE stream
+ * given by steam.
+ */
+static void segment_dump(FILE *stream, struct kvm_segment *segment,
+ uint8_t indent)
+{
+ fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.8x "
+ "selector: 0x%.4x type: 0x%.2x\n",
+ indent, "", segment->base, segment->limit,
+ segment->selector, segment->type);
+ fprintf(stream, "%*spresent: 0x%.2x dpl: 0x%.2x "
+ "db: 0x%.2x s: 0x%.2x l: 0x%.2x\n",
+ indent, "", segment->present, segment->dpl,
+ segment->db, segment->s, segment->l);
+ fprintf(stream, "%*sg: 0x%.2x avl: 0x%.2x "
+ "unusable: 0x%.2x padding: 0x%.2x\n",
+ indent, "", segment->g, segment->avl,
+ segment->unusable, segment->padding);
+}
+
+/* dtable Dump
+ *
+ * Input Args:
+ * indent - Left margin indent amount
+ * dtable - KVM dtable
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the KVM dtable given by dtable, to the FILE stream
+ * given by steam.
+ */
+static void dtable_dump(FILE *stream, struct kvm_dtable *dtable,
+ uint8_t indent)
+{
+ fprintf(stream, "%*sbase: 0x%.16llx limit: 0x%.4x "
+ "padding: 0x%.4x 0x%.4x 0x%.4x\n",
+ indent, "", dtable->base, dtable->limit,
+ dtable->padding[0], dtable->padding[1], dtable->padding[2]);
+}
+
+/* System Register Dump
+ *
+ * Input Args:
+ * indent - Left margin indent amount
+ * sregs - System registers
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps the state of the system registers given by sregs, to the FILE stream
+ * given by steam.
+ */
+void sregs_dump(FILE *stream, struct kvm_sregs *sregs,
+ uint8_t indent)
+{
+ unsigned int i;
+
+ fprintf(stream, "%*scs:\n", indent, "");
+ segment_dump(stream, &sregs->cs, indent + 2);
+ fprintf(stream, "%*sds:\n", indent, "");
+ segment_dump(stream, &sregs->ds, indent + 2);
+ fprintf(stream, "%*ses:\n", indent, "");
+ segment_dump(stream, &sregs->es, indent + 2);
+ fprintf(stream, "%*sfs:\n", indent, "");
+ segment_dump(stream, &sregs->fs, indent + 2);
+ fprintf(stream, "%*sgs:\n", indent, "");
+ segment_dump(stream, &sregs->gs, indent + 2);
+ fprintf(stream, "%*sss:\n", indent, "");
+ segment_dump(stream, &sregs->ss, indent + 2);
+ fprintf(stream, "%*str:\n", indent, "");
+ segment_dump(stream, &sregs->tr, indent + 2);
+ fprintf(stream, "%*sldt:\n", indent, "");
+ segment_dump(stream, &sregs->ldt, indent + 2);
+
+ fprintf(stream, "%*sgdt:\n", indent, "");
+ dtable_dump(stream, &sregs->gdt, indent + 2);
+ fprintf(stream, "%*sidt:\n", indent, "");
+ dtable_dump(stream, &sregs->idt, indent + 2);
+
+ fprintf(stream, "%*scr0: 0x%.16llx cr2: 0x%.16llx "
+ "cr3: 0x%.16llx cr4: 0x%.16llx\n",
+ indent, "",
+ sregs->cr0, sregs->cr2, sregs->cr3, sregs->cr4);
+ fprintf(stream, "%*scr8: 0x%.16llx efer: 0x%.16llx "
+ "apic_base: 0x%.16llx\n",
+ indent, "",
+ sregs->cr8, sregs->efer, sregs->apic_base);
+
+ fprintf(stream, "%*sinterrupt_bitmap:\n", indent, "");
+ for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++) {
+ fprintf(stream, "%*s%.16llx\n", indent + 2, "",
+ sregs->interrupt_bitmap[i]);
+ }
+}
+
+void virt_pgd_alloc(struct kvm_vm *vm, uint32_t pgd_memslot)
+{
+ int rc;
+
+ TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ /* If needed, create page map l4 table. */
+ if (!vm->pgd_created) {
+ vm_paddr_t paddr = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot);
+ vm->pgd = paddr;
+
+ /* Set pointer to pgd tables in all the VCPUs that
+ * have already been created. Future VCPUs will have
+ * the value set as each one is created.
+ */
+ for (struct vcpu *vcpu = vm->vcpu_head; vcpu;
+ vcpu = vcpu->next) {
+ struct kvm_sregs sregs;
+
+ /* Obtain the current system register settings */
+ vcpu_sregs_get(vm, vcpu->id, &sregs);
+
+ /* Set and store the pointer to the start of the
+ * pgd tables.
+ */
+ sregs.cr3 = vm->pgd;
+ vcpu_sregs_set(vm, vcpu->id, &sregs);
+ }
+
+ vm->pgd_created = true;
+ }
+}
+
+/* VM Virtual Page Map
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vaddr - VM Virtual Address
+ * paddr - VM Physical Address
+ * pgd_memslot - Memory region slot for new virtual translation tables
+ *
+ * Output Args: None
+ *
+ * Return: None
+ *
+ * Within the VM given by vm, creates a virtual translation for the page
+ * starting at vaddr to the page starting at paddr.
+ */
+void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
+ uint32_t pgd_memslot)
+{
+ uint16_t index[4];
+ struct pageMapL4Entry *pml4e;
+
+ TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ TEST_ASSERT((vaddr % vm->page_size) == 0,
+ "Virtual address not on page boundary,\n"
+ " vaddr: 0x%lx vm->page_size: 0x%x",
+ vaddr, vm->page_size);
+ TEST_ASSERT(sparsebit_is_set(vm->vpages_valid,
+ (vaddr >> vm->page_shift)),
+ "Invalid virtual address, vaddr: 0x%lx",
+ vaddr);
+ TEST_ASSERT((paddr % vm->page_size) == 0,
+ "Physical address not on page boundary,\n"
+ " paddr: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->page_size);
+ TEST_ASSERT((paddr >> vm->page_shift) <= vm->max_gfn,
+ "Physical address beyond beyond maximum supported,\n"
+ " paddr: 0x%lx vm->max_gfn: 0x%lx vm->page_size: 0x%x",
+ paddr, vm->max_gfn, vm->page_size);
+
+ index[0] = (vaddr >> 12) & 0x1ffu;
+ index[1] = (vaddr >> 21) & 0x1ffu;
+ index[2] = (vaddr >> 30) & 0x1ffu;
+ index[3] = (vaddr >> 39) & 0x1ffu;
+
+ /* Allocate page directory pointer table if not present. */
+ pml4e = addr_gpa2hva(vm, vm->pgd);
+ if (!pml4e[index[3]].present) {
+ pml4e[index[3]].address = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+ >> vm->page_shift;
+ pml4e[index[3]].writable = true;
+ pml4e[index[3]].present = true;
+ }
+
+ /* Allocate page directory table if not present. */
+ struct pageDirectoryPointerEntry *pdpe;
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ if (!pdpe[index[2]].present) {
+ pdpe[index[2]].address = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+ >> vm->page_shift;
+ pdpe[index[2]].writable = true;
+ pdpe[index[2]].present = true;
+ }
+
+ /* Allocate page table if not present. */
+ struct pageDirectoryEntry *pde;
+ pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ if (!pde[index[1]].present) {
+ pde[index[1]].address = vm_phy_page_alloc(vm,
+ KVM_GUEST_PAGE_TABLE_MIN_PADDR, pgd_memslot)
+ >> vm->page_shift;
+ pde[index[1]].writable = true;
+ pde[index[1]].present = true;
+ }
+
+ /* Fill in page table entry. */
+ struct pageTableEntry *pte;
+ pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ pte[index[0]].address = paddr >> vm->page_shift;
+ pte[index[0]].writable = true;
+ pte[index[0]].present = 1;
+}
+
+/* Virtual Translation Tables Dump
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * indent - Left margin indent amount
+ *
+ * Output Args:
+ * stream - Output FILE stream
+ *
+ * Return: None
+ *
+ * Dumps to the FILE stream given by stream, the contents of all the
+ * virtual translation tables for the VM given by vm.
+ */
+void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
+{
+ struct pageMapL4Entry *pml4e, *pml4e_start;
+ struct pageDirectoryPointerEntry *pdpe, *pdpe_start;
+ struct pageDirectoryEntry *pde, *pde_start;
+ struct pageTableEntry *pte, *pte_start;
+
+ if (!vm->pgd_created)
+ return;
+
+ fprintf(stream, "%*s "
+ " no\n", indent, "");
+ fprintf(stream, "%*s index hvaddr gpaddr "
+ "addr w exec dirty\n",
+ indent, "");
+ pml4e_start = (struct pageMapL4Entry *) addr_gpa2hva(vm,
+ vm->pgd);
+ for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
+ pml4e = &pml4e_start[n1];
+ if (!pml4e->present)
+ continue;
+ fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+ " %u\n",
+ indent, "",
+ pml4e - pml4e_start, pml4e,
+ addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->address,
+ pml4e->writable, pml4e->execute_disable);
+
+ pdpe_start = addr_gpa2hva(vm, pml4e->address
+ * vm->page_size);
+ for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
+ pdpe = &pdpe_start[n2];
+ if (!pdpe->present)
+ continue;
+ fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10lx "
+ "%u %u\n",
+ indent, "",
+ pdpe - pdpe_start, pdpe,
+ addr_hva2gpa(vm, pdpe),
+ (uint64_t) pdpe->address, pdpe->writable,
+ pdpe->execute_disable);
+
+ pde_start = addr_gpa2hva(vm,
+ pdpe->address * vm->page_size);
+ for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
+ pde = &pde_start[n3];
+ if (!pde->present)
+ continue;
+ fprintf(stream, "%*spde 0x%-3zx %p "
+ "0x%-12lx 0x%-10lx %u %u\n",
+ indent, "", pde - pde_start, pde,
+ addr_hva2gpa(vm, pde),
+ (uint64_t) pde->address, pde->writable,
+ pde->execute_disable);
+
+ pte_start = addr_gpa2hva(vm,
+ pde->address * vm->page_size);
+ for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
+ pte = &pte_start[n4];
+ if (!pte->present)
+ continue;
+ fprintf(stream, "%*spte 0x%-3zx %p "
+ "0x%-12lx 0x%-10lx %u %u "
+ " %u 0x%-10lx\n",
+ indent, "",
+ pte - pte_start, pte,
+ addr_hva2gpa(vm, pte),
+ (uint64_t) pte->address,
+ pte->writable,
+ pte->execute_disable,
+ pte->dirty,
+ ((uint64_t) n1 << 27)
+ | ((uint64_t) n2 << 18)
+ | ((uint64_t) n3 << 9)
+ | ((uint64_t) n4));
+ }
+ }
+ }
+ }
+}
+
+/* Set Unusable Segment
+ *
+ * Input Args: None
+ *
+ * Output Args:
+ * segp - Pointer to segment register
+ *
+ * Return: None
+ *
+ * Sets the segment register pointed to by segp to an unusable state.
+ */
+static void kvm_seg_set_unusable(struct kvm_segment *segp)
+{
+ memset(segp, 0, sizeof(*segp));
+ segp->unusable = true;
+}
+
+/* Set Long Mode Flat Kernel Code Segment
+ *
+ * Input Args:
+ * selector - selector value
+ *
+ * Output Args:
+ * segp - Pointer to KVM segment
+ *
+ * Return: None
+ *
+ * Sets up the KVM segment pointed to by segp, to be a code segment
+ * with the selector value given by selector.
+ */
+static void kvm_seg_set_kernel_code_64bit(uint16_t selector,
+ struct kvm_segment *segp)
+{
+ memset(segp, 0, sizeof(*segp));
+ segp->selector = selector;
+ segp->limit = 0xFFFFFFFFu;
+ segp->s = 0x1; /* kTypeCodeData */
+ segp->type = 0x08 | 0x01 | 0x02; /* kFlagCode | kFlagCodeAccessed
+ * | kFlagCodeReadable
+ */
+ segp->g = true;
+ segp->l = true;
+ segp->present = 1;
+}
+
+/* Set Long Mode Flat Kernel Data Segment
+ *
+ * Input Args:
+ * selector - selector value
+ *
+ * Output Args:
+ * segp - Pointer to KVM segment
+ *
+ * Return: None
+ *
+ * Sets up the KVM segment pointed to by segp, to be a data segment
+ * with the selector value given by selector.
+ */
+static void kvm_seg_set_kernel_data_64bit(uint16_t selector,
+ struct kvm_segment *segp)
+{
+ memset(segp, 0, sizeof(*segp));
+ segp->selector = selector;
+ segp->limit = 0xFFFFFFFFu;
+ segp->s = 0x1; /* kTypeCodeData */
+ segp->type = 0x00 | 0x01 | 0x02; /* kFlagData | kFlagDataAccessed
+ * | kFlagDataWritable
+ */
+ segp->g = true;
+ segp->present = true;
+}
+
+/* Address Guest Virtual to Guest Physical
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * gpa - VM virtual address
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Equivalent VM physical address
+ *
+ * Translates the VM virtual address given by gva to a VM physical
+ * address and then locates the memory region containing the VM
+ * physical address, within the VM given by vm. When found, the host
+ * virtual address providing the memory to the vm physical address is returned.
+ * A TEST_ASSERT failure occurs if no region containing translated
+ * VM virtual address exists.
+ */
+vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
+{
+ uint16_t index[4];
+ struct pageMapL4Entry *pml4e;
+ struct pageDirectoryPointerEntry *pdpe;
+ struct pageDirectoryEntry *pde;
+ struct pageTableEntry *pte;
+ void *hva;
+
+ TEST_ASSERT(vm->mode == VM_MODE_FLAT48PG, "Attempt to use "
+ "unknown or unsupported guest mode, mode: 0x%x", vm->mode);
+
+ index[0] = (gva >> 12) & 0x1ffu;
+ index[1] = (gva >> 21) & 0x1ffu;
+ index[2] = (gva >> 30) & 0x1ffu;
+ index[3] = (gva >> 39) & 0x1ffu;
+
+ if (!vm->pgd_created)
+ goto unmapped_gva;
+ pml4e = addr_gpa2hva(vm, vm->pgd);
+ if (!pml4e[index[3]].present)
+ goto unmapped_gva;
+
+ pdpe = addr_gpa2hva(vm, pml4e[index[3]].address * vm->page_size);
+ if (!pdpe[index[2]].present)
+ goto unmapped_gva;
+
+ pde = addr_gpa2hva(vm, pdpe[index[2]].address * vm->page_size);
+ if (!pde[index[1]].present)
+ goto unmapped_gva;
+
+ pte = addr_gpa2hva(vm, pde[index[1]].address * vm->page_size);
+ if (!pte[index[0]].present)
+ goto unmapped_gva;
+
+ return (pte[index[0]].address * vm->page_size) + (gva & 0xfffu);
+
+unmapped_gva:
+ TEST_ASSERT(false, "No mapping for vm virtual address, "
+ "gva: 0x%lx", gva);
+}
+
+void vcpu_setup(struct kvm_vm *vm, int vcpuid)
+{
+ struct kvm_sregs sregs;
+
+ /* Set mode specific system register values. */
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+
+ switch (vm->mode) {
+ case VM_MODE_FLAT48PG:
+ sregs.cr0 = X86_CR0_PE | X86_CR0_NE | X86_CR0_PG;
+ sregs.cr4 |= X86_CR4_PAE;
+ sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
+
+ kvm_seg_set_unusable(&sregs.ldt);
+ kvm_seg_set_kernel_code_64bit(0x8, &sregs.cs);
+ kvm_seg_set_kernel_data_64bit(0x10, &sregs.ds);
+ kvm_seg_set_kernel_data_64bit(0x10, &sregs.es);
+ break;
+
+ default:
+ TEST_ASSERT(false, "Unknown guest mode, mode: 0x%x", vm->mode);
+ }
+ vcpu_sregs_set(vm, vcpuid, &sregs);
+
+ /* If virtual translation table have been setup, set system register
+ * to point to the tables. It's okay if they haven't been setup yet,
+ * in that the code that sets up the virtual translation tables, will
+ * go back through any VCPUs that have already been created and set
+ * their values.
+ */
+ if (vm->pgd_created) {
+ struct kvm_sregs sregs;
+
+ vcpu_sregs_get(vm, vcpuid, &sregs);
+
+ sregs.cr3 = vm->pgd;
+ vcpu_sregs_set(vm, vcpuid, &sregs);
+ }
+}
+/* Adds a vCPU with reasonable defaults (i.e., a stack)
+ *
+ * Input Args:
+ * vcpuid - The id of the VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ */
+void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code)
+{
+ struct kvm_mp_state mp_state;
+ struct kvm_regs regs;
+ vm_vaddr_t stack_vaddr;
+ stack_vaddr = vm_vaddr_alloc(vm, DEFAULT_STACK_PGS * getpagesize(),
+ DEFAULT_GUEST_STACK_VADDR_MIN, 0, 0);
+
+ /* Create VCPU */
+ vm_vcpu_add(vm, vcpuid);
+
+ /* Setup guest general purpose registers */
+ vcpu_regs_get(vm, vcpuid, &regs);
+ regs.rflags = regs.rflags | 0x2;
+ regs.rsp = stack_vaddr + (DEFAULT_STACK_PGS * getpagesize());
+ regs.rip = (unsigned long) guest_code;
+ vcpu_regs_set(vm, vcpuid, &regs);
+
+ /* Setup the MP state */
+ mp_state.mp_state = 0;
+ vcpu_set_mp_state(vm, vcpuid, &mp_state);
+}
+
+/* VM VCPU CPUID Set
+ *
+ * Input Args:
+ * vm - Virtual Machine
+ * vcpuid - VCPU id
+ * cpuid - The CPUID values to set.
+ *
+ * Output Args: None
+ *
+ * Return: void
+ *
+ * Set the VCPU's CPUID.
+ */
+void vcpu_set_cpuid(struct kvm_vm *vm,
+ uint32_t vcpuid, struct kvm_cpuid2 *cpuid)
+{
+ struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+ int rc;
+
+ TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+ rc = ioctl(vcpu->fd, KVM_SET_CPUID2, cpuid);
+ TEST_ASSERT(rc == 0, "KVM_SET_CPUID2 failed, rc: %i errno: %i",
+ rc, errno);
+
+}
+/* Create a VM with reasonable defaults
+ *
+ * Input Args:
+ * vcpuid - The id of the single VCPU to add to the VM.
+ * guest_code - The vCPU's entry point
+ *
+ * Output Args: None
+ *
+ * Return:
+ * Pointer to opaque structure that describes the created VM.
+ */
+struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code)
+{
+ struct kvm_vm *vm;
+
+ /* Create VM */
+ vm = vm_create(VM_MODE_FLAT48PG, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+ /* Setup guest code */
+ kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+
+ /* Setup IRQ Chip */
+ vm_create_irqchip(vm);
+
+ /* Add the first vCPU. */
+ vm_vcpu_add_default(vm, vcpuid, guest_code);
+
+ return vm;
+}
diff --git a/tools/testing/selftests/kvm/set_sregs_test.c b/tools/testing/selftests/kvm/set_sregs_test.c
new file mode 100644
index 000000000000..090fd3f19352
--- /dev/null
+++ b/tools/testing/selftests/kvm/set_sregs_test.c
@@ -0,0 +1,54 @@
+/*
+ * KVM_SET_SREGS tests
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * This is a regression test for the bug fixed by the following commit:
+ * d3802286fa0f ("kvm: x86: Disallow illegal IA32_APIC_BASE MSR values")
+ *
+ * That bug allowed a user-mode program that called the KVM_SET_SREGS
+ * ioctl to put a VCPU's local APIC into an invalid state.
+ *
+ */
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+
+#include "kvm_util.h"
+#include "x86.h"
+
+#define VCPU_ID 5
+
+int main(int argc, char *argv[])
+{
+ struct kvm_sregs sregs;
+ struct kvm_vm *vm;
+ int rc;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, NULL);
+
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ sregs.apic_base = 1 << 10;
+ rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+ TEST_ASSERT(rc, "Set IA32_APIC_BASE to %llx (invalid)",
+ sregs.apic_base);
+ sregs.apic_base = 1 << 11;
+ rc = _vcpu_sregs_set(vm, VCPU_ID, &sregs);
+ TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)",
+ sregs.apic_base);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/sync_regs_test.c b/tools/testing/selftests/kvm/sync_regs_test.c
new file mode 100644
index 000000000000..eae1ece3c31b
--- /dev/null
+++ b/tools/testing/selftests/kvm/sync_regs_test.c
@@ -0,0 +1,254 @@
+/*
+ * Test for x86 KVM_CAP_SYNC_REGS
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Verifies expected behavior of x86 KVM_CAP_SYNC_REGS functionality,
+ * including requesting an invalid register set, updates to/from values
+ * in kvm_run.s.regs when kvm_valid_regs and kvm_dirty_regs are toggled.
+ */
+
+#define _GNU_SOURCE /* for program_invocation_short_name */
+#include <fcntl.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+
+#define VCPU_ID 5
+#define PORT_HOST_SYNC 0x1000
+
+static void __exit_to_l0(uint16_t port, uint64_t arg0, uint64_t arg1)
+{
+ __asm__ __volatile__("in %[port], %%al"
+ :
+ : [port]"d"(port), "D"(arg0), "S"(arg1)
+ : "rax");
+}
+
+#define exit_to_l0(_port, _arg0, _arg1) \
+ __exit_to_l0(_port, (uint64_t) (_arg0), (uint64_t) (_arg1))
+
+#define GUEST_ASSERT(_condition) do { \
+ if (!(_condition)) \
+ exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition, 0);\
+} while (0)
+
+void guest_code(void)
+{
+ for (;;) {
+ exit_to_l0(PORT_HOST_SYNC, "hello", 0);
+ asm volatile ("inc %r11");
+ }
+}
+
+static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)
+{
+#define REG_COMPARE(reg) \
+ TEST_ASSERT(left->reg == right->reg, \
+ "Register " #reg \
+ " values did not match: 0x%llx, 0x%llx\n", \
+ left->reg, right->reg)
+ REG_COMPARE(rax);
+ REG_COMPARE(rbx);
+ REG_COMPARE(rcx);
+ REG_COMPARE(rdx);
+ REG_COMPARE(rsi);
+ REG_COMPARE(rdi);
+ REG_COMPARE(rsp);
+ REG_COMPARE(rbp);
+ REG_COMPARE(r8);
+ REG_COMPARE(r9);
+ REG_COMPARE(r10);
+ REG_COMPARE(r11);
+ REG_COMPARE(r12);
+ REG_COMPARE(r13);
+ REG_COMPARE(r14);
+ REG_COMPARE(r15);
+ REG_COMPARE(rip);
+ REG_COMPARE(rflags);
+#undef REG_COMPARE
+}
+
+static void compare_sregs(struct kvm_sregs *left, struct kvm_sregs *right)
+{
+}
+
+static void compare_vcpu_events(struct kvm_vcpu_events *left,
+ struct kvm_vcpu_events *right)
+{
+}
+
+#define TEST_SYNC_FIELDS (KVM_SYNC_X86_REGS|KVM_SYNC_X86_SREGS|KVM_SYNC_X86_EVENTS)
+#define INVALID_SYNC_FIELD 0x80000000
+
+int main(int argc, char *argv[])
+{
+ struct kvm_vm *vm;
+ struct kvm_run *run;
+ struct kvm_regs regs;
+ struct kvm_sregs sregs;
+ struct kvm_vcpu_events events;
+ int rv, cap;
+
+ /* Tell stdout not to buffer its content */
+ setbuf(stdout, NULL);
+
+ cap = kvm_check_cap(KVM_CAP_SYNC_REGS);
+ if ((cap & TEST_SYNC_FIELDS) != TEST_SYNC_FIELDS) {
+ fprintf(stderr, "KVM_CAP_SYNC_REGS not supported, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+ if ((cap & INVALID_SYNC_FIELD) != 0) {
+ fprintf(stderr, "The \"invalid\" field is not invalid, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+
+ /* Create VM */
+ vm = vm_create_default(VCPU_ID, guest_code);
+
+ run = vcpu_state(vm, VCPU_ID);
+
+ /* Request reading invalid register set from VCPU. */
+ run->kvm_valid_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+ run->kvm_valid_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_valid_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_valid_regs = 0;
+
+ /* Request setting invalid register set into VCPU. */
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+ run->kvm_dirty_regs = INVALID_SYNC_FIELD | TEST_SYNC_FIELDS;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(rv < 0 && errno == EINVAL,
+ "Invalid kvm_dirty_regs did not cause expected KVM_RUN error: %d\n",
+ rv);
+ vcpu_state(vm, VCPU_ID)->kvm_dirty_regs = 0;
+
+ /* Request and verify all valid register sets. */
+ /* TODO: BUILD TIME CHECK: TEST_ASSERT(KVM_SYNC_X86_NUM_FIELDS != 3); */
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+ compare_regs(&regs, &run->s.regs.regs);
+
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ compare_sregs(&sregs, &run->s.regs.sregs);
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+ compare_vcpu_events(&events, &run->s.regs.events);
+
+ /* Set and verify various register values. */
+ run->s.regs.regs.r11 = 0xBAD1DEA;
+ run->s.regs.sregs.apic_base = 1 << 11;
+ /* TODO run->s.regs.events.XYZ = ABC; */
+
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
+ run->kvm_dirty_regs = KVM_SYNC_X86_REGS | KVM_SYNC_X86_SREGS;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->s.regs.regs.r11 == 0xBAD1DEA + 1,
+ "r11 sync regs value incorrect 0x%llx.",
+ run->s.regs.regs.r11);
+ TEST_ASSERT(run->s.regs.sregs.apic_base == 1 << 11,
+ "apic_base sync regs value incorrect 0x%llx.",
+ run->s.regs.sregs.apic_base);
+
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+ compare_regs(&regs, &run->s.regs.regs);
+
+ vcpu_sregs_get(vm, VCPU_ID, &sregs);
+ compare_sregs(&sregs, &run->s.regs.sregs);
+
+ vcpu_events_get(vm, VCPU_ID, &events);
+ compare_vcpu_events(&events, &run->s.regs.events);
+
+ /* Clear kvm_dirty_regs bits, verify new s.regs values are
+ * overwritten with existing guest values.
+ */
+ run->kvm_valid_regs = TEST_SYNC_FIELDS;
+ run->kvm_dirty_regs = 0;
+ run->s.regs.regs.r11 = 0xDEADBEEF;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->s.regs.regs.r11 != 0xDEADBEEF,
+ "r11 sync regs value incorrect 0x%llx.",
+ run->s.regs.regs.r11);
+
+ /* Clear kvm_valid_regs bits and kvm_dirty_bits.
+ * Verify s.regs values are not overwritten with existing guest values
+ * and that guest values are not overwritten with kvm_sync_regs values.
+ */
+ run->kvm_valid_regs = 0;
+ run->kvm_dirty_regs = 0;
+ run->s.regs.regs.r11 = 0xAAAA;
+ regs.r11 = 0xBAC0;
+ vcpu_regs_set(vm, VCPU_ID, &regs);
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->s.regs.regs.r11 == 0xAAAA,
+ "r11 sync regs value incorrect 0x%llx.",
+ run->s.regs.regs.r11);
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+ TEST_ASSERT(regs.r11 == 0xBAC0 + 1,
+ "r11 guest value incorrect 0x%llx.",
+ regs.r11);
+
+ /* Clear kvm_valid_regs bits. Verify s.regs values are not overwritten
+ * with existing guest values but that guest values are overwritten
+ * with kvm_sync_regs values.
+ */
+ run->kvm_valid_regs = 0;
+ run->kvm_dirty_regs = TEST_SYNC_FIELDS;
+ run->s.regs.regs.r11 = 0xBBBB;
+ rv = _vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Unexpected exit reason: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+ TEST_ASSERT(run->s.regs.regs.r11 == 0xBBBB,
+ "r11 sync regs value incorrect 0x%llx.",
+ run->s.regs.regs.r11);
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+ TEST_ASSERT(regs.r11 == 0xBBBB + 1,
+ "r11 guest value incorrect 0x%llx.",
+ regs.r11);
+
+ kvm_vm_free(vm);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
new file mode 100644
index 000000000000..d7cb7944a42e
--- /dev/null
+++ b/tools/testing/selftests/kvm/vmx_tsc_adjust_test.c
@@ -0,0 +1,233 @@
+/*
+ * gtests/tests/vmx_tsc_adjust_test.c
+ *
+ * Copyright (C) 2018, Google LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ *
+ * IA32_TSC_ADJUST test
+ *
+ * According to the SDM, "if an execution of WRMSR to the
+ * IA32_TIME_STAMP_COUNTER MSR adds (or subtracts) value X from the TSC,
+ * the logical processor also adds (or subtracts) value X from the
+ * IA32_TSC_ADJUST MSR.
+ *
+ * Note that when L1 doesn't intercept writes to IA32_TSC, a
+ * WRMSR(IA32_TSC) from L2 sets L1's TSC value, not L2's perceived TSC
+ * value.
+ *
+ * This test verifies that this unusual case is handled correctly.
+ */
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "x86.h"
+#include "vmx.h"
+
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "../kselftest.h"
+
+#ifndef MSR_IA32_TSC_ADJUST
+#define MSR_IA32_TSC_ADJUST 0x3b
+#endif
+
+#define PAGE_SIZE 4096
+#define VCPU_ID 5
+
+#define TSC_ADJUST_VALUE (1ll << 32)
+#define TSC_OFFSET_VALUE -(1ll << 48)
+
+enum {
+ PORT_ABORT = 0x1000,
+ PORT_REPORT,
+ PORT_DONE,
+};
+
+struct vmx_page {
+ vm_vaddr_t virt;
+ vm_paddr_t phys;
+};
+
+enum {
+ VMXON_PAGE = 0,
+ VMCS_PAGE,
+ MSR_BITMAP_PAGE,
+
+ NUM_VMX_PAGES,
+};
+
+struct kvm_single_msr {
+ struct kvm_msrs header;
+ struct kvm_msr_entry entry;
+} __attribute__((packed));
+
+/* The virtual machine object. */
+static struct kvm_vm *vm;
+
+/* Array of vmx_page descriptors that is shared with the guest. */
+struct vmx_page *vmx_pages;
+
+#define exit_to_l0(_port, _arg) do_exit_to_l0(_port, (unsigned long) (_arg))
+static void do_exit_to_l0(uint16_t port, unsigned long arg)
+{
+ __asm__ __volatile__("in %[port], %%al"
+ :
+ : [port]"d"(port), "D"(arg)
+ : "rax");
+}
+
+
+#define GUEST_ASSERT(_condition) do { \
+ if (!(_condition)) \
+ exit_to_l0(PORT_ABORT, "Failed guest assert: " #_condition); \
+} while (0)
+
+static void check_ia32_tsc_adjust(int64_t max)
+{
+ int64_t adjust;
+
+ adjust = rdmsr(MSR_IA32_TSC_ADJUST);
+ exit_to_l0(PORT_REPORT, adjust);
+ GUEST_ASSERT(adjust <= max);
+}
+
+static void l2_guest_code(void)
+{
+ uint64_t l1_tsc = rdtsc() - TSC_OFFSET_VALUE;
+
+ wrmsr(MSR_IA32_TSC, l1_tsc - TSC_ADJUST_VALUE);
+ check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+ /* Exit to L1 */
+ __asm__ __volatile__("vmcall");
+}
+
+static void l1_guest_code(struct vmx_page *vmx_pages)
+{
+#define L2_GUEST_STACK_SIZE 64
+ unsigned long l2_guest_stack[L2_GUEST_STACK_SIZE];
+ uint32_t control;
+ uintptr_t save_cr3;
+
+ GUEST_ASSERT(rdtsc() < TSC_ADJUST_VALUE);
+ wrmsr(MSR_IA32_TSC, rdtsc() - TSC_ADJUST_VALUE);
+ check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+
+ prepare_for_vmx_operation();
+
+ /* Enter VMX root operation. */
+ *(uint32_t *)vmx_pages[VMXON_PAGE].virt = vmcs_revision();
+ GUEST_ASSERT(!vmxon(vmx_pages[VMXON_PAGE].phys));
+
+ /* Load a VMCS. */
+ *(uint32_t *)vmx_pages[VMCS_PAGE].virt = vmcs_revision();
+ GUEST_ASSERT(!vmclear(vmx_pages[VMCS_PAGE].phys));
+ GUEST_ASSERT(!vmptrld(vmx_pages[VMCS_PAGE].phys));
+
+ /* Prepare the VMCS for L2 execution. */
+ prepare_vmcs(l2_guest_code, &l2_guest_stack[L2_GUEST_STACK_SIZE]);
+ control = vmreadz(CPU_BASED_VM_EXEC_CONTROL);
+ control |= CPU_BASED_USE_MSR_BITMAPS | CPU_BASED_USE_TSC_OFFSETING;
+ vmwrite(CPU_BASED_VM_EXEC_CONTROL, control);
+ vmwrite(MSR_BITMAP, vmx_pages[MSR_BITMAP_PAGE].phys);
+ vmwrite(TSC_OFFSET, TSC_OFFSET_VALUE);
+
+ /* Jump into L2. First, test failure to load guest CR3. */
+ save_cr3 = vmreadz(GUEST_CR3);
+ vmwrite(GUEST_CR3, -1ull);
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) ==
+ (EXIT_REASON_FAILED_VMENTRY | EXIT_REASON_INVALID_STATE));
+ check_ia32_tsc_adjust(-1 * TSC_ADJUST_VALUE);
+ vmwrite(GUEST_CR3, save_cr3);
+
+ GUEST_ASSERT(!vmlaunch());
+ GUEST_ASSERT(vmreadz(VM_EXIT_REASON) == EXIT_REASON_VMCALL);
+
+ check_ia32_tsc_adjust(-2 * TSC_ADJUST_VALUE);
+
+ exit_to_l0(PORT_DONE, 0);
+}
+
+static void allocate_vmx_page(struct vmx_page *page)
+{
+ vm_vaddr_t virt;
+
+ virt = vm_vaddr_alloc(vm, PAGE_SIZE, 0, 0, 0);
+ memset(addr_gva2hva(vm, virt), 0, PAGE_SIZE);
+
+ page->virt = virt;
+ page->phys = addr_gva2gpa(vm, virt);
+}
+
+static vm_vaddr_t allocate_vmx_pages(void)
+{
+ vm_vaddr_t vmx_pages_vaddr;
+ int i;
+
+ vmx_pages_vaddr = vm_vaddr_alloc(
+ vm, sizeof(struct vmx_page) * NUM_VMX_PAGES, 0, 0, 0);
+
+ vmx_pages = (void *) addr_gva2hva(vm, vmx_pages_vaddr);
+
+ for (i = 0; i < NUM_VMX_PAGES; i++)
+ allocate_vmx_page(&vmx_pages[i]);
+
+ return vmx_pages_vaddr;
+}
+
+void report(int64_t val)
+{
+ printf("IA32_TSC_ADJUST is %ld (%lld * TSC_ADJUST_VALUE + %lld).\n",
+ val, val / TSC_ADJUST_VALUE, val % TSC_ADJUST_VALUE);
+}
+
+int main(int argc, char *argv[])
+{
+ vm_vaddr_t vmx_pages_vaddr;
+ struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+ if (!(entry->ecx & CPUID_VMX)) {
+ fprintf(stderr, "nested VMX not enabled, skipping test\n");
+ exit(KSFT_SKIP);
+ }
+
+ vm = vm_create_default_vmx(VCPU_ID, (void *) l1_guest_code);
+
+ /* Allocate VMX pages and shared descriptors (vmx_pages). */
+ vmx_pages_vaddr = allocate_vmx_pages();
+ vcpu_args_set(vm, VCPU_ID, 1, vmx_pages_vaddr);
+
+ for (;;) {
+ volatile struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+ struct kvm_regs regs;
+
+ vcpu_run(vm, VCPU_ID);
+ TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+ "Got exit_reason other than KVM_EXIT_IO: %u (%s),\n",
+ run->exit_reason,
+ exit_reason_str(run->exit_reason));
+
+ vcpu_regs_get(vm, VCPU_ID, &regs);
+
+ switch (run->io.port) {
+ case PORT_ABORT:
+ TEST_ASSERT(false, "%s", (const char *) regs.rdi);
+ /* NOT REACHED */
+ case PORT_REPORT:
+ report(regs.rdi);
+ break;
+ case PORT_DONE:
+ goto done;
+ default:
+ TEST_ASSERT(false, "Unknown port 0x%x.", run->io.port);
+ }
+ }
+
+ kvm_vm_free(vm);
+done:
+ return 0;
+}
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 195e9d4739a9..6466294366dc 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -19,25 +19,43 @@ TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES))
all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES)
.ONESHELL:
+define RUN_TEST_PRINT_RESULT
+ TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \
+ echo $$TEST_HDR_MSG; \
+ echo "========================================"; \
+ if [ ! -x $$TEST ]; then \
+ echo "$$TEST_HDR_MSG: Warning: file $$BASENAME_TEST is not executable, correct this.";\
+ echo "not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]"; \
+ else \
+ cd `dirname $$TEST` > /dev/null; \
+ if [ "X$(summary)" != "X" ]; then \
+ (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && \
+ echo "ok 1..$$test_num $$TEST_HDR_MSG [PASS]") || \
+ (if [ $$? -eq $$skip ]; then \
+ echo "not ok 1..$$test_num $$TEST_HDR_MSG [SKIP]"; \
+ else echo "not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]"; \
+ fi;) \
+ else \
+ (./$$BASENAME_TEST && \
+ echo "ok 1..$$test_num $$TEST_HDR_MSG [PASS]") || \
+ (if [ $$? -eq $$skip ]; then \
+ echo "not ok 1..$$test_num $$TEST_HDR_MSG [SKIP]"; \
+ else echo "not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]"; \
+ fi;) \
+ fi; \
+ cd - > /dev/null; \
+ fi;
+endef
+
define RUN_TESTS
- @export KSFT_TAP_LEVEL=`echo 1`;
- @test_num=`echo 0`;
- @echo "TAP version 13";
- @for TEST in $(1); do \
+ @export KSFT_TAP_LEVEL=`echo 1`; \
+ test_num=`echo 0`; \
+ skip=`echo 4`; \
+ echo "TAP version 13"; \
+ for TEST in $(1); do \
BASENAME_TEST=`basename $$TEST`; \
test_num=`echo $$test_num+1 | bc`; \
- echo "selftests: $$BASENAME_TEST"; \
- echo "========================================"; \
- if [ ! -x $$TEST ]; then \
- echo "selftests: Warning: file $$BASENAME_TEST is not executable, correct this.";\
- echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; \
- else \
- if [ "X$(summary)" != "X" ]; then \
- cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST > /tmp/$$BASENAME_TEST 2>&1 && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
- else \
- cd `dirname $$TEST` > /dev/null; (./$$BASENAME_TEST && echo "ok 1..$$test_num selftests: $$BASENAME_TEST [PASS]") || echo "not ok 1..$$test_num selftests: $$BASENAME_TEST [FAIL]"; cd - > /dev/null;\
- fi; \
- fi; \
+ $(call RUN_TEST_PRINT_RESULT,$(TEST),$(BASENAME_TEST),$(test_num),$(skip)) \
done;
endef
@@ -76,9 +94,18 @@ else
endif
define EMIT_TESTS
- @for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
+ @test_num=`echo 0`; \
+ for TEST in $(TEST_GEN_PROGS) $(TEST_CUSTOM_PROGS) $(TEST_PROGS); do \
BASENAME_TEST=`basename $$TEST`; \
- echo "(./$$BASENAME_TEST >> \$$OUTPUT 2>&1 && echo \"selftests: $$BASENAME_TEST [PASS]\") || echo \"selftests: $$BASENAME_TEST [FAIL]\""; \
+ test_num=`echo $$test_num+1 | bc`; \
+ TEST_HDR_MSG="selftests: "`basename $$PWD`:" $$BASENAME_TEST"; \
+ echo "echo $$TEST_HDR_MSG"; \
+ if [ ! -x $$TEST ]; then \
+ echo "echo \"$$TEST_HDR_MSG: Warning: file $$BASENAME_TEST is not executable, correct this.\""; \
+ echo "echo \"not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]\""; \
+ else
+ echo "(./$$BASENAME_TEST >> \$$OUTPUT 2>&1 && echo \"ok 1..$$test_num $$TEST_HDR_MSG [PASS]\") || (if [ \$$? -eq \$$skip ]; then echo \"not ok 1..$$test_num $$TEST_HDR_MSG [SKIP]\"; else echo \"not ok 1..$$test_num $$TEST_HDR_MSG [FAIL]\"; fi;)"; \
+ fi; \
done;
endef
diff --git a/tools/testing/selftests/lib/Makefile b/tools/testing/selftests/lib/Makefile
index 08360060ab14..70d5711e3ac8 100644
--- a/tools/testing/selftests/lib/Makefile
+++ b/tools/testing/selftests/lib/Makefile
@@ -3,6 +3,6 @@
# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
all:
-TEST_PROGS := printf.sh bitmap.sh
+TEST_PROGS := printf.sh bitmap.sh prime_numbers.sh
include ../lib.mk
diff --git a/tools/testing/selftests/lib/bitmap.sh b/tools/testing/selftests/lib/bitmap.sh
index 4dee4d2a8bbe..5a90006d1aea 100755
--- a/tools/testing/selftests/lib/bitmap.sh
+++ b/tools/testing/selftests/lib/bitmap.sh
@@ -1,9 +1,13 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
# Runs bitmap infrastructure tests using test_bitmap kernel module
if ! /sbin/modprobe -q -n test_bitmap; then
- echo "bitmap: [SKIP]"
- exit 77
+ echo "bitmap: module test_bitmap is not found [SKIP]"
+ exit $ksft_skip
fi
if /sbin/modprobe -q test_bitmap; then
diff --git a/tools/testing/selftests/lib/prime_numbers.sh b/tools/testing/selftests/lib/prime_numbers.sh
index b363994e5e11..78e7483c8d60 100755
--- a/tools/testing/selftests/lib/prime_numbers.sh
+++ b/tools/testing/selftests/lib/prime_numbers.sh
@@ -2,9 +2,12 @@
# SPDX-License-Identifier: GPL-2.0
# Checks fast/slow prime_number generation for inconsistencies
-if ! /sbin/modprobe -q -r prime_numbers; then
- echo "prime_numbers: [SKIP]"
- exit 77
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+if ! /sbin/modprobe -q -n prime_numbers; then
+ echo "prime_numbers: module prime_numbers is not found [SKIP]"
+ exit $ksft_skip
fi
if /sbin/modprobe -q prime_numbers selftest=65536; then
diff --git a/tools/testing/selftests/lib/printf.sh b/tools/testing/selftests/lib/printf.sh
index 0c37377fd7d4..45a23e2d64ad 100755
--- a/tools/testing/selftests/lib/printf.sh
+++ b/tools/testing/selftests/lib/printf.sh
@@ -1,9 +1,13 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
# Runs printf infrastructure using test_printf kernel module
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
if ! /sbin/modprobe -q -n test_printf; then
- echo "printf: [SKIP]"
- exit 77
+ echo "printf: module test_printf is not found [SKIP]"
+ exit $ksft_skip
fi
if /sbin/modprobe -q test_printf; then
diff --git a/tools/testing/selftests/locking/Makefile b/tools/testing/selftests/locking/Makefile
new file mode 100644
index 000000000000..6e7761ab3536
--- /dev/null
+++ b/tools/testing/selftests/locking/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for locking/ww_mutx selftests
+
+# No binaries, but make sure arg-less "make" doesn't trigger "run_tests"
+all:
+
+TEST_PROGS := ww_mutex.sh
+
+include ../lib.mk
diff --git a/tools/testing/selftests/locking/ww_mutex.sh b/tools/testing/selftests/locking/ww_mutex.sh
index 2c3d6b1878c2..91e4ac7566af 100644..100755
--- a/tools/testing/selftests/locking/ww_mutex.sh
+++ b/tools/testing/selftests/locking/ww_mutex.sh
@@ -1,6 +1,14 @@
#!/bin/sh
# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
# Runs API tests for struct ww_mutex (Wait/Wound mutexes)
+if ! /sbin/modprobe -q -n test-ww_mutex; then
+ echo "ww_mutex: module test-ww_mutex is not found [SKIP]"
+ exit $ksft_skip
+fi
if /sbin/modprobe -q test-ww_mutex; then
/sbin/modprobe -q -r test-ww_mutex
diff --git a/tools/testing/selftests/media_tests/Makefile b/tools/testing/selftests/media_tests/Makefile
index c82cec2497de..60826d7d37d4 100644
--- a/tools/testing/selftests/media_tests/Makefile
+++ b/tools/testing/selftests/media_tests/Makefile
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0
+#
+CFLAGS += -I../ -I../../../../usr/include/
TEST_GEN_PROGS := media_device_test media_device_open video_device_test
-all: $(TEST_GEN_PROGS)
include ../lib.mk
diff --git a/tools/testing/selftests/media_tests/media_device_open.c b/tools/testing/selftests/media_tests/media_device_open.c
index a5ce5434bafd..93183a37b133 100644
--- a/tools/testing/selftests/media_tests/media_device_open.c
+++ b/tools/testing/selftests/media_tests/media_device_open.c
@@ -34,6 +34,8 @@
#include <sys/stat.h>
#include <linux/media.h>
+#include "../kselftest.h"
+
int main(int argc, char **argv)
{
int opt;
@@ -61,10 +63,8 @@ int main(int argc, char **argv)
}
}
- if (getuid() != 0) {
- printf("Please run the test as root - Exiting.\n");
- exit(-1);
- }
+ if (getuid() != 0)
+ ksft_exit_skip("Please run the test as root - Exiting.\n");
/* Open Media device and keep it open */
fd = open(media_device, O_RDWR);
diff --git a/tools/testing/selftests/media_tests/media_device_test.c b/tools/testing/selftests/media_tests/media_device_test.c
index 421a367e4bb3..4b9953359e40 100644
--- a/tools/testing/selftests/media_tests/media_device_test.c
+++ b/tools/testing/selftests/media_tests/media_device_test.c
@@ -39,6 +39,8 @@
#include <time.h>
#include <linux/media.h>
+#include "../kselftest.h"
+
int main(int argc, char **argv)
{
int opt;
@@ -66,10 +68,8 @@ int main(int argc, char **argv)
}
}
- if (getuid() != 0) {
- printf("Please run the test as root - Exiting.\n");
- exit(-1);
- }
+ if (getuid() != 0)
+ ksft_exit_skip("Please run the test as root - Exiting.\n");
/* Generate random number of interations */
srand((unsigned int) time(NULL));
@@ -88,7 +88,7 @@ int main(int argc, char **argv)
"other Oops in the dmesg. Enable KaSan kernel\n"
"config option for use-after-free error detection.\n\n");
- printf("Running test for %d iternations\n", count);
+ printf("Running test for %d iterations\n", count);
while (count > 0) {
ret = ioctl(fd, MEDIA_IOC_DEVICE_INFO, &mdi);
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index 22bffd55a523..6793f8ecc8e7 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -293,10 +293,9 @@ static int test_membarrier_query(void)
}
ksft_exit_fail_msg("sys_membarrier() failed\n");
}
- if (!(ret & MEMBARRIER_CMD_GLOBAL)) {
- ksft_test_result_fail("sys_membarrier() CMD_GLOBAL query failed\n");
- ksft_exit_fail_msg("sys_membarrier is not supported.\n");
- }
+ if (!(ret & MEMBARRIER_CMD_GLOBAL))
+ ksft_exit_skip(
+ "sys_membarrier unsupported: CMD_GLOBAL not found.\n");
ksft_test_result_pass("sys_membarrier available\n");
return 0;
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index 0862e6f47a38..53a848109f7b 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -4,9 +4,9 @@ CFLAGS += -I../../../../include/uapi/
CFLAGS += -I../../../../include/
CFLAGS += -I../../../../usr/include/
-TEST_PROGS := run_tests.sh
-TEST_FILES := run_fuse_test.sh
-TEST_GEN_FILES := memfd_test fuse_mnt fuse_test
+TEST_GEN_PROGS := memfd_test
+TEST_PROGS := run_fuse_test.sh run_hugetlbfs_test.sh
+TEST_GEN_FILES := fuse_mnt fuse_test
fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
diff --git a/tools/testing/selftests/memfd/run_tests.sh b/tools/testing/selftests/memfd/run_hugetlbfs_test.sh
index c2d41ed81b24..fb633eeb0290 100755
--- a/tools/testing/selftests/memfd/run_tests.sh
+++ b/tools/testing/selftests/memfd/run_hugetlbfs_test.sh
@@ -1,11 +1,8 @@
#!/bin/bash
# please run as root
-#
-# Normal tests requiring no special resources
-#
-./run_fuse_test.sh
-./memfd_test
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
#
# To test memfd_create with hugetlbfs, there needs to be hpages_test
@@ -29,12 +26,13 @@ if [ -n "$freepgs" ] && [ $freepgs -lt $hpages_test ]; then
nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
hpages_needed=`expr $hpages_test - $freepgs`
+ if [ $UID != 0 ]; then
+ echo "Please run memfd with hugetlbfs test as root"
+ exit $ksft_skip
+ fi
+
echo 3 > /proc/sys/vm/drop_caches
echo $(( $hpages_needed + $nr_hugepgs )) > /proc/sys/vm/nr_hugepages
- if [ $? -ne 0 ]; then
- echo "Please run this test as root"
- exit 1
- fi
while read name size unit; do
if [ "$name" = "HugePages_Free:" ]; then
freepgs=$size
@@ -53,7 +51,7 @@ if [ $freepgs -lt $hpages_test ]; then
fi
printf "Not enough huge pages available (%d < %d)\n" \
$freepgs $needpgs
- exit 1
+ exit $ksft_skip
fi
#
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 686da510f989..e0a625e34f40 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -4,11 +4,8 @@ all:
include ../lib.mk
TEST_PROGS := mem-on-off-test.sh
-override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
-
-override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))"
run_full_test:
- @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
+ @/bin/bash ./mem-on-off-test.sh -r 10 && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
clean:
diff --git a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
index ae2c790d0880..b37585e6aa38 100755
--- a/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
+++ b/tools/testing/selftests/memory-hotplug/mem-on-off-test.sh
@@ -3,30 +3,33 @@
SYSFS=
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
prerequisite()
{
msg="skip all tests:"
if [ $UID != 0 ]; then
echo $msg must be run as root >&2
- exit 0
+ exit $ksft_skip
fi
SYSFS=`mount -t sysfs | head -1 | awk '{ print $3 }'`
if [ ! -d "$SYSFS" ]; then
echo $msg sysfs is not mounted >&2
- exit 0
+ exit $ksft_skip
fi
if ! ls $SYSFS/devices/system/memory/memory* > /dev/null 2>&1; then
echo $msg memory hotplug is not supported >&2
- exit 0
+ exit $ksft_skip
fi
if ! grep -q 1 $SYSFS/devices/system/memory/memory*/removable; then
echo $msg no hot-pluggable memory >&2
- exit 0
+ exit $ksft_skip
fi
}
@@ -133,7 +136,8 @@ offline_memory_expect_fail()
error=-12
priority=0
-ratio=10
+# Run with default of ratio=2 for Kselftest run
+ratio=2
retval=0
while getopts e:hp:r: opt; do
diff --git a/tools/testing/selftests/mount/Makefile b/tools/testing/selftests/mount/Makefile
index e094f71c6dbc..026890744215 100644
--- a/tools/testing/selftests/mount/Makefile
+++ b/tools/testing/selftests/mount/Makefile
@@ -3,15 +3,7 @@
CFLAGS = -Wall \
-O2
-TEST_GEN_PROGS := unprivileged-remount-test
+TEST_PROGS := run_tests.sh
+TEST_GEN_FILES := unprivileged-remount-test
include ../lib.mk
-
-override RUN_TESTS := if [ -f /proc/self/uid_map ] ; \
- then \
- ./unprivileged-remount-test ; \
- else \
- echo "WARN: No /proc/self/uid_map exist, test skipped." ; \
- fi
-override EMIT_TESTS := echo "$(RUN_TESTS)"
-
diff --git a/tools/testing/selftests/mount/run_tests.sh b/tools/testing/selftests/mount/run_tests.sh
new file mode 100755
index 000000000000..4ab8f507dcba
--- /dev/null
+++ b/tools/testing/selftests/mount/run_tests.sh
@@ -0,0 +1,12 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# Run mount selftests
+if [ -f /proc/self/uid_map ] ; then
+ ./unprivileged-remount-test ;
+else
+ echo "WARN: No /proc/self/uid_map exist, test skipped." ;
+ exit $ksft_skip
+fi
diff --git a/tools/testing/selftests/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 743d3f9e5918..8a58055fc1f5 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -1,17 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -O2
LDLIBS = -lrt -lpthread -lpopt
+
TEST_GEN_PROGS := mq_open_tests mq_perf_tests
include ../lib.mk
-
-override define RUN_TESTS
- @$(OUTPUT)/mq_open_tests /test1 || echo "selftests: mq_open_tests [FAIL]"
- @$(OUTPUT)/mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
-endef
-
-override define EMIT_TESTS
- echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\""
- echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\""
-endef
-
diff --git a/tools/testing/selftests/mqueue/mq_open_tests.c b/tools/testing/selftests/mqueue/mq_open_tests.c
index e0a74bd207a5..9403ac01ba11 100644
--- a/tools/testing/selftests/mqueue/mq_open_tests.c
+++ b/tools/testing/selftests/mqueue/mq_open_tests.c
@@ -33,6 +33,8 @@
#include <mqueue.h>
#include <error.h>
+#include "../kselftest.h"
+
static char *usage =
"Usage:\n"
" %s path\n"
@@ -53,6 +55,7 @@ int saved_def_msgs, saved_def_msgsize, saved_max_msgs, saved_max_msgsize;
int cur_def_msgs, cur_def_msgsize, cur_max_msgs, cur_max_msgsize;
FILE *def_msgs, *def_msgsize, *max_msgs, *max_msgsize;
char *queue_path;
+char *default_queue_path = "/test1";
mqd_t queue = -1;
static inline void __set(FILE *stream, int value, char *err_msg);
@@ -238,35 +241,33 @@ int main(int argc, char *argv[])
struct mq_attr attr, result;
if (argc != 2) {
- fprintf(stderr, "Must pass a valid queue name\n\n");
- fprintf(stderr, usage, argv[0]);
- exit(1);
- }
+ printf("Using Default queue path - %s\n", default_queue_path);
+ queue_path = default_queue_path;
+ } else {
/*
* Although we can create a msg queue with a non-absolute path name,
* unlink will fail. So, if the name doesn't start with a /, add one
* when we save it.
*/
- if (*argv[1] == '/')
- queue_path = strdup(argv[1]);
- else {
- queue_path = malloc(strlen(argv[1]) + 2);
- if (!queue_path) {
- perror("malloc()");
- exit(1);
+ if (*argv[1] == '/')
+ queue_path = strdup(argv[1]);
+ else {
+ queue_path = malloc(strlen(argv[1]) + 2);
+ if (!queue_path) {
+ perror("malloc()");
+ exit(1);
+ }
+ queue_path[0] = '/';
+ queue_path[1] = 0;
+ strcat(queue_path, argv[1]);
}
- queue_path[0] = '/';
- queue_path[1] = 0;
- strcat(queue_path, argv[1]);
}
- if (getuid() != 0) {
- fprintf(stderr, "Not running as root, but almost all tests "
+ if (getuid() != 0)
+ ksft_exit_skip("Not running as root, but almost all tests "
"require root in order to modify\nsystem settings. "
"Exiting.\n");
- exit(1);
- }
/* Find out what files there are for us to make tweaks in */
def_msgs = fopen(DEF_MSGS, "r+");
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index 8188f72de93c..b019e0b8221c 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -39,6 +39,8 @@
#include <popt.h>
#include <error.h>
+#include "../kselftest.h"
+
static char *usage =
"Usage:\n"
" %s [-c #[,#..] -f] path\n"
@@ -626,12 +628,10 @@ int main(int argc, char *argv[])
cpus_to_pin[0] = cpus_online - 1;
}
- if (getuid() != 0) {
- fprintf(stderr, "Not running as root, but almost all tests "
+ if (getuid() != 0)
+ ksft_exit_skip("Not running as root, but almost all tests "
"require root in order to modify\nsystem settings. "
"Exiting.\n");
- exit(1);
- }
max_msgs = fopen(MAX_MSGS, "r+");
max_msgsize = fopen(MAX_MSGSIZE, "r+");
diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index c612d6e38c62..128e548aa377 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -1,9 +1,14 @@
msg_zerocopy
socket
psock_fanout
+psock_snd
psock_tpacket
reuseport_bpf
reuseport_bpf_cpu
reuseport_bpf_numa
reuseport_dualstack
reuseaddr_conflict
+tcp_mmap
+udpgso
+udpgso_bench_rx
+udpgso_bench_tx
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 785fc18a16b4..663e11e85727 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -5,12 +5,18 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g
CFLAGS += -I../../../../usr/include/
TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh
-TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh
+TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh
+TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
+TEST_PROGS_EXTENDED := in_netns.sh
TEST_GEN_FILES = socket
TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
+TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
+TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
include ../lib.mk
$(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma
+$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread
+$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 6a75a3ea44ad..7ba089b33e8b 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -7,3 +7,8 @@ CONFIG_NET_L3_MASTER_DEV=y
CONFIG_IPV6=y
CONFIG_IPV6_MULTIPLE_TABLES=y
CONFIG_VETH=y
+CONFIG_INET_XFRM_MODE_TUNNEL=y
+CONFIG_NET_IPVTI=y
+CONFIG_INET6_XFRM_MODE_TUNNEL=y
+CONFIG_IPV6_VTI=y
+CONFIG_DUMMY=y
diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
new file mode 100755
index 000000000000..d4cfb6a7a086
--- /dev/null
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -0,0 +1,248 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking IPv4 and IPv6 FIB rules API
+
+ret=0
+
+PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+IP="ip -netns testns"
+
+RTABLE=100
+GW_IP4=192.51.100.2
+SRC_IP=192.51.100.3
+GW_IP6=2001:db8:1::2
+SRC_IP6=2001:db8:1::3
+
+DEV_ADDR=192.51.100.1
+DEV=dummy0
+
+log_test()
+{
+ local rc=$1
+ local expected=$2
+ local msg="$3"
+
+ if [ ${rc} -eq ${expected} ]; then
+ nsuccess=$((nsuccess+1))
+ printf "\n TEST: %-50s [ OK ]\n" "${msg}"
+ else
+ nfail=$((nfail+1))
+ printf "\n TEST: %-50s [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
+}
+
+log_section()
+{
+ echo
+ echo "######################################################################"
+ echo "TEST SECTION: $*"
+ echo "######################################################################"
+}
+
+setup()
+{
+ set -e
+ ip netns add testns
+ $IP link set dev lo up
+
+ $IP link add dummy0 type dummy
+ $IP link set dev dummy0 up
+ $IP address add 198.51.100.1/24 dev dummy0
+ $IP -6 address add 2001:db8:1::1/64 dev dummy0
+
+ set +e
+}
+
+cleanup()
+{
+ $IP link del dev dummy0 &> /dev/null
+ ip netns del testns
+}
+
+fib_check_iproute_support()
+{
+ ip rule help 2>&1 | grep -q $1
+ if [ $? -ne 0 ]; then
+ echo "SKIP: iproute2 iprule too old, missing $1 match"
+ return 1
+ fi
+
+ ip route get help 2>&1 | grep -q $2
+ if [ $? -ne 0 ]; then
+ echo "SKIP: iproute2 get route too old, missing $2 match"
+ return 1
+ fi
+
+ return 0
+}
+
+fib_rule6_del()
+{
+ $IP -6 rule del $1
+ log_test $? 0 "rule6 del $1"
+}
+
+fib_rule6_del_by_pref()
+{
+ pref=$($IP -6 rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1)
+ $IP -6 rule del pref $pref
+}
+
+fib_rule6_test_match_n_redirect()
+{
+ local match="$1"
+ local getmatch="$2"
+
+ $IP -6 rule add $match table $RTABLE
+ $IP -6 route get $GW_IP6 $getmatch | grep -q "table $RTABLE"
+ log_test $? 0 "rule6 check: $1"
+
+ fib_rule6_del_by_pref "$match"
+ log_test $? 0 "rule6 del by pref: $match"
+}
+
+fib_rule6_test()
+{
+ # setup the fib rule redirect route
+ $IP -6 route add table $RTABLE default via $GW_IP6 dev $DEV onlink
+
+ match="oif $DEV"
+ fib_rule6_test_match_n_redirect "$match" "$match" "oif redirect to table"
+
+ match="from $SRC_IP6 iif $DEV"
+ fib_rule6_test_match_n_redirect "$match" "$match" "iif redirect to table"
+
+ match="tos 0x10"
+ fib_rule6_test_match_n_redirect "$match" "$match" "tos redirect to table"
+
+ match="fwmark 0x64"
+ getmatch="mark 0x64"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table"
+
+ fib_check_iproute_support "uidrange" "uid"
+ if [ $? -eq 0 ]; then
+ match="uidrange 100-100"
+ getmatch="uid 100"
+ fib_rule6_test_match_n_redirect "$match" "$getmatch" "uid redirect to table"
+ fi
+
+ fib_check_iproute_support "sport" "sport"
+ if [ $? -eq 0 ]; then
+ match="sport 666 dport 777"
+ fib_rule6_test_match_n_redirect "$match" "$match" "sport and dport redirect to table"
+ fi
+
+ fib_check_iproute_support "ipproto" "ipproto"
+ if [ $? -eq 0 ]; then
+ match="ipproto tcp"
+ fib_rule6_test_match_n_redirect "$match" "$match" "ipproto match"
+ fi
+
+ fib_check_iproute_support "ipproto" "ipproto"
+ if [ $? -eq 0 ]; then
+ match="ipproto icmp"
+ fib_rule6_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+ fi
+}
+
+fib_rule4_del()
+{
+ $IP rule del $1
+ log_test $? 0 "del $1"
+}
+
+fib_rule4_del_by_pref()
+{
+ pref=$($IP rule show | grep "$1 lookup $TABLE" | cut -d ":" -f 1)
+ $IP rule del pref $pref
+}
+
+fib_rule4_test_match_n_redirect()
+{
+ local match="$1"
+ local getmatch="$2"
+
+ $IP rule add $match table $RTABLE
+ $IP route get $GW_IP4 $getmatch | grep -q "table $RTABLE"
+ log_test $? 0 "rule4 check: $1"
+
+ fib_rule4_del_by_pref "$match"
+ log_test $? 0 "rule4 del by pref: $match"
+}
+
+fib_rule4_test()
+{
+ # setup the fib rule redirect route
+ $IP route add table $RTABLE default via $GW_IP4 dev $DEV onlink
+
+ match="oif $DEV"
+ fib_rule4_test_match_n_redirect "$match" "$match" "oif redirect to table"
+
+ match="from $SRC_IP iif $DEV"
+ fib_rule4_test_match_n_redirect "$match" "$match" "iif redirect to table"
+
+ match="tos 0x10"
+ fib_rule4_test_match_n_redirect "$match" "$match" "tos redirect to table"
+
+ match="fwmark 0x64"
+ getmatch="mark 0x64"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" "fwmark redirect to table"
+
+ fib_check_iproute_support "uidrange" "uid"
+ if [ $? -eq 0 ]; then
+ match="uidrange 100-100"
+ getmatch="uid 100"
+ fib_rule4_test_match_n_redirect "$match" "$getmatch" "uid redirect to table"
+ fi
+
+ fib_check_iproute_support "sport" "sport"
+ if [ $? -eq 0 ]; then
+ match="sport 666 dport 777"
+ fib_rule4_test_match_n_redirect "$match" "$match" "sport and dport redirect to table"
+ fi
+
+ fib_check_iproute_support "ipproto" "ipproto"
+ if [ $? -eq 0 ]; then
+ match="ipproto tcp"
+ fib_rule4_test_match_n_redirect "$match" "$match" "ipproto tcp match"
+ fi
+
+ fib_check_iproute_support "ipproto" "ipproto"
+ if [ $? -eq 0 ]; then
+ match="ipproto icmp"
+ fib_rule4_test_match_n_redirect "$match" "$match" "ipproto icmp match"
+ fi
+}
+
+run_fibrule_tests()
+{
+ log_section "IPv4 fib rule"
+ fib_rule4_test
+ log_section "IPv6 fib rule"
+ fib_rule6_test
+}
+
+if [ "$(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
+
+# start clean
+cleanup &> /dev/null
+setup
+run_fibrule_tests
+cleanup
+
+exit $ret
diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
index 9164e60d4b66..78245d60d8bc 100755..100644
--- a/tools/testing/selftests/net/fib_tests.sh
+++ b/tools/testing/selftests/net/fib_tests.sh
@@ -5,9 +5,14 @@
# different events.
ret=0
-
-VERBOSE=${VERBOSE:=0}
-PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+# all tests in this script. Can be overridden with -t option
+TESTS="unregister down carrier nexthop ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric"
+VERBOSE=0
+PAUSE_ON_FAIL=no
+PAUSE=no
IP="ip -netns testns"
log_test()
@@ -18,8 +23,10 @@ log_test()
if [ ${rc} -eq ${expected} ]; then
printf " TEST: %-60s [ OK ]\n" "${msg}"
+ nsuccess=$((nsuccess+1))
else
ret=1
+ nfail=$((nfail+1))
printf " TEST: %-60s [FAIL]\n" "${msg}"
if [ "${PAUSE_ON_FAIL}" = "yes" ]; then
echo
@@ -28,6 +35,13 @@ log_test()
[ "$a" = "q" ] && exit 1
fi
fi
+
+ if [ "${PAUSE}" = "yes" ]; then
+ echo
+ echo "hit enter to continue, 'q' to quit"
+ read a
+ [ "$a" = "q" ] && exit 1
+ fi
}
setup()
@@ -563,39 +577,863 @@ fib_nexthop_test()
}
################################################################################
-#
+# Tests on route add and replace
+
+run_cmd()
+{
+ local cmd="$1"
+ local out
+ local stderr="2>/dev/null"
+
+ if [ "$VERBOSE" = "1" ]; then
+ printf " COMMAND: $cmd\n"
+ stderr=
+ fi
+
+ out=$(eval $cmd $stderr)
+ rc=$?
+ if [ "$VERBOSE" = "1" -a -n "$out" ]; then
+ echo " $out"
+ fi
+
+ [ "$VERBOSE" = "1" ] && echo
+
+ return $rc
+}
+
+# add route for a prefix, flushing any existing routes first
+# expected to be the first step of a test
+add_route6()
+{
+ local pfx="$1"
+ local nh="$2"
+ local out
+
+ if [ "$VERBOSE" = "1" ]; then
+ echo
+ echo " ##################################################"
+ echo
+ fi
+
+ run_cmd "$IP -6 ro flush ${pfx}"
+ [ $? -ne 0 ] && exit 1
+
+ out=$($IP -6 ro ls match ${pfx})
+ if [ -n "$out" ]; then
+ echo "Failed to flush routes for prefix used for tests."
+ exit 1
+ fi
+
+ run_cmd "$IP -6 ro add ${pfx} ${nh}"
+ if [ $? -ne 0 ]; then
+ echo "Failed to add initial route for test."
+ exit 1
+ fi
+}
+
+# add initial route - used in replace route tests
+add_initial_route6()
+{
+ add_route6 "2001:db8:104::/64" "$1"
+}
+
+check_route6()
+{
+ local pfx="2001:db8:104::/64"
+ local expected="$1"
+ local out
+ local rc=0
+
+ out=$($IP -6 ro ls match ${pfx} | sed -e 's/ pref medium//')
+ [ "${out}" = "${expected}" ] && return 0
+
+ if [ -z "${out}" ]; then
+ if [ "$VERBOSE" = "1" ]; then
+ printf "\nNo route entry found\n"
+ printf "Expected:\n"
+ printf " ${expected}\n"
+ fi
+ return 1
+ fi
+
+ # tricky way to convert output to 1-line without ip's
+ # messy '\'; this drops all extra white space
+ out=$(echo ${out})
+ if [ "${out}" != "${expected}" ]; then
+ rc=1
+ if [ "${VERBOSE}" = "1" ]; then
+ printf " Unexpected route entry. Have:\n"
+ printf " ${out}\n"
+ printf " Expected:\n"
+ printf " ${expected}\n\n"
+ fi
+ fi
+
+ return $rc
+}
+
+route_cleanup()
+{
+ $IP li del red 2>/dev/null
+ $IP li del dummy1 2>/dev/null
+ $IP li del veth1 2>/dev/null
+ $IP li del veth3 2>/dev/null
+
+ cleanup &> /dev/null
+}
+
+route_setup()
+{
+ route_cleanup
+ setup
+
+ [ "${VERBOSE}" = "1" ] && set -x
+ set -e
+
+ $IP li add red up type vrf table 101
+ $IP li add veth1 type veth peer name veth2
+ $IP li add veth3 type veth peer name veth4
+
+ $IP li set veth1 up
+ $IP li set veth3 up
+ $IP li set veth2 vrf red up
+ $IP li set veth4 vrf red up
+ $IP li add dummy1 type dummy
+ $IP li set dummy1 vrf red up
+
+ $IP -6 addr add 2001:db8:101::1/64 dev veth1
+ $IP -6 addr add 2001:db8:101::2/64 dev veth2
+ $IP -6 addr add 2001:db8:103::1/64 dev veth3
+ $IP -6 addr add 2001:db8:103::2/64 dev veth4
+ $IP -6 addr add 2001:db8:104::1/64 dev dummy1
+
+ $IP addr add 172.16.101.1/24 dev veth1
+ $IP addr add 172.16.101.2/24 dev veth2
+ $IP addr add 172.16.103.1/24 dev veth3
+ $IP addr add 172.16.103.2/24 dev veth4
+ $IP addr add 172.16.104.1/24 dev dummy1
+
+ set +ex
+}
+
+# assumption is that basic add of a single path route works
+# otherwise just adding an address on an interface is broken
+ipv6_rt_add()
+{
+ local rc
+
+ echo
+ echo "IPv6 route add / append tests"
+
+ # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2"
+ log_test $? 2 "Attempt to add duplicate route - gw"
+
+ # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro add 2001:db8:104::/64 dev veth3"
+ log_test $? 2 "Attempt to add duplicate route - dev only"
+
+ # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
+ log_test $? 2 "Attempt to add duplicate route - reject route"
+
+ # iproute2 prepend only sets NLM_F_CREATE
+ # - adds a new route; does NOT convert existing route to ECMP
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro prepend 2001:db8:104::/64 via 2001:db8:103::2"
+ check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024 2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
+ log_test $? 0 "Add new route for existing prefix (w/o NLM_F_EXCL)"
+
+ # route append with same prefix adds a new route
+ # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+ log_test $? 0 "Append nexthop to existing route - gw"
+
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop dev veth3 weight 1"
+ log_test $? 0 "Append nexthop to existing route - dev only"
+
+ # multipath route can not have a nexthop that is a reject route
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro append unreachable 2001:db8:104::/64"
+ log_test $? 2 "Append nexthop to existing route - reject route"
+
+ # reject route can not be converted to multipath route
+ run_cmd "$IP -6 ro flush 2001:db8:104::/64"
+ run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
+ run_cmd "$IP -6 ro append 2001:db8:104::/64 via 2001:db8:103::2"
+ log_test $? 2 "Append nexthop to existing reject route - gw"
+
+ run_cmd "$IP -6 ro flush 2001:db8:104::/64"
+ run_cmd "$IP -6 ro add unreachable 2001:db8:104::/64"
+ run_cmd "$IP -6 ro append 2001:db8:104::/64 dev veth3"
+ log_test $? 2 "Append nexthop to existing reject route - dev only"
+
+ # insert mpath directly
+ add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+ log_test $? 0 "Add multipath route"
+
+ add_route6 "2001:db8:104::/64" "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro add 2001:db8:104::/64 nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ log_test $? 2 "Attempt to add duplicate multipath route"
+
+ # insert of a second route without append but different metric
+ add_route6 "2001:db8:104::/64" "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::2 metric 512"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ run_cmd "$IP -6 ro add 2001:db8:104::/64 via 2001:db8:103::3 metric 256"
+ rc=$?
+ fi
+ log_test $rc 0 "Route add with different metrics"
+
+ run_cmd "$IP -6 ro del 2001:db8:104::/64 metric 512"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 via 2001:db8:103::3 dev veth3 metric 256 2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024"
+ rc=$?
+ fi
+ log_test $rc 0 "Route delete with metric"
+}
+
+ipv6_rt_replace_single()
+{
+ # single path with single path
+ #
+ add_initial_route6 "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:103::2"
+ check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
+ log_test $? 0 "Single path with single path"
+
+ # single path with multipath
+ #
+ add_initial_route6 "nexthop via 2001:db8:101::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::2"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+ log_test $? 0 "Single path with multipath"
+
+ # single path with reject
+ #
+ add_initial_route6 "nexthop via 2001:db8:101::2"
+ run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
+ check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
+ log_test $? 0 "Single path with reject route"
+
+ # single path with single path using MULTIPATH attribute
+ #
+ add_initial_route6 "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:103::2"
+ check_route6 "2001:db8:104::/64 via 2001:db8:103::2 dev veth3 metric 1024"
+ log_test $? 0 "Single path with single path via multipath attribute"
+
+ # route replace fails - invalid nexthop
+ add_initial_route6 "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:104::2"
+ if [ $? -eq 0 ]; then
+ # previous command is expected to fail so if it returns 0
+ # that means the test failed.
+ log_test 0 1 "Invalid nexthop"
+ else
+ check_route6 "2001:db8:104::/64 via 2001:db8:101::2 dev veth1 metric 1024"
+ log_test $? 0 "Invalid nexthop"
+ fi
+
+ # replace non-existent route
+ # - note use of change versus replace since ip adds NLM_F_CREATE
+ # for replace
+ add_initial_route6 "via 2001:db8:101::2"
+ run_cmd "$IP -6 ro change 2001:db8:105::/64 via 2001:db8:101::2"
+ log_test $? 2 "Single path - replace of non-existent route"
+}
+
+ipv6_rt_replace_mpath()
+{
+ # multipath with multipath
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::3 dev veth1 weight 1 nexthop via 2001:db8:103::3 dev veth3 weight 1"
+ log_test $? 0 "Multipath with multipath"
+
+ # multipath with single
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 via 2001:db8:101::3"
+ check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
+ log_test $? 0 "Multipath with single path"
+
+ # multipath with single
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3"
+ check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024"
+ log_test $? 0 "Multipath with single path via multipath attribute"
+
+ # multipath with reject
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace unreachable 2001:db8:104::/64"
+ check_route6 "unreachable 2001:db8:104::/64 dev lo metric 1024"
+ log_test $? 0 "Multipath with reject route"
+
+ # route replace fails - invalid nexthop 1
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+ log_test $? 0 "Multipath - invalid first nexthop"
+
+ # route replace fails - invalid nexthop 2
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:113::3"
+ check_route6 "2001:db8:104::/64 metric 1024 nexthop via 2001:db8:101::2 dev veth1 weight 1 nexthop via 2001:db8:103::2 dev veth3 weight 1"
+ log_test $? 0 "Multipath - invalid second nexthop"
+
+ # multipath non-existent route
+ add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2"
+ run_cmd "$IP -6 ro change 2001:db8:105::/64 nexthop via 2001:db8:101::3 nexthop via 2001:db8:103::3"
+ log_test $? 2 "Multipath - replace of non-existent route"
+}
+
+ipv6_rt_replace()
+{
+ echo
+ echo "IPv6 route replace tests"
+
+ ipv6_rt_replace_single
+ ipv6_rt_replace_mpath
+}
+
+ipv6_route_test()
+{
+ route_setup
+
+ ipv6_rt_add
+ ipv6_rt_replace
+
+ route_cleanup
+}
+
+ip_addr_metric_check()
+{
+ ip addr help 2>&1 | grep -q metric
+ if [ $? -ne 0 ]; then
+ echo "iproute2 command does not support metric for addresses. Skipping test"
+ return 1
+ fi
+
+ return 0
+}
+
+ipv6_addr_metric_test()
+{
+ local rc
+
+ echo
+ echo "IPv6 prefix route tests"
+
+ ip_addr_metric_check || return 1
+
+ setup
+
+ set -e
+ $IP li add dummy1 type dummy
+ $IP li add dummy2 type dummy
+ $IP li set dummy1 up
+ $IP li set dummy2 up
+
+ # default entry is metric 256
+ run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64"
+ run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64"
+ set +e
+
+ check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 256 2001:db8:104::/64 dev dummy2 proto kernel metric 256"
+ log_test $? 0 "Default metric"
+
+ set -e
+ run_cmd "$IP -6 addr flush dev dummy1"
+ run_cmd "$IP -6 addr add dev dummy1 2001:db8:104::1/64 metric 257"
+ set +e
+
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 256 2001:db8:104::/64 dev dummy1 proto kernel metric 257"
+ log_test $? 0 "User specified metric on first device"
+
+ set -e
+ run_cmd "$IP -6 addr flush dev dummy2"
+ run_cmd "$IP -6 addr add dev dummy2 2001:db8:104::2/64 metric 258"
+ set +e
+
+ check_route6 "2001:db8:104::/64 dev dummy1 proto kernel metric 257 2001:db8:104::/64 dev dummy2 proto kernel metric 258"
+ log_test $? 0 "User specified metric on second device"
-fib_test()
+ run_cmd "$IP -6 addr del dev dummy1 2001:db8:104::1/64 metric 257"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 258"
+ rc=$?
+ fi
+ log_test $rc 0 "Delete of address on first device"
+
+ run_cmd "$IP -6 addr change dev dummy2 2001:db8:104::2/64 metric 259"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Modify metric of address"
+
+ # verify prefix route removed on down
+ run_cmd "ip netns exec testns sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1"
+ run_cmd "$IP li set dev dummy2 down"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 ""
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route removed on link down"
+
+ # verify prefix route re-inserted with assigned metric
+ run_cmd "$IP li set dev dummy2 up"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route6 "2001:db8:104::/64 dev dummy2 proto kernel metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route with metric on link up"
+
+ $IP li del dummy1
+ $IP li del dummy2
+ cleanup
+}
+
+# add route for a prefix, flushing any existing routes first
+# expected to be the first step of a test
+add_route()
+{
+ local pfx="$1"
+ local nh="$2"
+ local out
+
+ if [ "$VERBOSE" = "1" ]; then
+ echo
+ echo " ##################################################"
+ echo
+ fi
+
+ run_cmd "$IP ro flush ${pfx}"
+ [ $? -ne 0 ] && exit 1
+
+ out=$($IP ro ls match ${pfx})
+ if [ -n "$out" ]; then
+ echo "Failed to flush routes for prefix used for tests."
+ exit 1
+ fi
+
+ run_cmd "$IP ro add ${pfx} ${nh}"
+ if [ $? -ne 0 ]; then
+ echo "Failed to add initial route for test."
+ exit 1
+ fi
+}
+
+# add initial route - used in replace route tests
+add_initial_route()
{
- if [ -n "$TEST" ]; then
- eval $TEST
+ add_route "172.16.104.0/24" "$1"
+}
+
+check_route()
+{
+ local pfx="172.16.104.0/24"
+ local expected="$1"
+ local out
+ local rc=0
+
+ out=$($IP ro ls match ${pfx})
+ [ "${out}" = "${expected}" ] && return 0
+
+ if [ -z "${out}" ]; then
+ if [ "$VERBOSE" = "1" ]; then
+ printf "\nNo route entry found\n"
+ printf "Expected:\n"
+ printf " ${expected}\n"
+ fi
+ return 1
+ fi
+
+ # tricky way to convert output to 1-line without ip's
+ # messy '\'; this drops all extra white space
+ out=$(echo ${out})
+ if [ "${out}" != "${expected}" ]; then
+ rc=1
+ if [ "${VERBOSE}" = "1" ]; then
+ printf " Unexpected route entry. Have:\n"
+ printf " ${out}\n"
+ printf " Expected:\n"
+ printf " ${expected}\n\n"
+ fi
+ fi
+
+ return $rc
+}
+
+# assumption is that basic add of a single path route works
+# otherwise just adding an address on an interface is broken
+ipv4_rt_add()
+{
+ local rc
+
+ echo
+ echo "IPv4 route add / append tests"
+
+ # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2"
+ log_test $? 2 "Attempt to add duplicate route - gw"
+
+ # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro add 172.16.104.0/24 dev veth3"
+ log_test $? 2 "Attempt to add duplicate route - dev only"
+
+ # route add same prefix - fails with EEXISTS b/c ip adds NLM_F_EXCL
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro add unreachable 172.16.104.0/24"
+ log_test $? 2 "Attempt to add duplicate route - reject route"
+
+ # iproute2 prepend only sets NLM_F_CREATE
+ # - adds a new route; does NOT convert existing route to ECMP
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro prepend 172.16.104.0/24 via 172.16.103.2"
+ check_route "172.16.104.0/24 via 172.16.103.2 dev veth3 172.16.104.0/24 via 172.16.101.2 dev veth1"
+ log_test $? 0 "Add new nexthop for existing prefix"
+
+ # route append with same prefix adds a new route
+ # - iproute2 sets NLM_F_CREATE | NLM_F_APPEND
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2"
+ check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.2 dev veth3"
+ log_test $? 0 "Append nexthop to existing route - gw"
+
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro append 172.16.104.0/24 dev veth3"
+ check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 dev veth3 scope link"
+ log_test $? 0 "Append nexthop to existing route - dev only"
+
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro append unreachable 172.16.104.0/24"
+ check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 unreachable 172.16.104.0/24"
+ log_test $? 0 "Append nexthop to existing route - reject route"
+
+ run_cmd "$IP ro flush 172.16.104.0/24"
+ run_cmd "$IP ro add unreachable 172.16.104.0/24"
+ run_cmd "$IP ro append 172.16.104.0/24 via 172.16.103.2"
+ check_route "unreachable 172.16.104.0/24 172.16.104.0/24 via 172.16.103.2 dev veth3"
+ log_test $? 0 "Append nexthop to existing reject route - gw"
+
+ run_cmd "$IP ro flush 172.16.104.0/24"
+ run_cmd "$IP ro add unreachable 172.16.104.0/24"
+ run_cmd "$IP ro append 172.16.104.0/24 dev veth3"
+ check_route "unreachable 172.16.104.0/24 172.16.104.0/24 dev veth3 scope link"
+ log_test $? 0 "Append nexthop to existing reject route - dev only"
+
+ # insert mpath directly
+ add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+ log_test $? 0 "add multipath route"
+
+ add_route "172.16.104.0/24" "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro add 172.16.104.0/24 nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ log_test $? 2 "Attempt to add duplicate multipath route"
+
+ # insert of a second route without append but different metric
+ add_route "172.16.104.0/24" "via 172.16.101.2"
+ run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.2 metric 512"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ run_cmd "$IP ro add 172.16.104.0/24 via 172.16.103.3 metric 256"
+ rc=$?
+ fi
+ log_test $rc 0 "Route add with different metrics"
+
+ run_cmd "$IP ro del 172.16.104.0/24 metric 512"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 via 172.16.101.2 dev veth1 172.16.104.0/24 via 172.16.103.3 dev veth3 metric 256"
+ rc=$?
+ fi
+ log_test $rc 0 "Route delete with metric"
+}
+
+ipv4_rt_replace_single()
+{
+ # single path with single path
+ #
+ add_initial_route "via 172.16.101.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.103.2"
+ check_route "172.16.104.0/24 via 172.16.103.2 dev veth3"
+ log_test $? 0 "Single path with single path"
+
+ # single path with multipath
+ #
+ add_initial_route "nexthop via 172.16.101.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.2"
+ check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+ log_test $? 0 "Single path with multipath"
+
+ # single path with reject
+ #
+ add_initial_route "nexthop via 172.16.101.2"
+ run_cmd "$IP ro replace unreachable 172.16.104.0/24"
+ check_route "unreachable 172.16.104.0/24"
+ log_test $? 0 "Single path with reject route"
+
+ # single path with single path using MULTIPATH attribute
+ #
+ add_initial_route "via 172.16.101.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.103.2"
+ check_route "172.16.104.0/24 via 172.16.103.2 dev veth3"
+ log_test $? 0 "Single path with single path via multipath attribute"
+
+ # route replace fails - invalid nexthop
+ add_initial_route "via 172.16.101.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 via 2001:db8:104::2"
+ if [ $? -eq 0 ]; then
+ # previous command is expected to fail so if it returns 0
+ # that means the test failed.
+ log_test 0 1 "Invalid nexthop"
else
- fib_unreg_test
- fib_down_test
- fib_carrier_test
- fib_nexthop_test
+ check_route "172.16.104.0/24 via 172.16.101.2 dev veth1"
+ log_test $? 0 "Invalid nexthop"
+ fi
+
+ # replace non-existent route
+ # - note use of change versus replace since ip adds NLM_F_CREATE
+ # for replace
+ add_initial_route "via 172.16.101.2"
+ run_cmd "$IP ro change 172.16.105.0/24 via 172.16.101.2"
+ log_test $? 2 "Single path - replace of non-existent route"
+}
+
+ipv4_rt_replace_mpath()
+{
+ # multipath with multipath
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3"
+ check_route "172.16.104.0/24 nexthop via 172.16.101.3 dev veth1 weight 1 nexthop via 172.16.103.3 dev veth3 weight 1"
+ log_test $? 0 "Multipath with multipath"
+
+ # multipath with single
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 via 172.16.101.3"
+ check_route "172.16.104.0/24 via 172.16.101.3 dev veth1"
+ log_test $? 0 "Multipath with single path"
+
+ # multipath with single
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3"
+ check_route "172.16.104.0/24 via 172.16.101.3 dev veth1"
+ log_test $? 0 "Multipath with single path via multipath attribute"
+
+ # multipath with reject
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro replace unreachable 172.16.104.0/24"
+ check_route "unreachable 172.16.104.0/24"
+ log_test $? 0 "Multipath with reject route"
+
+ # route replace fails - invalid nexthop 1
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.111.3 nexthop via 172.16.103.3"
+ check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+ log_test $? 0 "Multipath - invalid first nexthop"
+
+ # route replace fails - invalid nexthop 2
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro replace 172.16.104.0/24 nexthop via 172.16.101.3 nexthop via 172.16.113.3"
+ check_route "172.16.104.0/24 nexthop via 172.16.101.2 dev veth1 weight 1 nexthop via 172.16.103.2 dev veth3 weight 1"
+ log_test $? 0 "Multipath - invalid second nexthop"
+
+ # multipath non-existent route
+ add_initial_route "nexthop via 172.16.101.2 nexthop via 172.16.103.2"
+ run_cmd "$IP ro change 172.16.105.0/24 nexthop via 172.16.101.3 nexthop via 172.16.103.3"
+ log_test $? 2 "Multipath - replace of non-existent route"
+}
+
+ipv4_rt_replace()
+{
+ echo
+ echo "IPv4 route replace tests"
+
+ ipv4_rt_replace_single
+ ipv4_rt_replace_mpath
+}
+
+ipv4_route_test()
+{
+ route_setup
+
+ ipv4_rt_add
+ ipv4_rt_replace
+
+ route_cleanup
+}
+
+ipv4_addr_metric_test()
+{
+ local rc
+
+ echo
+ echo "IPv4 prefix route tests"
+
+ ip_addr_metric_check || return 1
+
+ setup
+
+ set -e
+ $IP li add dummy1 type dummy
+ $IP li add dummy2 type dummy
+ $IP li set dummy1 up
+ $IP li set dummy2 up
+
+ # default entry is metric 256
+ run_cmd "$IP addr add dev dummy1 172.16.104.1/24"
+ run_cmd "$IP addr add dev dummy2 172.16.104.2/24"
+ set +e
+
+ check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2"
+ log_test $? 0 "Default metric"
+
+ set -e
+ run_cmd "$IP addr flush dev dummy1"
+ run_cmd "$IP addr add dev dummy1 172.16.104.1/24 metric 257"
+ set +e
+
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257"
+ log_test $? 0 "User specified metric on first device"
+
+ set -e
+ run_cmd "$IP addr flush dev dummy2"
+ run_cmd "$IP addr add dev dummy2 172.16.104.2/24 metric 258"
+ set +e
+
+ check_route "172.16.104.0/24 dev dummy1 proto kernel scope link src 172.16.104.1 metric 257 172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258"
+ log_test $? 0 "User specified metric on second device"
+
+ run_cmd "$IP addr del dev dummy1 172.16.104.1/24 metric 257"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 258"
+ rc=$?
+ fi
+ log_test $rc 0 "Delete of address on first device"
+
+ run_cmd "$IP addr change dev dummy2 172.16.104.2/24 metric 259"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259"
+ rc=$?
+ fi
+ log_test $rc 0 "Modify metric of address"
+
+ # verify prefix route removed on down
+ run_cmd "$IP li set dev dummy2 down"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route ""
+ rc=$?
+ fi
+ log_test $rc 0 "Prefix route removed on link down"
+
+ # verify prefix route re-inserted with assigned metric
+ run_cmd "$IP li set dev dummy2 up"
+ rc=$?
+ if [ $rc -eq 0 ]; then
+ check_route "172.16.104.0/24 dev dummy2 proto kernel scope link src 172.16.104.2 metric 259"
+ rc=$?
fi
+ log_test $rc 0 "Prefix route with metric on link up"
+
+ $IP li del dummy1
+ $IP li del dummy2
+ cleanup
+}
+
+################################################################################
+# usage
+
+usage()
+{
+ cat <<EOF
+usage: ${0##*/} OPTS
+
+ -t <test> Test(s) to run (default: all)
+ (options: $TESTS)
+ -p Pause on fail
+ -P Pause after each test before cleanup
+ -v verbose mode (show commands and output)
+EOF
}
+################################################################################
+# main
+
+while getopts :t:pPhv o
+do
+ case $o in
+ t) TESTS=$OPTARG;;
+ p) PAUSE_ON_FAIL=yes;;
+ P) PAUSE=yes;;
+ v) VERBOSE=$(($VERBOSE + 1));;
+ h) usage; exit 0;;
+ *) usage; exit 1;;
+ esac
+done
+
+PEER_CMD="ip netns exec ${PEER_NS}"
+
+# make sure we don't pause twice
+[ "${PAUSE}" = "yes" ] && PAUSE_ON_FAIL=no
+
if [ "$(id -u)" -ne 0 ];then
echo "SKIP: Need root privileges"
- exit 0
+ exit $ksft_skip;
fi
if [ ! -x "$(command -v ip)" ]; then
echo "SKIP: Could not run test without ip tool"
- exit 0
+ exit $ksft_skip
fi
ip route help 2>&1 | grep -q fibmatch
if [ $? -ne 0 ]; then
echo "SKIP: iproute2 too old, missing fibmatch"
- exit 0
+ exit $ksft_skip
fi
# start clean
cleanup &> /dev/null
-fib_test
+for t in $TESTS
+do
+ case $t in
+ fib_unreg_test|unregister) fib_unreg_test;;
+ fib_down_test|down) fib_down_test;;
+ fib_carrier_test|carrier) fib_carrier_test;;
+ fib_nexthop_test|nexthop) fib_nexthop_test;;
+ ipv6_route_test|ipv6_rt) ipv6_route_test;;
+ ipv4_route_test|ipv4_rt) ipv4_route_test;;
+ ipv6_addr_metric) ipv6_addr_metric_test;;
+ ipv4_addr_metric) ipv4_addr_metric_test;;
+
+ help) echo "Test names: $TESTS"; exit 0;;
+ esac
+done
+
+if [ "$TESTS" != "none" ]; then
+ printf "\nTests passed: %3d\n" ${nsuccess}
+ printf "Tests failed: %3d\n" ${nfail}
+fi
exit $ret
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 75d922438bc9..d8313d0438b7 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,6 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
NUM_NETIFS=4
CHECK_TC="yes"
source lib.sh
@@ -75,14 +76,31 @@ cleanup()
vrf_cleanup
}
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:1::2
+}
+
+learning()
+{
+ learning_test "br0" $swp1 $h1 $h2
+}
+
+flooding()
+{
+ flood_test $swp2 $h1 $h2
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-ping_test $h1 192.0.2.2
-ping6_test $h1 2001:db8:1::2
-learning_test "br0" $swp1 $h1 $h2
-flood_test $swp2 $h1 $h2
+tests_run
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
index 1cddf06f691d..c15c6c85c984 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh
@@ -1,6 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding"
NUM_NETIFS=4
source lib.sh
@@ -73,14 +74,31 @@ cleanup()
vrf_cleanup
}
+ping_ipv4()
+{
+ ping_test $h1 192.0.2.2
+}
+
+ping_ipv6()
+{
+ ping6_test $h1 2001:db8:1::2
+}
+
+learning()
+{
+ learning_test "br0" $swp1 $h1 $h2
+}
+
+flooding()
+{
+ flood_test $swp2 $h1 $h2
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-ping_test $h1 192.0.2.2
-ping6_test $h1 2001:db8:1::2
-learning_test "br0" $swp1 $h1 $h2
-flood_test $swp2 $h1 $h2
+tests_run
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 1ac6c62271f3..7b18a53aa556 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -321,6 +321,50 @@ simple_if_fini()
vrf_destroy $vrf_name
}
+tunnel_create()
+{
+ local name=$1; shift
+ local type=$1; shift
+ local local=$1; shift
+ local remote=$1; shift
+
+ ip link add name $name type $type \
+ local $local remote $remote "$@"
+ ip link set dev $name up
+}
+
+tunnel_destroy()
+{
+ local name=$1; shift
+
+ ip link del dev $name
+}
+
+vlan_create()
+{
+ local if_name=$1; shift
+ local vid=$1; shift
+ local vrf=$1; shift
+ local ips=("${@}")
+ local name=$if_name.$vid
+
+ ip link add name $name link $if_name type vlan id $vid
+ if [ "$vrf" != "" ]; then
+ ip link set dev $name master $vrf
+ fi
+ ip link set dev $name up
+ __addr_add_del $name add "${ips[@]}"
+}
+
+vlan_destroy()
+{
+ local if_name=$1; shift
+ local vid=$1; shift
+ local name=$if_name.$vid
+
+ ip link del dev $name
+}
+
master_name_get()
{
local if_name=$1
@@ -335,6 +379,15 @@ link_stats_tx_packets_get()
ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]'
}
+tc_rule_stats_get()
+{
+ local dev=$1; shift
+ local pref=$1; shift
+
+ tc -j -s filter show dev $dev ingress pref $pref |
+ jq '.[1].options.actions[].stats.packets'
+}
+
mac_get()
{
local if_name=$1
@@ -353,19 +406,33 @@ bridge_ageing_time_get()
echo $((ageing_time / 100))
}
-forwarding_enable()
+declare -A SYSCTL_ORIG
+sysctl_set()
+{
+ local key=$1; shift
+ local value=$1; shift
+
+ SYSCTL_ORIG[$key]=$(sysctl -n $key)
+ sysctl -qw $key=$value
+}
+
+sysctl_restore()
{
- ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding)
- ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding)
+ local key=$1; shift
- sysctl -q -w net.ipv4.conf.all.forwarding=1
- sysctl -q -w net.ipv6.conf.all.forwarding=1
+ sysctl -qw $key=${SYSCTL_ORIG["$key"]}
+}
+
+forwarding_enable()
+{
+ sysctl_set net.ipv4.conf.all.forwarding 1
+ sysctl_set net.ipv6.conf.all.forwarding 1
}
forwarding_restore()
{
- sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd
- sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd
+ sysctl_restore net.ipv6.conf.all.forwarding
+ sysctl_restore net.ipv4.conf.all.forwarding
}
tc_offload_check()
@@ -381,6 +448,115 @@ tc_offload_check()
return 0
}
+trap_install()
+{
+ local dev=$1; shift
+ local direction=$1; shift
+
+ # For slow-path testing, we need to install a trap to get to
+ # slow path the packets that would otherwise be switched in HW.
+ tc filter add dev $dev $direction pref 1 flower skip_sw action trap
+}
+
+trap_uninstall()
+{
+ local dev=$1; shift
+ local direction=$1; shift
+
+ tc filter del dev $dev $direction pref 1 flower skip_sw
+}
+
+slow_path_trap_install()
+{
+ if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
+ trap_install "$@"
+ fi
+}
+
+slow_path_trap_uninstall()
+{
+ if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
+ trap_uninstall "$@"
+ fi
+}
+
+__icmp_capture_add_del()
+{
+ local add_del=$1; shift
+ local pref=$1; shift
+ local vsuf=$1; shift
+ local tundev=$1; shift
+ local filter=$1; shift
+
+ tc filter $add_del dev "$tundev" ingress \
+ proto ip$vsuf pref $pref \
+ flower ip_proto icmp$vsuf $filter \
+ action pass
+}
+
+icmp_capture_install()
+{
+ __icmp_capture_add_del add 100 "" "$@"
+}
+
+icmp_capture_uninstall()
+{
+ __icmp_capture_add_del del 100 "" "$@"
+}
+
+icmp6_capture_install()
+{
+ __icmp_capture_add_del add 100 v6 "$@"
+}
+
+icmp6_capture_uninstall()
+{
+ __icmp_capture_add_del del 100 v6 "$@"
+}
+
+__vlan_capture_add_del()
+{
+ local add_del=$1; shift
+ local pref=$1; shift
+ local dev=$1; shift
+ local filter=$1; shift
+
+ tc filter $add_del dev "$dev" ingress \
+ proto 802.1q pref $pref \
+ flower $filter \
+ action pass
+}
+
+vlan_capture_install()
+{
+ __vlan_capture_add_del add 100 "$@"
+}
+
+vlan_capture_uninstall()
+{
+ __vlan_capture_add_del del 100 "$@"
+}
+
+matchall_sink_create()
+{
+ local dev=$1; shift
+
+ tc qdisc add dev $dev clsact
+ tc filter add dev $dev ingress \
+ pref 10000 \
+ matchall \
+ action drop
+}
+
+tests_run()
+{
+ local current_test
+
+ for current_test in ${TESTS:-$ALL_TESTS}; do
+ $current_test
+ done
+}
+
##############################################################################
# Tests
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh
new file mode 100755
index 000000000000..e6fd7a18c655
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh
@@ -0,0 +1,159 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the device to mirror to is a
+# gretap or ip6gretap netdevice. Expect that the packets come out encapsulated,
+# and another gretap / ip6gretap netdevice is then capable of decapsulating the
+# traffic. Test that the payload is what is expected (ICMP ping request or
+# reply, depending on test).
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+ test_gretap_mac
+ test_ip6gretap_mac
+ test_two_spans
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_mac()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local prot=$1; shift
+ local what=$1; shift
+
+ local swp3mac=$(mac_get $swp3)
+ local h3mac=$(mac_get $h3)
+
+ RET=0
+
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+ tc filter add dev $h3 ingress pref 77 prot $prot \
+ flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \
+ action pass
+
+ mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+
+ tc filter del dev $h3 ingress pref 77
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what: envelope MAC ($tcflags)"
+}
+
+test_two_spans()
+{
+ RET=0
+
+ mirror_install $swp1 ingress gt4 "matchall $tcflags"
+ mirror_install $swp1 egress gt6 "matchall $tcflags"
+ quick_test_span_gre_dir gt4 ingress
+ quick_test_span_gre_dir gt6 egress
+
+ mirror_uninstall $swp1 ingress
+ fail_test_span_gre_dir gt4 ingress
+ quick_test_span_gre_dir gt6 egress
+
+ mirror_install $swp1 ingress gt4 "matchall $tcflags"
+ mirror_uninstall $swp1 egress
+ quick_test_span_gre_dir gt4 ingress
+ fail_test_span_gre_dir gt6 egress
+
+ mirror_uninstall $swp1 ingress
+ log_test "two simultaneously configured mirrors ($tcflags)"
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+ full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+test_gretap_mac()
+{
+ test_span_gre_mac gt4 ingress ip "mirror to gretap"
+ test_span_gre_mac gt4 egress ip "mirror to gretap"
+}
+
+test_ip6gretap_mac()
+{
+ test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap"
+ test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh
new file mode 100755
index 000000000000..360ca133bead
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh
@@ -0,0 +1,226 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o--> mirror | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 BR $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | +---------------------------------------------------------------------+ |
+# | | OL + gt6 (ip6gretap) + gt4 (gretap) | |
+# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | |
+# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | |
+# | | : ttl=100 : ttl=100 | |
+# | | : tos=inherit : tos=inherit | |
+# | +-------------------------:--|-------------------:--|-----------------+ |
+# | : | : | |
+# | +-------------------------:--|-------------------:--|-----------------+ |
+# | | UL : |,---------------------' | |
+# | | + $swp3 : || : | |
+# | | | 192.0.2.129/28 : vv : | |
+# | | | 2001:db8:2::1/64 : + ul (dummy) : | |
+# | +---|---------------------:----------------------:--------------------+ |
+# +-----|---------------------:----------------------:----------------------+
+# | : :
+# +-----|---------------------:----------------------:----------------------+
+# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) |
+# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 |
+# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 |
+# | ttl=100 ttl=100 |
+# | tos=inherit tos=inherit |
+# | |
+# +-------------------------------------------------------------------------+
+#
+# This tests mirroring to gretap and ip6gretap configured in an overlay /
+# underlay manner, i.e. with a bound dummy device that marks underlay VRF where
+# the encapsulated packed should be routed.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28
+}
+
+h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/28
+}
+
+h3_create()
+{
+ simple_if_init $h3 192.0.2.130/28 2001:db8:2::2/64
+
+ tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129
+ ip link set h3-gt4 vrf v$h3
+ matchall_sink_create h3-gt4
+
+ tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1
+ ip link set h3-gt6 vrf v$h3
+ matchall_sink_create h3-gt6
+}
+
+h3_destroy()
+{
+ tunnel_destroy h3-gt6
+ tunnel_destroy h3-gt4
+
+ simple_if_fini $h3 192.0.2.130/28 2001:db8:2::2/64
+}
+
+switch_create()
+{
+ # Bridge between H1 and H2.
+
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+
+ # Underlay.
+
+ simple_if_init $swp3 192.0.2.129/28 2001:db8:2::1/64
+
+ ip link add name ul type dummy
+ ip link set dev ul master v$swp3
+ ip link set dev ul up
+
+ # Overlay.
+
+ vrf_create vrf-ol
+ ip link set dev vrf-ol up
+
+ tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+ ttl 100 tos inherit dev ul
+ ip link set dev gt4 master vrf-ol
+ ip link set dev gt4 up
+
+ tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \
+ ttl 100 tos inherit dev ul allow-localremote
+ ip link set dev gt6 master vrf-ol
+ ip link set dev gt6 up
+}
+
+switch_destroy()
+{
+ vrf_destroy vrf-ol
+
+ tunnel_destroy gt6
+ tunnel_destroy gt4
+
+ simple_if_fini $swp3 192.0.2.129/28 2001:db8:2::1/64
+
+ ip link del dev ul
+
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link del dev br1
+}
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+
+ h1_create
+ h2_create
+ h3_create
+
+ switch_create
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ switch_destroy
+
+ h3_destroy
+ h2_destroy
+ h1_destroy
+
+ vrf_cleanup
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap w/ UL"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap w/ UL"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap w/ UL"
+ full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap w/ UL"
+}
+
+test_all()
+{
+ RET=0
+
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
new file mode 100755
index 000000000000..3bb4c2ba7b14
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
@@ -0,0 +1,121 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device without vlan filtering (802.1d). The device attached to that
+# bridge is a VLAN.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+ test_gretap_stp
+ test_ip6gretap_stp
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip link add name br2 type bridge vlan_filtering 0
+ ip link set dev br2 up
+
+ vlan_create $swp3 555
+
+ ip link set dev $swp3.555 master br2
+ ip route add 192.0.2.130/32 dev br2
+ ip -6 route add 2001:db8:2::2/128 dev br2
+
+ ip address add dev br2 192.0.2.129/32
+ ip address add dev br2 2001:db8:2::1/128
+
+ vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ vlan_destroy $h3 555
+ ip link del dev br2
+ vlan_destroy $swp3 555
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_vlan_match()
+{
+ local tundev=$1; shift
+ local vlan_match=$1; shift
+ local what=$1; shift
+
+ full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what"
+ full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what"
+}
+
+test_gretap()
+{
+ test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+}
+
+test_gretap_stp()
+{
+ full_test_span_gre_stp gt4 $swp3.555 "mirror to gretap"
+}
+
+test_ip6gretap_stp()
+{
+ full_test_span_gre_stp gt6 $swp3.555 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
new file mode 100755
index 000000000000..aa29d46186a8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
@@ -0,0 +1,278 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test how mirrors to gretap and ip6gretap react to changes to relevant
+# configuration.
+
+ALL_TESTS="
+ test_ttl
+ test_tun_up
+ test_egress_up
+ test_remote_ip
+ test_tun_del
+ test_route_del
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ # This test downs $swp3, which deletes the configured IPv6 address
+ # unless this sysctl is set.
+ sysctl_set net.ipv6.conf.$swp3.keep_addr_on_down 1
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ sysctl_restore net.ipv6.conf.$swp3.keep_addr_on_down
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_ttl()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local prot=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ tc filter add dev $h3 ingress pref 77 prot $prot \
+ flower ip_ttl 50 action pass
+
+ mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0
+
+ ip link set dev $tundev type $type ttl 50
+ mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10
+
+ ip link set dev $tundev type $type ttl 100
+ tc filter del dev $h3 ingress pref 77
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: TTL change ($tcflags)"
+}
+
+test_span_gre_tun_up()
+{
+ local tundev=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $tundev down
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ ip link set dev $tundev up
+
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: tunnel down/up ($tcflags)"
+}
+
+test_span_gre_egress_up()
+{
+ local tundev=$1; shift
+ local remote_ip=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $swp3 down
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ # After setting the device up, wait for neighbor to get resolved so that
+ # we can expect mirroring to work.
+ ip link set dev $swp3 up
+ while true; do
+ ip neigh sh dev $swp3 $remote_ip nud reachable |
+ grep -q ^
+ if [[ $? -ne 0 ]]; then
+ sleep 1
+ else
+ break
+ fi
+ done
+
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: egress down/up ($tcflags)"
+}
+
+test_span_gre_remote_ip()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local correct_ip=$1; shift
+ local wrong_ip=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip link set dev $tundev type $type remote $wrong_ip
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+
+ ip link set dev $tundev type $type remote $correct_ip
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: remote address change ($tcflags)"
+}
+
+test_span_gre_tun_del()
+{
+ local tundev=$1; shift
+ local type=$1; shift
+ local flags=$1; shift
+ local local_ip=$1; shift
+ local remote_ip=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir $tundev ingress
+ ip link del dev $tundev
+ fail_test_span_gre_dir $tundev ingress
+
+ tunnel_create $tundev $type $local_ip $remote_ip \
+ ttl 100 tos inherit $flags
+
+ # Recreating the tunnel doesn't reestablish mirroring, so reinstall it
+ # and verify it works for the follow-up tests.
+ mirror_uninstall $swp1 ingress
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: tunnel deleted ($tcflags)"
+}
+
+test_span_gre_route_del()
+{
+ local tundev=$1; shift
+ local edev=$1; shift
+ local route=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir $tundev ingress
+
+ ip route del $route dev $edev
+ fail_test_span_gre_dir $tundev ingress
+
+ ip route add $route dev $edev
+ quick_test_span_gre_dir $tundev ingress
+
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: underlay route removal ($tcflags)"
+}
+
+test_ttl()
+{
+ test_span_gre_ttl gt4 gretap ip "mirror to gretap"
+ test_span_gre_ttl gt6 ip6gretap ipv6 "mirror to ip6gretap"
+}
+
+test_tun_up()
+{
+ test_span_gre_tun_up gt4 "mirror to gretap"
+ test_span_gre_tun_up gt6 "mirror to ip6gretap"
+}
+
+test_egress_up()
+{
+ test_span_gre_egress_up gt4 192.0.2.130 "mirror to gretap"
+ test_span_gre_egress_up gt6 2001:db8:2::2 "mirror to ip6gretap"
+}
+
+test_remote_ip()
+{
+ test_span_gre_remote_ip gt4 gretap 192.0.2.130 192.0.2.132 "mirror to gretap"
+ test_span_gre_remote_ip gt6 ip6gretap 2001:db8:2::2 2001:db8:2::4 "mirror to ip6gretap"
+}
+
+test_tun_del()
+{
+ test_span_gre_tun_del gt4 gretap "" \
+ 192.0.2.129 192.0.2.130 "mirror to gretap"
+ test_span_gre_tun_del gt6 ip6gretap allow-localremote \
+ 2001:db8:2::1 2001:db8:2::2 "mirror to ip6gretap"
+}
+
+test_route_del()
+{
+ test_span_gre_route_del gt4 $swp3 192.0.2.128/28 "mirror to gretap"
+ test_span_gre_route_del gt6 $swp3 2001:db8:2::/64 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh
new file mode 100755
index 000000000000..12914f40612d
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh
@@ -0,0 +1,137 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# This tests flower-triggered mirroring to gretap and ip6gretap netdevices. The
+# interfaces on H1 and H2 have two addresses each. Flower match on one of the
+# addresses is configured with mirror action. It is expected that when pinging
+# this address, mirroring takes place, whereas when pinging the other one,
+# there's no mirroring.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+
+ ip address add dev $h1 192.0.2.3/28
+ ip address add dev $h2 192.0.2.4/28
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h2 192.0.2.4/28
+ ip address del dev $h1 192.0.2.3/28
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_dir_acl()
+{
+ test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4
+}
+
+fail_test_span_gre_dir_acl()
+{
+ fail_test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4
+}
+
+full_test_span_gre_dir_acl()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local match_dip=$1; shift
+ local what=$1; shift
+
+ mirror_install $swp1 $direction $tundev \
+ "protocol ip flower $tcflags dst_ip $match_dip"
+ fail_test_span_gre_dir $tundev $direction
+ test_span_gre_dir_acl "$tundev" "$direction" \
+ "$forward_type" "$backward_type"
+ mirror_uninstall $swp1 $direction
+
+ # Test lack of mirroring after ACL mirror is uninstalled.
+ fail_test_span_gre_dir_acl "$tundev" "$direction"
+
+ log_test "$direction $what ($tcflags)"
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir_acl gt4 ingress 8 0 192.0.2.4 "ACL mirror to gretap"
+ full_test_span_gre_dir_acl gt4 egress 0 8 192.0.2.3 "ACL mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ full_test_span_gre_dir_acl gt6 ingress 8 0 192.0.2.4 "ACL mirror to ip6gretap"
+ full_test_span_gre_dir_acl gt6 egress 0 8 192.0.2.3 "ACL mirror to ip6gretap"
+}
+
+test_all()
+{
+ RET=0
+
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
new file mode 100644
index 000000000000..619b469365be
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
@@ -0,0 +1,130 @@
+# SPDX-License-Identifier: GPL-2.0
+
+source mirror_lib.sh
+
+quick_test_span_gre_dir_ips()
+{
+ local tundev=$1; shift
+
+ do_test_span_dir_ips 10 h3-$tundev "$@"
+}
+
+fail_test_span_gre_dir_ips()
+{
+ local tundev=$1; shift
+
+ do_test_span_dir_ips 0 h3-$tundev "$@"
+}
+
+test_span_gre_dir_ips()
+{
+ local tundev=$1; shift
+
+ test_span_dir_ips h3-$tundev "$@"
+}
+
+full_test_span_gre_dir_ips()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local what=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+ test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \
+ "$backward_type" "$ip1" "$ip2"
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what ($tcflags)"
+}
+
+full_test_span_gre_dir_vlan_ips()
+{
+ local tundev=$1; shift
+ local direction=$1; shift
+ local vlan_match=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local what=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+
+ test_span_dir_ips "h3-$tundev" "$direction" "$forward_type" \
+ "$backward_type" "$ip1" "$ip2"
+
+ tc filter add dev $h3 ingress pref 77 prot 802.1q \
+ flower $vlan_match ip_proto 0x2f \
+ action pass
+ mirror_test v$h1 $ip1 $ip2 $h3 77 10
+ tc filter del dev $h3 ingress pref 77
+
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what ($tcflags)"
+}
+
+quick_test_span_gre_dir()
+{
+ quick_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+fail_test_span_gre_dir()
+{
+ fail_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+test_span_gre_dir()
+{
+ test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_dir()
+{
+ full_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_dir_vlan()
+{
+ full_test_span_gre_dir_vlan_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+full_test_span_gre_stp_ips()
+{
+ local tundev=$1; shift
+ local nbpdev=$1; shift
+ local what=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+ local h3mac=$(mac_get $h3)
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2
+
+ bridge link set dev $nbpdev state disabled
+ sleep 1
+ fail_test_span_gre_dir_ips $tundev ingress $ip1 $ip2
+
+ bridge link set dev $nbpdev state forwarding
+ sleep 1
+ quick_test_span_gre_dir_ips $tundev ingress $ip1 $ip2
+
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: STP state ($tcflags)"
+}
+
+full_test_span_gre_stp()
+{
+ full_test_span_gre_stp_ips "$@" 192.0.2.1 192.0.2.2
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh
new file mode 100755
index 000000000000..fc0508e40fca
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh
@@ -0,0 +1,115 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for mirroring to gretap and ip6gretap, such that the neighbor entry for
+# the tunnel remote address has invalid address at the time that the mirroring
+# is set up. Later on, the neighbor is deleted and it is expected to be
+# reinitialized using the usual ARP process, and the mirroring offload updated.
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.129/28
+ ip address add dev $h3 192.0.2.130/28
+
+ ip address add dev $swp3 2001:db8:2::1/64
+ ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip address del dev $h3 2001:db8:2::2/64
+ ip address del dev $swp3 2001:db8:2::1/64
+
+ ip address del dev $h3 192.0.2.130/28
+ ip address del dev $swp3 192.0.2.129/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_span_gre_neigh()
+{
+ local addr=$1; shift
+ local tundev=$1; shift
+ local direction=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ ip neigh replace dev $swp3 $addr lladdr 00:11:22:33:44:55
+ mirror_install $swp1 $direction $tundev "matchall $tcflags"
+ fail_test_span_gre_dir $tundev ingress
+ ip neigh del dev $swp3 $addr
+ quick_test_span_gre_dir $tundev ingress
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction $what: neighbor change ($tcflags)"
+}
+
+test_gretap()
+{
+ test_span_gre_neigh 192.0.2.130 gt4 ingress "mirror to gretap"
+ test_span_gre_neigh 192.0.2.130 gt4 egress "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ test_span_gre_neigh 2001:db8:2::2 gt6 ingress "mirror to ip6gretap"
+ test_span_gre_neigh 2001:db8:2::2 gt6 egress "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
new file mode 100755
index 000000000000..8fa681eb90e7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
@@ -0,0 +1,127 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test that gretap and ip6gretap mirroring works when the other tunnel endpoint
+# is reachable through a next-hop route (as opposed to directly-attached route).
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ sysctl_set net.ipv4.conf.all.rp_filter 0
+ sysctl_set net.ipv4.conf.$h3.rp_filter 0
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip address add dev $swp3 192.0.2.161/28
+ ip address add dev $h3 192.0.2.162/28
+ ip address add dev gt4 192.0.2.129/32
+ ip address add dev h3-gt4 192.0.2.130/32
+
+ # IPv6 route can't be added after address. Such routes are rejected due
+ # to the gateway address having been configured on the local system. It
+ # works the other way around though.
+ ip address add dev $swp3 2001:db8:4::1/64
+ ip -6 route add 2001:db8:2::2/128 via 2001:db8:4::2
+ ip address add dev $h3 2001:db8:4::2/64
+ ip address add dev gt6 2001:db8:2::1
+ ip address add dev h3-gt6 2001:db8:2::2
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip -6 route del 2001:db8:2::2/128 via 2001:db8:4::2
+ ip address del dev $h3 2001:db8:4::2/64
+ ip address del dev $swp3 2001:db8:4::1/64
+
+ ip address del dev $h3 192.0.2.162/28
+ ip address del dev $swp3 192.0.2.161/28
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+
+ sysctl_restore net.ipv4.conf.$h3.rp_filter
+ sysctl_restore net.ipv4.conf.all.rp_filter
+}
+
+test_gretap()
+{
+ RET=0
+ mirror_install $swp1 ingress gt4 "matchall $tcflags"
+
+ # For IPv4, test that there's no mirroring without the route directing
+ # the traffic to tunnel remote address. Then add it and test that
+ # mirroring starts. For IPv6 we can't test this due to the limitation
+ # that routes for locally-specified IPv6 addresses can't be added.
+ fail_test_span_gre_dir gt4 ingress
+
+ ip route add 192.0.2.130/32 via 192.0.2.162
+ quick_test_span_gre_dir gt4 ingress
+ ip route del 192.0.2.130/32 via 192.0.2.162
+
+ mirror_uninstall $swp1 ingress
+ log_test "mirror to gre with next-hop remote ($tcflags)"
+}
+
+test_ip6gretap()
+{
+ RET=0
+
+ mirror_install $swp1 ingress gt6 "matchall $tcflags"
+ quick_test_span_gre_dir gt6 ingress
+ mirror_uninstall $swp1 ingress
+
+ log_test "mirror to ip6gre with next-hop remote ($tcflags)"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
new file mode 100644
index 000000000000..253419564708
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
@@ -0,0 +1,94 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This is the standard topology for testing mirroring to gretap and ip6gretap
+# netdevices. The tests that use it tweak it in one way or another--importantly,
+# $swp3 and $h3 need to have addresses set up.
+#
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o--> mirror | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 BR $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | + $swp3 + gt6 (ip6gretap) + gt4 (gretap) |
+# | | : loc=2001:db8:2::1 : loc=192.0.2.129 |
+# | | : rem=2001:db8:2::2 : rem=192.0.2.130 |
+# | | : ttl=100 : ttl=100 |
+# | | : tos=inherit : tos=inherit |
+# | | : : |
+# +-----|---------------------:----------------------:----------------------+
+# | : :
+# +-----|---------------------:----------------------:----------------------+
+# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) |
+# | loc=2001:db8:2::2 loc=192.0.2.130 |
+# | rem=2001:db8:2::1 rem=192.0.2.129 |
+# | ttl=100 ttl=100 |
+# | tos=inherit tos=inherit |
+# | |
+# +-------------------------------------------------------------------------+
+
+source mirror_topo_lib.sh
+
+mirror_gre_topo_h3_create()
+{
+ mirror_topo_h3_create
+
+ tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129
+ ip link set h3-gt4 vrf v$h3
+ matchall_sink_create h3-gt4
+
+ tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1
+ ip link set h3-gt6 vrf v$h3
+ matchall_sink_create h3-gt6
+}
+
+mirror_gre_topo_h3_destroy()
+{
+ tunnel_destroy h3-gt6
+ tunnel_destroy h3-gt4
+
+ mirror_topo_h3_destroy
+}
+
+mirror_gre_topo_switch_create()
+{
+ mirror_topo_switch_create
+
+ tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+ ttl 100 tos inherit
+
+ tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \
+ ttl 100 tos inherit allow-localremote
+}
+
+mirror_gre_topo_switch_destroy()
+{
+ tunnel_destroy gt6
+ tunnel_destroy gt4
+
+ mirror_topo_switch_destroy
+}
+
+mirror_gre_topo_create()
+{
+ mirror_topo_h1_create
+ mirror_topo_h2_create
+ mirror_gre_topo_h3_create
+
+ mirror_gre_topo_switch_create
+}
+
+mirror_gre_topo_destroy()
+{
+ mirror_gre_topo_switch_destroy
+
+ mirror_gre_topo_h3_destroy
+ mirror_topo_h2_destroy
+ mirror_topo_h1_destroy
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh
new file mode 100755
index 000000000000..88cecdb9a861
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan.sh
@@ -0,0 +1,92 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" that mirrors to a gretap netdevice
+# whose underlay route points at a vlan device.
+
+ALL_TESTS="
+ test_gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ ip link add name $swp3.555 link $swp3 type vlan id 555
+ ip address add dev $swp3.555 192.0.2.129/32
+ ip address add dev $swp3.555 2001:db8:2::1/128
+ ip link set dev $swp3.555 up
+
+ ip route add 192.0.2.130/32 dev $swp3.555
+ ip -6 route add 2001:db8:2::2/128 dev $swp3.555
+
+ ip link add name $h3.555 link $h3 type vlan id 555
+ ip link set dev $h3.555 master v$h3
+ ip address add dev $h3.555 192.0.2.130/28
+ ip address add dev $h3.555 2001:db8:2::2/64
+ ip link set dev $h3.555 up
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link del dev $h3.555
+ ip link del dev $swp3.555
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_gretap()
+{
+ full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+ full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
new file mode 100755
index 000000000000..5dbc7a08f4bd
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -0,0 +1,270 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# mirror_gre_topo_lib.sh for more details.
+#
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# vlan device on top of a bridge device with vlan filtering (802.1q).
+
+ALL_TESTS="
+ test_gretap
+ test_ip6gretap
+ test_gretap_forbidden_cpu
+ test_ip6gretap_forbidden_cpu
+ test_gretap_forbidden_egress
+ test_ip6gretap_forbidden_egress
+ test_gretap_untagged_egress
+ test_ip6gretap_untagged_egress
+ test_gretap_fdb_roaming
+ test_ip6gretap_fdb_roaming
+ test_gretap_stp
+ test_ip6gretap_stp
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_gre_topo_create
+
+ vlan_create br1 555 "" 192.0.2.129/32 2001:db8:2::1/128
+ bridge vlan add dev br1 vid 555 self
+ ip route rep 192.0.2.130/32 dev br1.555
+ ip -6 route rep 2001:db8:2::2/128 dev br1.555
+
+ vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+
+ ip link set dev $swp3 master br1
+ bridge vlan add dev $swp3 vid 555
+ bridge vlan add dev $swp2 vid 555
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ ip link set dev $swp2 nomaster
+ ip link set dev $swp3 nomaster
+ vlan_destroy $h3 555
+ vlan_destroy br1 555
+
+ mirror_gre_topo_destroy
+ vrf_cleanup
+}
+
+test_vlan_match()
+{
+ local tundev=$1; shift
+ local vlan_match=$1; shift
+ local what=$1; shift
+
+ full_test_span_gre_dir_vlan $tundev ingress "$vlan_match" 8 0 "$what"
+ full_test_span_gre_dir_vlan $tundev egress "$vlan_match" 0 8 "$what"
+}
+
+test_gretap()
+{
+ test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+ test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+}
+
+test_span_gre_forbidden_cpu()
+{
+ local tundev=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ # Run the pass-test first, to prime neighbor table.
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir $tundev ingress
+
+ # Now forbid the VLAN at the bridge and see it fail.
+ bridge vlan del dev br1 vid 555 self
+ sleep 1
+ fail_test_span_gre_dir $tundev ingress
+
+ bridge vlan add dev br1 vid 555 self
+ sleep 1
+ quick_test_span_gre_dir $tundev ingress
+
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: vlan forbidden at a bridge ($tcflags)"
+}
+
+test_gretap_forbidden_cpu()
+{
+ test_span_gre_forbidden_cpu gt4 "mirror to gretap"
+}
+
+test_ip6gretap_forbidden_cpu()
+{
+ test_span_gre_forbidden_cpu gt6 "mirror to ip6gretap"
+}
+
+test_span_gre_forbidden_egress()
+{
+ local tundev=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir $tundev ingress
+
+ bridge vlan del dev $swp3 vid 555
+ sleep 1
+ fail_test_span_gre_dir $tundev ingress
+
+ bridge vlan add dev $swp3 vid 555
+ # Re-prime FDB
+ arping -I br1.555 192.0.2.130 -fqc 1
+ sleep 1
+ quick_test_span_gre_dir $tundev ingress
+
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: vlan forbidden at a bridge egress ($tcflags)"
+}
+
+test_gretap_forbidden_egress()
+{
+ test_span_gre_forbidden_egress gt4 "mirror to gretap"
+}
+
+test_ip6gretap_forbidden_egress()
+{
+ test_span_gre_forbidden_egress gt6 "mirror to ip6gretap"
+}
+
+test_span_gre_untagged_egress()
+{
+ local tundev=$1; shift
+ local what=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+
+ quick_test_span_gre_dir $tundev ingress
+ quick_test_span_vlan_dir $h3 555 ingress
+
+ bridge vlan add dev $swp3 vid 555 pvid untagged
+ sleep 1
+ quick_test_span_gre_dir $tundev ingress
+ fail_test_span_vlan_dir $h3 555 ingress
+
+ bridge vlan add dev $swp3 vid 555
+ sleep 1
+ quick_test_span_gre_dir $tundev ingress
+ quick_test_span_vlan_dir $h3 555 ingress
+
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: vlan untagged at a bridge egress ($tcflags)"
+}
+
+test_gretap_untagged_egress()
+{
+ test_span_gre_untagged_egress gt4 "mirror to gretap"
+}
+
+test_ip6gretap_untagged_egress()
+{
+ test_span_gre_untagged_egress gt6 "mirror to ip6gretap"
+}
+
+test_span_gre_fdb_roaming()
+{
+ local tundev=$1; shift
+ local what=$1; shift
+ local h3mac=$(mac_get $h3)
+
+ RET=0
+
+ mirror_install $swp1 ingress $tundev "matchall $tcflags"
+ quick_test_span_gre_dir $tundev ingress
+
+ bridge fdb del dev $swp3 $h3mac vlan 555 master
+ bridge fdb add dev $swp2 $h3mac vlan 555 master
+ sleep 1
+ fail_test_span_gre_dir $tundev ingress
+
+ bridge fdb del dev $swp2 $h3mac vlan 555 master
+ # Re-prime FDB
+ arping -I br1.555 192.0.2.130 -fqc 1
+ sleep 1
+ quick_test_span_gre_dir $tundev ingress
+
+ mirror_uninstall $swp1 ingress
+
+ log_test "$what: MAC roaming ($tcflags)"
+}
+
+test_gretap_fdb_roaming()
+{
+ test_span_gre_fdb_roaming gt4 "mirror to gretap"
+}
+
+test_ip6gretap_fdb_roaming()
+{
+ test_span_gre_fdb_roaming gt6 "mirror to ip6gretap"
+}
+
+test_gretap_stp()
+{
+ full_test_span_gre_stp gt4 $swp3 "mirror to gretap"
+}
+
+test_ip6gretap_stp()
+{
+ full_test_span_gre_stp gt6 $swp3 "mirror to ip6gretap"
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+
+ tests_run
+
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
new file mode 100644
index 000000000000..d36dc26c6c51
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -0,0 +1,132 @@
+# SPDX-License-Identifier: GPL-2.0
+
+mirror_install()
+{
+ local from_dev=$1; shift
+ local direction=$1; shift
+ local to_dev=$1; shift
+ local filter=$1; shift
+
+ tc filter add dev $from_dev $direction \
+ pref 1000 $filter \
+ action mirred egress mirror dev $to_dev
+}
+
+mirror_uninstall()
+{
+ local from_dev=$1; shift
+ local direction=$1; shift
+
+ tc filter del dev $swp1 $direction pref 1000
+}
+
+mirror_test()
+{
+ local vrf_name=$1; shift
+ local sip=$1; shift
+ local dip=$1; shift
+ local dev=$1; shift
+ local pref=$1; shift
+ local expect=$1; shift
+
+ local t0=$(tc_rule_stats_get $dev $pref)
+ ip vrf exec $vrf_name \
+ ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null
+ local t1=$(tc_rule_stats_get $dev $pref)
+ local delta=$((t1 - t0))
+ # Tolerate a couple stray extra packets.
+ ((expect <= delta && delta <= expect + 2))
+ check_err $? "Expected to capture $expect packets, got $delta."
+}
+
+do_test_span_dir_ips()
+{
+ local expect=$1; shift
+ local dev=$1; shift
+ local direction=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ icmp_capture_install $dev
+ mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
+ mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
+ icmp_capture_uninstall $dev
+}
+
+quick_test_span_dir_ips()
+{
+ do_test_span_dir_ips 10 "$@"
+}
+
+fail_test_span_dir_ips()
+{
+ do_test_span_dir_ips 0 "$@"
+}
+
+test_span_dir_ips()
+{
+ local dev=$1; shift
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ quick_test_span_dir_ips "$dev" "$direction" "$ip1" "$ip2"
+
+ icmp_capture_install $dev "type $forward_type"
+ mirror_test v$h1 $ip1 $ip2 $dev 100 10
+ icmp_capture_uninstall $dev
+
+ icmp_capture_install $dev "type $backward_type"
+ mirror_test v$h2 $ip2 $ip1 $dev 100 10
+ icmp_capture_uninstall $dev
+}
+
+fail_test_span_dir()
+{
+ fail_test_span_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+test_span_dir()
+{
+ test_span_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+do_test_span_vlan_dir_ips()
+{
+ local expect=$1; shift
+ local dev=$1; shift
+ local vid=$1; shift
+ local direction=$1; shift
+ local ip1=$1; shift
+ local ip2=$1; shift
+
+ # Install the capture as skip_hw to avoid double-counting of packets.
+ # The traffic is meant for local box anyway, so will be trapped to
+ # kernel.
+ vlan_capture_install $dev "skip_hw vlan_id $vid"
+ mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
+ mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
+ vlan_capture_uninstall $dev
+}
+
+quick_test_span_vlan_dir_ips()
+{
+ do_test_span_vlan_dir_ips 10 "$@"
+}
+
+fail_test_span_vlan_dir_ips()
+{
+ do_test_span_vlan_dir_ips 0 "$@"
+}
+
+quick_test_span_vlan_dir()
+{
+ quick_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
+
+fail_test_span_vlan_dir()
+{
+ fail_test_span_vlan_dir_ips "$@" 192.0.2.1 192.0.2.2
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh
new file mode 100644
index 000000000000..04979e5962e7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_topo_lib.sh
@@ -0,0 +1,101 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# This is the standard topology for testing mirroring. The tests that use it
+# tweak it in one way or another--typically add more devices to the topology.
+#
+# +---------------------+ +---------------------+
+# | H1 | | H2 |
+# | + $h1 | | $h2 + |
+# | | 192.0.2.1/28 | | 192.0.2.2/28 | |
+# +-----|---------------+ +---------------|-----+
+# | |
+# +-----|-------------------------------------------------------------|-----+
+# | SW o--> mirror | |
+# | +---|-------------------------------------------------------------|---+ |
+# | | + $swp1 BR $swp2 + | |
+# | +---------------------------------------------------------------------+ |
+# | |
+# | + $swp3 |
+# +-----|-------------------------------------------------------------------+
+# |
+# +-----|-------------------------------------------------------------------+
+# | H3 + $h3 |
+# | |
+# +-------------------------------------------------------------------------+
+
+mirror_topo_h1_create()
+{
+ simple_if_init $h1 192.0.2.1/28
+}
+
+mirror_topo_h1_destroy()
+{
+ simple_if_fini $h1 192.0.2.1/28
+}
+
+mirror_topo_h2_create()
+{
+ simple_if_init $h2 192.0.2.2/28
+}
+
+mirror_topo_h2_destroy()
+{
+ simple_if_fini $h2 192.0.2.2/28
+}
+
+mirror_topo_h3_create()
+{
+ simple_if_init $h3
+ tc qdisc add dev $h3 clsact
+}
+
+mirror_topo_h3_destroy()
+{
+ tc qdisc del dev $h3 clsact
+ simple_if_fini $h3
+}
+
+mirror_topo_switch_create()
+{
+ ip link set dev $swp3 up
+
+ ip link add name br1 type bridge vlan_filtering 1
+ ip link set dev br1 up
+
+ ip link set dev $swp1 master br1
+ ip link set dev $swp1 up
+
+ ip link set dev $swp2 master br1
+ ip link set dev $swp2 up
+
+ tc qdisc add dev $swp1 clsact
+}
+
+mirror_topo_switch_destroy()
+{
+ tc qdisc del dev $swp1 clsact
+
+ ip link set dev $swp1 down
+ ip link set dev $swp2 down
+ ip link del dev br1
+
+ ip link set dev $swp3 down
+}
+
+mirror_topo_create()
+{
+ mirror_topo_h1_create
+ mirror_topo_h2_create
+ mirror_topo_h3_create
+
+ mirror_topo_switch_create
+}
+
+mirror_topo_destroy()
+{
+ mirror_topo_switch_destroy
+
+ mirror_topo_h3_destroy
+ mirror_topo_h2_destroy
+ mirror_topo_h1_destroy
+}
diff --git a/tools/testing/selftests/net/forwarding/mirror_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_vlan.sh
new file mode 100755
index 000000000000..9ab2ce77b332
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_vlan.sh
@@ -0,0 +1,131 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing mirroring. See mirror_topo_lib.sh
+# for more details.
+#
+# Test for "tc action mirred egress mirror" that mirrors to a vlan device.
+
+ALL_TESTS="
+ test_vlan
+ test_tagged_vlan
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_topo_lib.sh
+
+setup_prepare()
+{
+ h1=${NETIFS[p1]}
+ swp1=${NETIFS[p2]}
+
+ swp2=${NETIFS[p3]}
+ h2=${NETIFS[p4]}
+
+ swp3=${NETIFS[p5]}
+ h3=${NETIFS[p6]}
+
+ vrf_prepare
+ mirror_topo_create
+
+ vlan_create $swp3 555
+
+ vlan_create $h3 555 v$h3
+ matchall_sink_create $h3.555
+
+ vlan_create $h1 111 v$h1 192.0.2.17/28
+ bridge vlan add dev $swp1 vid 111
+
+ vlan_create $h2 111 v$h2 192.0.2.18/28
+ bridge vlan add dev $swp2 vid 111
+}
+
+cleanup()
+{
+ pre_cleanup
+
+ vlan_destroy $h2 111
+ vlan_destroy $h1 111
+ vlan_destroy $h3 555
+ vlan_destroy $swp3 555
+
+ mirror_topo_destroy
+ vrf_cleanup
+}
+
+test_vlan_dir()
+{
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 $direction $swp3.555 "matchall $tcflags"
+ test_span_dir "$h3.555" "$direction" "$forward_type" "$backward_type"
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction mirror to vlan ($tcflags)"
+}
+
+test_vlan()
+{
+ test_vlan_dir ingress 8 0
+ test_vlan_dir egress 0 8
+}
+
+test_tagged_vlan_dir()
+{
+ local direction=$1; shift
+ local forward_type=$1; shift
+ local backward_type=$1; shift
+
+ RET=0
+
+ mirror_install $swp1 $direction $swp3.555 "matchall $tcflags"
+ do_test_span_vlan_dir_ips 10 "$h3.555" 111 "$direction" \
+ 192.0.2.17 192.0.2.18
+ do_test_span_vlan_dir_ips 0 "$h3.555" 555 "$direction" \
+ 192.0.2.17 192.0.2.18
+ mirror_uninstall $swp1 $direction
+
+ log_test "$direction mirror tagged to vlan ($tcflags)"
+}
+
+test_tagged_vlan()
+{
+ test_tagged_vlan_dir ingress 8 0
+ test_tagged_vlan_dir egress 0 8
+}
+
+test_all()
+{
+ slow_path_trap_install $swp1 ingress
+ slow_path_trap_install $swp1 egress
+ trap_install $h3 ingress
+
+ tests_run
+
+ trap_uninstall $h3 ingress
+ slow_path_trap_uninstall $swp1 egress
+ slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+ echo "WARN: Could not test offloaded functionality"
+else
+ tcflags="skip_sw"
+ test_all
+fi
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh
index cc6a14abfa87..a75cb51cc5bd 100755
--- a/tools/testing/selftests/net/forwarding/router.sh
+++ b/tools/testing/selftests/net/forwarding/router.sh
@@ -1,6 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6"
NUM_NETIFS=4
source lib.sh
@@ -114,12 +115,21 @@ cleanup()
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
-ping_test $h1 198.51.100.2
-ping6_test $h1 2001:db8:2::2
+tests_run
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh
index 3bc351008db6..8b6d0fb6d604 100755
--- a/tools/testing/selftests/net/forwarding/router_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/router_multipath.sh
@@ -1,6 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test"
NUM_NETIFS=8
source lib.sh
@@ -191,7 +192,7 @@ multipath_eval()
diff=$(echo $weights_ratio - $packets_ratio | bc -l)
diff=${diff#-}
- test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0
+ test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
check_err $? "Too large discrepancy between expected and measured ratios"
log_test "$desc"
log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
@@ -204,13 +205,11 @@ multipath4_test()
local weight_rp13=$3
local t0_rp12 t0_rp13 t1_rp12 t1_rp13
local packets_rp12 packets_rp13
- local hash_policy
# Transmit multiple flows from h1 to h2 and make sure they are
# distributed between both multipath links (rp12 and rp13)
# according to the configured weights.
- hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy)
- sysctl -q -w net.ipv4.fib_multipath_hash_policy=1
+ sysctl_set net.ipv4.fib_multipath_hash_policy 1
ip route replace 198.51.100.0/24 vrf vrf-r1 \
nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \
nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13
@@ -232,7 +231,7 @@ multipath4_test()
ip route replace 198.51.100.0/24 vrf vrf-r1 \
nexthop via 169.254.2.22 dev $rp12 \
nexthop via 169.254.3.23 dev $rp13
- sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy
+ sysctl_restore net.ipv4.fib_multipath_hash_policy
}
multipath6_l4_test()
@@ -242,13 +241,11 @@ multipath6_l4_test()
local weight_rp13=$3
local t0_rp12 t0_rp13 t1_rp12 t1_rp13
local packets_rp12 packets_rp13
- local hash_policy
# Transmit multiple flows from h1 to h2 and make sure they are
# distributed between both multipath links (rp12 and rp13)
# according to the configured weights.
- hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy)
- sysctl -q -w net.ipv6.fib_multipath_hash_policy=1
+ sysctl_set net.ipv6.fib_multipath_hash_policy 1
ip route replace 2001:db8:2::/64 vrf vrf-r1 \
nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \
@@ -271,7 +268,7 @@ multipath6_l4_test()
nexthop via fe80:2::22 dev $rp12 \
nexthop via fe80:3::23 dev $rp13
- sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy
+ sysctl_restore net.ipv6.fib_multipath_hash_policy
}
multipath6_test()
@@ -364,13 +361,21 @@ cleanup()
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
-ping_test $h1 198.51.100.2
-ping6_test $h1 2001:db8:2::2
-multipath_test
+tests_run
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index 3a6385ebd5d0..813d02d1939d 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -1,6 +1,8 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \
+ mirred_egress_mirror_test gact_trap_test"
NUM_NETIFS=4
source tc_common.sh
source lib.sh
@@ -111,6 +113,10 @@ gact_trap_test()
{
RET=0
+ if [[ "$tcflags" != "skip_sw" ]]; then
+ return 0;
+ fi
+
tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \
skip_hw dst_ip 192.0.2.2 action drop
tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \
@@ -179,24 +185,29 @@ cleanup()
ip link set $swp1 address $swp1origmac
}
+mirred_egress_redirect_test()
+{
+ mirred_egress_test "redirect"
+}
+
+mirred_egress_mirror_test()
+{
+ mirred_egress_test "mirror"
+}
+
trap cleanup EXIT
setup_prepare
setup_wait
-gact_drop_and_ok_test
-mirred_egress_test "redirect"
-mirred_egress_test "mirror"
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- gact_drop_and_ok_test
- mirred_egress_test "redirect"
- mirred_egress_test "mirror"
- gact_trap_test
+ tests_run
fi
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh
index 2fd15226974b..d2c783e94df3 100755
--- a/tools/testing/selftests/net/forwarding/tc_chains.sh
+++ b/tools/testing/selftests/net/forwarding/tc_chains.sh
@@ -1,6 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="unreachable_chain_test gact_goto_chain_test"
NUM_NETIFS=2
source tc_common.sh
source lib.sh
@@ -107,16 +108,14 @@ trap cleanup EXIT
setup_prepare
setup_wait
-unreachable_chain_test
-gact_goto_chain_test
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- unreachable_chain_test
- gact_goto_chain_test
+ tests_run
fi
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh
index 032b882adfc0..20d1077e5a3d 100755
--- a/tools/testing/selftests/net/forwarding/tc_flower.sh
+++ b/tools/testing/selftests/net/forwarding/tc_flower.sh
@@ -1,6 +1,8 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \
+ match_src_ip_test match_ip_flags_test"
NUM_NETIFS=2
source tc_common.sh
source lib.sh
@@ -149,6 +151,74 @@ match_src_ip_test()
log_test "src_ip match ($tcflags)"
}
+match_ip_flags_test()
+{
+ RET=0
+
+ tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+ $tcflags ip_flags frag action continue
+ tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+ $tcflags ip_flags firstfrag action continue
+ tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+ $tcflags ip_flags nofirstfrag action continue
+ tc filter add dev $h2 ingress protocol ip pref 4 handle 104 flower \
+ $tcflags ip_flags nofrag action drop
+
+ $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip "frag=0" -q
+
+ tc_check_packets "dev $h2 ingress" 101 1
+ check_fail $? "Matched on wrong frag filter (nofrag)"
+
+ tc_check_packets "dev $h2 ingress" 102 1
+ check_fail $? "Matched on wrong firstfrag filter (nofrag)"
+
+ tc_check_packets "dev $h2 ingress" 103 1
+ check_err $? "Did not match on nofirstfrag filter (nofrag) "
+
+ tc_check_packets "dev $h2 ingress" 104 1
+ check_err $? "Did not match on nofrag filter (nofrag)"
+
+ $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip "frag=0,mf" -q
+
+ tc_check_packets "dev $h2 ingress" 101 1
+ check_err $? "Did not match on frag filter (1stfrag)"
+
+ tc_check_packets "dev $h2 ingress" 102 1
+ check_err $? "Did not match fistfrag filter (1stfrag)"
+
+ tc_check_packets "dev $h2 ingress" 103 1
+ check_err $? "Matched on wrong nofirstfrag filter (1stfrag)"
+
+ tc_check_packets "dev $h2 ingress" 104 1
+ check_err $? "Match on wrong nofrag filter (1stfrag)"
+
+ $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip "frag=256,mf" -q
+ $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip "frag=256" -q
+
+ tc_check_packets "dev $h2 ingress" 101 3
+ check_err $? "Did not match on frag filter (no1stfrag)"
+
+ tc_check_packets "dev $h2 ingress" 102 1
+ check_err $? "Matched on wrong firstfrag filter (no1stfrag)"
+
+ tc_check_packets "dev $h2 ingress" 103 3
+ check_err $? "Did not match on nofirstfrag filter (no1stfrag)"
+
+ tc_check_packets "dev $h2 ingress" 104 1
+ check_err $? "Matched on nofrag filter (no1stfrag)"
+
+ tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+ tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+ tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+ tc filter del dev $h2 ingress protocol ip pref 4 handle 104 flower
+
+ log_test "ip_flags match ($tcflags)"
+}
+
setup_prepare()
{
h1=${NETIFS[p1]}
@@ -177,20 +247,14 @@ trap cleanup EXIT
setup_prepare
setup_wait
-match_dst_mac_test
-match_src_mac_test
-match_dst_ip_test
-match_src_ip_test
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- match_dst_mac_test
- match_src_mac_test
- match_dst_ip_test
- match_src_ip_test
+ tests_run
fi
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
index 077b98048ef4..b5b917203815 100755
--- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh
+++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
@@ -1,6 +1,7 @@
#!/bin/bash
# SPDX-License-Identifier: GPL-2.0
+ALL_TESTS="shared_block_test"
NUM_NETIFS=4
source tc_common.sh
source lib.sh
@@ -109,14 +110,14 @@ trap cleanup EXIT
setup_prepare
setup_wait
-shared_block_test
+tests_run
tc_offload_check
if [[ $? -ne 0 ]]; then
log_info "Could not test offloaded functionality"
else
tcflags="skip_sw"
- shared_block_test
+ tests_run
fi
exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/msg_zerocopy.sh b/tools/testing/selftests/net/msg_zerocopy.sh
index d571d213418d..c43c6debda06 100755
--- a/tools/testing/selftests/net/msg_zerocopy.sh
+++ b/tools/testing/selftests/net/msg_zerocopy.sh
@@ -21,6 +21,14 @@ readonly DADDR6='fd::2'
readonly path_sysctl_mem="net.core.optmem_max"
+# No arguments: automated test
+if [[ "$#" -eq "0" ]]; then
+ $0 4 tcp -t 1
+ $0 6 tcp -t 1
+ echo "OK. All tests passed"
+ exit 0
+fi
+
# Argument parsing
if [[ "$#" -lt "2" ]]; then
echo "Usage: $0 [4|6] [tcp|udp|raw|raw_hdrincl|packet|packet_dgram] <args>"
diff --git a/tools/testing/selftests/net/netdevice.sh b/tools/testing/selftests/net/netdevice.sh
index 903679e0ff31..e3afcb424710 100755
--- a/tools/testing/selftests/net/netdevice.sh
+++ b/tools/testing/selftests/net/netdevice.sh
@@ -8,6 +8,9 @@
# if not they probably have failed earlier in the boot process and their logged error will be catched by another test
#
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
# this function will try to up the interface
# if already up, nothing done
# arg1: network interface name
@@ -18,7 +21,7 @@ kci_net_start()
ip link show "$netdev" |grep -q UP
if [ $? -eq 0 ];then
echo "SKIP: $netdev: interface already up"
- return 0
+ return $ksft_skip
fi
ip link set "$netdev" up
@@ -61,12 +64,12 @@ kci_net_setup()
ip address show "$netdev" |grep '^[[:space:]]*inet'
if [ $? -eq 0 ];then
echo "SKIP: $netdev: already have an IP"
- return 0
+ return $ksft_skip
fi
# TODO what ipaddr to set ? DHCP ?
echo "SKIP: $netdev: set IP address"
- return 0
+ return $ksft_skip
}
# test an ethtool command
@@ -84,6 +87,7 @@ kci_netdev_ethtool_test()
if [ $ret -ne 0 ];then
if [ $ret -eq "$1" ];then
echo "SKIP: $netdev: ethtool $2 not supported"
+ return $ksft_skip
else
echo "FAIL: $netdev: ethtool $2"
return 1
@@ -104,7 +108,7 @@ kci_netdev_ethtool()
ethtool --version 2>/dev/null >/dev/null
if [ $? -ne 0 ];then
echo "SKIP: ethtool not present"
- return 1
+ return $ksft_skip
fi
TMP_ETHTOOL_FEATURES="$(mktemp)"
@@ -176,13 +180,13 @@ kci_test_netdev()
#check for needed privileges
if [ "$(id -u)" -ne 0 ];then
echo "SKIP: Need root privileges"
- exit 0
+ exit $ksft_skip
fi
ip link show 2>/dev/null >/dev/null
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without the ip tool"
- exit 0
+ exit $ksft_skip
fi
TMP_LIST_NETDEV="$(mktemp)"
diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh
index 1e428781a625..f8cc38afffa2 100755
--- a/tools/testing/selftests/net/pmtu.sh
+++ b/tools/testing/selftests/net/pmtu.sh
@@ -43,6 +43,9 @@
# that MTU is properly calculated instead when MTU is not configured from
# userspace
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
tests="
pmtu_vti6_exception vti6: PMTU exceptions
pmtu_vti4_exception vti4: PMTU exceptions
@@ -162,7 +165,7 @@ setup_xfrm6() {
}
setup() {
- [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return 1
+ [ "$(id -u)" -ne 0 ] && echo " need to run as root" && return $ksft_skip
cleanup_done=0
for arg do
@@ -368,7 +371,7 @@ test_pmtu_vti6_link_add_mtu() {
fail=0
- min=1280
+ min=68 # vti6 can carry IPv4 packets too
max=$((65535 - 40))
# Check invalid values first
for v in $((min - 1)) $((max + 1)); do
@@ -384,7 +387,7 @@ test_pmtu_vti6_link_add_mtu() {
done
# Now check valid values
- for v in 1280 1300 $((65535 - 40)); do
+ for v in 68 1280 1300 $((65535 - 40)); do
${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10
mtu="$(link_get_mtu "${ns_a}" vti6_a)"
${ns_a} ip link del vti6_a
diff --git a/tools/testing/selftests/net/psock_snd.c b/tools/testing/selftests/net/psock_snd.c
new file mode 100644
index 000000000000..7d15e10a9fb6
--- /dev/null
+++ b/tools/testing/selftests/net/psock_snd.c
@@ -0,0 +1,397 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <linux/filter.h>
+#include <linux/bpf.h>
+#include <linux/if_packet.h>
+#include <linux/if_vlan.h>
+#include <linux/virtio_net.h>
+#include <net/if.h>
+#include <net/ethernet.h>
+#include <netinet/ip.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include "psock_lib.h"
+
+static bool cfg_use_bind;
+static bool cfg_use_csum_off;
+static bool cfg_use_csum_off_bad;
+static bool cfg_use_dgram;
+static bool cfg_use_gso;
+static bool cfg_use_qdisc_bypass;
+static bool cfg_use_vlan;
+static bool cfg_use_vnet;
+
+static char *cfg_ifname = "lo";
+static int cfg_mtu = 1500;
+static int cfg_payload_len = DATA_LEN;
+static int cfg_truncate_len = INT_MAX;
+static uint16_t cfg_port = 8000;
+
+/* test sending up to max mtu + 1 */
+#define TEST_SZ (sizeof(struct virtio_net_hdr) + ETH_HLEN + ETH_MAX_MTU + 1)
+
+static char tbuf[TEST_SZ], rbuf[TEST_SZ];
+
+static unsigned long add_csum_hword(const uint16_t *start, int num_u16)
+{
+ unsigned long sum = 0;
+ int i;
+
+ for (i = 0; i < num_u16; i++)
+ sum += start[i];
+
+ return sum;
+}
+
+static uint16_t build_ip_csum(const uint16_t *start, int num_u16,
+ unsigned long sum)
+{
+ sum += add_csum_hword(start, num_u16);
+
+ while (sum >> 16)
+ sum = (sum & 0xffff) + (sum >> 16);
+
+ return ~sum;
+}
+
+static int build_vnet_header(void *header)
+{
+ struct virtio_net_hdr *vh = header;
+
+ vh->hdr_len = ETH_HLEN + sizeof(struct iphdr) + sizeof(struct udphdr);
+
+ if (cfg_use_csum_off) {
+ vh->flags |= VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ vh->csum_start = ETH_HLEN + sizeof(struct iphdr);
+ vh->csum_offset = __builtin_offsetof(struct udphdr, check);
+
+ /* position check field exactly one byte beyond end of packet */
+ if (cfg_use_csum_off_bad)
+ vh->csum_start += sizeof(struct udphdr) + cfg_payload_len -
+ vh->csum_offset - 1;
+ }
+
+ if (cfg_use_gso) {
+ vh->gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ vh->gso_size = cfg_mtu - sizeof(struct iphdr);
+ }
+
+ return sizeof(*vh);
+}
+
+static int build_eth_header(void *header)
+{
+ struct ethhdr *eth = header;
+
+ if (cfg_use_vlan) {
+ uint16_t *tag = header + ETH_HLEN;
+
+ eth->h_proto = htons(ETH_P_8021Q);
+ tag[1] = htons(ETH_P_IP);
+ return ETH_HLEN + 4;
+ }
+
+ eth->h_proto = htons(ETH_P_IP);
+ return ETH_HLEN;
+}
+
+static int build_ipv4_header(void *header, int payload_len)
+{
+ struct iphdr *iph = header;
+
+ iph->ihl = 5;
+ iph->version = 4;
+ iph->ttl = 8;
+ iph->tot_len = htons(sizeof(*iph) + sizeof(struct udphdr) + payload_len);
+ iph->id = htons(1337);
+ iph->protocol = IPPROTO_UDP;
+ iph->saddr = htonl((172 << 24) | (17 << 16) | 2);
+ iph->daddr = htonl((172 << 24) | (17 << 16) | 1);
+ iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0);
+
+ return iph->ihl << 2;
+}
+
+static int build_udp_header(void *header, int payload_len)
+{
+ const int alen = sizeof(uint32_t);
+ struct udphdr *udph = header;
+ int len = sizeof(*udph) + payload_len;
+
+ udph->source = htons(9);
+ udph->dest = htons(cfg_port);
+ udph->len = htons(len);
+
+ if (cfg_use_csum_off)
+ udph->check = build_ip_csum(header - (2 * alen), alen,
+ htons(IPPROTO_UDP) + udph->len);
+ else
+ udph->check = 0;
+
+ return sizeof(*udph);
+}
+
+static int build_packet(int payload_len)
+{
+ int off = 0;
+
+ off += build_vnet_header(tbuf);
+ off += build_eth_header(tbuf + off);
+ off += build_ipv4_header(tbuf + off, payload_len);
+ off += build_udp_header(tbuf + off, payload_len);
+
+ if (off + payload_len > sizeof(tbuf))
+ error(1, 0, "payload length exceeds max");
+
+ memset(tbuf + off, DATA_CHAR, payload_len);
+
+ return off + payload_len;
+}
+
+static void do_bind(int fd)
+{
+ struct sockaddr_ll laddr = {0};
+
+ laddr.sll_family = AF_PACKET;
+ laddr.sll_protocol = htons(ETH_P_IP);
+ laddr.sll_ifindex = if_nametoindex(cfg_ifname);
+ if (!laddr.sll_ifindex)
+ error(1, errno, "if_nametoindex");
+
+ if (bind(fd, (void *)&laddr, sizeof(laddr)))
+ error(1, errno, "bind");
+}
+
+static void do_send(int fd, char *buf, int len)
+{
+ int ret;
+
+ if (!cfg_use_vnet) {
+ buf += sizeof(struct virtio_net_hdr);
+ len -= sizeof(struct virtio_net_hdr);
+ }
+ if (cfg_use_dgram) {
+ buf += ETH_HLEN;
+ len -= ETH_HLEN;
+ }
+
+ if (cfg_use_bind) {
+ ret = write(fd, buf, len);
+ } else {
+ struct sockaddr_ll laddr = {0};
+
+ laddr.sll_protocol = htons(ETH_P_IP);
+ laddr.sll_ifindex = if_nametoindex(cfg_ifname);
+ if (!laddr.sll_ifindex)
+ error(1, errno, "if_nametoindex");
+
+ ret = sendto(fd, buf, len, 0, (void *)&laddr, sizeof(laddr));
+ }
+
+ if (ret == -1)
+ error(1, errno, "write");
+ if (ret != len)
+ error(1, 0, "write: %u %u", ret, len);
+
+ fprintf(stderr, "tx: %u\n", ret);
+}
+
+static int do_tx(void)
+{
+ const int one = 1;
+ int fd, len;
+
+ fd = socket(PF_PACKET, cfg_use_dgram ? SOCK_DGRAM : SOCK_RAW, 0);
+ if (fd == -1)
+ error(1, errno, "socket t");
+
+ if (cfg_use_bind)
+ do_bind(fd);
+
+ if (cfg_use_qdisc_bypass &&
+ setsockopt(fd, SOL_PACKET, PACKET_QDISC_BYPASS, &one, sizeof(one)))
+ error(1, errno, "setsockopt qdisc bypass");
+
+ if (cfg_use_vnet &&
+ setsockopt(fd, SOL_PACKET, PACKET_VNET_HDR, &one, sizeof(one)))
+ error(1, errno, "setsockopt vnet");
+
+ len = build_packet(cfg_payload_len);
+
+ if (cfg_truncate_len < len)
+ len = cfg_truncate_len;
+
+ do_send(fd, tbuf, len);
+
+ if (close(fd))
+ error(1, errno, "close t");
+
+ return len;
+}
+
+static int setup_rx(void)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ struct sockaddr_in raddr = {0};
+ int fd;
+
+ fd = socket(PF_INET, SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket r");
+
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcv timeout");
+
+ raddr.sin_family = AF_INET;
+ raddr.sin_port = htons(cfg_port);
+ raddr.sin_addr.s_addr = htonl(INADDR_ANY);
+
+ if (bind(fd, (void *)&raddr, sizeof(raddr)))
+ error(1, errno, "bind r");
+
+ return fd;
+}
+
+static void do_rx(int fd, int expected_len, char *expected)
+{
+ int ret;
+
+ ret = recv(fd, rbuf, sizeof(rbuf), 0);
+ if (ret == -1)
+ error(1, errno, "recv");
+ if (ret != expected_len)
+ error(1, 0, "recv: %u != %u", ret, expected_len);
+
+ if (memcmp(rbuf, expected, ret))
+ error(1, 0, "recv: data mismatch");
+
+ fprintf(stderr, "rx: %u\n", ret);
+}
+
+static int setup_sniffer(void)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ int fd;
+
+ fd = socket(PF_PACKET, SOCK_RAW, 0);
+ if (fd == -1)
+ error(1, errno, "socket p");
+
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcv timeout");
+
+ pair_udp_setfilter(fd);
+ do_bind(fd);
+
+ return fd;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "bcCdgl:qt:vV")) != -1) {
+ switch (c) {
+ case 'b':
+ cfg_use_bind = true;
+ break;
+ case 'c':
+ cfg_use_csum_off = true;
+ break;
+ case 'C':
+ cfg_use_csum_off_bad = true;
+ break;
+ case 'd':
+ cfg_use_dgram = true;
+ break;
+ case 'g':
+ cfg_use_gso = true;
+ break;
+ case 'l':
+ cfg_payload_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'q':
+ cfg_use_qdisc_bypass = true;
+ break;
+ case 't':
+ cfg_truncate_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'v':
+ cfg_use_vnet = true;
+ break;
+ case 'V':
+ cfg_use_vlan = true;
+ break;
+ default:
+ error(1, 0, "%s: parse error", argv[0]);
+ }
+ }
+
+ if (cfg_use_vlan && cfg_use_dgram)
+ error(1, 0, "option vlan (-V) conflicts with dgram (-d)");
+
+ if (cfg_use_csum_off && !cfg_use_vnet)
+ error(1, 0, "option csum offload (-c) requires vnet (-v)");
+
+ if (cfg_use_csum_off_bad && !cfg_use_csum_off)
+ error(1, 0, "option csum bad (-C) requires csum offload (-c)");
+
+ if (cfg_use_gso && !cfg_use_csum_off)
+ error(1, 0, "option gso (-g) requires csum offload (-c)");
+}
+
+static void run_test(void)
+{
+ int fdr, fds, total_len;
+
+ fdr = setup_rx();
+ fds = setup_sniffer();
+
+ total_len = do_tx();
+
+ /* BPF filter accepts only this length, vlan changes MAC */
+ if (cfg_payload_len == DATA_LEN && !cfg_use_vlan)
+ do_rx(fds, total_len - sizeof(struct virtio_net_hdr),
+ tbuf + sizeof(struct virtio_net_hdr));
+
+ do_rx(fdr, cfg_payload_len, tbuf + total_len - cfg_payload_len);
+
+ if (close(fds))
+ error(1, errno, "close s");
+ if (close(fdr))
+ error(1, errno, "close r");
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ if (system("ip link set dev lo mtu 1500"))
+ error(1, errno, "ip link set mtu");
+ if (system("ip addr add dev lo 172.17.0.1/24"))
+ error(1, errno, "ip addr add");
+
+ run_test();
+
+ fprintf(stderr, "OK\n\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/net/psock_snd.sh b/tools/testing/selftests/net/psock_snd.sh
new file mode 100755
index 000000000000..6331d91b86a6
--- /dev/null
+++ b/tools/testing/selftests/net/psock_snd.sh
@@ -0,0 +1,98 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of packet socket send regression tests
+
+set -e
+
+readonly mtu=1500
+readonly iphlen=20
+readonly udphlen=8
+
+readonly vnet_hlen=10
+readonly eth_hlen=14
+
+readonly mss="$((${mtu} - ${iphlen} - ${udphlen}))"
+readonly mss_exceeds="$((${mss} + 1))"
+
+readonly max_mtu=65535
+readonly max_mss="$((${max_mtu} - ${iphlen} - ${udphlen}))"
+readonly max_mss_exceeds="$((${max_mss} + 1))"
+
+# functional checks (not a full cross-product)
+
+echo "dgram"
+./in_netns.sh ./psock_snd -d
+
+echo "dgram bind"
+./in_netns.sh ./psock_snd -d -b
+
+echo "raw"
+./in_netns.sh ./psock_snd
+
+echo "raw bind"
+./in_netns.sh ./psock_snd -b
+
+echo "raw qdisc bypass"
+./in_netns.sh ./psock_snd -q
+
+echo "raw vlan"
+./in_netns.sh ./psock_snd -V
+
+echo "raw vnet hdr"
+./in_netns.sh ./psock_snd -v
+
+echo "raw csum_off"
+./in_netns.sh ./psock_snd -v -c
+
+echo "raw csum_off with bad offset (fails)"
+(! ./in_netns.sh ./psock_snd -v -c -C)
+
+
+# bounds check: send {max, max + 1, min, min - 1} lengths
+
+echo "raw min size"
+./in_netns.sh ./psock_snd -l 0
+
+echo "raw mtu size"
+./in_netns.sh ./psock_snd -l "${mss}"
+
+echo "raw mtu size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -l "${mss_exceeds}")
+
+# fails due to ARPHRD_ETHER check in packet_extra_vlan_len_allowed
+#
+# echo "raw vlan mtu size"
+# ./in_netns.sh ./psock_snd -V -l "${mss}"
+
+echo "raw vlan mtu size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -V -l "${mss_exceeds}")
+
+echo "dgram mtu size"
+./in_netns.sh ./psock_snd -d -l "${mss}"
+
+echo "dgram mtu size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -d -l "${mss_exceeds}")
+
+echo "raw truncate hlen (fails: does not arrive)"
+(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen}))")
+
+echo "raw truncate hlen - 1 (fails: EINVAL)"
+(! ./in_netns.sh ./psock_snd -t "$((${vnet_hlen} + ${eth_hlen} - 1))")
+
+
+# gso checks: implies -l, because with gso len must exceed gso_size
+
+echo "raw gso min size"
+./in_netns.sh ./psock_snd -v -c -g -l "${mss_exceeds}"
+
+echo "raw gso min size - 1 (fails)"
+(! ./in_netns.sh ./psock_snd -v -c -g -l "${mss}")
+
+echo "raw gso max size"
+./in_netns.sh ./psock_snd -v -c -g -l "${max_mss}"
+
+echo "raw gso max size + 1 (fails)"
+(! ./in_netns.sh ./psock_snd -v -c -g -l "${max_mss_exceeds}")
+
+echo "OK. All tests passed"
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 7f6cd9fdacf3..7ec4fa4d55dc 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -60,6 +60,8 @@
#include "psock_lib.h"
+#include "../kselftest.h"
+
#ifndef bug_on
# define bug_on(cond) assert(!(cond))
#endif
@@ -825,7 +827,7 @@ static int test_tpacket(int version, int type)
fprintf(stderr, "test: skip %s %s since user and kernel "
"space have different bit width\n",
tpacket_str[version], type_str[type]);
- return 0;
+ return KSFT_SKIP;
}
sock = pfsocket(version);
diff --git a/tools/testing/selftests/net/reuseport_bpf_numa.c b/tools/testing/selftests/net/reuseport_bpf_numa.c
index 365c32e84189..c9f478b40996 100644
--- a/tools/testing/selftests/net/reuseport_bpf_numa.c
+++ b/tools/testing/selftests/net/reuseport_bpf_numa.c
@@ -23,6 +23,8 @@
#include <unistd.h>
#include <numa.h>
+#include "../kselftest.h"
+
static const int PORT = 8888;
static void build_rcv_group(int *rcv_fd, size_t len, int family, int proto)
@@ -229,7 +231,7 @@ int main(void)
int *rcv_fd, nodes;
if (numa_available() < 0)
- error(1, errno, "no numa api support");
+ ksft_exit_skip("no numa api support\n");
nodes = numa_max_node() + 1;
diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index e6f485235435..0d7a44fa30af 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -7,6 +7,9 @@
devdummy="test-dummy0"
ret=0
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
# set global exit status, but never reset nonzero one.
check_err()
{
@@ -333,7 +336,7 @@ kci_test_vrf()
ip link show type vrf 2>/dev/null
if [ $? -ne 0 ]; then
echo "SKIP: vrf: iproute2 too old"
- return 0
+ return $ksft_skip
fi
ip link add "$vrfname" type vrf table 10
@@ -409,7 +412,7 @@ kci_test_encap_fou()
ip fou help 2>&1 |grep -q 'Usage: ip fou'
if [ $? -ne 0 ];then
echo "SKIP: fou: iproute2 too old"
- return 1
+ return $ksft_skip
fi
ip netns exec "$testns" ip fou add port 7777 ipproto 47 2>/dev/null
@@ -444,7 +447,7 @@ kci_test_encap()
ip netns add "$testns"
if [ $? -ne 0 ]; then
echo "SKIP encap tests: cannot add net namespace $testns"
- return 1
+ return $ksft_skip
fi
ip netns exec "$testns" ip link set lo up
@@ -469,7 +472,7 @@ kci_test_macsec()
ip macsec help 2>&1 | grep -q "^Usage: ip macsec"
if [ $? -ne 0 ]; then
echo "SKIP: macsec: iproute2 too old"
- return 0
+ return $ksft_skip
fi
ip link add link "$devdummy" "$msname" type macsec port 42 encrypt on
@@ -502,6 +505,108 @@ kci_test_macsec()
echo "PASS: macsec"
}
+#-------------------------------------------------------------------
+# Example commands
+# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
+# spi 0x07 mode transport reqid 0x07 replay-window 32 \
+# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+# sel src 14.0.0.52/24 dst 14.0.0.70/24
+# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \
+# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \
+# spi 0x07 mode transport reqid 0x07
+#
+# Subcommands not tested
+# ip x s update
+# ip x s allocspi
+# ip x s deleteall
+# ip x p update
+# ip x p deleteall
+# ip x p set
+#-------------------------------------------------------------------
+kci_test_ipsec()
+{
+ srcip="14.0.0.52"
+ dstip="14.0.0.70"
+ algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+
+ # flush to be sure there's nothing configured
+ ip x s flush ; ip x p flush
+ check_err $?
+
+ # start the monitor in the background
+ tmpfile=`mktemp ipsectestXXX`
+ ip x m > $tmpfile &
+ mpid=$!
+ sleep 0.2
+
+ ipsecid="proto esp src $srcip dst $dstip spi 0x07"
+ ip x s add $ipsecid \
+ mode transport reqid 0x07 replay-window 32 \
+ $algo sel src $srcip/24 dst $dstip/24
+ check_err $?
+
+ lines=`ip x s list | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x s count | grep -q "SAD count 1"
+ check_err $?
+
+ lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x s delete $ipsecid
+ check_err $?
+
+ lines=`ip x s list | wc -l`
+ test $lines -eq 0
+ check_err $?
+
+ ipsecsel="dir out src $srcip/24 dst $dstip/24"
+ ip x p add $ipsecsel \
+ tmpl proto esp src $srcip dst $dstip \
+ spi 0x07 mode transport reqid 0x07
+ check_err $?
+
+ lines=`ip x p list | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x p count | grep -q "SPD IN 0 OUT 1 FWD 0"
+ check_err $?
+
+ lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l`
+ test $lines -eq 2
+ check_err $?
+
+ ip x p delete $ipsecsel
+ check_err $?
+
+ lines=`ip x p list | wc -l`
+ test $lines -eq 0
+ check_err $?
+
+ # check the monitor results
+ kill $mpid
+ lines=`wc -l $tmpfile | cut "-d " -f1`
+ test $lines -eq 20
+ check_err $?
+ rm -rf $tmpfile
+
+ # clean up any leftovers
+ ip x s flush
+ check_err $?
+ ip x p flush
+ check_err $?
+
+ if [ $ret -ne 0 ]; then
+ echo "FAIL: ipsec"
+ return 1
+ fi
+ echo "PASS: ipsec"
+}
+
kci_test_gretap()
{
testns="testns"
@@ -511,14 +616,14 @@ kci_test_gretap()
ip netns add "$testns"
if [ $? -ne 0 ]; then
echo "SKIP gretap tests: cannot add net namespace $testns"
- return 1
+ return $ksft_skip
fi
ip link help gretap 2>&1 | grep -q "^Usage:"
if [ $? -ne 0 ];then
echo "SKIP: gretap: iproute2 too old"
ip netns del "$testns"
- return 1
+ return $ksft_skip
fi
# test native tunnel
@@ -561,14 +666,14 @@ kci_test_ip6gretap()
ip netns add "$testns"
if [ $? -ne 0 ]; then
echo "SKIP ip6gretap tests: cannot add net namespace $testns"
- return 1
+ return $ksft_skip
fi
ip link help ip6gretap 2>&1 | grep -q "^Usage:"
if [ $? -ne 0 ];then
echo "SKIP: ip6gretap: iproute2 too old"
ip netns del "$testns"
- return 1
+ return $ksft_skip
fi
# test native tunnel
@@ -611,13 +716,13 @@ kci_test_erspan()
ip link help erspan 2>&1 | grep -q "^Usage:"
if [ $? -ne 0 ];then
echo "SKIP: erspan: iproute2 too old"
- return 1
+ return $ksft_skip
fi
ip netns add "$testns"
if [ $? -ne 0 ]; then
echo "SKIP erspan tests: cannot add net namespace $testns"
- return 1
+ return $ksft_skip
fi
# test native tunnel erspan v1
@@ -676,13 +781,13 @@ kci_test_ip6erspan()
ip link help ip6erspan 2>&1 | grep -q "^Usage:"
if [ $? -ne 0 ];then
echo "SKIP: ip6erspan: iproute2 too old"
- return 1
+ return $ksft_skip
fi
ip netns add "$testns"
if [ $? -ne 0 ]; then
echo "SKIP ip6erspan tests: cannot add net namespace $testns"
- return 1
+ return $ksft_skip
fi
# test native tunnel ip6erspan v1
@@ -755,6 +860,7 @@ kci_test_rtnl()
kci_test_vrf
kci_test_encap
kci_test_macsec
+ kci_test_ipsec
kci_del_dummy
}
@@ -762,14 +868,14 @@ kci_test_rtnl()
#check for needed privileges
if [ "$(id -u)" -ne 0 ];then
echo "SKIP: Need root privileges"
- exit 0
+ exit $ksft_skip
fi
for x in ip tc;do
$x -Version 2>/dev/null >/dev/null
if [ $? -ne 0 ];then
echo "SKIP: Could not run test without the $x tool"
- exit 0
+ exit $ksft_skip
fi
done
diff --git a/tools/testing/selftests/net/tcp_inq.c b/tools/testing/selftests/net/tcp_inq.c
new file mode 100644
index 000000000000..d044b29ddabc
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_inq.c
@@ -0,0 +1,189 @@
+/*
+ * Copyright 2018 Google Inc.
+ * Author: Soheil Hassas Yeganeh (soheil@google.com)
+ *
+ * Simple example on how to use TCP_INQ and TCP_CM_INQ.
+ *
+ * License (GPLv2):
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ */
+#define _GNU_SOURCE
+
+#include <error.h>
+#include <netinet/in.h>
+#include <netinet/tcp.h>
+#include <pthread.h>
+#include <stdio.h>
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <unistd.h>
+
+#ifndef TCP_INQ
+#define TCP_INQ 36
+#endif
+
+#ifndef TCP_CM_INQ
+#define TCP_CM_INQ TCP_INQ
+#endif
+
+#define BUF_SIZE 8192
+#define CMSG_SIZE 32
+
+static int family = AF_INET6;
+static socklen_t addr_len = sizeof(struct sockaddr_in6);
+static int port = 4974;
+
+static void setup_loopback_addr(int family, struct sockaddr_storage *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (family) {
+ case PF_INET:
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = AF_INET;
+ addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+ addr4->sin_port = htons(port);
+ break;
+ case PF_INET6:
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_addr = in6addr_loopback;
+ addr6->sin6_port = htons(port);
+ break;
+ default:
+ error(1, 0, "illegal family");
+ }
+}
+
+void *start_server(void *arg)
+{
+ int server_fd = (int)(unsigned long)arg;
+ struct sockaddr_in addr;
+ socklen_t addrlen = sizeof(addr);
+ char *buf;
+ int fd;
+ int r;
+
+ buf = malloc(BUF_SIZE);
+
+ for (;;) {
+ fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen);
+ if (fd == -1) {
+ perror("accept");
+ break;
+ }
+ do {
+ r = send(fd, buf, BUF_SIZE, 0);
+ } while (r < 0 && errno == EINTR);
+ if (r < 0)
+ perror("send");
+ if (r != BUF_SIZE)
+ fprintf(stderr, "can only send %d bytes\n", r);
+ /* TCP_INQ can overestimate in-queue by one byte if we send
+ * the FIN packet. Sleep for 1 second, so that the client
+ * likely invoked recvmsg().
+ */
+ sleep(1);
+ close(fd);
+ }
+
+ free(buf);
+ close(server_fd);
+ pthread_exit(0);
+}
+
+int main(int argc, char *argv[])
+{
+ struct sockaddr_storage listen_addr, addr;
+ int c, one = 1, inq = -1;
+ pthread_t server_thread;
+ char cmsgbuf[CMSG_SIZE];
+ struct iovec iov[1];
+ struct cmsghdr *cm;
+ struct msghdr msg;
+ int server_fd, fd;
+ char *buf;
+
+ while ((c = getopt(argc, argv, "46p:")) != -1) {
+ switch (c) {
+ case '4':
+ family = PF_INET;
+ addr_len = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ family = PF_INET6;
+ addr_len = sizeof(struct sockaddr_in6);
+ break;
+ case 'p':
+ port = atoi(optarg);
+ break;
+ }
+ }
+
+ server_fd = socket(family, SOCK_STREAM, 0);
+ if (server_fd < 0)
+ error(1, errno, "server socket");
+ setup_loopback_addr(family, &listen_addr);
+ if (setsockopt(server_fd, SOL_SOCKET, SO_REUSEADDR,
+ &one, sizeof(one)) != 0)
+ error(1, errno, "setsockopt(SO_REUSEADDR)");
+ if (bind(server_fd, (const struct sockaddr *)&listen_addr,
+ addr_len) == -1)
+ error(1, errno, "bind");
+ if (listen(server_fd, 128) == -1)
+ error(1, errno, "listen");
+ if (pthread_create(&server_thread, NULL, start_server,
+ (void *)(unsigned long)server_fd) != 0)
+ error(1, errno, "pthread_create");
+
+ fd = socket(family, SOCK_STREAM, 0);
+ if (fd < 0)
+ error(1, errno, "client socket");
+ setup_loopback_addr(family, &addr);
+ if (connect(fd, (const struct sockaddr *)&addr, addr_len) == -1)
+ error(1, errno, "connect");
+ if (setsockopt(fd, SOL_TCP, TCP_INQ, &one, sizeof(one)) != 0)
+ error(1, errno, "setsockopt(TCP_INQ)");
+
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_iov = iov;
+ msg.msg_iovlen = 1;
+ msg.msg_control = cmsgbuf;
+ msg.msg_controllen = sizeof(cmsgbuf);
+ msg.msg_flags = 0;
+
+ buf = malloc(BUF_SIZE);
+ iov[0].iov_base = buf;
+ iov[0].iov_len = BUF_SIZE / 2;
+
+ if (recvmsg(fd, &msg, 0) != iov[0].iov_len)
+ error(1, errno, "recvmsg");
+ if (msg.msg_flags & MSG_CTRUNC)
+ error(1, 0, "control message is truncated");
+
+ for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm))
+ if (cm->cmsg_level == SOL_TCP && cm->cmsg_type == TCP_CM_INQ)
+ inq = *((int *) CMSG_DATA(cm));
+
+ if (inq != BUF_SIZE - iov[0].iov_len) {
+ fprintf(stderr, "unexpected inq: %d\n", inq);
+ exit(1);
+ }
+
+ printf("PASSED\n");
+ free(buf);
+ close(fd);
+ return 0;
+}
diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c
new file mode 100644
index 000000000000..77f762780199
--- /dev/null
+++ b/tools/testing/selftests/net/tcp_mmap.c
@@ -0,0 +1,447 @@
+/*
+ * Copyright 2018 Google Inc.
+ * Author: Eric Dumazet (edumazet@google.com)
+ *
+ * Reference program demonstrating tcp mmap() usage,
+ * and SO_RCVLOWAT hints for receiver.
+ *
+ * Note : NIC with header split is needed to use mmap() on TCP :
+ * Each incoming frame must be a multiple of PAGE_SIZE bytes of TCP payload.
+ *
+ * How to use on loopback interface :
+ *
+ * ifconfig lo mtu 61512 # 15*4096 + 40 (ipv6 header) + 32 (TCP with TS option header)
+ * tcp_mmap -s -z &
+ * tcp_mmap -H ::1 -z
+ *
+ * Or leave default lo mtu, but use -M option to set TCP_MAXSEG option to (4096 + 12)
+ * (4096 : page size on x86, 12: TCP TS option length)
+ * tcp_mmap -s -z -M $((4096+12)) &
+ * tcp_mmap -H ::1 -z -M $((4096+12))
+ *
+ * Note: -z option on sender uses MSG_ZEROCOPY, which forces a copy when packets go through loopback interface.
+ * We might use sendfile() instead, but really this test program is about mmap(), for receivers ;)
+ *
+ * $ ./tcp_mmap -s & # Without mmap()
+ * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done
+ * received 32768 MB (0 % mmap'ed) in 14.1157 s, 19.4732 Gbit
+ * cpu usage user:0.057 sys:7.815, 240.234 usec per MB, 65531 c-switches
+ * received 32768 MB (0 % mmap'ed) in 14.6833 s, 18.7204 Gbit
+ * cpu usage user:0.043 sys:8.103, 248.596 usec per MB, 65524 c-switches
+ * received 32768 MB (0 % mmap'ed) in 11.143 s, 24.6682 Gbit
+ * cpu usage user:0.044 sys:6.576, 202.026 usec per MB, 65519 c-switches
+ * received 32768 MB (0 % mmap'ed) in 14.9056 s, 18.4413 Gbit
+ * cpu usage user:0.036 sys:8.193, 251.129 usec per MB, 65530 c-switches
+ * $ kill %1 # kill tcp_mmap server
+ *
+ * $ ./tcp_mmap -s -z & # With mmap()
+ * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done
+ * received 32768 MB (99.9939 % mmap'ed) in 6.73792 s, 40.7956 Gbit
+ * cpu usage user:0.045 sys:2.827, 87.6465 usec per MB, 65532 c-switches
+ * received 32768 MB (99.9939 % mmap'ed) in 7.26732 s, 37.8238 Gbit
+ * cpu usage user:0.037 sys:3.087, 95.3369 usec per MB, 65532 c-switches
+ * received 32768 MB (99.9939 % mmap'ed) in 7.61661 s, 36.0893 Gbit
+ * cpu usage user:0.046 sys:3.559, 110.016 usec per MB, 65529 c-switches
+ * received 32768 MB (99.9939 % mmap'ed) in 7.43764 s, 36.9577 Gbit
+ * cpu usage user:0.035 sys:3.467, 106.873 usec per MB, 65530 c-switches
+ *
+ * License (GPLv2):
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sys/types.h>
+#include <fcntl.h>
+#include <error.h>
+#include <sys/socket.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <errno.h>
+#include <time.h>
+#include <sys/time.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+#include <poll.h>
+#include <linux/tcp.h>
+#include <assert.h>
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY 0x4000000
+#endif
+
+#define FILE_SZ (1UL << 35)
+static int cfg_family = AF_INET6;
+static socklen_t cfg_alen = sizeof(struct sockaddr_in6);
+static int cfg_port = 8787;
+
+static int rcvbuf; /* Default: autotuning. Can be set with -r <integer> option */
+static int sndbuf; /* Default: autotuning. Can be set with -w <integer> option */
+static int zflg; /* zero copy option. (MSG_ZEROCOPY for sender, mmap() for receiver */
+static int xflg; /* hash received data (simple xor) (-h option) */
+static int keepflag; /* -k option: receiver shall keep all received file in memory (no munmap() calls) */
+
+static int chunk_size = 512*1024;
+
+unsigned long htotal;
+
+static inline void prefetch(const void *x)
+{
+#if defined(__x86_64__)
+ asm volatile("prefetcht0 %P0" : : "m" (*(const char *)x));
+#endif
+}
+
+void hash_zone(void *zone, unsigned int length)
+{
+ unsigned long temp = htotal;
+
+ while (length >= 8*sizeof(long)) {
+ prefetch(zone + 384);
+ temp ^= *(unsigned long *)zone;
+ temp ^= *(unsigned long *)(zone + sizeof(long));
+ temp ^= *(unsigned long *)(zone + 2*sizeof(long));
+ temp ^= *(unsigned long *)(zone + 3*sizeof(long));
+ temp ^= *(unsigned long *)(zone + 4*sizeof(long));
+ temp ^= *(unsigned long *)(zone + 5*sizeof(long));
+ temp ^= *(unsigned long *)(zone + 6*sizeof(long));
+ temp ^= *(unsigned long *)(zone + 7*sizeof(long));
+ zone += 8*sizeof(long);
+ length -= 8*sizeof(long);
+ }
+ while (length >= 1) {
+ temp ^= *(unsigned char *)zone;
+ zone += 1;
+ length--;
+ }
+ htotal = temp;
+}
+
+void *child_thread(void *arg)
+{
+ unsigned long total_mmap = 0, total = 0;
+ struct tcp_zerocopy_receive zc;
+ unsigned long delta_usec;
+ int flags = MAP_SHARED;
+ struct timeval t0, t1;
+ char *buffer = NULL;
+ void *addr = NULL;
+ double throughput;
+ struct rusage ru;
+ int lu, fd;
+
+ fd = (int)(unsigned long)arg;
+
+ gettimeofday(&t0, NULL);
+
+ fcntl(fd, F_SETFL, O_NDELAY);
+ buffer = malloc(chunk_size);
+ if (!buffer) {
+ perror("malloc");
+ goto error;
+ }
+ if (zflg) {
+ addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0);
+ if (addr == (void *)-1)
+ zflg = 0;
+ }
+ while (1) {
+ struct pollfd pfd = { .fd = fd, .events = POLLIN, };
+ int sub;
+
+ poll(&pfd, 1, 10000);
+ if (zflg) {
+ socklen_t zc_len = sizeof(zc);
+ int res;
+
+ zc.address = (__u64)addr;
+ zc.length = chunk_size;
+ zc.recv_skip_hint = 0;
+ res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE,
+ &zc, &zc_len);
+ if (res == -1)
+ break;
+
+ if (zc.length) {
+ assert(zc.length <= chunk_size);
+ total_mmap += zc.length;
+ if (xflg)
+ hash_zone(addr, zc.length);
+ total += zc.length;
+ }
+ if (zc.recv_skip_hint) {
+ assert(zc.recv_skip_hint <= chunk_size);
+ lu = read(fd, buffer, zc.recv_skip_hint);
+ if (lu > 0) {
+ if (xflg)
+ hash_zone(buffer, lu);
+ total += lu;
+ }
+ }
+ continue;
+ }
+ sub = 0;
+ while (sub < chunk_size) {
+ lu = read(fd, buffer + sub, chunk_size - sub);
+ if (lu == 0)
+ goto end;
+ if (lu < 0)
+ break;
+ if (xflg)
+ hash_zone(buffer + sub, lu);
+ total += lu;
+ sub += lu;
+ }
+ }
+end:
+ gettimeofday(&t1, NULL);
+ delta_usec = (t1.tv_sec - t0.tv_sec) * 1000000 + t1.tv_usec - t0.tv_usec;
+
+ throughput = 0;
+ if (delta_usec)
+ throughput = total * 8.0 / (double)delta_usec / 1000.0;
+ getrusage(RUSAGE_THREAD, &ru);
+ if (total > 1024*1024) {
+ unsigned long total_usec;
+ unsigned long mb = total >> 20;
+ total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec +
+ 1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec;
+ printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n"
+ " cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n",
+ total / (1024.0 * 1024.0),
+ 100.0*total_mmap/total,
+ (double)delta_usec / 1000000.0,
+ throughput,
+ (double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0,
+ (double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0,
+ (double)total_usec/mb,
+ ru.ru_nvcsw);
+ }
+error:
+ free(buffer);
+ close(fd);
+ if (zflg)
+ munmap(addr, chunk_size);
+ pthread_exit(0);
+}
+
+static void apply_rcvsnd_buf(int fd)
+{
+ if (rcvbuf && setsockopt(fd, SOL_SOCKET,
+ SO_RCVBUF, &rcvbuf, sizeof(rcvbuf)) == -1) {
+ perror("setsockopt SO_RCVBUF");
+ }
+
+ if (sndbuf && setsockopt(fd, SOL_SOCKET,
+ SO_SNDBUF, &sndbuf, sizeof(sndbuf)) == -1) {
+ perror("setsockopt SO_SNDBUF");
+ }
+}
+
+
+static void setup_sockaddr(int domain, const char *str_addr,
+ struct sockaddr_storage *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (domain) {
+ case PF_INET:
+ memset(addr4, 0, sizeof(*addr4));
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (str_addr &&
+ inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", str_addr);
+ break;
+ case PF_INET6:
+ memset(addr6, 0, sizeof(*addr6));
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (str_addr &&
+ inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", str_addr);
+ break;
+ default:
+ error(1, 0, "illegal domain");
+ }
+}
+
+static void do_accept(int fdlisten)
+{
+ if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT,
+ &chunk_size, sizeof(chunk_size)) == -1) {
+ perror("setsockopt SO_RCVLOWAT");
+ }
+
+ apply_rcvsnd_buf(fdlisten);
+
+ while (1) {
+ struct sockaddr_in addr;
+ socklen_t addrlen = sizeof(addr);
+ pthread_t th;
+ int fd, res;
+
+ fd = accept(fdlisten, (struct sockaddr *)&addr, &addrlen);
+ if (fd == -1) {
+ perror("accept");
+ continue;
+ }
+ res = pthread_create(&th, NULL, child_thread,
+ (void *)(unsigned long)fd);
+ if (res) {
+ errno = res;
+ perror("pthread_create");
+ close(fd);
+ }
+ }
+}
+
+int main(int argc, char *argv[])
+{
+ struct sockaddr_storage listenaddr, addr;
+ unsigned int max_pacing_rate = 0;
+ unsigned long total = 0;
+ char *host = NULL;
+ int fd, c, on = 1;
+ char *buffer;
+ int sflg = 0;
+ int mss = 0;
+
+ while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:")) != -1) {
+ switch (c) {
+ case '4':
+ cfg_family = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ cfg_family = PF_INET6;
+ cfg_alen = sizeof(struct sockaddr_in6);
+ break;
+ case 'p':
+ cfg_port = atoi(optarg);
+ break;
+ case 'H':
+ host = optarg;
+ break;
+ case 's': /* server : listen for incoming connections */
+ sflg++;
+ break;
+ case 'r':
+ rcvbuf = atoi(optarg);
+ break;
+ case 'w':
+ sndbuf = atoi(optarg);
+ break;
+ case 'z':
+ zflg = 1;
+ break;
+ case 'M':
+ mss = atoi(optarg);
+ break;
+ case 'x':
+ xflg = 1;
+ break;
+ case 'k':
+ keepflag = 1;
+ break;
+ case 'P':
+ max_pacing_rate = atoi(optarg) ;
+ break;
+ default:
+ exit(1);
+ }
+ }
+ if (sflg) {
+ int fdlisten = socket(cfg_family, SOCK_STREAM, 0);
+
+ if (fdlisten == -1) {
+ perror("socket");
+ exit(1);
+ }
+ apply_rcvsnd_buf(fdlisten);
+ setsockopt(fdlisten, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on));
+
+ setup_sockaddr(cfg_family, host, &listenaddr);
+
+ if (mss &&
+ setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG,
+ &mss, sizeof(mss)) == -1) {
+ perror("setsockopt TCP_MAXSEG");
+ exit(1);
+ }
+ if (bind(fdlisten, (const struct sockaddr *)&listenaddr, cfg_alen) == -1) {
+ perror("bind");
+ exit(1);
+ }
+ if (listen(fdlisten, 128) == -1) {
+ perror("listen");
+ exit(1);
+ }
+ do_accept(fdlisten);
+ }
+ buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (buffer == (char *)-1) {
+ perror("mmap");
+ exit(1);
+ }
+
+ fd = socket(AF_INET6, SOCK_STREAM, 0);
+ if (fd == -1) {
+ perror("socket");
+ exit(1);
+ }
+ apply_rcvsnd_buf(fd);
+
+ setup_sockaddr(cfg_family, host, &addr);
+
+ if (mss &&
+ setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) {
+ perror("setsockopt TCP_MAXSEG");
+ exit(1);
+ }
+ if (connect(fd, (const struct sockaddr *)&addr, cfg_alen) == -1) {
+ perror("connect");
+ exit(1);
+ }
+ if (max_pacing_rate &&
+ setsockopt(fd, SOL_SOCKET, SO_MAX_PACING_RATE,
+ &max_pacing_rate, sizeof(max_pacing_rate)) == -1)
+ perror("setsockopt SO_MAX_PACING_RATE");
+
+ if (zflg && setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY,
+ &on, sizeof(on)) == -1) {
+ perror("setsockopt SO_ZEROCOPY, (-z option disabled)");
+ zflg = 0;
+ }
+ while (total < FILE_SZ) {
+ long wr = FILE_SZ - total;
+
+ if (wr > chunk_size)
+ wr = chunk_size;
+ /* Note : we just want to fill the pipe with 0 bytes */
+ wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0);
+ if (wr <= 0)
+ break;
+ total += wr;
+ }
+ close(fd);
+ munmap(buffer, chunk_size);
+ return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c
new file mode 100644
index 000000000000..e279051bc631
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.c
@@ -0,0 +1,693 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <stddef.h>
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <net/if.h>
+#include <linux/in.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <netinet/if_ether.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT 103
+#endif
+
+#ifndef UDP_MAX_SEGMENTS
+#define UDP_MAX_SEGMENTS (1 << 6UL)
+#endif
+
+#define CONST_MTU_TEST 1500
+
+#define CONST_HDRLEN_V4 (sizeof(struct iphdr) + sizeof(struct udphdr))
+#define CONST_HDRLEN_V6 (sizeof(struct ip6_hdr) + sizeof(struct udphdr))
+
+#define CONST_MSS_V4 (CONST_MTU_TEST - CONST_HDRLEN_V4)
+#define CONST_MSS_V6 (CONST_MTU_TEST - CONST_HDRLEN_V6)
+
+#define CONST_MAX_SEGS_V4 (ETH_MAX_MTU / CONST_MSS_V4)
+#define CONST_MAX_SEGS_V6 (ETH_MAX_MTU / CONST_MSS_V6)
+
+static bool cfg_do_ipv4;
+static bool cfg_do_ipv6;
+static bool cfg_do_connected;
+static bool cfg_do_connectionless;
+static bool cfg_do_msgmore;
+static bool cfg_do_setsockopt;
+static int cfg_specific_test_id = -1;
+
+static const char cfg_ifname[] = "lo";
+static unsigned short cfg_port = 9000;
+
+static char buf[ETH_MAX_MTU];
+
+struct testcase {
+ int tlen; /* send() buffer size, may exceed mss */
+ bool tfail; /* send() call is expected to fail */
+ int gso_len; /* mss after applying gso */
+ int r_num_mss; /* recv(): number of calls of full mss */
+ int r_len_last; /* recv(): size of last non-mss dgram, if any */
+};
+
+const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT;
+const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) };
+
+struct testcase testcases_v4[] = {
+ {
+ /* no GSO: send a single byte */
+ .tlen = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* no GSO: send a single MSS */
+ .tlen = CONST_MSS_V4,
+ .r_num_mss = 1,
+ },
+ {
+ /* no GSO: send a single MSS + 1B: fail */
+ .tlen = CONST_MSS_V4 + 1,
+ .tfail = true,
+ },
+ {
+ /* send a single MSS: will fail with GSO, because the segment
+ * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+ */
+ .tlen = CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send a single MSS + 1B */
+ .tlen = CONST_MSS_V4 + 1,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* send exactly 2 MSS */
+ .tlen = CONST_MSS_V4 * 2,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2 MSS + 1B */
+ .tlen = (CONST_MSS_V4 * 2) + 1,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send MAX segs */
+ .tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4),
+ },
+
+ {
+ /* send MAX bytes */
+ .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4,
+ .gso_len = CONST_MSS_V4,
+ .r_num_mss = CONST_MAX_SEGS_V4,
+ .r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 -
+ (CONST_MAX_SEGS_V4 * CONST_MSS_V4),
+ },
+ {
+ /* send MAX + 1: fail */
+ .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1,
+ .gso_len = CONST_MSS_V4,
+ .tfail = true,
+ },
+ {
+ /* send a single 1B MSS: will fail, see single MSS above */
+ .tlen = 1,
+ .gso_len = 1,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send 2 1B segments */
+ .tlen = 2,
+ .gso_len = 1,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2B + 2B + 1B segments */
+ .tlen = 5,
+ .gso_len = 2,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send max number of min sized segments */
+ .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+ .gso_len = 1,
+ .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4,
+ },
+ {
+ /* send max number + 1 of min sized segments: fail */
+ .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V4 + 1,
+ .gso_len = 1,
+ .tfail = true,
+ },
+ {
+ /* EOL */
+ }
+};
+
+#ifndef IP6_MAX_MTU
+#define IP6_MAX_MTU (ETH_MAX_MTU + sizeof(struct ip6_hdr))
+#endif
+
+struct testcase testcases_v6[] = {
+ {
+ /* no GSO: send a single byte */
+ .tlen = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* no GSO: send a single MSS */
+ .tlen = CONST_MSS_V6,
+ .r_num_mss = 1,
+ },
+ {
+ /* no GSO: send a single MSS + 1B: fail */
+ .tlen = CONST_MSS_V6 + 1,
+ .tfail = true,
+ },
+ {
+ /* send a single MSS: will fail with GSO, because the segment
+ * logic in udp4_ufo_fragment demands a gso skb to be > MTU
+ */
+ .tlen = CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send a single MSS + 1B */
+ .tlen = CONST_MSS_V6 + 1,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 1,
+ .r_len_last = 1,
+ },
+ {
+ /* send exactly 2 MSS */
+ .tlen = CONST_MSS_V6 * 2,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2 MSS + 1B */
+ .tlen = (CONST_MSS_V6 * 2) + 1,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send MAX segs */
+ .tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6),
+ },
+
+ {
+ /* send MAX bytes */
+ .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6,
+ .gso_len = CONST_MSS_V6,
+ .r_num_mss = CONST_MAX_SEGS_V6,
+ .r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 -
+ (CONST_MAX_SEGS_V6 * CONST_MSS_V6),
+ },
+ {
+ /* send MAX + 1: fail */
+ .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1,
+ .gso_len = CONST_MSS_V6,
+ .tfail = true,
+ },
+ {
+ /* send a single 1B MSS: will fail, see single MSS above */
+ .tlen = 1,
+ .gso_len = 1,
+ .tfail = true,
+ .r_num_mss = 1,
+ },
+ {
+ /* send 2 1B segments */
+ .tlen = 2,
+ .gso_len = 1,
+ .r_num_mss = 2,
+ },
+ {
+ /* send 2B + 2B + 1B segments */
+ .tlen = 5,
+ .gso_len = 2,
+ .r_num_mss = 2,
+ .r_len_last = 1,
+ },
+ {
+ /* send max number of min sized segments */
+ .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+ .gso_len = 1,
+ .r_num_mss = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6,
+ },
+ {
+ /* send max number + 1 of min sized segments: fail */
+ .tlen = UDP_MAX_SEGMENTS - CONST_HDRLEN_V6 + 1,
+ .gso_len = 1,
+ .tfail = true,
+ },
+ {
+ /* EOL */
+ }
+};
+
+static unsigned int get_device_mtu(int fd, const char *ifname)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCGIFMTU, &ifr))
+ error(1, errno, "ioctl get mtu");
+
+ return ifr.ifr_mtu;
+}
+
+static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu)
+{
+ struct ifreq ifr;
+
+ memset(&ifr, 0, sizeof(ifr));
+
+ ifr.ifr_mtu = mtu;
+ strcpy(ifr.ifr_name, ifname);
+
+ if (ioctl(fd, SIOCSIFMTU, &ifr))
+ error(1, errno, "ioctl set mtu");
+}
+
+static void set_device_mtu(int fd, int mtu)
+{
+ int val;
+
+ val = get_device_mtu(fd, cfg_ifname);
+ fprintf(stderr, "device mtu (orig): %u\n", val);
+
+ __set_device_mtu(fd, cfg_ifname, mtu);
+ val = get_device_mtu(fd, cfg_ifname);
+ if (val != mtu)
+ error(1, 0, "unable to set device mtu to %u\n", val);
+
+ fprintf(stderr, "device mtu (test): %u\n", val);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+ int level, name, val;
+
+ if (is_ipv4) {
+ level = SOL_IP;
+ name = IP_MTU_DISCOVER;
+ val = IP_PMTUDISC_DO;
+ } else {
+ level = SOL_IPV6;
+ name = IPV6_MTU_DISCOVER;
+ val = IPV6_PMTUDISC_DO;
+ }
+
+ if (setsockopt(fd, level, name, &val, sizeof(val)))
+ error(1, errno, "setsockopt path mtu");
+}
+
+static unsigned int get_path_mtu(int fd, bool is_ipv4)
+{
+ socklen_t vallen;
+ unsigned int mtu;
+ int ret;
+
+ vallen = sizeof(mtu);
+ if (is_ipv4)
+ ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen);
+ else
+ ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen);
+
+ if (ret)
+ error(1, errno, "getsockopt mtu");
+
+
+ fprintf(stderr, "path mtu (read): %u\n", mtu);
+ return mtu;
+}
+
+/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */
+static void set_route_mtu(int mtu, bool is_ipv4)
+{
+ struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK };
+ struct nlmsghdr *nh;
+ struct rtattr *rta;
+ struct rtmsg *rt;
+ char data[NLMSG_ALIGN(sizeof(*nh)) +
+ NLMSG_ALIGN(sizeof(*rt)) +
+ NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) +
+ NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) +
+ NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))];
+ int fd, ret, alen, off = 0;
+
+ alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6);
+
+ fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+ if (fd == -1)
+ error(1, errno, "socket netlink");
+
+ memset(data, 0, sizeof(data));
+
+ nh = (void *)data;
+ nh->nlmsg_type = RTM_NEWROUTE;
+ nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE;
+ off += NLMSG_ALIGN(sizeof(*nh));
+
+ rt = (void *)(data + off);
+ rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6;
+ rt->rtm_table = RT_TABLE_MAIN;
+ rt->rtm_dst_len = alen << 3;
+ rt->rtm_protocol = RTPROT_BOOT;
+ rt->rtm_scope = RT_SCOPE_UNIVERSE;
+ rt->rtm_type = RTN_UNICAST;
+ off += NLMSG_ALIGN(sizeof(*rt));
+
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_DST;
+ rta->rta_len = RTA_LENGTH(alen);
+ if (is_ipv4)
+ memcpy(RTA_DATA(rta), &addr4, alen);
+ else
+ memcpy(RTA_DATA(rta), &addr6, alen);
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_OIF;
+ rta->rta_len = RTA_LENGTH(sizeof(int));
+ *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo");
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* MTU is a subtype in a metrics type */
+ rta = (void *)(data + off);
+ rta->rta_type = RTA_METRICS;
+ rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int));
+ off += NLMSG_ALIGN(rta->rta_len);
+
+ /* now fill MTU subtype. Note that it fits within above rta_len */
+ rta = (void *)(((char *) rta) + RTA_LENGTH(0));
+ rta->rta_type = RTAX_MTU;
+ rta->rta_len = RTA_LENGTH(sizeof(int));
+ *((int *)(RTA_DATA(rta))) = mtu;
+
+ nh->nlmsg_len = off;
+
+ ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr));
+ if (ret != off)
+ error(1, errno, "send netlink: %uB != %uB\n", ret, off);
+
+ if (close(fd))
+ error(1, errno, "close netlink");
+
+ fprintf(stderr, "route mtu (test): %u\n", mtu);
+}
+
+static bool __send_one(int fd, struct msghdr *msg, int flags)
+{
+ int ret;
+
+ ret = sendmsg(fd, msg, flags);
+ if (ret == -1 &&
+ (errno == EMSGSIZE || errno == ENOMEM || errno == EINVAL))
+ return false;
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != msg->msg_iov->iov_len)
+ error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len);
+ if (msg->msg_flags)
+ error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags);
+
+ return true;
+}
+
+static bool send_one(int fd, int len, int gso_len,
+ struct sockaddr *addr, socklen_t alen)
+{
+ char control[CMSG_SPACE(sizeof(uint16_t))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ struct cmsghdr *cm;
+
+ iov.iov_base = buf;
+ iov.iov_len = len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_name = addr;
+ msg.msg_namelen = alen;
+
+ if (gso_len && !cfg_do_setsockopt) {
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+
+ cm = CMSG_FIRSTHDR(&msg);
+ cm->cmsg_level = SOL_UDP;
+ cm->cmsg_type = UDP_SEGMENT;
+ cm->cmsg_len = CMSG_LEN(sizeof(uint16_t));
+ *((uint16_t *) CMSG_DATA(cm)) = gso_len;
+ }
+
+ /* If MSG_MORE, send 1 byte followed by remainder */
+ if (cfg_do_msgmore && len > 1) {
+ iov.iov_len = 1;
+ if (!__send_one(fd, &msg, MSG_MORE))
+ error(1, 0, "send 1B failed");
+
+ iov.iov_base++;
+ iov.iov_len = len - 1;
+ }
+
+ return __send_one(fd, &msg, 0);
+}
+
+static int recv_one(int fd, int flags)
+{
+ int ret;
+
+ ret = recv(fd, buf, sizeof(buf), flags);
+ if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT))
+ return 0;
+ if (ret == -1)
+ error(1, errno, "recv");
+
+ return ret;
+}
+
+static void run_one(struct testcase *test, int fdt, int fdr,
+ struct sockaddr *addr, socklen_t alen)
+{
+ int i, ret, val, mss;
+ bool sent;
+
+ fprintf(stderr, "ipv%d tx:%d gso:%d %s\n",
+ addr->sa_family == AF_INET ? 4 : 6,
+ test->tlen, test->gso_len,
+ test->tfail ? "(fail)" : "");
+
+ val = test->gso_len;
+ if (cfg_do_setsockopt) {
+ if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val)))
+ error(1, errno, "setsockopt udp segment");
+ }
+
+ sent = send_one(fdt, test->tlen, test->gso_len, addr, alen);
+ if (sent && test->tfail)
+ error(1, 0, "send succeeded while expecting failure");
+ if (!sent && !test->tfail)
+ error(1, 0, "send failed while expecting success");
+ if (!sent)
+ return;
+
+ if (test->gso_len)
+ mss = test->gso_len;
+ else
+ mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6;
+
+
+ /* Recv all full MSS datagrams */
+ for (i = 0; i < test->r_num_mss; i++) {
+ ret = recv_one(fdr, 0);
+ if (ret != mss)
+ error(1, 0, "recv.%d: %d != %d", i, ret, mss);
+ }
+
+ /* Recv the non-full last datagram, if tlen was not a multiple of mss */
+ if (test->r_len_last) {
+ ret = recv_one(fdr, 0);
+ if (ret != test->r_len_last)
+ error(1, 0, "recv.%d: %d != %d (last)",
+ i, ret, test->r_len_last);
+ }
+
+ /* Verify received all data */
+ ret = recv_one(fdr, MSG_DONTWAIT);
+ if (ret)
+ error(1, 0, "recv: unexpected datagram");
+}
+
+static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen)
+{
+ struct testcase *tests, *test;
+
+ tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6;
+
+ for (test = tests; test->tlen; test++) {
+ /* if a specific test is given, then skip all others */
+ if (cfg_specific_test_id == -1 ||
+ cfg_specific_test_id == test - tests)
+ run_one(test, fdt, fdr, addr, alen);
+ }
+}
+
+static void run_test(struct sockaddr *addr, socklen_t alen)
+{
+ struct timeval tv = { .tv_usec = 100 * 1000 };
+ int fdr, fdt, val;
+
+ fdr = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fdr == -1)
+ error(1, errno, "socket r");
+
+ if (bind(fdr, addr, alen))
+ error(1, errno, "bind");
+
+ /* Have tests fail quickly instead of hang */
+ if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv)))
+ error(1, errno, "setsockopt rcv timeout");
+
+ fdt = socket(addr->sa_family, SOCK_DGRAM, 0);
+ if (fdt == -1)
+ error(1, errno, "socket t");
+
+ /* Do not fragment these datagrams: only succeed if GSO works */
+ set_pmtu_discover(fdt, addr->sa_family == AF_INET);
+
+ if (cfg_do_connectionless) {
+ set_device_mtu(fdt, CONST_MTU_TEST);
+ run_all(fdt, fdr, addr, alen);
+ }
+
+ if (cfg_do_connected) {
+ set_device_mtu(fdt, CONST_MTU_TEST + 100);
+ set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET);
+
+ if (connect(fdt, addr, alen))
+ error(1, errno, "connect");
+
+ val = get_path_mtu(fdt, addr->sa_family == AF_INET);
+ if (val != CONST_MTU_TEST)
+ error(1, 0, "bad path mtu %u\n", val);
+
+ run_all(fdt, fdr, addr, 0 /* use connected addr */);
+ }
+
+ if (close(fdt))
+ error(1, errno, "close t");
+ if (close(fdr))
+ error(1, errno, "close r");
+}
+
+static void run_test_v4(void)
+{
+ struct sockaddr_in addr = {0};
+
+ addr.sin_family = AF_INET;
+ addr.sin_port = htons(cfg_port);
+ addr.sin_addr = addr4;
+
+ run_test((void *)&addr, sizeof(addr));
+}
+
+static void run_test_v6(void)
+{
+ struct sockaddr_in6 addr = {0};
+
+ addr.sin6_family = AF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = addr6;
+
+ run_test((void *)&addr, sizeof(addr));
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "46cCmst:")) != -1) {
+ switch (c) {
+ case '4':
+ cfg_do_ipv4 = true;
+ break;
+ case '6':
+ cfg_do_ipv6 = true;
+ break;
+ case 'c':
+ cfg_do_connected = true;
+ break;
+ case 'C':
+ cfg_do_connectionless = true;
+ break;
+ case 'm':
+ cfg_do_msgmore = true;
+ break;
+ case 's':
+ cfg_do_setsockopt = true;
+ break;
+ case 't':
+ cfg_specific_test_id = strtoul(optarg, NULL, 0);
+ break;
+ default:
+ error(1, 0, "%s: parse error", argv[0]);
+ }
+ }
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ if (cfg_do_ipv4)
+ run_test_v4();
+ if (cfg_do_ipv6)
+ run_test_v6();
+
+ fprintf(stderr, "OK\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh
new file mode 100755
index 000000000000..fec24f584fe9
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso.sh
@@ -0,0 +1,29 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso regression tests
+
+echo "ipv4 cmsg"
+./in_netns.sh ./udpgso -4 -C
+
+echo "ipv4 setsockopt"
+./in_netns.sh ./udpgso -4 -C -s
+
+echo "ipv6 cmsg"
+./in_netns.sh ./udpgso -6 -C
+
+echo "ipv6 setsockopt"
+./in_netns.sh ./udpgso -6 -C -s
+
+echo "ipv4 connected"
+./in_netns.sh ./udpgso -4 -c
+
+# blocked on 2nd loopback address
+# echo "ipv6 connected"
+# ./in_netns.sh ./udpgso -6 -c
+
+echo "ipv4 msg_more"
+./in_netns.sh ./udpgso -4 -C -m
+
+echo "ipv6 msg_more"
+./in_netns.sh ./udpgso -6 -C -m
diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh
new file mode 100755
index 000000000000..792fa4d0285e
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench.sh
@@ -0,0 +1,74 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgso benchmarks
+
+wake_children() {
+ local -r jobs="$(jobs -p)"
+
+ if [[ "${jobs}" != "" ]]; then
+ kill -1 ${jobs} 2>/dev/null
+ fi
+}
+trap wake_children EXIT
+
+run_one() {
+ local -r args=$@
+
+ ./udpgso_bench_rx &
+ ./udpgso_bench_rx -t &
+
+ ./udpgso_bench_tx ${args}
+}
+
+run_in_netns() {
+ local -r args=$@
+
+ ./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+ local -r args=$@
+
+ echo "udp"
+ run_in_netns ${args}
+
+ echo "udp gso"
+ run_in_netns ${args} -S
+
+ echo "udp gso zerocopy"
+ run_in_netns ${args} -S -z
+}
+
+run_tcp() {
+ local -r args=$@
+
+ echo "tcp"
+ run_in_netns ${args} -t
+
+ echo "tcp zerocopy"
+ run_in_netns ${args} -t -z
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 127.0.0.1"
+ local -r ipv6_args="${core_args} -6 -D ::1"
+
+ echo "ipv4"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv4_args}"
+
+ echo "ipv6"
+ run_tcp "${ipv4_args}"
+ run_udp "${ipv6_args}"
+}
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+else
+ run_in_netns $@
+fi
diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c
new file mode 100644
index 000000000000..727cf67a3f75
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench_rx.c
@@ -0,0 +1,265 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <error.h>
+#include <errno.h>
+#include <limits.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+static int cfg_port = 8000;
+static bool cfg_tcp;
+static bool cfg_verify;
+
+static bool interrupted;
+static unsigned long packets, bytes;
+
+static void sigint_handler(int signum)
+{
+ if (signum == SIGINT)
+ interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static void do_poll(int fd)
+{
+ struct pollfd pfd;
+ int ret;
+
+ pfd.events = POLLIN;
+ pfd.revents = 0;
+ pfd.fd = fd;
+
+ do {
+ ret = poll(&pfd, 1, 10);
+ if (ret == -1)
+ error(1, errno, "poll");
+ if (ret == 0)
+ continue;
+ if (pfd.revents != POLLIN)
+ error(1, errno, "poll: 0x%x expected 0x%x\n",
+ pfd.revents, POLLIN);
+ } while (!ret && !interrupted);
+}
+
+static int do_socket(bool do_tcp)
+{
+ struct sockaddr_in6 addr = {0};
+ int fd, val;
+
+ fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket");
+
+ val = 1 << 21;
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val)))
+ error(1, errno, "setsockopt rcvbuf");
+ val = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val)))
+ error(1, errno, "setsockopt reuseport");
+
+ addr.sin6_family = PF_INET6;
+ addr.sin6_port = htons(cfg_port);
+ addr.sin6_addr = in6addr_any;
+ if (bind(fd, (void *) &addr, sizeof(addr)))
+ error(1, errno, "bind");
+
+ if (do_tcp) {
+ int accept_fd = fd;
+
+ if (listen(accept_fd, 1))
+ error(1, errno, "listen");
+
+ do_poll(accept_fd);
+
+ fd = accept(accept_fd, NULL, NULL);
+ if (fd == -1)
+ error(1, errno, "accept");
+ if (close(accept_fd))
+ error(1, errno, "close accept fd");
+ }
+
+ return fd;
+}
+
+/* Flush all outstanding bytes for the tcp receive queue */
+static void do_flush_tcp(int fd)
+{
+ int ret;
+
+ while (true) {
+ /* MSG_TRUNC flushes up to len bytes */
+ ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ return;
+ if (ret == -1)
+ error(1, errno, "flush");
+ if (ret == 0) {
+ /* client detached */
+ exit(0);
+ }
+
+ packets++;
+ bytes += ret;
+ }
+
+}
+
+static char sanitized_char(char val)
+{
+ return (val >= 'a' && val <= 'z') ? val : '.';
+}
+
+static void do_verify_udp(const char *data, int len)
+{
+ char cur = data[0];
+ int i;
+
+ /* verify contents */
+ if (cur < 'a' || cur > 'z')
+ error(1, 0, "data initial byte out of range");
+
+ for (i = 1; i < len; i++) {
+ if (cur == 'z')
+ cur = 'a';
+ else
+ cur++;
+
+ if (data[i] != cur)
+ error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n",
+ i, len,
+ sanitized_char(data[i]), data[i],
+ sanitized_char(cur), cur);
+ }
+}
+
+/* Flush all outstanding datagrams. Verify first few bytes of each. */
+static void do_flush_udp(int fd)
+{
+ static char rbuf[ETH_DATA_LEN];
+ int ret, len, budget = 256;
+
+ len = cfg_verify ? sizeof(rbuf) : 0;
+ while (budget--) {
+ /* MSG_TRUNC will make return value full datagram length */
+ ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT);
+ if (ret == -1 && errno == EAGAIN)
+ return;
+ if (ret == -1)
+ error(1, errno, "recv");
+ if (len) {
+ if (ret == 0)
+ error(1, errno, "recv: 0 byte datagram\n");
+
+ do_verify_udp(rbuf, ret);
+ }
+
+ packets++;
+ bytes += ret;
+ }
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-tv] [-p port]", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int c;
+
+ while ((c = getopt(argc, argv, "ptv")) != -1) {
+ switch (c) {
+ case 'p':
+ cfg_port = htons(strtoul(optarg, NULL, 0));
+ break;
+ case 't':
+ cfg_tcp = true;
+ break;
+ case 'v':
+ cfg_verify = true;
+ break;
+ }
+ }
+
+ if (optind != argc)
+ usage(argv[0]);
+
+ if (cfg_tcp && cfg_verify)
+ error(1, 0, "TODO: implement verify mode for tcp");
+}
+
+static void do_recv(void)
+{
+ unsigned long tnow, treport;
+ int fd;
+
+ fd = do_socket(cfg_tcp);
+
+ treport = gettimeofday_ms() + 1000;
+ do {
+ do_poll(fd);
+
+ if (cfg_tcp)
+ do_flush_tcp(fd);
+ else
+ do_flush_udp(fd);
+
+ tnow = gettimeofday_ms();
+ if (tnow > treport) {
+ if (packets)
+ fprintf(stderr,
+ "%s rx: %6lu MB/s %8lu calls/s\n",
+ cfg_tcp ? "tcp" : "udp",
+ bytes >> 20, packets);
+ bytes = packets = 0;
+ treport = tnow + 1000;
+ }
+
+ } while (!interrupted);
+
+ if (close(fd))
+ error(1, errno, "close");
+}
+
+int main(int argc, char **argv)
+{
+ parse_opts(argc, argv);
+
+ signal(SIGINT, sigint_handler);
+
+ do_recv();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c
new file mode 100644
index 000000000000..e821564053cf
--- /dev/null
+++ b/tools/testing/selftests/net/udpgso_bench_tx.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <netinet/if_ether.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <sched.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/socket.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#ifndef ETH_MAX_MTU
+#define ETH_MAX_MTU 0xFFFFU
+#endif
+
+#ifndef UDP_SEGMENT
+#define UDP_SEGMENT 103
+#endif
+
+#ifndef SO_ZEROCOPY
+#define SO_ZEROCOPY 60
+#endif
+
+#ifndef MSG_ZEROCOPY
+#define MSG_ZEROCOPY 0x4000000
+#endif
+
+#define NUM_PKT 100
+
+static bool cfg_cache_trash;
+static int cfg_cpu = -1;
+static int cfg_connected = true;
+static int cfg_family = PF_UNSPEC;
+static uint16_t cfg_mss;
+static int cfg_payload_len = (1472 * 42);
+static int cfg_port = 8000;
+static int cfg_runtime_ms = -1;
+static bool cfg_segment;
+static bool cfg_sendmmsg;
+static bool cfg_tcp;
+static bool cfg_zerocopy;
+
+static socklen_t cfg_alen;
+static struct sockaddr_storage cfg_dst_addr;
+
+static bool interrupted;
+static char buf[NUM_PKT][ETH_MAX_MTU];
+
+static void sigint_handler(int signum)
+{
+ if (signum == SIGINT)
+ interrupted = true;
+}
+
+static unsigned long gettimeofday_ms(void)
+{
+ struct timeval tv;
+
+ gettimeofday(&tv, NULL);
+ return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int set_cpu(int cpu)
+{
+ cpu_set_t mask;
+
+ CPU_ZERO(&mask);
+ CPU_SET(cpu, &mask);
+ if (sched_setaffinity(0, sizeof(mask), &mask))
+ error(1, 0, "setaffinity %d", cpu);
+
+ return 0;
+}
+
+static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr)
+{
+ struct sockaddr_in6 *addr6 = (void *) sockaddr;
+ struct sockaddr_in *addr4 = (void *) sockaddr;
+
+ switch (domain) {
+ case PF_INET:
+ addr4->sin_family = AF_INET;
+ addr4->sin_port = htons(cfg_port);
+ if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1)
+ error(1, 0, "ipv4 parse error: %s", str_addr);
+ break;
+ case PF_INET6:
+ addr6->sin6_family = AF_INET6;
+ addr6->sin6_port = htons(cfg_port);
+ if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1)
+ error(1, 0, "ipv6 parse error: %s", str_addr);
+ break;
+ default:
+ error(1, 0, "illegal domain");
+ }
+}
+
+static void flush_zerocopy(int fd)
+{
+ struct msghdr msg = {0}; /* flush */
+ int ret;
+
+ while (1) {
+ ret = recvmsg(fd, &msg, MSG_ERRQUEUE);
+ if (ret == -1 && errno == EAGAIN)
+ break;
+ if (ret == -1)
+ error(1, errno, "errqueue");
+ if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC))
+ error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags);
+ msg.msg_flags = 0;
+ }
+}
+
+static int send_tcp(int fd, char *data)
+{
+ int ret, done = 0, count = 0;
+
+ while (done < cfg_payload_len) {
+ ret = send(fd, data + done, cfg_payload_len - done,
+ cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "write");
+
+ done += ret;
+ count++;
+ }
+
+ return count;
+}
+
+static int send_udp(int fd, char *data)
+{
+ int ret, total_len, len, count = 0;
+
+ total_len = cfg_payload_len;
+
+ while (total_len) {
+ len = total_len < cfg_mss ? total_len : cfg_mss;
+
+ ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0,
+ cfg_connected ? NULL : (void *)&cfg_dst_addr,
+ cfg_connected ? 0 : cfg_alen);
+ if (ret == -1)
+ error(1, errno, "write");
+ if (ret != len)
+ error(1, errno, "write: %uB != %uB\n", ret, len);
+
+ total_len -= len;
+ count++;
+ }
+
+ return count;
+}
+
+static int send_udp_sendmmsg(int fd, char *data)
+{
+ const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN;
+ struct mmsghdr mmsgs[max_nr_msg];
+ struct iovec iov[max_nr_msg];
+ unsigned int off = 0, left;
+ int i = 0, ret;
+
+ memset(mmsgs, 0, sizeof(mmsgs));
+
+ left = cfg_payload_len;
+ while (left) {
+ if (i == max_nr_msg)
+ error(1, 0, "sendmmsg: exceeds max_nr_msg");
+
+ iov[i].iov_base = data + off;
+ iov[i].iov_len = cfg_mss < left ? cfg_mss : left;
+
+ mmsgs[i].msg_hdr.msg_iov = iov + i;
+ mmsgs[i].msg_hdr.msg_iovlen = 1;
+
+ off += iov[i].iov_len;
+ left -= iov[i].iov_len;
+ i++;
+ }
+
+ ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "sendmmsg");
+
+ return ret;
+}
+
+static void send_udp_segment_cmsg(struct cmsghdr *cm)
+{
+ uint16_t *valp;
+
+ cm->cmsg_level = SOL_UDP;
+ cm->cmsg_type = UDP_SEGMENT;
+ cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss));
+ valp = (void *)CMSG_DATA(cm);
+ *valp = cfg_mss;
+}
+
+static int send_udp_segment(int fd, char *data)
+{
+ char control[CMSG_SPACE(sizeof(cfg_mss))] = {0};
+ struct msghdr msg = {0};
+ struct iovec iov = {0};
+ int ret;
+
+ iov.iov_base = data;
+ iov.iov_len = cfg_payload_len;
+
+ msg.msg_iov = &iov;
+ msg.msg_iovlen = 1;
+
+ msg.msg_control = control;
+ msg.msg_controllen = sizeof(control);
+ send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg));
+
+ msg.msg_name = (void *)&cfg_dst_addr;
+ msg.msg_namelen = cfg_alen;
+
+ ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0);
+ if (ret == -1)
+ error(1, errno, "sendmsg");
+ if (ret != iov.iov_len)
+ error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len);
+
+ return 1;
+}
+
+static void usage(const char *filepath)
+{
+ error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]",
+ filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+ int max_len, hdrlen;
+ int c;
+
+ while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) {
+ switch (c) {
+ case '4':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET;
+ cfg_alen = sizeof(struct sockaddr_in);
+ break;
+ case '6':
+ if (cfg_family != PF_UNSPEC)
+ error(1, 0, "Pass one of -4 or -6");
+ cfg_family = PF_INET6;
+ cfg_alen = sizeof(struct sockaddr_in6);
+ break;
+ case 'c':
+ cfg_cache_trash = true;
+ break;
+ case 'C':
+ cfg_cpu = strtol(optarg, NULL, 0);
+ break;
+ case 'D':
+ setup_sockaddr(cfg_family, optarg, &cfg_dst_addr);
+ break;
+ case 'l':
+ cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000;
+ break;
+ case 'm':
+ cfg_sendmmsg = true;
+ break;
+ case 'p':
+ cfg_port = strtoul(optarg, NULL, 0);
+ break;
+ case 's':
+ cfg_payload_len = strtoul(optarg, NULL, 0);
+ break;
+ case 'S':
+ cfg_segment = true;
+ break;
+ case 't':
+ cfg_tcp = true;
+ break;
+ case 'u':
+ cfg_connected = false;
+ break;
+ case 'z':
+ cfg_zerocopy = true;
+ break;
+ }
+ }
+
+ if (optind != argc)
+ usage(argv[0]);
+
+ if (cfg_family == PF_UNSPEC)
+ error(1, 0, "must pass one of -4 or -6");
+ if (cfg_tcp && !cfg_connected)
+ error(1, 0, "connectionless tcp makes no sense");
+ if (cfg_segment && cfg_sendmmsg)
+ error(1, 0, "cannot combine segment offload and sendmmsg");
+
+ if (cfg_family == PF_INET)
+ hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr);
+ else
+ hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr);
+
+ cfg_mss = ETH_DATA_LEN - hdrlen;
+ max_len = ETH_MAX_MTU - hdrlen;
+
+ if (cfg_payload_len > max_len)
+ error(1, 0, "payload length %u exceeds max %u",
+ cfg_payload_len, max_len);
+}
+
+static void set_pmtu_discover(int fd, bool is_ipv4)
+{
+ int level, name, val;
+
+ if (is_ipv4) {
+ level = SOL_IP;
+ name = IP_MTU_DISCOVER;
+ val = IP_PMTUDISC_DO;
+ } else {
+ level = SOL_IPV6;
+ name = IPV6_MTU_DISCOVER;
+ val = IPV6_PMTUDISC_DO;
+ }
+
+ if (setsockopt(fd, level, name, &val, sizeof(val)))
+ error(1, errno, "setsockopt path mtu");
+}
+
+int main(int argc, char **argv)
+{
+ unsigned long num_msgs, num_sends;
+ unsigned long tnow, treport, tstop;
+ int fd, i, val;
+
+ parse_opts(argc, argv);
+
+ if (cfg_cpu > 0)
+ set_cpu(cfg_cpu);
+
+ for (i = 0; i < sizeof(buf[0]); i++)
+ buf[0][i] = 'a' + (i % 26);
+ for (i = 1; i < NUM_PKT; i++)
+ memcpy(buf[i], buf[0], sizeof(buf[0]));
+
+ signal(SIGINT, sigint_handler);
+
+ fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0);
+ if (fd == -1)
+ error(1, errno, "socket");
+
+ if (cfg_zerocopy) {
+ val = 1;
+ if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val)))
+ error(1, errno, "setsockopt zerocopy");
+ }
+
+ if (cfg_connected &&
+ connect(fd, (void *)&cfg_dst_addr, cfg_alen))
+ error(1, errno, "connect");
+
+ if (cfg_segment)
+ set_pmtu_discover(fd, cfg_family == PF_INET);
+
+ num_msgs = num_sends = 0;
+ tnow = gettimeofday_ms();
+ tstop = tnow + cfg_runtime_ms;
+ treport = tnow + 1000;
+
+ i = 0;
+ do {
+ if (cfg_tcp)
+ num_sends += send_tcp(fd, buf[i]);
+ else if (cfg_segment)
+ num_sends += send_udp_segment(fd, buf[i]);
+ else if (cfg_sendmmsg)
+ num_sends += send_udp_sendmmsg(fd, buf[i]);
+ else
+ num_sends += send_udp(fd, buf[i]);
+ num_msgs++;
+
+ if (cfg_zerocopy && ((num_msgs & 0xF) == 0))
+ flush_zerocopy(fd);
+
+ tnow = gettimeofday_ms();
+ if (tnow > treport) {
+ fprintf(stderr,
+ "%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n",
+ cfg_tcp ? "tcp" : "udp",
+ (num_msgs * cfg_payload_len) >> 20,
+ num_sends, num_msgs);
+ num_msgs = num_sends = 0;
+ treport = tnow + 1000;
+ }
+
+ /* cold cache when writing buffer */
+ if (cfg_cache_trash)
+ i = ++i < NUM_PKT ? i : 0;
+
+ } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop));
+
+ if (close(fd))
+ error(1, errno, "close");
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
new file mode 100644
index 000000000000..6c16f77c722c
--- /dev/null
+++ b/tools/testing/selftests/proc/.gitignore
@@ -0,0 +1,8 @@
+/proc-loadavg-001
+/proc-self-map-files-001
+/proc-self-map-files-002
+/proc-self-syscall
+/proc-self-wchan
+/proc-uptime-001
+/proc-uptime-002
+/read
diff --git a/tools/testing/selftests/proc/Makefile b/tools/testing/selftests/proc/Makefile
new file mode 100644
index 000000000000..dbb87e56264c
--- /dev/null
+++ b/tools/testing/selftests/proc/Makefile
@@ -0,0 +1,13 @@
+CFLAGS += -Wall -O2
+
+TEST_GEN_PROGS :=
+TEST_GEN_PROGS += proc-loadavg-001
+TEST_GEN_PROGS += proc-self-map-files-001
+TEST_GEN_PROGS += proc-self-map-files-002
+TEST_GEN_PROGS += proc-self-syscall
+TEST_GEN_PROGS += proc-self-wchan
+TEST_GEN_PROGS += proc-uptime-001
+TEST_GEN_PROGS += proc-uptime-002
+TEST_GEN_PROGS += read
+
+include ../lib.mk
diff --git a/tools/testing/selftests/proc/config b/tools/testing/selftests/proc/config
new file mode 100644
index 000000000000..68fbd2b35884
--- /dev/null
+++ b/tools/testing/selftests/proc/config
@@ -0,0 +1 @@
+CONFIG_PROC_FS=y
diff --git a/tools/testing/selftests/proc/proc-loadavg-001.c b/tools/testing/selftests/proc/proc-loadavg-001.c
new file mode 100644
index 000000000000..fcff7047000d
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-loadavg-001.c
@@ -0,0 +1,83 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test that /proc/loadavg correctly reports last pid in pid namespace. */
+#define _GNU_SOURCE
+#include <errno.h>
+#include <sched.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/wait.h>
+
+int main(void)
+{
+ pid_t pid;
+ int wstatus;
+
+ if (unshare(CLONE_NEWPID) == -1) {
+ if (errno == ENOSYS || errno == EPERM)
+ return 2;
+ return 1;
+ }
+
+ pid = fork();
+ if (pid == -1)
+ return 1;
+ if (pid == 0) {
+ char buf[128], *p;
+ int fd;
+ ssize_t rv;
+
+ fd = open("/proc/loadavg" , O_RDONLY);
+ if (fd == -1)
+ return 1;
+ rv = read(fd, buf, sizeof(buf));
+ if (rv < 3)
+ return 1;
+ p = buf + rv;
+
+ /* pid 1 */
+ if (!(p[-3] == ' ' && p[-2] == '1' && p[-1] == '\n'))
+ return 1;
+
+ pid = fork();
+ if (pid == -1)
+ return 1;
+ if (pid == 0)
+ return 0;
+ if (waitpid(pid, NULL, 0) == -1)
+ return 1;
+
+ lseek(fd, 0, SEEK_SET);
+ rv = read(fd, buf, sizeof(buf));
+ if (rv < 3)
+ return 1;
+ p = buf + rv;
+
+ /* pid 2 */
+ if (!(p[-3] == ' ' && p[-2] == '2' && p[-1] == '\n'))
+ return 1;
+
+ return 0;
+ }
+
+ if (waitpid(pid, &wstatus, 0) == -1)
+ return 1;
+ if (WIFEXITED(wstatus) && WEXITSTATUS(wstatus) == 0)
+ return 0;
+ return 1;
+}
diff --git a/tools/testing/selftests/proc/proc-self-map-files-001.c b/tools/testing/selftests/proc/proc-self-map-files-001.c
new file mode 100644
index 000000000000..4209c64283d6
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-map-files-001.c
@@ -0,0 +1,82 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test readlink /proc/self/map_files/... */
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <stdlib.h>
+
+static void pass(const char *fmt, unsigned long a, unsigned long b)
+{
+ char name[64];
+ char buf[64];
+
+ snprintf(name, sizeof(name), fmt, a, b);
+ if (readlink(name, buf, sizeof(buf)) == -1)
+ exit(1);
+}
+
+static void fail(const char *fmt, unsigned long a, unsigned long b)
+{
+ char name[64];
+ char buf[64];
+
+ snprintf(name, sizeof(name), fmt, a, b);
+ if (readlink(name, buf, sizeof(buf)) == -1 && errno == ENOENT)
+ return;
+ exit(1);
+}
+
+int main(void)
+{
+ const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+ void *p;
+ int fd;
+ unsigned long a, b;
+
+ fd = open("/dev/zero", O_RDONLY);
+ if (fd == -1)
+ return 1;
+
+ p = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE, fd, 0);
+ if (p == MAP_FAILED)
+ return 1;
+
+ a = (unsigned long)p;
+ b = (unsigned long)p + PAGE_SIZE;
+
+ pass("/proc/self/map_files/%lx-%lx", a, b);
+ fail("/proc/self/map_files/ %lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx -%lx", a, b);
+ fail("/proc/self/map_files/%lx- %lx", a, b);
+ fail("/proc/self/map_files/%lx-%lx ", a, b);
+ fail("/proc/self/map_files/0%lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx-0%lx", a, b);
+ if (sizeof(long) == 4) {
+ fail("/proc/self/map_files/100000000%lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx-100000000%lx", a, b);
+ } else if (sizeof(long) == 8) {
+ fail("/proc/self/map_files/10000000000000000%lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx-10000000000000000%lx", a, b);
+ } else
+ return 1;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-self-map-files-002.c b/tools/testing/selftests/proc/proc-self-map-files-002.c
new file mode 100644
index 000000000000..6f1f4a6e1ecb
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-map-files-002.c
@@ -0,0 +1,85 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+/* Test readlink /proc/self/map_files/... with address 0. */
+#include <errno.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <stdlib.h>
+
+static void pass(const char *fmt, unsigned long a, unsigned long b)
+{
+ char name[64];
+ char buf[64];
+
+ snprintf(name, sizeof(name), fmt, a, b);
+ if (readlink(name, buf, sizeof(buf)) == -1)
+ exit(1);
+}
+
+static void fail(const char *fmt, unsigned long a, unsigned long b)
+{
+ char name[64];
+ char buf[64];
+
+ snprintf(name, sizeof(name), fmt, a, b);
+ if (readlink(name, buf, sizeof(buf)) == -1 && errno == ENOENT)
+ return;
+ exit(1);
+}
+
+int main(void)
+{
+ const unsigned int PAGE_SIZE = sysconf(_SC_PAGESIZE);
+ void *p;
+ int fd;
+ unsigned long a, b;
+
+ fd = open("/dev/zero", O_RDONLY);
+ if (fd == -1)
+ return 1;
+
+ p = mmap(NULL, PAGE_SIZE, PROT_NONE, MAP_PRIVATE|MAP_FILE|MAP_FIXED, fd, 0);
+ if (p == MAP_FAILED) {
+ if (errno == EPERM)
+ return 2;
+ return 1;
+ }
+
+ a = (unsigned long)p;
+ b = (unsigned long)p + PAGE_SIZE;
+
+ pass("/proc/self/map_files/%lx-%lx", a, b);
+ fail("/proc/self/map_files/ %lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx -%lx", a, b);
+ fail("/proc/self/map_files/%lx- %lx", a, b);
+ fail("/proc/self/map_files/%lx-%lx ", a, b);
+ fail("/proc/self/map_files/0%lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx-0%lx", a, b);
+ if (sizeof(long) == 4) {
+ fail("/proc/self/map_files/100000000%lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx-100000000%lx", a, b);
+ } else if (sizeof(long) == 8) {
+ fail("/proc/self/map_files/10000000000000000%lx-%lx", a, b);
+ fail("/proc/self/map_files/%lx-10000000000000000%lx", a, b);
+ } else
+ return 1;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-self-syscall.c b/tools/testing/selftests/proc/proc-self-syscall.c
new file mode 100644
index 000000000000..5ab5f4810e43
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-syscall.c
@@ -0,0 +1,60 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <unistd.h>
+#include <string.h>
+#include <stdio.h>
+
+static inline ssize_t sys_read(int fd, void *buf, size_t len)
+{
+ return syscall(SYS_read, fd, buf, len);
+}
+
+int main(void)
+{
+ char buf1[64];
+ char buf2[64];
+ int fd;
+ ssize_t rv;
+
+ fd = open("/proc/self/syscall", O_RDONLY);
+ if (fd == -1) {
+ if (errno == ENOENT)
+ return 2;
+ return 1;
+ }
+
+ /* Do direct system call as libc can wrap anything. */
+ snprintf(buf1, sizeof(buf1), "%ld 0x%lx 0x%lx 0x%lx",
+ (long)SYS_read, (long)fd, (long)buf2, (long)sizeof(buf2));
+
+ memset(buf2, 0, sizeof(buf2));
+ rv = sys_read(fd, buf2, sizeof(buf2));
+ if (rv < 0)
+ return 1;
+ if (rv < strlen(buf1))
+ return 1;
+ if (strncmp(buf1, buf2, strlen(buf1)) != 0)
+ return 1;
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-self-wchan.c b/tools/testing/selftests/proc/proc-self-wchan.c
new file mode 100644
index 000000000000..a38b2fbaa7ad
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-self-wchan.c
@@ -0,0 +1,40 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <unistd.h>
+
+int main(void)
+{
+ char buf[64];
+ int fd;
+
+ fd = open("/proc/self/wchan", O_RDONLY);
+ if (fd == -1) {
+ if (errno == ENOENT)
+ return 2;
+ return 1;
+ }
+
+ buf[0] = '\0';
+ if (read(fd, buf, sizeof(buf)) != 1)
+ return 1;
+ if (buf[0] != '0')
+ return 1;
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-uptime-001.c b/tools/testing/selftests/proc/proc-uptime-001.c
new file mode 100644
index 000000000000..781f7a50fc3f
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-uptime-001.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+// Test that values in /proc/uptime increment monotonically.
+#undef NDEBUG
+#include <assert.h>
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "proc-uptime.h"
+
+int main(void)
+{
+ uint64_t start, u0, u1, i0, i1;
+ int fd;
+
+ fd = open("/proc/uptime", O_RDONLY);
+ assert(fd >= 0);
+
+ proc_uptime(fd, &u0, &i0);
+ start = u0;
+ do {
+ proc_uptime(fd, &u1, &i1);
+ assert(u1 >= u0);
+ assert(i1 >= i0);
+ u0 = u1;
+ i0 = i1;
+ } while (u1 - start < 100);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-uptime-002.c b/tools/testing/selftests/proc/proc-uptime-002.c
new file mode 100644
index 000000000000..30e2b7849089
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-uptime-002.c
@@ -0,0 +1,79 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+// Test that values in /proc/uptime increment monotonically
+// while shifting across CPUs.
+#define _GNU_SOURCE
+#undef NDEBUG
+#include <assert.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include <stdint.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+
+#include "proc-uptime.h"
+
+static inline int sys_sched_getaffinity(pid_t pid, unsigned int len, unsigned long *m)
+{
+ return syscall(SYS_sched_getaffinity, pid, len, m);
+}
+
+static inline int sys_sched_setaffinity(pid_t pid, unsigned int len, unsigned long *m)
+{
+ return syscall(SYS_sched_setaffinity, pid, len, m);
+}
+
+int main(void)
+{
+ unsigned int len;
+ unsigned long *m;
+ unsigned int cpu;
+ uint64_t u0, u1, i0, i1;
+ int fd;
+
+ /* find out "nr_cpu_ids" */
+ m = NULL;
+ len = 0;
+ do {
+ len += sizeof(unsigned long);
+ free(m);
+ m = malloc(len);
+ } while (sys_sched_getaffinity(0, len, m) == -EINVAL);
+
+ fd = open("/proc/uptime", O_RDONLY);
+ assert(fd >= 0);
+
+ proc_uptime(fd, &u0, &i0);
+ for (cpu = 0; cpu < len * 8; cpu++) {
+ memset(m, 0, len);
+ m[cpu / (8 * sizeof(unsigned long))] |= 1UL << (cpu % (8 * sizeof(unsigned long)));
+
+ /* CPU might not exist, ignore error */
+ sys_sched_setaffinity(0, len, m);
+
+ proc_uptime(fd, &u1, &i1);
+ assert(u1 >= u0);
+ assert(i1 >= i0);
+ u0 = u1;
+ i0 = i1;
+ }
+
+ return 0;
+}
diff --git a/tools/testing/selftests/proc/proc-uptime.h b/tools/testing/selftests/proc/proc-uptime.h
new file mode 100644
index 000000000000..0e464b50e9d9
--- /dev/null
+++ b/tools/testing/selftests/proc/proc-uptime.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+static unsigned long long xstrtoull(const char *p, char **end)
+{
+ if (*p == '0') {
+ *end = (char *)p + 1;
+ return 0;
+ } else if ('1' <= *p && *p <= '9') {
+ unsigned long long val;
+
+ errno = 0;
+ val = strtoull(p, end, 10);
+ assert(errno == 0);
+ return val;
+ } else
+ assert(0);
+}
+
+static void proc_uptime(int fd, uint64_t *uptime, uint64_t *idle)
+{
+ uint64_t val1, val2;
+ char buf[64], *p;
+ ssize_t rv;
+
+ /* save "p < end" checks */
+ memset(buf, 0, sizeof(buf));
+ rv = pread(fd, buf, sizeof(buf), 0);
+ assert(0 <= rv && rv <= sizeof(buf));
+ buf[sizeof(buf) - 1] = '\0';
+
+ p = buf;
+
+ val1 = xstrtoull(p, &p);
+ assert(p[0] == '.');
+ assert('0' <= p[1] && p[1] <= '9');
+ assert('0' <= p[2] && p[2] <= '9');
+ assert(p[3] == ' ');
+
+ val2 = (p[1] - '0') * 10 + p[2] - '0';
+ *uptime = val1 * 100 + val2;
+
+ p += 4;
+
+ val1 = xstrtoull(p, &p);
+ assert(p[0] == '.');
+ assert('0' <= p[1] && p[1] <= '9');
+ assert('0' <= p[2] && p[2] <= '9');
+ assert(p[3] == '\n');
+
+ val2 = (p[1] - '0') * 10 + p[2] - '0';
+ *idle = val1 * 100 + val2;
+
+ assert(p + 4 == buf + rv);
+}
diff --git a/tools/testing/selftests/proc/read.c b/tools/testing/selftests/proc/read.c
new file mode 100644
index 000000000000..1e73c2232097
--- /dev/null
+++ b/tools/testing/selftests/proc/read.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright © 2018 Alexey Dobriyan <adobriyan@gmail.com>
+ *
+ * Permission to use, copy, modify, and distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+// Test
+// 1) read of every file in /proc
+// 2) readlink of every symlink in /proc
+// 3) recursively (1) + (2) for every directory in /proc
+// 4) write to /proc/*/clear_refs and /proc/*/task/*/clear_refs
+// 5) write to /proc/sysrq-trigger
+#undef NDEBUG
+#include <assert.h>
+#include <errno.h>
+#include <sys/types.h>
+#include <dirent.h>
+#include <stdbool.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <unistd.h>
+
+static inline bool streq(const char *s1, const char *s2)
+{
+ return strcmp(s1, s2) == 0;
+}
+
+static struct dirent *xreaddir(DIR *d)
+{
+ struct dirent *de;
+
+ errno = 0;
+ de = readdir(d);
+ if (!de && errno != 0) {
+ exit(1);
+ }
+ return de;
+}
+
+static void f_reg(DIR *d, const char *filename)
+{
+ char buf[4096];
+ int fd;
+ ssize_t rv;
+
+ /* read from /proc/kmsg can block */
+ fd = openat(dirfd(d), filename, O_RDONLY|O_NONBLOCK);
+ if (fd == -1)
+ return;
+ rv = read(fd, buf, sizeof(buf));
+ assert((0 <= rv && rv <= sizeof(buf)) || rv == -1);
+ close(fd);
+}
+
+static void f_reg_write(DIR *d, const char *filename, const char *buf, size_t len)
+{
+ int fd;
+ ssize_t rv;
+
+ fd = openat(dirfd(d), filename, O_WRONLY);
+ if (fd == -1)
+ return;
+ rv = write(fd, buf, len);
+ assert((0 <= rv && rv <= len) || rv == -1);
+ close(fd);
+}
+
+static void f_lnk(DIR *d, const char *filename)
+{
+ char buf[4096];
+ ssize_t rv;
+
+ rv = readlinkat(dirfd(d), filename, buf, sizeof(buf));
+ assert((0 <= rv && rv <= sizeof(buf)) || rv == -1);
+}
+
+static void f(DIR *d, unsigned int level)
+{
+ struct dirent *de;
+
+ de = xreaddir(d);
+ assert(de->d_type == DT_DIR);
+ assert(streq(de->d_name, "."));
+
+ de = xreaddir(d);
+ assert(de->d_type == DT_DIR);
+ assert(streq(de->d_name, ".."));
+
+ while ((de = xreaddir(d))) {
+ assert(!streq(de->d_name, "."));
+ assert(!streq(de->d_name, ".."));
+
+ switch (de->d_type) {
+ DIR *dd;
+ int fd;
+
+ case DT_REG:
+ if (level == 0 && streq(de->d_name, "sysrq-trigger")) {
+ f_reg_write(d, de->d_name, "h", 1);
+ } else if (level == 1 && streq(de->d_name, "clear_refs")) {
+ f_reg_write(d, de->d_name, "1", 1);
+ } else if (level == 3 && streq(de->d_name, "clear_refs")) {
+ f_reg_write(d, de->d_name, "1", 1);
+ } else {
+ f_reg(d, de->d_name);
+ }
+ break;
+ case DT_DIR:
+ fd = openat(dirfd(d), de->d_name, O_DIRECTORY|O_RDONLY);
+ if (fd == -1)
+ continue;
+ dd = fdopendir(fd);
+ if (!dd)
+ continue;
+ f(dd, level + 1);
+ closedir(dd);
+ break;
+ case DT_LNK:
+ f_lnk(d, de->d_name);
+ break;
+ default:
+ assert(0);
+ }
+ }
+}
+
+int main(void)
+{
+ DIR *d;
+
+ d = opendir("/proc");
+ if (!d)
+ return 2;
+ f(d, 0);
+ return 0;
+}
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
new file mode 100755
index 000000000000..98f650c9bf54
--- /dev/null
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -0,0 +1,56 @@
+#!/bin/sh
+#
+# Invoke a text editor on all console.log files for all runs with diagnostics,
+# that is, on all such files having a console.log.diags counterpart.
+# Note that both console.log.diags and console.log are passed to the
+# editor (currently defaulting to "vi"), allowing the user to get an
+# idea of what to search for in the console.log file.
+#
+# Usage: kvm-find-errors.sh directory
+#
+# The "directory" above should end with the date/time directory, for example,
+# "tools/testing/selftests/rcutorture/res/2018.02.25-14:27:27".
+
+rundir="${1}"
+if test -z "$rundir" -o ! -d "$rundir"
+then
+ echo Usage: $0 directory
+fi
+editor=${EDITOR-vi}
+
+# Find builds with errors
+files=
+for i in ${rundir}/*/Make.out
+do
+ if egrep -q "error:|warning:" < $i
+ then
+ egrep "error:|warning:" < $i > $i.diags
+ files="$files $i.diags $i"
+ fi
+done
+if test -n "$files"
+then
+ $editor $files
+else
+ echo No build errors.
+fi
+if grep -q -e "--buildonly" < ${rundir}/log
+then
+ echo Build-only run, no console logs to check.
+fi
+
+# Find console logs with errors
+files=
+for i in ${rundir}/*/console.log
+do
+ if test -r $i.diags
+ then
+ files="$files $i.diags $i"
+ fi
+done
+if test -n "$files"
+then
+ $editor $files
+else
+ echo No errors in console logs.
+fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index c2e1bb6d0cba..477ecb1293ab 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -34,11 +34,15 @@ fi
configfile=`echo $i | sed -e 's/^.*\///'`
ngps=`grep ver: $i/console.log 2> /dev/null | tail -1 | sed -e 's/^.* ver: //' -e 's/ .*$//'`
+stopstate="`grep 'End-test grace-period state: g' $i/console.log 2> /dev/null |
+ tail -1 | sed -e 's/^\[[ 0-9.]*] //' |
+ awk '{ print \"[\" $1 \" \" $5 \" \" $6 \" \" $7 \"]\"; }' |
+ tr -d '\012\015'`"
if test -z "$ngps"
then
- echo "$configfile -------"
+ echo "$configfile ------- " $stopstate
else
- title="$configfile ------- $ngps grace periods"
+ title="$configfile ------- $ngps GPs"
dur=`sed -e 's/^.* rcutorture.shutdown_secs=//' -e 's/ .*$//' < $i/qemu-cmd 2> /dev/null`
if test -z "$dur"
then
@@ -46,9 +50,9 @@ else
else
ngpsps=`awk -v ngps=$ngps -v dur=$dur '
BEGIN { print ngps / dur }' < /dev/null`
- title="$title ($ngpsps per second)"
+ title="$title ($ngpsps/s)"
fi
- echo $title
+ echo $title $stopstate
nclosecalls=`grep --binary-files=text 'torture: Reader Batch' $i/console.log | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
if test -z "$nclosecalls"
then
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index f7e988f369dd..c27e97824163 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -48,10 +48,6 @@ do
cat $i/Make.oldconfig.err
fi
parse-build.sh $i/Make.out $configfile
- if test "$TORTURE_SUITE" != rcuperf
- then
- parse-torture.sh $i/console.log $configfile
- fi
parse-console.sh $i/console.log $configfile
if test -r $i/Warnings
then
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 5f8fbb0d7c17..c5b0f94341d9 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -267,5 +267,4 @@ then
echo Unknown PID, cannot kill qemu command
fi
-parse-torture.sh $resdir/console.log $title
parse-console.sh $resdir/console.log $title
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 08aa7d50ae0e..17293436f551 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -24,57 +24,146 @@
#
# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
+T=${TMPDIR-/tmp}/parse-console.sh.$$
file="$1"
title="$2"
+trap 'rm -f $T.seq $T.diags' 0
+
. functions.sh
+# Check for presence and readability of console output file
+if test -f "$file" -a -r "$file"
+then
+ :
+else
+ echo $title unreadable console output file: $file
+ exit 1
+fi
if grep -Pq '\x00' < $file
then
print_warning Console output contains nul bytes, old qemu still running?
fi
-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' < $file | grep -v 'ODEBUG: ' | grep -v 'Warning: unable to open an initial console' > $1.diags
-if test -s $1.diags
+cat /dev/null > $file.diags
+
+# Check for proper termination, except that rcuperf runs don't indicate this.
+if test "$TORTURE_SUITE" != rcuperf
then
- print_warning Assertion failure in $file $title
- # cat $1.diags
+ # check for abject failure
+
+ if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
+ then
+ nerrs=`grep --binary-files=text '!!!' $file |
+ tail -1 |
+ awk '
+ {
+ for (i=NF-8;i<=NF;i++)
+ sum+=$i;
+ }
+ END { print sum }'`
+ print_bug $title FAILURE, $nerrs instances
+ exit
+ fi
+
+ grep --binary-files=text 'torture:.*ver:' $file |
+ egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' |
+ sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
+ awk '
+ BEGIN {
+ ver = 0;
+ badseq = 0;
+ }
+
+ {
+ if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
+ badseqno1 = ver;
+ badseqno2 = $5;
+ badseqnr = NR;
+ badseq = 1;
+ }
+ ver = $5
+ }
+
+ END {
+ if (badseq) {
+ if (badseqno1 == badseqno2 && badseqno2 == ver)
+ print "GP HANG at " ver " torture stat " badseqnr;
+ else
+ print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
+ }
+ }' > $T.seq
+
+ if grep -q SUCCESS $file
+ then
+ if test -s $T.seq
+ then
+ print_warning $title `cat $T.seq`
+ echo " " $file
+ exit 2
+ fi
+ else
+ if grep -q "_HOTPLUG:" $file
+ then
+ print_warning HOTPLUG FAILURES $title `cat $T.seq`
+ echo " " $file
+ exit 3
+ fi
+ echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
+ if test -s $T.seq
+ then
+ print_warning $title `cat $T.seq`
+ fi
+ exit 2
+ fi
+fi | tee -a $file.diags
+
+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' < $file |
+grep -v 'ODEBUG: ' |
+grep -v 'Warning: unable to open an initial console' > $T.diags
+if test -s $T.diags
+then
+ print_warning "Assertion failure in $file $title"
+ # cat $T.diags
summary=""
- n_badness=`grep -c Badness $1`
+ n_badness=`grep -c Badness $file`
if test "$n_badness" -ne 0
then
summary="$summary Badness: $n_badness"
fi
- n_warn=`grep -v 'Warning: unable to open an initial console' $1 | egrep -c 'WARNING:|Warn'`
+ n_warn=`grep -v 'Warning: unable to open an initial console' $file | egrep -c 'WARNING:|Warn'`
if test "$n_warn" -ne 0
then
summary="$summary Warnings: $n_warn"
fi
- n_bugs=`egrep -c 'BUG|Oops:' $1`
+ n_bugs=`egrep -c 'BUG|Oops:' $file`
if test "$n_bugs" -ne 0
then
summary="$summary Bugs: $n_bugs"
fi
- n_calltrace=`grep -c 'Call Trace:' $1`
+ n_calltrace=`grep -c 'Call Trace:' $file`
if test "$n_calltrace" -ne 0
then
summary="$summary Call Traces: $n_calltrace"
fi
- n_lockdep=`grep -c =========== $1`
+ n_lockdep=`grep -c =========== $file`
if test "$n_badness" -ne 0
then
summary="$summary lockdep: $n_badness"
fi
- n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $1`
+ n_stalls=`egrep -c 'detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state' $file`
if test "$n_stalls" -ne 0
then
summary="$summary Stalls: $n_stalls"
fi
- n_starves=`grep -c 'rcu_.*kthread starved for' $1`
+ n_starves=`grep -c 'rcu_.*kthread starved for' $file`
if test "$n_starves" -ne 0
then
summary="$summary Starves: $n_starves"
fi
print_warning Summary: $summary
-else
- rm $1.diags
+ cat $T.diags >> $file.diags
+fi
+if ! test -s $file.diags
+then
+ rm -f $file.diags
fi
diff --git a/tools/testing/selftests/rcutorture/bin/parse-torture.sh b/tools/testing/selftests/rcutorture/bin/parse-torture.sh
deleted file mode 100755
index 5987e50cfeb4..000000000000
--- a/tools/testing/selftests/rcutorture/bin/parse-torture.sh
+++ /dev/null
@@ -1,105 +0,0 @@
-#!/bin/bash
-#
-# Check the console output from a torture run for goodness.
-# The "file" is a pathname on the local system, and "title" is
-# a text string for error-message purposes.
-#
-# The file must contain torture output, but can be interspersed
-# with other dmesg text, as in console-log output.
-#
-# Usage: parse-torture.sh file title
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License as published by
-# the Free Software Foundation; either version 2 of the License, or
-# (at your option) any later version.
-#
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
-# GNU General Public License for more details.
-#
-# You should have received a copy of the GNU General Public License
-# along with this program; if not, you can access it online at
-# http://www.gnu.org/licenses/gpl-2.0.html.
-#
-# Copyright (C) IBM Corporation, 2011
-#
-# Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
-
-T=${TMPDIR-/tmp}/parse-torture.sh.$$
-file="$1"
-title="$2"
-
-trap 'rm -f $T.seq' 0
-
-. functions.sh
-
-# check for presence of torture output file.
-
-if test -f "$file" -a -r "$file"
-then
- :
-else
- echo $title unreadable torture output file: $file
- exit 1
-fi
-
-# check for abject failure
-
-if grep -q FAILURE $file || grep -q -e '-torture.*!!!' $file
-then
- nerrs=`grep --binary-files=text '!!!' $file | tail -1 | awk '{for (i=NF-8;i<=NF;i++) sum+=$i; } END {print sum}'`
- print_bug $title FAILURE, $nerrs instances
- echo " " $url
- exit
-fi
-
-grep --binary-files=text 'torture:.*ver:' $file | egrep --binary-files=text -v '\(null\)|rtc: 000000000* ' | sed -e 's/^(initramfs)[^]]*] //' -e 's/^\[[^]]*] //' |
-awk '
-BEGIN {
- ver = 0;
- badseq = 0;
- }
-
- {
- if (!badseq && ($5 + 0 != $5 || $5 <= ver)) {
- badseqno1 = ver;
- badseqno2 = $5;
- badseqnr = NR;
- badseq = 1;
- }
- ver = $5
- }
-
-END {
- if (badseq) {
- if (badseqno1 == badseqno2 && badseqno2 == ver)
- print "GP HANG at " ver " torture stat " badseqnr;
- else
- print "BAD SEQ " badseqno1 ":" badseqno2 " last:" ver " version " badseqnr;
- }
- }' > $T.seq
-
-if grep -q SUCCESS $file
-then
- if test -s $T.seq
- then
- print_warning $title $title `cat $T.seq`
- echo " " $file
- exit 2
- fi
-else
- if grep -q "_HOTPLUG:" $file
- then
- print_warning HOTPLUG FAILURES $title `cat $T.seq`
- echo " " $file
- exit 3
- fi
- echo $title no success message, `grep --binary-files=text 'ver:' $file | wc -l` successful version messages
- if test -s $T.seq
- then
- print_warning $title `cat $T.seq`
- fi
- exit 2
-fi
diff --git a/tools/testing/selftests/rtc/.gitignore b/tools/testing/selftests/rtc/.gitignore
new file mode 100644
index 000000000000..d0ad44f6294a
--- /dev/null
+++ b/tools/testing/selftests/rtc/.gitignore
@@ -0,0 +1,2 @@
+rtctest
+setdate
diff --git a/tools/testing/selftests/rtc/Makefile b/tools/testing/selftests/rtc/Makefile
new file mode 100644
index 000000000000..de9c8566672a
--- /dev/null
+++ b/tools/testing/selftests/rtc/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+CFLAGS += -O3 -Wl,-no-as-needed -Wall
+LDFLAGS += -lrt -lpthread -lm
+
+TEST_GEN_PROGS = rtctest
+
+TEST_GEN_PROGS_EXTENDED = setdate
+
+include ../lib.mk
diff --git a/tools/testing/selftests/rtc/rtctest.c b/tools/testing/selftests/rtc/rtctest.c
new file mode 100644
index 000000000000..e20b017e7073
--- /dev/null
+++ b/tools/testing/selftests/rtc/rtctest.c
@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Real Time Clock Driver Test Program
+ *
+ * Copyright (c) 2018 Alexandre Belloni <alexandre.belloni@bootlin.com>
+ */
+
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/rtc.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <time.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+#define NUM_UIE 3
+#define ALARM_DELTA 3
+
+static char *rtc_file = "/dev/rtc0";
+
+FIXTURE(rtc) {
+ int fd;
+};
+
+FIXTURE_SETUP(rtc) {
+ self->fd = open(rtc_file, O_RDONLY);
+ ASSERT_NE(-1, self->fd);
+}
+
+FIXTURE_TEARDOWN(rtc) {
+ close(self->fd);
+}
+
+TEST_F(rtc, date_read) {
+ int rc;
+ struct rtc_time rtc_tm;
+
+ /* Read the RTC time/date */
+ rc = ioctl(self->fd, RTC_RD_TIME, &rtc_tm);
+ ASSERT_NE(-1, rc);
+
+ TH_LOG("Current RTC date/time is %02d/%02d/%02d %02d:%02d:%02d.",
+ rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900,
+ rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec);
+}
+
+TEST_F(rtc, uie_read) {
+ int i, rc, irq = 0;
+ unsigned long data;
+
+ /* Turn on update interrupts */
+ rc = ioctl(self->fd, RTC_UIE_ON, 0);
+ if (rc == -1) {
+ ASSERT_EQ(EINVAL, errno);
+ TH_LOG("skip update IRQs not supported.");
+ return;
+ }
+
+ for (i = 0; i < NUM_UIE; i++) {
+ /* This read will block */
+ rc = read(self->fd, &data, sizeof(data));
+ ASSERT_NE(-1, rc);
+ irq++;
+ }
+
+ EXPECT_EQ(NUM_UIE, irq);
+
+ rc = ioctl(self->fd, RTC_UIE_OFF, 0);
+ ASSERT_NE(-1, rc);
+}
+
+TEST_F(rtc, uie_select) {
+ int i, rc, irq = 0;
+ unsigned long data;
+
+ /* Turn on update interrupts */
+ rc = ioctl(self->fd, RTC_UIE_ON, 0);
+ if (rc == -1) {
+ ASSERT_EQ(EINVAL, errno);
+ TH_LOG("skip update IRQs not supported.");
+ return;
+ }
+
+ for (i = 0; i < NUM_UIE; i++) {
+ struct timeval tv = { .tv_sec = 2 };
+ fd_set readfds;
+
+ FD_ZERO(&readfds);
+ FD_SET(self->fd, &readfds);
+ /* The select will wait until an RTC interrupt happens. */
+ rc = select(self->fd + 1, &readfds, NULL, NULL, &tv);
+ ASSERT_NE(-1, rc);
+ ASSERT_NE(0, rc);
+
+ /* This read won't block */
+ rc = read(self->fd, &data, sizeof(unsigned long));
+ ASSERT_NE(-1, rc);
+ irq++;
+ }
+
+ EXPECT_EQ(NUM_UIE, irq);
+
+ rc = ioctl(self->fd, RTC_UIE_OFF, 0);
+ ASSERT_NE(-1, rc);
+}
+
+TEST_F(rtc, alarm_alm_set) {
+ struct timeval tv = { .tv_sec = ALARM_DELTA + 2 };
+ unsigned long data;
+ struct rtc_time tm;
+ fd_set readfds;
+ time_t secs, new;
+ int rc;
+
+ rc = ioctl(self->fd, RTC_RD_TIME, &tm);
+ ASSERT_NE(-1, rc);
+
+ secs = timegm((struct tm *)&tm) + ALARM_DELTA;
+ gmtime_r(&secs, (struct tm *)&tm);
+
+ rc = ioctl(self->fd, RTC_ALM_SET, &tm);
+ if (rc == -1) {
+ ASSERT_EQ(EINVAL, errno);
+ TH_LOG("skip alarms are not supported.");
+ return;
+ }
+
+ rc = ioctl(self->fd, RTC_ALM_READ, &tm);
+ ASSERT_NE(-1, rc);
+
+ TH_LOG("Alarm time now set to %02d:%02d:%02d.",
+ tm.tm_hour, tm.tm_min, tm.tm_sec);
+
+ /* Enable alarm interrupts */
+ rc = ioctl(self->fd, RTC_AIE_ON, 0);
+ ASSERT_NE(-1, rc);
+
+ FD_ZERO(&readfds);
+ FD_SET(self->fd, &readfds);
+
+ rc = select(self->fd + 1, &readfds, NULL, NULL, &tv);
+ ASSERT_NE(-1, rc);
+ EXPECT_NE(0, rc);
+
+ /* Disable alarm interrupts */
+ rc = ioctl(self->fd, RTC_AIE_OFF, 0);
+ ASSERT_NE(-1, rc);
+
+ if (rc == 0)
+ return;
+
+ rc = read(self->fd, &data, sizeof(unsigned long));
+ ASSERT_NE(-1, rc);
+ TH_LOG("data: %lx", data);
+
+ rc = ioctl(self->fd, RTC_RD_TIME, &tm);
+ ASSERT_NE(-1, rc);
+
+ new = timegm((struct tm *)&tm);
+ ASSERT_EQ(new, secs);
+}
+
+TEST_F(rtc, alarm_wkalm_set) {
+ struct timeval tv = { .tv_sec = ALARM_DELTA + 2 };
+ struct rtc_wkalrm alarm = { 0 };
+ struct rtc_time tm;
+ unsigned long data;
+ fd_set readfds;
+ time_t secs, new;
+ int rc;
+
+ rc = ioctl(self->fd, RTC_RD_TIME, &alarm.time);
+ ASSERT_NE(-1, rc);
+
+ secs = timegm((struct tm *)&alarm.time) + ALARM_DELTA;
+ gmtime_r(&secs, (struct tm *)&alarm.time);
+
+ alarm.enabled = 1;
+
+ rc = ioctl(self->fd, RTC_WKALM_SET, &alarm);
+ if (rc == -1) {
+ ASSERT_EQ(EINVAL, errno);
+ TH_LOG("skip alarms are not supported.");
+ return;
+ }
+
+ rc = ioctl(self->fd, RTC_WKALM_RD, &alarm);
+ ASSERT_NE(-1, rc);
+
+ TH_LOG("Alarm time now set to %02d/%02d/%02d %02d:%02d:%02d.",
+ alarm.time.tm_mday, alarm.time.tm_mon + 1,
+ alarm.time.tm_year + 1900, alarm.time.tm_hour,
+ alarm.time.tm_min, alarm.time.tm_sec);
+
+ FD_ZERO(&readfds);
+ FD_SET(self->fd, &readfds);
+
+ rc = select(self->fd + 1, &readfds, NULL, NULL, &tv);
+ ASSERT_NE(-1, rc);
+ EXPECT_NE(0, rc);
+
+ rc = read(self->fd, &data, sizeof(unsigned long));
+ ASSERT_NE(-1, rc);
+
+ rc = ioctl(self->fd, RTC_RD_TIME, &tm);
+ ASSERT_NE(-1, rc);
+
+ new = timegm((struct tm *)&tm);
+ ASSERT_EQ(new, secs);
+}
+
+static void __attribute__((constructor))
+__constructor_order_last(void)
+{
+ if (!__constructor_order)
+ __constructor_order = _CONSTRUCTOR_ORDER_BACKWARD;
+}
+
+int main(int argc, char **argv)
+{
+ switch (argc) {
+ case 2:
+ rtc_file = argv[1];
+ /* FALLTHROUGH */
+ case 1:
+ break;
+ default:
+ fprintf(stderr, "usage: %s [rtcdev]\n", argv[0]);
+ return 1;
+ }
+
+ return test_harness_run(argc, argv);
+}
diff --git a/tools/testing/selftests/timers/rtctest_setdate.c b/tools/testing/selftests/rtc/setdate.c
index 2cb78489eca4..2cb78489eca4 100644
--- a/tools/testing/selftests/timers/rtctest_setdate.c
+++ b/tools/testing/selftests/rtc/setdate.c
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 168c66d74fc5..e1473234968d 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -134,11 +134,15 @@ struct seccomp_data {
#endif
#ifndef SECCOMP_FILTER_FLAG_TSYNC
-#define SECCOMP_FILTER_FLAG_TSYNC 1
+#define SECCOMP_FILTER_FLAG_TSYNC (1UL << 0)
#endif
#ifndef SECCOMP_FILTER_FLAG_LOG
-#define SECCOMP_FILTER_FLAG_LOG 2
+#define SECCOMP_FILTER_FLAG_LOG (1UL << 1)
+#endif
+
+#ifndef SECCOMP_FILTER_FLAG_SPEC_ALLOW
+#define SECCOMP_FILTER_FLAG_SPEC_ALLOW (1UL << 2)
#endif
#ifndef PTRACE_SECCOMP_GET_METADATA
@@ -2072,14 +2076,26 @@ TEST(seccomp_syscall_mode_lock)
TEST(detect_seccomp_filter_flags)
{
unsigned int flags[] = { SECCOMP_FILTER_FLAG_TSYNC,
- SECCOMP_FILTER_FLAG_LOG };
+ SECCOMP_FILTER_FLAG_LOG,
+ SECCOMP_FILTER_FLAG_SPEC_ALLOW };
unsigned int flag, all_flags;
int i;
long ret;
/* Test detection of known-good filter flags */
for (i = 0, all_flags = 0; i < ARRAY_SIZE(flags); i++) {
+ int bits = 0;
+
flag = flags[i];
+ /* Make sure the flag is a single bit! */
+ while (flag) {
+ if (flag & 0x1)
+ bits ++;
+ flag >>= 1;
+ }
+ ASSERT_EQ(1, bits);
+ flag = flags[i];
+
ret = seccomp(SECCOMP_SET_MODE_FILTER, flag, NULL);
ASSERT_NE(ENOSYS, errno) {
TH_LOG("Kernel does not support seccomp syscall!");
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 5b012f4981d4..6f289a49e5ec 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -66,7 +66,7 @@
"cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
"expExitCode": "0",
"verifyCmd": "$TC action get action bpf index 667",
- "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c default-action pipe.*index 667 ref",
+ "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
"matchCount": "1",
"teardown": [
"$TC action flush action bpf",
@@ -92,10 +92,15 @@
"cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
"expExitCode": "255",
"verifyCmd": "$TC action get action bpf index 667",
- "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9].*index 667 ref",
+ "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
"matchCount": "0",
"teardown": [
- "$TC action flush action bpf",
+ [
+ "$TC action flush action bpf",
+ 0,
+ 1,
+ 255
+ ],
"rm -f _c.o"
]
},
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
index 93cf8fea8ae7..3a2f51fc7fd4 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
@@ -398,13 +398,83 @@
255
]
],
- "cmdUnderTest": "for i in `seq 1 32`; do cmd=\"action csum tcp continue index $i \"; args=\"$args$cmd\"; done && $TC actions add $args",
- "expExitCode": "255",
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
"verifyCmd": "$TC actions ls action csum",
"matchPattern": "^[ \t]+index [0-9]* ref",
"matchCount": "32",
"teardown": [
"$TC actions flush action csum"
]
+ },
+ {
+ "id": "b4e9",
+ "name": "Delete batch of 32 csum actions",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action csum",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "0015",
+ "name": "Add batch of 32 csum tcp actions with large cookies",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions ls action csum",
+ "matchPattern": "^[ \t]+index [0-9]* ref",
+ "matchCount": "32",
+ "teardown": [
+ "$TC actions flush action csum"
+ ]
+ },
+ {
+ "id": "989e",
+ "name": "Delete batch of 32 csum actions with large cookies",
+ "category": [
+ "actions",
+ "csum"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action csum",
+ 0,
+ 1,
+ 255
+ ],
+ "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\""
+ ],
+ "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action csum",
+ "matchPattern": "^[ \t]+index [0-9]+ ref",
+ "matchCount": "0",
+ "teardown": []
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
index 9f34f0753969..de97e4ff705c 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json
@@ -1,7 +1,7 @@
[
{
- "id": "a568",
- "name": "Add action with ife type",
+ "id": "7682",
+ "name": "Create valid ife encode action with mark and pass control",
"category": [
"actions",
"ife"
@@ -12,21 +12,782 @@
0,
1,
255
- ],
- "$TC actions add action ife encode type 0xDEAD index 1"
+ ]
],
- "cmdUnderTest": "$TC actions get action ife index 1",
+ "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 2",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "ef47",
+ "name": "Create valid ife encode action with mark and pipe control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 10 pipe index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 2",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark.*index 2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "df43",
+ "name": "Create valid ife encode action with mark and continue control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow mark continue index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 2",
+ "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*allow mark.*index 2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "e4cf",
+ "name": "Create valid ife encode action with mark and drop control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 789 drop index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 2",
+ "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*use mark 789.*index 2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "ccba",
+ "name": "Create valid ife encode action with mark and reclassify control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 656768 reclassify index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 2",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 656768.*index 2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "a1cf",
+ "name": "Create valid ife encode action with mark and jump control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 65 jump 1 index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 2",
+ "matchPattern": "action order [0-9]*: ife encode action jump 1.*type 0xED3E.*use mark 65.*index 2",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "cb3d",
+ "name": "Create valid ife encode action with mark value at 32-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295 reclassify index 90",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 90",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 4294967295.*index 90",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "1efb",
+ "name": "Create ife encode action with mark value exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295999 pipe index 90",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 90",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark 4294967295999.*index 90",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "95ed",
+ "name": "Create valid ife encode action with prio and pass control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow prio pass index 9",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 9",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow prio.*index 9",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "aa17",
+ "name": "Create valid ife encode action with prio and pipe control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 7 pipe index 9",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 9",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 7.*index 9",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "74c7",
+ "name": "Create valid ife encode action with prio and continue control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 3 continue index 9",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 9",
+ "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use prio 3.*index 9",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "7a97",
+ "name": "Create valid ife encode action with prio and drop control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow prio drop index 9",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 9",
+ "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow prio.*index 9",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "f66b",
+ "name": "Create valid ife encode action with prio and reclassify control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 998877 reclassify index 9",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 9",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 998877.*index 9",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "3056",
+ "name": "Create valid ife encode action with prio and jump control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 998877 jump 10 index 9",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 9",
+ "matchPattern": "action order [0-9]*: ife encode action jump 10.*type 0xED3E.*use prio 998877.*index 9",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "7dd3",
+ "name": "Create valid ife encode action with prio value at 32-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 4294967295 reclassify index 99",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 99",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 4294967295.*index 99",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "2ca1",
+ "name": "Create ife encode action with prio value exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 4294967298 pipe index 99",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 99",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 4294967298.*index 99",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "05bb",
+ "name": "Create valid ife encode action with tcindex and pass control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow tcindex pass index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "ce65",
+ "name": "Create valid ife encode action with tcindex and pipe control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use tcindex 111 pipe index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 111.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "09cd",
+ "name": "Create valid ife encode action with tcindex and continue control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "8eb5",
+ "name": "Create valid ife encode action with tcindex and continue control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "451a",
+ "name": "Create valid ife encode action with tcindex and drop control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow tcindex drop index 77",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 77",
+ "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow tcindex.*index 77",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "d76c",
+ "name": "Create valid ife encode action with tcindex and reclassify control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow tcindex reclassify index 77",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 77",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*allow tcindex.*index 77",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "e731",
+ "name": "Create valid ife encode action with tcindex and jump control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow tcindex jump 999 index 77",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 77",
+ "matchPattern": "action order [0-9]*: ife encode action jump 999.*type 0xED3E.*allow tcindex.*index 77",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "b7b8",
+ "name": "Create valid ife encode action with tcindex value at 16-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use tcindex 65535 pass index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*use tcindex 65535.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action skbedit"
+ ]
+ },
+ {
+ "id": "d0d8",
+ "name": "Create ife encode action with tcindex value exceeding 16-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use tcindex 65539 pipe index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 65539.*index 1",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "2a9c",
+ "name": "Create valid ife encode action with mac src parameter",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow mark src 00:11:22:33:44:55 pipe index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow mark src 00:11:22:33:44:55.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "cf5c",
+ "name": "Create valid ife encode action with mac dst parameter",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 9876 dst 00:11:22:33:44:55 reclassify index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 9876 dst 00:11:22:33:44:55.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "2353",
+ "name": "Create valid ife encode action with mac src and mac dst parameters",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow tcindex src 00:aa:bb:cc:dd:ee dst 00:11:22:33:44:55 pass index 11",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 11",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex dst 00:11:22:33:44:55 src 00:aa:bb:cc:dd:ee .*index 11",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "552c",
+ "name": "Create valid ife encode action with mark and type parameters",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use mark 7 type 0xfefe pass index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xFEFE.*use mark 7.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "0421",
+ "name": "Create valid ife encode action with prio and type parameters",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use prio 444 type 0xabba pipe index 21",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 21",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xABBA.*use prio 444.*index 21",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "4017",
+ "name": "Create valid ife encode action with tcindex and type parameters",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode use tcindex 5000 type 0xabcd reclassify index 21",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 21",
+ "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xABCD.*use tcindex 5000.*index 21",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "fac3",
+ "name": "Create valid ife encode action with index at 32-bit maximnum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 4294967295",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "7c25",
+ "name": "Create valid ife decode action with pass control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife decode pass index 1",
"expExitCode": "0",
"verifyCmd": "$TC actions get action ife index 1",
- "matchPattern": "type 0xDEAD",
+ "matchPattern": "action order [0-9]*: ife decode action pass.*type 0x0.*allow mark allow tcindex allow prio.*index 1",
"matchCount": "1",
"teardown": [
"$TC actions flush action ife"
]
},
{
- "id": "b983",
- "name": "Add action without ife type",
+ "id": "dccb",
+ "name": "Create valid ife decode action with pipe control",
"category": [
"actions",
"ife"
@@ -37,16 +798,267 @@
0,
1,
255
- ],
- "$TC actions add action ife encode index 1"
+ ]
],
- "cmdUnderTest": "$TC actions get action ife index 1",
+ "cmdUnderTest": "$TC actions add action ife decode pipe index 1",
"expExitCode": "0",
"verifyCmd": "$TC actions get action ife index 1",
- "matchPattern": "type 0xED3E",
+ "matchPattern": "action order [0-9]*: ife decode action pipe.*type 0x0.*allow mark allow tcindex allow prio.*index 1",
"matchCount": "1",
"teardown": [
"$TC actions flush action ife"
]
+ },
+ {
+ "id": "7bb9",
+ "name": "Create valid ife decode action with continue control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife decode continue index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife decode action continue.*type 0x0.*allow mark allow tcindex allow prio.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "d9ad",
+ "name": "Create valid ife decode action with drop control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife decode drop index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife decode action drop.*type 0x0.*allow mark allow tcindex allow prio.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "219f",
+ "name": "Create valid ife decode action with reclassify control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife decode reclassify index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife decode action reclassify.*type 0x0.*allow mark allow tcindex allow prio.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "8f44",
+ "name": "Create valid ife decode action with jump control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife decode jump 10 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 1",
+ "matchPattern": "action order [0-9]*: ife decode action jump 10.*type 0x0.*allow mark allow tcindex allow prio.*index 1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "56cf",
+ "name": "Create ife encode action with index exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295999",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 4294967295999",
+ "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295999",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "ee94",
+ "name": "Create ife encode action with invalid control",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow mark kuka index 4",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 4",
+ "matchPattern": "action order [0-9]*: ife encode action kuka.*type 0xED3E.*allow mark.*index 4",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "b330",
+ "name": "Create ife encode action with cookie",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow prio pipe index 4 cookie aabbccddeeff112233445566778800a1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action ife index 4",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow prio.*index 4.*cookie aabbccddeeff112233445566778800a1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action ife"
+ ]
+ },
+ {
+ "id": "bbc0",
+ "name": "Create ife encode action with invalid argument",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow foo pipe index 4",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 4",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow foo.*index 4",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "d54a",
+ "name": "Create ife encode action with invalid type argument",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow prio type 70000 pipe index 4",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 4",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0x11170.*allow prio.*index 4",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "7ee0",
+ "name": "Create ife encode action with invalid mac src argument",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow prio src 00:11:22:33:44:pp pipe index 4",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 4",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "0a7d",
+ "name": "Create ife encode action with invalid mac dst argument",
+ "category": [
+ "actions",
+ "ife"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action ife",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action ife encode allow prio dst 00.111-22:33:44:aa pipe index 4",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action ife index 4",
+ "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4",
+ "matchCount": "0",
+ "teardown": []
}
]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
index 443c9b3c8664..6e4edfae1799 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -340,7 +340,7 @@
},
{
"id": "8b69",
- "name": "Add mirred mirror action with maximum index",
+ "name": "Add mirred mirror action with index at 32-bit maximum",
"category": [
"actions",
"mirred"
@@ -363,6 +363,28 @@
]
},
{
+ "id": "3f66",
+ "name": "Add mirred mirror action with index exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "mirred"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action mirred",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action mirred ingress mirror dev lo pipe index 429496729555",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action mirred index 429496729555",
+ "matchPattern": "action order [0-9]*: mirred \\(Ingress Mirror to device lo\\) pipe.*index 429496729555",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
"id": "a70e",
"name": "Delete mirred mirror action",
"category": [
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index 38d85a1d7492..f03763d81617 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -401,11 +401,11 @@
],
"cmdUnderTest": "$TC actions add action police rate 10mbit burst 10k index 4294967295",
"expExitCode": "0",
- "verifyCmd": "$TC actions get action mirred index 4294967295",
+ "verifyCmd": "$TC actions get action police index 4294967295",
"matchPattern": "action order [0-9]*: police 0xffffffff rate 10Mbit burst 10Kb mtu 2Kb",
"matchCount": "1",
"teardown": [
- "$TC actions flush action mirred"
+ "$TC actions flush action police"
]
},
{
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
new file mode 100644
index 000000000000..3aca33c00039
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json
@@ -0,0 +1,588 @@
+[
+ {
+ "id": "9784",
+ "name": "Add valid sample action with mandatory arguments",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 10 group 1 index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 2",
+ "matchPattern": "action order [0-9]+: sample rate 1/10 group 1.*index 2 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "5c91",
+ "name": "Add valid sample action with mandatory arguments and continue control action",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 700 group 2 continue index 2",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 2",
+ "matchPattern": "action order [0-9]+: sample rate 1/700 group 2 continue.*index 2 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "334b",
+ "name": "Add valid sample action with mandatory arguments and drop control action",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 10000 group 11 drop index 22",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/10000 group 11 drop.*index 22 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "da69",
+ "name": "Add valid sample action with mandatory arguments and reclassify control action",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 20000 group 72 reclassify index 100",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/20000 group 72 reclassify.*index 100 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "13ce",
+ "name": "Add valid sample action with mandatory arguments and pipe control action",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 20 group 2 pipe index 100",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/20 group 2 pipe.*index 100 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "1886",
+ "name": "Add valid sample action with mandatory arguments and jump control action",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 700 group 25 jump 4 index 200",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 200",
+ "matchPattern": "action order [0-9]+: sample rate 1/700 group 25 jump 4.*index 200 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "b6d4",
+ "name": "Add sample action with mandatory arguments and invalid control action",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 200000 group 52 foo index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/200000 group 52 foo.*index 1 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "a874",
+ "name": "Add invalid sample action without mandatory arguments",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample.*index 1 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "ac01",
+ "name": "Add invalid sample action without mandatory argument rate",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample group 10 index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample.*group 10.*index 1 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "4203",
+ "name": "Add invalid sample action without mandatory argument group",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 100 index 10",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 10",
+ "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "14a7",
+ "name": "Add invalid sample action without mandatory argument group",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 100 index 10",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 10",
+ "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "8f2e",
+ "name": "Add valid sample action with trunc argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 1024 index 10",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 10",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 1024 pipe.*index 10 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "45f8",
+ "name": "Add sample action with maximum rate argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 4294967295 group 4 index 10",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 10",
+ "matchPattern": "action order [0-9]+: sample rate 1/4294967295 group 4 pipe.*index 10 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "ad0c",
+ "name": "Add sample action with maximum trunc argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 16000 group 4 trunc 4294967295 index 10",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 10",
+ "matchPattern": "action order [0-9]+: sample rate 1/16000 group 4 trunc_size 4294967295 pipe.*index 10 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "83a9",
+ "name": "Add sample action with maximum group argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 4294 group 4294967295 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 1",
+ "matchPattern": "action order [0-9]+: sample rate 1/4294 group 4294967295 pipe.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "ed27",
+ "name": "Add sample action with invalid rate argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 4294967296 group 4 index 10",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 10",
+ "matchPattern": "action order [0-9]+: sample rate 1/4294967296 group 4 pipe.*index 10 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "2eae",
+ "name": "Add sample action with invalid group argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 4098 group 5294967299 continue index 1",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 1",
+ "matchPattern": "action order [0-9]+: sample rate 1/4098 group 5294967299 continue.*index 1 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "6ff3",
+ "name": "Add sample action with invalid trunc size",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 112233445566 index 11",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 11",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 112233445566.*index 11 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "2b2a",
+ "name": "Add sample action with invalid index",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 5294967299",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action sample index 5294967299",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 5294967299 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "dee2",
+ "name": "Add sample action with maximum allowed index",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 4294967295",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 4294967295",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 4294967295 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "560e",
+ "name": "Add sample action with cookie",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 45 cookie aabbccdd",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action sample index 45",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 45.*cookie aabbccdd",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "704a",
+ "name": "Replace existing sample action with new rate argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action sample rate 1024 group 4 index 4"
+ ],
+ "cmdUnderTest": "$TC actions replace action sample rate 2048 group 4 index 4",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/2048 group 4 pipe.*index 4",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "60eb",
+ "name": "Replace existing sample action with new group argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action sample rate 1024 group 4 index 4"
+ ],
+ "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 index 4",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "2cce",
+ "name": "Replace existing sample action with new trunc argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action sample rate 1024 group 4 trunc 48 index 4"
+ ],
+ "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 trunc 64 index 4",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 trunc_size 64 pipe.*index 4",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ },
+ {
+ "id": "59d1",
+ "name": "Replace existing sample action with new control argument",
+ "category": [
+ "actions",
+ "sample"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action sample",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action sample rate 1024 group 4 reclassify index 4"
+ ],
+ "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 pipe index 4",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action sample",
+ "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action sample"
+ ]
+ }
+]
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
index 4510ddfa6e54..69ea09eefffc 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/vlan.json
@@ -1,7 +1,7 @@
[
{
"id": "6f5a",
- "name": "Add vlan pop action",
+ "name": "Add vlan pop action with pipe opcode",
"category": [
"actions",
"vlan"
@@ -14,18 +14,18 @@
255
]
],
- "cmdUnderTest": "$TC actions add action vlan pop index 8",
+ "cmdUnderTest": "$TC actions add action vlan pop pipe index 8",
"expExitCode": "0",
"verifyCmd": "$TC actions list action vlan",
- "matchPattern": "action order [0-9]+: vlan.*pop.*index 8 ref",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*pipe.*index 8 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action vlan"
]
},
{
- "id": "ee6f",
- "name": "Add vlan pop action with large index",
+ "id": "df35",
+ "name": "Add vlan pop action with pass opcode",
"category": [
"actions",
"vlan"
@@ -38,10 +38,82 @@
255
]
],
- "cmdUnderTest": "$TC actions add action vlan pop index 4294967295",
+ "cmdUnderTest": "$TC actions add action vlan pop pass index 8",
"expExitCode": "0",
- "verifyCmd": "$TC actions list action vlan",
- "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*pass.*index 8 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "b0d4",
+ "name": "Add vlan pop action with drop opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop drop index 8",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*drop.*index 8 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "95ee",
+ "name": "Add vlan pop action with reclassify opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop reclassify index 8",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*reclassify.*index 8 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "0283",
+ "name": "Add vlan pop action with continue opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop continue index 8",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 8",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*continue.*index 8 ref",
"matchCount": "1",
"teardown": [
"$TC actions flush action vlan"
@@ -96,6 +168,74 @@
]
},
{
+ "id": "a178",
+ "name": "Add vlan pop action with invalid opcode",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop foo index 8",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*foo.*index 8 ref",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
+ "id": "ee6f",
+ "name": "Add vlan pop action with index at 32-bit maximum",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop index 4294967295",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action vlan",
+ "matchPattern": "action order [0-9]+: vlan.*pop.*index 4294967295 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "0dfa",
+ "name": "Add vlan pop action with index exceeding 32-bit maximum",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan pop reclassify index 429496729599",
+ "expExitCode": "255",
+ "verifyCmd": "$TC actions get action vlan index 429496729599",
+ "matchPattern": "action order [0-9]+: vlan.*pop.reclassify.*index 429496729599",
+ "matchCount": "0",
+ "teardown": []
+ },
+ {
"id": "2b91",
"name": "Add vlan invalid action",
"category": [
@@ -115,13 +255,11 @@
"verifyCmd": "$TC actions list action vlan",
"matchPattern": "action order [0-9]+: vlan.*bad_mode",
"matchCount": "0",
- "teardown": [
- "$TC actions flush action vlan"
- ]
+ "teardown": []
},
{
"id": "57fc",
- "name": "Add vlan action with invalid protocol type",
+ "name": "Add vlan push action with invalid protocol type",
"category": [
"actions",
"vlan"
@@ -139,9 +277,7 @@
"verifyCmd": "$TC actions list action vlan",
"matchPattern": "action order [0-9]+: vlan.*push",
"matchCount": "0",
- "teardown": [
- "$TC actions flush action vlan"
- ]
+ "teardown": []
},
{
"id": "3989",
@@ -216,6 +352,30 @@
]
},
{
+ "id": "1f4b",
+ "name": "Add vlan push action with maximum 12-bit vlan ID",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan push id 4094 index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 4094.*protocol 802.1Q.*priority 0.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
"id": "1f7b",
"name": "Add vlan push action with invalid vlan ID",
"category": [
@@ -240,6 +400,30 @@
]
},
{
+ "id": "fe40",
+ "name": "Add vlan push action with maximum 3-bit IEEE 802.1p priority",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ]
+ ],
+ "cmdUnderTest": "$TC actions add action vlan push id 4 priority 7 reclassify index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 4.*protocol 802.1Q.*priority 7.*reclassify.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
"id": "5d02",
"name": "Add vlan push action with invalid IEEE 802.1p priority",
"category": [
@@ -259,9 +443,7 @@
"verifyCmd": "$TC actions list action vlan",
"matchPattern": "action order [0-9]+: vlan.*push id 5.*index 1 ref",
"matchCount": "0",
- "teardown": [
- "$TC actions flush action vlan"
- ]
+ "teardown": []
},
{
"id": "6812",
@@ -312,6 +494,106 @@
]
},
{
+ "id": "3deb",
+ "name": "Replace existing vlan push action with new ID",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan push id 500 pipe index 12"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan push id 700 pipe index 12",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 12",
+ "matchPattern": "action order [0-9]+: vlan.*push id 700 protocol 802.1Q priority 0 pipe.*index 12 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "9e76",
+ "name": "Replace existing vlan push action with new protocol",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan push id 1 protocol 802.1Q pipe index 1"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan push id 1 protocol 802.1ad pipe index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1ad priority 0 pipe.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "ede4",
+ "name": "Replace existing vlan push action with new priority",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan push id 1 protocol 802.1Q priority 3 reclassify index 1"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan push id 1 priority 4 reclassify index 1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*push id 1 protocol 802.1Q priority 4 reclassify.*index 1 ref",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
+ "id": "d413",
+ "name": "Replace existing vlan pop action with new cookie",
+ "category": [
+ "actions",
+ "vlan"
+ ],
+ "setup": [
+ [
+ "$TC actions flush action vlan",
+ 0,
+ 1,
+ 255
+ ],
+ "$TC actions add action vlan pop continue index 1 cookie 22334455"
+ ],
+ "cmdUnderTest": "$TC actions replace action vlan pop continue index 1 cookie a1b1c2d1",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions get action vlan index 1",
+ "matchPattern": "action order [0-9]+: vlan.*pop continue.*index 1 ref.*cookie a1b1c2d1",
+ "matchCount": "1",
+ "teardown": [
+ "$TC actions flush action vlan"
+ ]
+ },
+ {
"id": "83a4",
"name": "Delete vlan pop action",
"category": [
@@ -385,7 +667,7 @@
},
{
"id": "1d78",
- "name": "Add vlan action with cookie",
+ "name": "Add vlan push action with cookie",
"category": [
"actions",
"vlan"
diff --git a/tools/testing/selftests/timers/.gitignore b/tools/testing/selftests/timers/.gitignore
index 2c8ac8416299..32a9eadb2d4e 100644
--- a/tools/testing/selftests/timers/.gitignore
+++ b/tools/testing/selftests/timers/.gitignore
@@ -9,7 +9,7 @@ nanosleep
nsleep-lat
posix_timers
raw_skew
-rtctest
+rtcpie
set-2038
set-tai
set-timer-lat
@@ -19,4 +19,3 @@ valid-adjtimex
adjtick
set-tz
freq-step
-rtctest_setdate
diff --git a/tools/testing/selftests/timers/Makefile b/tools/testing/selftests/timers/Makefile
index 3496680981f2..c02683cfb6c9 100644
--- a/tools/testing/selftests/timers/Makefile
+++ b/tools/testing/selftests/timers/Makefile
@@ -5,13 +5,13 @@ LDFLAGS += -lrt -lpthread -lm
# these are all "safe" tests that don't modify
# system time or require escalated privileges
TEST_GEN_PROGS = posix_timers nanosleep nsleep-lat set-timer-lat mqueue-lat \
- inconsistency-check raw_skew threadtest rtctest
+ inconsistency-check raw_skew threadtest rtcpie
DESTRUCTIVE_TESTS = alarmtimer-suspend valid-adjtimex adjtick change_skew \
skew_consistency clocksource-switch freq-step leap-a-day \
leapcrash set-tai set-2038 set-tz
-TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS) rtctest_setdate
+TEST_GEN_PROGS_EXTENDED = $(DESTRUCTIVE_TESTS)
include ../lib.mk
diff --git a/tools/testing/selftests/timers/rtcpie.c b/tools/testing/selftests/timers/rtcpie.c
new file mode 100644
index 000000000000..47b5bad1b393
--- /dev/null
+++ b/tools/testing/selftests/timers/rtcpie.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Real Time Clock Periodic Interrupt test program
+ *
+ * Since commit 6610e0893b8bc ("RTC: Rework RTC code to use timerqueue for
+ * events"), PIE are completely handled using hrtimers, without actually using
+ * any underlying hardware RTC.
+ *
+ */
+
+#include <stdio.h>
+#include <linux/rtc.h>
+#include <sys/ioctl.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <errno.h>
+
+/*
+ * This expects the new RTC class driver framework, working with
+ * clocks that will often not be clones of what the PC-AT had.
+ * Use the command line to specify another RTC if you need one.
+ */
+static const char default_rtc[] = "/dev/rtc0";
+
+int main(int argc, char **argv)
+{
+ int i, fd, retval, irqcount = 0;
+ unsigned long tmp, data, old_pie_rate;
+ const char *rtc = default_rtc;
+ struct timeval start, end, diff;
+
+ switch (argc) {
+ case 2:
+ rtc = argv[1];
+ /* FALLTHROUGH */
+ case 1:
+ break;
+ default:
+ fprintf(stderr, "usage: rtctest [rtcdev] [d]\n");
+ return 1;
+ }
+
+ fd = open(rtc, O_RDONLY);
+
+ if (fd == -1) {
+ perror(rtc);
+ exit(errno);
+ }
+
+ /* Read periodic IRQ rate */
+ retval = ioctl(fd, RTC_IRQP_READ, &old_pie_rate);
+ if (retval == -1) {
+ /* not all RTCs support periodic IRQs */
+ if (errno == EINVAL) {
+ fprintf(stderr, "\nNo periodic IRQ support\n");
+ goto done;
+ }
+ perror("RTC_IRQP_READ ioctl");
+ exit(errno);
+ }
+ fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", old_pie_rate);
+
+ fprintf(stderr, "Counting 20 interrupts at:");
+ fflush(stderr);
+
+ /* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */
+ for (tmp=2; tmp<=64; tmp*=2) {
+
+ retval = ioctl(fd, RTC_IRQP_SET, tmp);
+ if (retval == -1) {
+ /* not all RTCs can change their periodic IRQ rate */
+ if (errno == EINVAL) {
+ fprintf(stderr,
+ "\n...Periodic IRQ rate is fixed\n");
+ goto done;
+ }
+ perror("RTC_IRQP_SET ioctl");
+ exit(errno);
+ }
+
+ fprintf(stderr, "\n%ldHz:\t", tmp);
+ fflush(stderr);
+
+ /* Enable periodic interrupts */
+ retval = ioctl(fd, RTC_PIE_ON, 0);
+ if (retval == -1) {
+ perror("RTC_PIE_ON ioctl");
+ exit(errno);
+ }
+
+ for (i=1; i<21; i++) {
+ gettimeofday(&start, NULL);
+ /* This blocks */
+ retval = read(fd, &data, sizeof(unsigned long));
+ if (retval == -1) {
+ perror("read");
+ exit(errno);
+ }
+ gettimeofday(&end, NULL);
+ timersub(&end, &start, &diff);
+ if (diff.tv_sec > 0 ||
+ diff.tv_usec > ((1000000L / tmp) * 1.10)) {
+ fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n",
+ diff.tv_sec, diff.tv_usec,
+ (1000000L / tmp));
+ fflush(stdout);
+ exit(-1);
+ }
+
+ fprintf(stderr, " %d",i);
+ fflush(stderr);
+ irqcount++;
+ }
+
+ /* Disable periodic interrupts */
+ retval = ioctl(fd, RTC_PIE_OFF, 0);
+ if (retval == -1) {
+ perror("RTC_PIE_OFF ioctl");
+ exit(errno);
+ }
+ }
+
+done:
+ ioctl(fd, RTC_IRQP_SET, old_pie_rate);
+
+ fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n");
+
+ close(fd);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/timers/rtctest.c b/tools/testing/selftests/timers/rtctest.c
deleted file mode 100644
index 411eff625e66..000000000000
--- a/tools/testing/selftests/timers/rtctest.c
+++ /dev/null
@@ -1,403 +0,0 @@
-/*
- * Real Time Clock Driver Test/Example Program
- *
- * Compile with:
- * gcc -s -Wall -Wstrict-prototypes rtctest.c -o rtctest
- *
- * Copyright (C) 1996, Paul Gortmaker.
- *
- * Released under the GNU General Public License, version 2,
- * included herein by reference.
- *
- */
-
-#include <stdio.h>
-#include <linux/rtc.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
-#include <sys/types.h>
-#include <fcntl.h>
-#include <unistd.h>
-#include <stdlib.h>
-#include <errno.h>
-
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
-/*
- * This expects the new RTC class driver framework, working with
- * clocks that will often not be clones of what the PC-AT had.
- * Use the command line to specify another RTC if you need one.
- */
-static const char default_rtc[] = "/dev/rtc0";
-
-static struct rtc_time cutoff_dates[] = {
- {
- .tm_year = 70, /* 1970 -1900 */
- .tm_mday = 1,
- },
- /* signed time_t 19/01/2038 3:14:08 */
- {
- .tm_year = 138,
- .tm_mday = 19,
- },
- {
- .tm_year = 138,
- .tm_mday = 20,
- },
- {
- .tm_year = 199, /* 2099 -1900 */
- .tm_mday = 1,
- },
- {
- .tm_year = 200, /* 2100 -1900 */
- .tm_mday = 1,
- },
- /* unsigned time_t 07/02/2106 7:28:15*/
- {
- .tm_year = 205,
- .tm_mon = 1,
- .tm_mday = 7,
- },
- {
- .tm_year = 206,
- .tm_mon = 1,
- .tm_mday = 8,
- },
- /* signed time on 64bit in nanoseconds 12/04/2262 01:47:16*/
- {
- .tm_year = 362,
- .tm_mon = 3,
- .tm_mday = 12,
- },
- {
- .tm_year = 362, /* 2262 -1900 */
- .tm_mon = 3,
- .tm_mday = 13,
- },
-};
-
-static int compare_dates(struct rtc_time *a, struct rtc_time *b)
-{
- if (a->tm_year != b->tm_year ||
- a->tm_mon != b->tm_mon ||
- a->tm_mday != b->tm_mday ||
- a->tm_hour != b->tm_hour ||
- a->tm_min != b->tm_min ||
- ((b->tm_sec - a->tm_sec) > 1))
- return 1;
-
- return 0;
-}
-
-int main(int argc, char **argv)
-{
- int i, fd, retval, irqcount = 0, dangerous = 0;
- unsigned long tmp, data;
- struct rtc_time rtc_tm;
- const char *rtc = default_rtc;
- struct timeval start, end, diff;
-
- switch (argc) {
- case 3:
- if (*argv[2] == 'd')
- dangerous = 1;
- case 2:
- rtc = argv[1];
- /* FALLTHROUGH */
- case 1:
- break;
- default:
- fprintf(stderr, "usage: rtctest [rtcdev] [d]\n");
- return 1;
- }
-
- fd = open(rtc, O_RDONLY);
-
- if (fd == -1) {
- perror(rtc);
- exit(errno);
- }
-
- fprintf(stderr, "\n\t\t\tRTC Driver Test Example.\n\n");
-
- /* Turn on update interrupts (one per second) */
- retval = ioctl(fd, RTC_UIE_ON, 0);
- if (retval == -1) {
- if (errno == EINVAL) {
- fprintf(stderr,
- "\n...Update IRQs not supported.\n");
- goto test_READ;
- }
- perror("RTC_UIE_ON ioctl");
- exit(errno);
- }
-
- fprintf(stderr, "Counting 5 update (1/sec) interrupts from reading %s:",
- rtc);
- fflush(stderr);
- for (i=1; i<6; i++) {
- /* This read will block */
- retval = read(fd, &data, sizeof(unsigned long));
- if (retval == -1) {
- perror("read");
- exit(errno);
- }
- fprintf(stderr, " %d",i);
- fflush(stderr);
- irqcount++;
- }
-
- fprintf(stderr, "\nAgain, from using select(2) on /dev/rtc:");
- fflush(stderr);
- for (i=1; i<6; i++) {
- struct timeval tv = {5, 0}; /* 5 second timeout on select */
- fd_set readfds;
-
- FD_ZERO(&readfds);
- FD_SET(fd, &readfds);
- /* The select will wait until an RTC interrupt happens. */
- retval = select(fd+1, &readfds, NULL, NULL, &tv);
- if (retval == -1) {
- perror("select");
- exit(errno);
- }
- /* This read won't block unlike the select-less case above. */
- retval = read(fd, &data, sizeof(unsigned long));
- if (retval == -1) {
- perror("read");
- exit(errno);
- }
- fprintf(stderr, " %d",i);
- fflush(stderr);
- irqcount++;
- }
-
- /* Turn off update interrupts */
- retval = ioctl(fd, RTC_UIE_OFF, 0);
- if (retval == -1) {
- perror("RTC_UIE_OFF ioctl");
- exit(errno);
- }
-
-test_READ:
- /* Read the RTC time/date */
- retval = ioctl(fd, RTC_RD_TIME, &rtc_tm);
- if (retval == -1) {
- perror("RTC_RD_TIME ioctl");
- exit(errno);
- }
-
- fprintf(stderr, "\n\nCurrent RTC date/time is %d-%d-%d, %02d:%02d:%02d.\n",
- rtc_tm.tm_mday, rtc_tm.tm_mon + 1, rtc_tm.tm_year + 1900,
- rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec);
-
- /* Set the alarm to 5 sec in the future, and check for rollover */
- rtc_tm.tm_sec += 5;
- if (rtc_tm.tm_sec >= 60) {
- rtc_tm.tm_sec %= 60;
- rtc_tm.tm_min++;
- }
- if (rtc_tm.tm_min == 60) {
- rtc_tm.tm_min = 0;
- rtc_tm.tm_hour++;
- }
- if (rtc_tm.tm_hour == 24)
- rtc_tm.tm_hour = 0;
-
- retval = ioctl(fd, RTC_ALM_SET, &rtc_tm);
- if (retval == -1) {
- if (errno == EINVAL) {
- fprintf(stderr,
- "\n...Alarm IRQs not supported.\n");
- goto test_PIE;
- }
-
- perror("RTC_ALM_SET ioctl");
- exit(errno);
- }
-
- /* Read the current alarm settings */
- retval = ioctl(fd, RTC_ALM_READ, &rtc_tm);
- if (retval == -1) {
- if (errno == EINVAL) {
- fprintf(stderr,
- "\n...EINVAL reading current alarm setting.\n");
- goto test_PIE;
- }
- perror("RTC_ALM_READ ioctl");
- exit(errno);
- }
-
- fprintf(stderr, "Alarm time now set to %02d:%02d:%02d.\n",
- rtc_tm.tm_hour, rtc_tm.tm_min, rtc_tm.tm_sec);
-
- /* Enable alarm interrupts */
- retval = ioctl(fd, RTC_AIE_ON, 0);
- if (retval == -1) {
- if (errno == EINVAL || errno == EIO) {
- fprintf(stderr,
- "\n...Alarm IRQs not supported.\n");
- goto test_PIE;
- }
-
- perror("RTC_AIE_ON ioctl");
- exit(errno);
- }
-
- fprintf(stderr, "Waiting 5 seconds for alarm...");
- fflush(stderr);
- /* This blocks until the alarm ring causes an interrupt */
- retval = read(fd, &data, sizeof(unsigned long));
- if (retval == -1) {
- perror("read");
- exit(errno);
- }
- irqcount++;
- fprintf(stderr, " okay. Alarm rang.\n");
-
- /* Disable alarm interrupts */
- retval = ioctl(fd, RTC_AIE_OFF, 0);
- if (retval == -1) {
- perror("RTC_AIE_OFF ioctl");
- exit(errno);
- }
-
-test_PIE:
- /* Read periodic IRQ rate */
- retval = ioctl(fd, RTC_IRQP_READ, &tmp);
- if (retval == -1) {
- /* not all RTCs support periodic IRQs */
- if (errno == EINVAL) {
- fprintf(stderr, "\nNo periodic IRQ support\n");
- goto test_DATE;
- }
- perror("RTC_IRQP_READ ioctl");
- exit(errno);
- }
- fprintf(stderr, "\nPeriodic IRQ rate is %ldHz.\n", tmp);
-
- fprintf(stderr, "Counting 20 interrupts at:");
- fflush(stderr);
-
- /* The frequencies 128Hz, 256Hz, ... 8192Hz are only allowed for root. */
- for (tmp=2; tmp<=64; tmp*=2) {
-
- retval = ioctl(fd, RTC_IRQP_SET, tmp);
- if (retval == -1) {
- /* not all RTCs can change their periodic IRQ rate */
- if (errno == EINVAL) {
- fprintf(stderr,
- "\n...Periodic IRQ rate is fixed\n");
- goto test_DATE;
- }
- perror("RTC_IRQP_SET ioctl");
- exit(errno);
- }
-
- fprintf(stderr, "\n%ldHz:\t", tmp);
- fflush(stderr);
-
- /* Enable periodic interrupts */
- retval = ioctl(fd, RTC_PIE_ON, 0);
- if (retval == -1) {
- perror("RTC_PIE_ON ioctl");
- exit(errno);
- }
-
- for (i=1; i<21; i++) {
- gettimeofday(&start, NULL);
- /* This blocks */
- retval = read(fd, &data, sizeof(unsigned long));
- if (retval == -1) {
- perror("read");
- exit(errno);
- }
- gettimeofday(&end, NULL);
- timersub(&end, &start, &diff);
- if (diff.tv_sec > 0 ||
- diff.tv_usec > ((1000000L / tmp) * 1.10)) {
- fprintf(stderr, "\nPIE delta error: %ld.%06ld should be close to 0.%06ld\n",
- diff.tv_sec, diff.tv_usec,
- (1000000L / tmp));
- fflush(stdout);
- exit(-1);
- }
-
- fprintf(stderr, " %d",i);
- fflush(stderr);
- irqcount++;
- }
-
- /* Disable periodic interrupts */
- retval = ioctl(fd, RTC_PIE_OFF, 0);
- if (retval == -1) {
- perror("RTC_PIE_OFF ioctl");
- exit(errno);
- }
- }
-
-test_DATE:
- if (!dangerous)
- goto done;
-
- fprintf(stderr, "\nTesting problematic dates\n");
-
- for (i = 0; i < ARRAY_SIZE(cutoff_dates); i++) {
- struct rtc_time current;
-
- /* Write the new date in RTC */
- retval = ioctl(fd, RTC_SET_TIME, &cutoff_dates[i]);
- if (retval == -1) {
- perror("RTC_SET_TIME ioctl");
- close(fd);
- exit(errno);
- }
-
- /* Read back */
- retval = ioctl(fd, RTC_RD_TIME, &current);
- if (retval == -1) {
- perror("RTC_RD_TIME ioctl");
- exit(errno);
- }
-
- if(compare_dates(&cutoff_dates[i], &current)) {
- fprintf(stderr,"Setting date %d failed\n",
- cutoff_dates[i].tm_year + 1900);
- goto done;
- }
-
- cutoff_dates[i].tm_sec += 5;
-
- /* Write the new alarm in RTC */
- retval = ioctl(fd, RTC_ALM_SET, &cutoff_dates[i]);
- if (retval == -1) {
- perror("RTC_ALM_SET ioctl");
- close(fd);
- exit(errno);
- }
-
- /* Read back */
- retval = ioctl(fd, RTC_ALM_READ, &current);
- if (retval == -1) {
- perror("RTC_ALM_READ ioctl");
- exit(errno);
- }
-
- if(compare_dates(&cutoff_dates[i], &current)) {
- fprintf(stderr,"Setting alarm %d failed\n",
- cutoff_dates[i].tm_year + 1900);
- goto done;
- }
-
- fprintf(stderr, "Setting year %d is OK \n",
- cutoff_dates[i].tm_year + 1900);
- }
-done:
- fprintf(stderr, "\n\n\t\t\t *** Test complete ***\n");
-
- close(fd);
-
- return 0;
-}
diff --git a/tools/testing/selftests/uevent/Makefile b/tools/testing/selftests/uevent/Makefile
new file mode 100644
index 000000000000..f7baa9aa2932
--- /dev/null
+++ b/tools/testing/selftests/uevent/Makefile
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+all:
+
+include ../lib.mk
+
+.PHONY: all clean
+
+BINARIES := uevent_filtering
+CFLAGS += -Wl,-no-as-needed -Wall
+
+uevent_filtering: uevent_filtering.c ../kselftest.h ../kselftest_harness.h
+ $(CC) $(CFLAGS) $< -o $@
+
+TEST_PROGS += $(BINARIES)
+EXTRA_CLEAN := $(BINARIES)
+
+all: $(BINARIES)
diff --git a/tools/testing/selftests/uevent/config b/tools/testing/selftests/uevent/config
new file mode 100644
index 000000000000..1038f4515be8
--- /dev/null
+++ b/tools/testing/selftests/uevent/config
@@ -0,0 +1,2 @@
+CONFIG_USER_NS=y
+CONFIG_NET=y
diff --git a/tools/testing/selftests/uevent/uevent_filtering.c b/tools/testing/selftests/uevent/uevent_filtering.c
new file mode 100644
index 000000000000..f83391aa42cf
--- /dev/null
+++ b/tools/testing/selftests/uevent/uevent_filtering.c
@@ -0,0 +1,486 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <fcntl.h>
+#include <linux/netlink.h>
+#include <signal.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/prctl.h>
+#include <sys/socket.h>
+#include <sched.h>
+#include <sys/eventfd.h>
+#include <sys/stat.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+#include "../kselftest.h"
+#include "../kselftest_harness.h"
+
+#define __DEV_FULL "/sys/devices/virtual/mem/full/uevent"
+#define __UEVENT_BUFFER_SIZE (2048 * 2)
+#define __UEVENT_HEADER "add@/devices/virtual/mem/full"
+#define __UEVENT_HEADER_LEN sizeof("add@/devices/virtual/mem/full")
+#define __UEVENT_LISTEN_ALL -1
+
+ssize_t read_nointr(int fd, void *buf, size_t count)
+{
+ ssize_t ret;
+
+again:
+ ret = read(fd, buf, count);
+ if (ret < 0 && errno == EINTR)
+ goto again;
+
+ return ret;
+}
+
+ssize_t write_nointr(int fd, const void *buf, size_t count)
+{
+ ssize_t ret;
+
+again:
+ ret = write(fd, buf, count);
+ if (ret < 0 && errno == EINTR)
+ goto again;
+
+ return ret;
+}
+
+int wait_for_pid(pid_t pid)
+{
+ int status, ret;
+
+again:
+ ret = waitpid(pid, &status, 0);
+ if (ret == -1) {
+ if (errno == EINTR)
+ goto again;
+
+ return -1;
+ }
+
+ if (ret != pid)
+ goto again;
+
+ if (!WIFEXITED(status) || WEXITSTATUS(status) != 0)
+ return -1;
+
+ return 0;
+}
+
+static int uevent_listener(unsigned long post_flags, bool expect_uevent,
+ int sync_fd)
+{
+ int sk_fd, ret;
+ socklen_t sk_addr_len;
+ int fret = -1, rcv_buf_sz = __UEVENT_BUFFER_SIZE;
+ uint64_t sync_add = 1;
+ struct sockaddr_nl sk_addr = { 0 }, rcv_addr = { 0 };
+ char buf[__UEVENT_BUFFER_SIZE] = { 0 };
+ struct iovec iov = { buf, __UEVENT_BUFFER_SIZE };
+ char control[CMSG_SPACE(sizeof(struct ucred))];
+ struct msghdr hdr = {
+ &rcv_addr, sizeof(rcv_addr), &iov, 1,
+ control, sizeof(control), 0,
+ };
+
+ sk_fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC,
+ NETLINK_KOBJECT_UEVENT);
+ if (sk_fd < 0) {
+ fprintf(stderr, "%s - Failed to open uevent socket\n", strerror(errno));
+ return -1;
+ }
+
+ ret = setsockopt(sk_fd, SOL_SOCKET, SO_RCVBUF, &rcv_buf_sz,
+ sizeof(rcv_buf_sz));
+ if (ret < 0) {
+ fprintf(stderr, "%s - Failed to set socket options\n", strerror(errno));
+ goto on_error;
+ }
+
+ sk_addr.nl_family = AF_NETLINK;
+ sk_addr.nl_groups = __UEVENT_LISTEN_ALL;
+
+ sk_addr_len = sizeof(sk_addr);
+ ret = bind(sk_fd, (struct sockaddr *)&sk_addr, sk_addr_len);
+ if (ret < 0) {
+ fprintf(stderr, "%s - Failed to bind socket\n", strerror(errno));
+ goto on_error;
+ }
+
+ ret = getsockname(sk_fd, (struct sockaddr *)&sk_addr, &sk_addr_len);
+ if (ret < 0) {
+ fprintf(stderr, "%s - Failed to retrieve socket name\n", strerror(errno));
+ goto on_error;
+ }
+
+ if ((size_t)sk_addr_len != sizeof(sk_addr)) {
+ fprintf(stderr, "Invalid socket address size\n");
+ goto on_error;
+ }
+
+ if (post_flags & CLONE_NEWUSER) {
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ fprintf(stderr,
+ "%s - Failed to unshare user namespace\n",
+ strerror(errno));
+ goto on_error;
+ }
+ }
+
+ if (post_flags & CLONE_NEWNET) {
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ fprintf(stderr,
+ "%s - Failed to unshare network namespace\n",
+ strerror(errno));
+ goto on_error;
+ }
+ }
+
+ ret = write_nointr(sync_fd, &sync_add, sizeof(sync_add));
+ close(sync_fd);
+ if (ret != sizeof(sync_add)) {
+ fprintf(stderr, "Failed to synchronize with parent process\n");
+ goto on_error;
+ }
+
+ fret = 0;
+ for (;;) {
+ ssize_t r;
+
+ r = recvmsg(sk_fd, &hdr, 0);
+ if (r <= 0) {
+ fprintf(stderr, "%s - Failed to receive uevent\n", strerror(errno));
+ ret = -1;
+ break;
+ }
+
+ /* ignore libudev messages */
+ if (memcmp(buf, "libudev", 8) == 0)
+ continue;
+
+ /* ignore uevents we didn't trigger */
+ if (memcmp(buf, __UEVENT_HEADER, __UEVENT_HEADER_LEN) != 0)
+ continue;
+
+ if (!expect_uevent) {
+ fprintf(stderr, "Received unexpected uevent:\n");
+ ret = -1;
+ }
+
+ if (TH_LOG_ENABLED) {
+ /* If logging is enabled dump the received uevent. */
+ (void)write_nointr(STDERR_FILENO, buf, r);
+ (void)write_nointr(STDERR_FILENO, "\n", 1);
+ }
+
+ break;
+ }
+
+on_error:
+ close(sk_fd);
+
+ return fret;
+}
+
+int trigger_uevent(unsigned int times)
+{
+ int fd, ret;
+ unsigned int i;
+
+ fd = open(__DEV_FULL, O_RDWR | O_CLOEXEC);
+ if (fd < 0) {
+ if (errno != ENOENT)
+ return -EINVAL;
+
+ return -1;
+ }
+
+ for (i = 0; i < times; i++) {
+ ret = write_nointr(fd, "add\n", sizeof("add\n") - 1);
+ if (ret < 0) {
+ fprintf(stderr, "Failed to trigger uevent\n");
+ break;
+ }
+ }
+ close(fd);
+
+ return ret;
+}
+
+int set_death_signal(void)
+{
+ int ret;
+ pid_t ppid;
+
+ ret = prctl(PR_SET_PDEATHSIG, SIGKILL, 0, 0, 0);
+
+ /* Check whether we have been orphaned. */
+ ppid = getppid();
+ if (ppid == 1) {
+ pid_t self;
+
+ self = getpid();
+ ret = kill(self, SIGKILL);
+ }
+
+ if (ret < 0)
+ return -1;
+
+ return 0;
+}
+
+static int do_test(unsigned long pre_flags, unsigned long post_flags,
+ bool expect_uevent, int sync_fd)
+{
+ int ret;
+ uint64_t wait_val;
+ pid_t pid;
+ sigset_t mask;
+ sigset_t orig_mask;
+ struct timespec timeout;
+
+ sigemptyset(&mask);
+ sigaddset(&mask, SIGCHLD);
+
+ ret = sigprocmask(SIG_BLOCK, &mask, &orig_mask);
+ if (ret < 0) {
+ fprintf(stderr, "%s- Failed to block SIGCHLD\n", strerror(errno));
+ return -1;
+ }
+
+ pid = fork();
+ if (pid < 0) {
+ fprintf(stderr, "%s - Failed to fork() new process\n", strerror(errno));
+ return -1;
+ }
+
+ if (pid == 0) {
+ /* Make sure that we go away when our parent dies. */
+ ret = set_death_signal();
+ if (ret < 0) {
+ fprintf(stderr, "Failed to set PR_SET_PDEATHSIG to SIGKILL\n");
+ _exit(EXIT_FAILURE);
+ }
+
+ if (pre_flags & CLONE_NEWUSER) {
+ ret = unshare(CLONE_NEWUSER);
+ if (ret < 0) {
+ fprintf(stderr,
+ "%s - Failed to unshare user namespace\n",
+ strerror(errno));
+ _exit(EXIT_FAILURE);
+ }
+ }
+
+ if (pre_flags & CLONE_NEWNET) {
+ ret = unshare(CLONE_NEWNET);
+ if (ret < 0) {
+ fprintf(stderr,
+ "%s - Failed to unshare network namespace\n",
+ strerror(errno));
+ _exit(EXIT_FAILURE);
+ }
+ }
+
+ if (uevent_listener(post_flags, expect_uevent, sync_fd) < 0)
+ _exit(EXIT_FAILURE);
+
+ _exit(EXIT_SUCCESS);
+ }
+
+ ret = read_nointr(sync_fd, &wait_val, sizeof(wait_val));
+ if (ret != sizeof(wait_val)) {
+ fprintf(stderr, "Failed to synchronize with child process\n");
+ _exit(EXIT_FAILURE);
+ }
+
+ /* Trigger 10 uevents to account for the case where the kernel might
+ * drop some.
+ */
+ ret = trigger_uevent(10);
+ if (ret < 0)
+ fprintf(stderr, "Failed triggering uevents\n");
+
+ /* Wait for 2 seconds before considering this failed. This should be
+ * plenty of time for the kernel to deliver the uevent even under heavy
+ * load.
+ */
+ timeout.tv_sec = 2;
+ timeout.tv_nsec = 0;
+
+again:
+ ret = sigtimedwait(&mask, NULL, &timeout);
+ if (ret < 0) {
+ if (errno == EINTR)
+ goto again;
+
+ if (!expect_uevent)
+ ret = kill(pid, SIGTERM); /* success */
+ else
+ ret = kill(pid, SIGUSR1); /* error */
+ if (ret < 0)
+ return -1;
+ }
+
+ ret = wait_for_pid(pid);
+ if (ret < 0)
+ return -1;
+
+ return ret;
+}
+
+static void signal_handler(int sig)
+{
+ if (sig == SIGTERM)
+ _exit(EXIT_SUCCESS);
+
+ _exit(EXIT_FAILURE);
+}
+
+TEST(uevent_filtering)
+{
+ int ret, sync_fd;
+ struct sigaction act;
+
+ if (geteuid()) {
+ TH_LOG("Uevent filtering tests require root privileges. Skipping test");
+ _exit(KSFT_SKIP);
+ }
+
+ ret = access(__DEV_FULL, F_OK);
+ EXPECT_EQ(0, ret) {
+ if (errno == ENOENT) {
+ TH_LOG(__DEV_FULL " does not exist. Skipping test");
+ _exit(KSFT_SKIP);
+ }
+
+ _exit(KSFT_FAIL);
+ }
+
+ act.sa_handler = signal_handler;
+ act.sa_flags = 0;
+ sigemptyset(&act.sa_mask);
+
+ ret = sigaction(SIGTERM, &act, NULL);
+ ASSERT_EQ(0, ret);
+
+ sync_fd = eventfd(0, EFD_CLOEXEC);
+ ASSERT_GE(sync_fd, 0);
+
+ /*
+ * Setup:
+ * - Open uevent listening socket in initial network namespace owned by
+ * initial user namespace.
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives uevent
+ */
+ ret = do_test(0, 0, true, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+ /*
+ * Setup:
+ * - Open uevent listening socket in non-initial network namespace
+ * owned by initial user namespace.
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives uevent
+ */
+ ret = do_test(CLONE_NEWNET, 0, true, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+ /*
+ * Setup:
+ * - unshare user namespace
+ * - Open uevent listening socket in initial network namespace
+ * owned by initial user namespace.
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives uevent
+ */
+ ret = do_test(CLONE_NEWUSER, 0, true, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+ /*
+ * Setup:
+ * - Open uevent listening socket in non-initial network namespace
+ * owned by non-initial user namespace.
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives no uevent
+ */
+ ret = do_test(CLONE_NEWUSER | CLONE_NEWNET, 0, false, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+ /*
+ * Setup:
+ * - Open uevent listening socket in initial network namespace
+ * owned by initial user namespace.
+ * - unshare network namespace
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives uevent
+ */
+ ret = do_test(0, CLONE_NEWNET, true, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+ /*
+ * Setup:
+ * - Open uevent listening socket in initial network namespace
+ * owned by initial user namespace.
+ * - unshare user namespace
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives uevent
+ */
+ ret = do_test(0, CLONE_NEWUSER, true, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+ /*
+ * Setup:
+ * - Open uevent listening socket in initial network namespace
+ * owned by initial user namespace.
+ * - unshare user namespace
+ * - unshare network namespace
+ * - Trigger uevent in initial network namespace owned by initial user
+ * namespace.
+ * Expected Result:
+ * - uevent listening socket receives uevent
+ */
+ ret = do_test(0, CLONE_NEWUSER | CLONE_NEWNET, true, sync_fd);
+ ASSERT_EQ(0, ret) {
+ goto do_cleanup;
+ }
+
+do_cleanup:
+ close(sync_fd);
+}
+
+TEST_HARNESS_MAIN
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index d744991c0f4f..186520198de7 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -8,10 +8,11 @@ include ../lib.mk
UNAME_M := $(shell uname -m)
CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
+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 mpx-mini-test ioperm \
- protection_keys test_vdso test_vsyscall
+ protection_keys test_vdso test_vsyscall mov_ss_trap
TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
test_FCMOV test_FCOMI test_FISTTP \
vdso_restorer
@@ -31,7 +32,12 @@ BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32))
BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
-CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
+CFLAGS := -O2 -g -std=gnu99 -pthread -Wall
+
+# call32_from_64 in thunks.S uses absolute addresses.
+ifeq ($(CAN_BUILD_WITH_NOPIE),1)
+CFLAGS += -no-pie
+endif
define gen-target-rule-32
$(1) $(1)_32: $(OUTPUT)/$(1)_32
diff --git a/tools/testing/selftests/x86/mov_ss_trap.c b/tools/testing/selftests/x86/mov_ss_trap.c
new file mode 100644
index 000000000000..3c3a022654f3
--- /dev/null
+++ b/tools/testing/selftests/x86/mov_ss_trap.c
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mov_ss_trap.c: Exercise the bizarre side effects of a watchpoint on MOV SS
+ *
+ * This does MOV SS from a watchpointed address followed by various
+ * types of kernel entries. A MOV SS that hits a watchpoint will queue
+ * up a #DB trap but will not actually deliver that trap. The trap
+ * will be delivered after the next instruction instead. The CPU's logic
+ * seems to be:
+ *
+ * - Any fault: drop the pending #DB trap.
+ * - INT $N, INT3, INTO, SYSCALL, SYSENTER: enter the kernel and then
+ * deliver #DB.
+ * - ICEBP: enter the kernel but do not deliver the watchpoint trap
+ * - breakpoint: only one #DB is delivered (phew!)
+ *
+ * There are plenty of ways for a kernel to handle this incorrectly. This
+ * test tries to exercise all the cases.
+ *
+ * This should mostly cover CVE-2018-1087 and CVE-2018-8897.
+ */
+#define _GNU_SOURCE
+
+#include <stdlib.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/user.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+#include <errno.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <err.h>
+#include <string.h>
+#include <setjmp.h>
+#include <sys/prctl.h>
+
+#define X86_EFLAGS_RF (1UL << 16)
+
+#if __x86_64__
+# define REG_IP REG_RIP
+#else
+# define REG_IP REG_EIP
+#endif
+
+unsigned short ss;
+extern unsigned char breakpoint_insn[];
+sigjmp_buf jmpbuf;
+static unsigned char altstack_data[SIGSTKSZ];
+
+static void enable_watchpoint(void)
+{
+ pid_t parent = getpid();
+ int status;
+
+ pid_t child = fork();
+ if (child < 0)
+ err(1, "fork");
+
+ if (child) {
+ if (waitpid(child, &status, 0) != child)
+ err(1, "waitpid for child");
+ } else {
+ unsigned long dr0, dr1, dr7;
+
+ dr0 = (unsigned long)&ss;
+ dr1 = (unsigned long)breakpoint_insn;
+ dr7 = ((1UL << 1) | /* G0 */
+ (3UL << 16) | /* RW0 = read or write */
+ (1UL << 18) | /* LEN0 = 2 bytes */
+ (1UL << 3)); /* G1, RW1 = insn */
+
+ if (ptrace(PTRACE_ATTACH, parent, NULL, NULL) != 0)
+ err(1, "PTRACE_ATTACH");
+
+ if (waitpid(parent, &status, 0) != parent)
+ err(1, "waitpid for child");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[0]), dr0) != 0)
+ err(1, "PTRACE_POKEUSER DR0");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[1]), dr1) != 0)
+ err(1, "PTRACE_POKEUSER DR1");
+
+ if (ptrace(PTRACE_POKEUSER, parent, (void *)offsetof(struct user, u_debugreg[7]), dr7) != 0)
+ err(1, "PTRACE_POKEUSER DR7");
+
+ printf("\tDR0 = %lx, DR1 = %lx, DR7 = %lx\n", dr0, dr1, dr7);
+
+ if (ptrace(PTRACE_DETACH, parent, NULL, NULL) != 0)
+ err(1, "PTRACE_DETACH");
+
+ exit(0);
+ }
+}
+
+static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
+ int flags)
+{
+ struct sigaction sa;
+ memset(&sa, 0, sizeof(sa));
+ sa.sa_sigaction = handler;
+ sa.sa_flags = SA_SIGINFO | flags;
+ sigemptyset(&sa.sa_mask);
+ if (sigaction(sig, &sa, 0))
+ err(1, "sigaction");
+}
+
+static char const * const signames[] = {
+ [SIGSEGV] = "SIGSEGV",
+ [SIGBUS] = "SIBGUS",
+ [SIGTRAP] = "SIGTRAP",
+ [SIGILL] = "SIGILL",
+};
+
+static void sigtrap(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot SIGTRAP with RIP=%lx, EFLAGS.RF=%d\n",
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP],
+ !!(ctx->uc_mcontext.gregs[REG_EFL] & X86_EFLAGS_RF));
+}
+
+static void handle_and_return(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot %s with RIP=%lx\n", signames[sig],
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+}
+
+static void handle_and_longjmp(int sig, siginfo_t *si, void *ctx_void)
+{
+ ucontext_t *ctx = ctx_void;
+
+ printf("\tGot %s with RIP=%lx\n", signames[sig],
+ (unsigned long)ctx->uc_mcontext.gregs[REG_IP]);
+
+ siglongjmp(jmpbuf, 1);
+}
+
+int main()
+{
+ unsigned long nr;
+
+ asm volatile ("mov %%ss, %[ss]" : [ss] "=m" (ss));
+ printf("\tSS = 0x%hx, &SS = 0x%p\n", ss, &ss);
+
+ if (prctl(PR_SET_PTRACER, PR_SET_PTRACER_ANY, 0, 0, 0) == 0)
+ printf("\tPR_SET_PTRACER_ANY succeeded\n");
+
+ printf("\tSet up a watchpoint\n");
+ sethandler(SIGTRAP, sigtrap, 0);
+ enable_watchpoint();
+
+ printf("[RUN]\tRead from watched memory (should get SIGTRAP)\n");
+ asm volatile ("mov %[ss], %[tmp]" : [tmp] "=r" (nr) : [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT3\n");
+ asm volatile ("mov %[ss], %%ss; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT 3\n");
+ asm volatile ("mov %[ss], %%ss; .byte 0xcd, 0x3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; CS CS INT3\n");
+ asm volatile ("mov %[ss], %%ss; .byte 0x2e, 0x2e; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; CSx14 INT3\n");
+ asm volatile ("mov %[ss], %%ss; .fill 14,1,0x2e; int3" :: [ss] "m" (ss));
+
+ printf("[RUN]\tMOV SS; INT 4\n");
+ sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; int $4" :: [ss] "m" (ss));
+
+#ifdef __i386__
+ printf("[RUN]\tMOV SS; INTO\n");
+ sethandler(SIGSEGV, handle_and_return, SA_RESETHAND);
+ nr = -1;
+ asm volatile ("add $1, %[tmp]; mov %[ss], %%ss; into"
+ : [tmp] "+r" (nr) : [ss] "m" (ss));
+#endif
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; ICEBP\n");
+
+ /* Some emulators (e.g. QEMU TCG) don't emulate ICEBP. */
+ sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+
+ asm volatile ("mov %[ss], %%ss; .byte 0xf1" :: [ss] "m" (ss));
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; CLI\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; cli" :: [ss] "m" (ss));
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; #PF\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; mov (-1), %[tmp]"
+ : [tmp] "=r" (nr) : [ss] "m" (ss));
+ }
+
+ /*
+ * INT $1: if #DB has DPL=3 and there isn't special handling,
+ * then the kernel will die.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; INT 1\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ asm volatile ("mov %[ss], %%ss; int $1" :: [ss] "m" (ss));
+ }
+
+#ifdef __x86_64__
+ /*
+ * In principle, we should test 32-bit SYSCALL as well, but
+ * the calling convention is so unpredictable that it's
+ * not obviously worth the effort.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; SYSCALL\n");
+ sethandler(SIGILL, handle_and_longjmp, SA_RESETHAND);
+ nr = SYS_getpid;
+ /*
+ * Toggle the high bit of RSP to make it noncanonical to
+ * strengthen this test on non-SMAP systems.
+ */
+ asm volatile ("btc $63, %%rsp\n\t"
+ "mov %[ss], %%ss; syscall\n\t"
+ "btc $63, %%rsp"
+ : "+a" (nr) : [ss] "m" (ss)
+ : "rcx"
+#ifdef __x86_64__
+ , "r11"
+#endif
+ );
+ }
+#endif
+
+ printf("[RUN]\tMOV SS; breakpointed NOP\n");
+ asm volatile ("mov %[ss], %%ss; breakpoint_insn: nop" :: [ss] "m" (ss));
+
+ /*
+ * Invoking SYSENTER directly breaks all the rules. Just handle
+ * the SIGSEGV.
+ */
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; SYSENTER\n");
+ stack_t stack = {
+ .ss_sp = altstack_data,
+ .ss_size = SIGSTKSZ,
+ };
+ if (sigaltstack(&stack, NULL) != 0)
+ err(1, "sigaltstack");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND | SA_ONSTACK);
+ nr = SYS_getpid;
+ asm volatile ("mov %[ss], %%ss; SYSENTER" : "+a" (nr)
+ : [ss] "m" (ss) : "flags", "rcx"
+#ifdef __x86_64__
+ , "r11"
+#endif
+ );
+
+ /* We're unreachable here. SYSENTER forgets RIP. */
+ }
+
+ if (sigsetjmp(jmpbuf, 1) == 0) {
+ printf("[RUN]\tMOV SS; INT $0x80\n");
+ sethandler(SIGSEGV, handle_and_longjmp, SA_RESETHAND);
+ nr = 20; /* compat getpid */
+ asm volatile ("mov %[ss], %%ss; int $0x80"
+ : "+a" (nr) : [ss] "m" (ss)
+ : "flags"
+#ifdef __x86_64__
+ , "r8", "r9", "r10", "r11"
+#endif
+ );
+ }
+
+ printf("[OK]\tI aten't dead\n");
+ return 0;
+}
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index 9c0325e1ea68..50f7e9272481 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -368,6 +368,11 @@ static int expected_bnd_index = -1;
uint64_t shadow_plb[NR_MPX_BOUNDS_REGISTERS][2]; /* shadow MPX bound registers */
unsigned long shadow_map[NR_MPX_BOUNDS_REGISTERS];
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR 3
+#endif
+
/*
* The kernel is supposed to provide some information about the bounds
* exception in the siginfo. It should match what we have in the bounds
@@ -419,8 +424,6 @@ void handler(int signum, siginfo_t *si, void *vucontext)
br_count++;
dprintf1("#BR 0x%jx (total seen: %d)\n", status, br_count);
-#define SEGV_BNDERR 3 /* failed address bound checks */
-
dprintf2("Saw a #BR! status 0x%jx at %016lx br_reason: %jx\n",
status, ip, br_reason);
dprintf2("si_signo: %d\n", si->si_signo);
diff --git a/tools/testing/selftests/x86/pkey-helpers.h b/tools/testing/selftests/x86/pkey-helpers.h
index b3cb7670e026..254e5436bdd9 100644
--- a/tools/testing/selftests/x86/pkey-helpers.h
+++ b/tools/testing/selftests/x86/pkey-helpers.h
@@ -26,30 +26,26 @@ static inline void sigsafe_printf(const char *format, ...)
{
va_list ap;
- va_start(ap, format);
if (!dprint_in_signal) {
+ va_start(ap, format);
vprintf(format, ap);
+ va_end(ap);
} else {
int ret;
- int len = vsnprintf(dprint_in_signal_buffer,
- DPRINT_IN_SIGNAL_BUF_SIZE,
- format, ap);
/*
- * len is amount that would have been printed,
- * but actual write is truncated at BUF_SIZE.
+ * No printf() functions are signal-safe.
+ * They deadlock easily. Write the format
+ * string to get some output, even if
+ * incomplete.
*/
- if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
- len = DPRINT_IN_SIGNAL_BUF_SIZE;
- ret = write(1, dprint_in_signal_buffer, len);
+ ret = write(1, format, strlen(format));
if (ret < 0)
- abort();
+ exit(1);
}
- va_end(ap);
}
#define dprintf_level(level, args...) do { \
if (level <= DEBUG_LEVEL) \
sigsafe_printf(args); \
- fflush(NULL); \
} while (0)
#define dprintf0(args...) dprintf_level(0, args)
#define dprintf1(args...) dprintf_level(1, args)
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index f15aa5a76fe3..460b4bdf4c1e 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -72,10 +72,9 @@ extern void abort_hooks(void);
test_nr, iteration_nr); \
dprintf0("errno at assert: %d", errno); \
abort_hooks(); \
- assert(condition); \
+ exit(__LINE__); \
} \
} while (0)
-#define raw_assert(cond) assert(cond)
void cat_into_file(char *str, char *file)
{
@@ -87,12 +86,17 @@ void cat_into_file(char *str, char *file)
* these need to be raw because they are called under
* pkey_assert()
*/
- raw_assert(fd >= 0);
+ if (fd < 0) {
+ fprintf(stderr, "error opening '%s'\n", str);
+ perror("error: ");
+ exit(__LINE__);
+ }
+
ret = write(fd, str, strlen(str));
if (ret != strlen(str)) {
perror("write to file failed");
fprintf(stderr, "filename: '%s' str: '%s'\n", file, str);
- raw_assert(0);
+ exit(__LINE__);
}
close(fd);
}
@@ -191,26 +195,30 @@ void lots_o_noops_around_write(int *write_to_me)
#ifdef __i386__
#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 380
+# define SYS_mprotect_key 380
#endif
+
#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 381
-# define SYS_pkey_free 382
+# define SYS_pkey_alloc 381
+# define SYS_pkey_free 382
#endif
-#define REG_IP_IDX REG_EIP
-#define si_pkey_offset 0x14
+
+#define REG_IP_IDX REG_EIP
+#define si_pkey_offset 0x14
#else
#ifndef SYS_mprotect_key
-# define SYS_mprotect_key 329
+# define SYS_mprotect_key 329
#endif
+
#ifndef SYS_pkey_alloc
-# define SYS_pkey_alloc 330
-# define SYS_pkey_free 331
+# define SYS_pkey_alloc 330
+# define SYS_pkey_free 331
#endif
-#define REG_IP_IDX REG_RIP
-#define si_pkey_offset 0x20
+
+#define REG_IP_IDX REG_RIP
+#define si_pkey_offset 0x20
#endif
@@ -225,8 +233,14 @@ void dump_mem(void *dumpme, int len_bytes)
}
}
-#define SEGV_BNDERR 3 /* failed address bound checks */
-#define SEGV_PKUERR 4
+/* Failed address bound checks: */
+#ifndef SEGV_BNDERR
+# define SEGV_BNDERR 3
+#endif
+
+#ifndef SEGV_PKUERR
+# define SEGV_PKUERR 4
+#endif
static char *si_code_str(int si_code)
{
@@ -289,13 +303,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
dump_mem(pkru_ptr - 128, 256);
pkey_assert(*pkru_ptr);
- si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
- dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
- dump_mem(si_pkey_ptr - 8, 24);
- siginfo_pkey = *si_pkey_ptr;
- pkey_assert(siginfo_pkey < NR_PKEYS);
- last_si_pkey = siginfo_pkey;
-
if ((si->si_code == SEGV_MAPERR) ||
(si->si_code == SEGV_ACCERR) ||
(si->si_code == SEGV_BNDERR)) {
@@ -303,6 +310,13 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
exit(4);
}
+ si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
+ dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
+ dump_mem((u8 *)si_pkey_ptr - 8, 24);
+ siginfo_pkey = *si_pkey_ptr;
+ pkey_assert(siginfo_pkey < NR_PKEYS);
+ last_si_pkey = siginfo_pkey;
+
dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
/* need __rdpkru() version so we do not do shadow_pkru checking */
dprintf1("signal pkru from pkru: %08x\n", __rdpkru());
@@ -311,22 +325,6 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
pkru_faults++;
dprintf1("<<<<==================================================\n");
- return;
- if (trapno == 14) {
- fprintf(stderr,
- "ERROR: In signal handler, page fault, trapno = %d, ip = %016lx\n",
- trapno, ip);
- fprintf(stderr, "si_addr %p\n", si->si_addr);
- fprintf(stderr, "REG_ERR: %lx\n",
- (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
- exit(1);
- } else {
- fprintf(stderr, "unexpected trap %d! at 0x%lx\n", trapno, ip);
- fprintf(stderr, "si_addr %p\n", si->si_addr);
- fprintf(stderr, "REG_ERR: %lx\n",
- (unsigned long)uctxt->uc_mcontext.gregs[REG_ERR]);
- exit(2);
- }
dprint_in_signal = 0;
}
@@ -393,10 +391,15 @@ pid_t fork_lazy_child(void)
return forkret;
}
-#define PKEY_DISABLE_ACCESS 0x1
-#define PKEY_DISABLE_WRITE 0x2
+#ifndef PKEY_DISABLE_ACCESS
+# define PKEY_DISABLE_ACCESS 0x1
+#endif
+
+#ifndef PKEY_DISABLE_WRITE
+# define PKEY_DISABLE_WRITE 0x2
+#endif
-u32 pkey_get(int pkey, unsigned long flags)
+static u32 hw_pkey_get(int pkey, unsigned long flags)
{
u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
u32 pkru = __rdpkru();
@@ -418,7 +421,7 @@ u32 pkey_get(int pkey, unsigned long flags)
return masked_pkru;
}
-int pkey_set(int pkey, unsigned long rights, unsigned long flags)
+static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags)
{
u32 mask = (PKEY_DISABLE_ACCESS|PKEY_DISABLE_WRITE);
u32 old_pkru = __rdpkru();
@@ -452,15 +455,15 @@ void pkey_disable_set(int pkey, int flags)
pkey, flags);
pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
- pkey_rights = pkey_get(pkey, syscall_flags);
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
pkey_assert(pkey_rights >= 0);
pkey_rights |= flags;
- ret = pkey_set(pkey, pkey_rights, syscall_flags);
+ ret = hw_pkey_set(pkey, pkey_rights, syscall_flags);
assert(!ret);
/*pkru and flags have the same format */
shadow_pkru |= flags << (pkey * 2);
@@ -468,8 +471,8 @@ void pkey_disable_set(int pkey, int flags)
pkey_assert(ret >= 0);
- pkey_rights = pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
@@ -483,24 +486,24 @@ void pkey_disable_clear(int pkey, int flags)
{
unsigned long syscall_flags = 0;
int ret;
- int pkey_rights = pkey_get(pkey, syscall_flags);
+ int pkey_rights = hw_pkey_get(pkey, syscall_flags);
u32 orig_pkru = rdpkru();
pkey_assert(flags & (PKEY_DISABLE_ACCESS | PKEY_DISABLE_WRITE));
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
pkey_assert(pkey_rights >= 0);
pkey_rights |= flags;
- ret = pkey_set(pkey, pkey_rights, 0);
+ ret = hw_pkey_set(pkey, pkey_rights, 0);
/* pkru and flags have the same format */
shadow_pkru &= ~(flags << (pkey * 2));
pkey_assert(ret >= 0);
- pkey_rights = pkey_get(pkey, syscall_flags);
- dprintf1("%s(%d) pkey_get(%d): %x\n", __func__,
+ pkey_rights = hw_pkey_get(pkey, syscall_flags);
+ dprintf1("%s(%d) hw_pkey_get(%d): %x\n", __func__,
pkey, pkey, pkey_rights);
dprintf1("%s(%d) pkru: 0x%x\n", __func__, pkey, rdpkru());
@@ -674,10 +677,12 @@ int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
struct pkey_malloc_record {
void *ptr;
long size;
+ int prot;
};
struct pkey_malloc_record *pkey_malloc_records;
+struct pkey_malloc_record *pkey_last_malloc_record;
long nr_pkey_malloc_records;
-void record_pkey_malloc(void *ptr, long size)
+void record_pkey_malloc(void *ptr, long size, int prot)
{
long i;
struct pkey_malloc_record *rec = NULL;
@@ -709,6 +714,8 @@ void record_pkey_malloc(void *ptr, long size)
(int)(rec - pkey_malloc_records), rec, ptr, size);
rec->ptr = ptr;
rec->size = size;
+ rec->prot = prot;
+ pkey_last_malloc_record = rec;
nr_pkey_malloc_records++;
}
@@ -753,7 +760,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey)
pkey_assert(ptr != (void *)-1);
ret = mprotect_pkey((void *)ptr, PAGE_SIZE, prot, pkey);
pkey_assert(!ret);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
rdpkru();
dprintf1("%s() for pkey %d @ %p\n", __func__, pkey, ptr);
@@ -774,7 +781,7 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey)
size = ALIGN_UP(size, HPAGE_SIZE * 2);
ptr = mmap(NULL, size, PROT_NONE, MAP_ANONYMOUS|MAP_PRIVATE, -1, 0);
pkey_assert(ptr != (void *)-1);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
mprotect_pkey(ptr, size, prot, pkey);
dprintf1("unaligned ptr: %p\n", ptr);
@@ -847,7 +854,7 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey)
pkey_assert(ptr != (void *)-1);
mprotect_pkey(ptr, size, prot, pkey);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
dprintf1("mmap()'d hugetlbfs for pkey %d @ %p\n", pkey, ptr);
return ptr;
@@ -869,7 +876,7 @@ void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey)
mprotect_pkey(ptr, size, prot, pkey);
- record_pkey_malloc(ptr, size);
+ record_pkey_malloc(ptr, size, prot);
dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr);
close(fd);
@@ -918,13 +925,21 @@ void *malloc_pkey(long size, int prot, u16 pkey)
}
int last_pkru_faults;
+#define UNKNOWN_PKEY -2
void expected_pk_fault(int pkey)
{
dprintf2("%s(): last_pkru_faults: %d pkru_faults: %d\n",
__func__, last_pkru_faults, pkru_faults);
dprintf2("%s(%d): last_si_pkey: %d\n", __func__, pkey, last_si_pkey);
pkey_assert(last_pkru_faults + 1 == pkru_faults);
- pkey_assert(last_si_pkey == pkey);
+
+ /*
+ * For exec-only memory, we do not know the pkey in
+ * advance, so skip this check.
+ */
+ if (pkey != UNKNOWN_PKEY)
+ pkey_assert(last_si_pkey == pkey);
+
/*
* The signal handler shold have cleared out PKRU to let the
* test program continue. We now have to restore it.
@@ -939,10 +954,11 @@ void expected_pk_fault(int pkey)
last_si_pkey = -1;
}
-void do_not_expect_pk_fault(void)
-{
- pkey_assert(last_pkru_faults == pkru_faults);
-}
+#define do_not_expect_pk_fault(msg) do { \
+ if (last_pkru_faults != pkru_faults) \
+ dprintf0("unexpected PK fault: %s\n", msg); \
+ pkey_assert(last_pkru_faults == pkru_faults); \
+} while (0)
int test_fds[10] = { -1 };
int nr_test_fds;
@@ -1151,12 +1167,15 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
pkey_assert(i < NR_PKEYS*2);
/*
- * There are 16 pkeys supported in hardware. One is taken
- * up for the default (0) and another can be taken up by
- * an execute-only mapping. Ensure that we can allocate
- * at least 14 (16-2).
+ * There are 16 pkeys supported in hardware. Three are
+ * allocated by the time we get here:
+ * 1. The default key (0)
+ * 2. One possibly consumed by an execute-only mapping.
+ * 3. One allocated by the test code and passed in via
+ * 'pkey' to this function.
+ * Ensure that we can allocate at least another 13 (16-3).
*/
- pkey_assert(i >= NR_PKEYS-2);
+ pkey_assert(i >= NR_PKEYS-3);
for (i = 0; i < nr_allocated_pkeys; i++) {
err = sys_pkey_free(allocated_pkeys[i]);
@@ -1165,6 +1184,35 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey)
}
}
+/*
+ * pkey 0 is special. It is allocated by default, so you do not
+ * have to call pkey_alloc() to use it first. Make sure that it
+ * is usable.
+ */
+void test_mprotect_with_pkey_0(int *ptr, u16 pkey)
+{
+ long size;
+ int prot;
+
+ assert(pkey_last_malloc_record);
+ size = pkey_last_malloc_record->size;
+ /*
+ * This is a bit of a hack. But mprotect() requires
+ * huge-page-aligned sizes when operating on hugetlbfs.
+ * So, make sure that we use something that's a multiple
+ * of a huge page when we can.
+ */
+ if (size >= HPAGE_SIZE)
+ size = HPAGE_SIZE;
+ prot = pkey_last_malloc_record->prot;
+
+ /* Use pkey 0 */
+ mprotect_pkey(ptr, size, prot, 0);
+
+ /* Make sure that we can set it back to the original pkey. */
+ mprotect_pkey(ptr, size, prot, pkey);
+}
+
void test_ptrace_of_child(int *ptr, u16 pkey)
{
__attribute__((__unused__)) int peek_result;
@@ -1228,7 +1276,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
pkey_assert(ret != -1);
/* Now access from the current task, and expect NO exception: */
peek_result = read_ptr(plain_ptr);
- do_not_expect_pk_fault();
+ do_not_expect_pk_fault("read plain pointer after ptrace");
ret = ptrace(PTRACE_DETACH, child_pid, ignored, 0);
pkey_assert(ret != -1);
@@ -1241,12 +1289,9 @@ void test_ptrace_of_child(int *ptr, u16 pkey)
free(plain_ptr_unaligned);
}
-void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+void *get_pointer_to_instructions(void)
{
void *p1;
- int scratch;
- int ptr_contents;
- int ret;
p1 = ALIGN_PTR_UP(&lots_o_noops_around_write, PAGE_SIZE);
dprintf3("&lots_o_noops: %p\n", &lots_o_noops_around_write);
@@ -1256,7 +1301,23 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
/* Point 'p1' at the *second* page of the function: */
p1 += PAGE_SIZE;
+ /*
+ * Try to ensure we fault this in on next touch to ensure
+ * we get an instruction fault as opposed to a data one
+ */
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+
+ return p1;
+}
+
+void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
+{
+ void *p1;
+ int scratch;
+ int ptr_contents;
+ int ret;
+
+ p1 = get_pointer_to_instructions();
lots_o_noops_around_write(&scratch);
ptr_contents = read_ptr(p1);
dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
@@ -1272,12 +1333,55 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey)
*/
madvise(p1, PAGE_SIZE, MADV_DONTNEED);
lots_o_noops_around_write(&scratch);
- do_not_expect_pk_fault();
+ do_not_expect_pk_fault("executing on PROT_EXEC memory");
ptr_contents = read_ptr(p1);
dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
expected_pk_fault(pkey);
}
+void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey)
+{
+ void *p1;
+ int scratch;
+ int ptr_contents;
+ int ret;
+
+ dprintf1("%s() start\n", __func__);
+
+ p1 = get_pointer_to_instructions();
+ lots_o_noops_around_write(&scratch);
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+
+ /* Use a *normal* mprotect(), not mprotect_pkey(): */
+ ret = mprotect(p1, PAGE_SIZE, PROT_EXEC);
+ pkey_assert(!ret);
+
+ dprintf2("pkru: %x\n", rdpkru());
+
+ /* Make sure this is an *instruction* fault */
+ madvise(p1, PAGE_SIZE, MADV_DONTNEED);
+ lots_o_noops_around_write(&scratch);
+ do_not_expect_pk_fault("executing on PROT_EXEC memory");
+ ptr_contents = read_ptr(p1);
+ dprintf2("ptr (%p) contents@%d: %x\n", p1, __LINE__, ptr_contents);
+ expected_pk_fault(UNKNOWN_PKEY);
+
+ /*
+ * Put the memory back to non-PROT_EXEC. Should clear the
+ * exec-only pkey off the VMA and allow it to be readable
+ * again. Go to PROT_NONE first to check for a kernel bug
+ * that did not clear the pkey when doing PROT_NONE.
+ */
+ ret = mprotect(p1, PAGE_SIZE, PROT_NONE);
+ pkey_assert(!ret);
+
+ ret = mprotect(p1, PAGE_SIZE, PROT_READ|PROT_EXEC);
+ pkey_assert(!ret);
+ ptr_contents = read_ptr(p1);
+ do_not_expect_pk_fault("plain read on recently PROT_EXEC area");
+}
+
void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey)
{
int size = PAGE_SIZE;
@@ -1302,6 +1406,8 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = {
test_kernel_gup_of_access_disabled_region,
test_kernel_gup_write_to_write_disabled_region,
test_executing_on_unreadable_memory,
+ test_implicit_mprotect_exec_only_memory,
+ test_mprotect_with_pkey_0,
test_ptrace_of_child,
test_pkey_syscalls_on_non_allocated_pkey,
test_pkey_syscalls_bad_args,
diff --git a/tools/testing/selftests/x86/test_syscall_vdso.c b/tools/testing/selftests/x86/test_syscall_vdso.c
index 40370354d4c1..c9c3281077bc 100644
--- a/tools/testing/selftests/x86/test_syscall_vdso.c
+++ b/tools/testing/selftests/x86/test_syscall_vdso.c
@@ -100,12 +100,19 @@ asm (
" shl $32, %r8\n"
" orq $0x7f7f7f7f, %r8\n"
" movq %r8, %r9\n"
- " movq %r8, %r10\n"
- " movq %r8, %r11\n"
- " movq %r8, %r12\n"
- " movq %r8, %r13\n"
- " movq %r8, %r14\n"
- " movq %r8, %r15\n"
+ " incq %r9\n"
+ " movq %r9, %r10\n"
+ " incq %r10\n"
+ " movq %r10, %r11\n"
+ " incq %r11\n"
+ " movq %r11, %r12\n"
+ " incq %r12\n"
+ " movq %r12, %r13\n"
+ " incq %r13\n"
+ " movq %r13, %r14\n"
+ " incq %r14\n"
+ " movq %r14, %r15\n"
+ " incq %r15\n"
" ret\n"
" .code32\n"
" .popsection\n"
@@ -128,12 +135,13 @@ int check_regs64(void)
int err = 0;
int num = 8;
uint64_t *r64 = &regs64.r8;
+ uint64_t expected = 0x7f7f7f7f7f7f7f7fULL;
if (!kernel_is_64bit)
return 0;
do {
- if (*r64 == 0x7f7f7f7f7f7f7f7fULL)
+ if (*r64 == expected++)
continue; /* register did not change */
if (syscall_addr != (long)&int80) {
/*
@@ -147,18 +155,17 @@ int check_regs64(void)
continue;
}
} else {
- /* INT80 syscall entrypoint can be used by
+ /*
+ * INT80 syscall entrypoint can be used by
* 64-bit programs too, unlike SYSCALL/SYSENTER.
* Therefore it must preserve R12+
* (they are callee-saved registers in 64-bit C ABI).
*
- * This was probably historically not intended,
- * but R8..11 are clobbered (cleared to 0).
- * IOW: they are the only registers which aren't
- * preserved across INT80 syscall.
+ * Starting in Linux 4.17 (and any kernel that
+ * backports the change), R8..11 are preserved.
+ * Historically (and probably unintentionally), they
+ * were clobbered or zeroed.
*/
- if (*r64 == 0 && num <= 11)
- continue;
}
printf("[FAIL]\tR%d has changed:%016llx\n", num, *r64);
err++;
diff --git a/tools/testing/selftests/x86/trivial_program.c b/tools/testing/selftests/x86/trivial_program.c
new file mode 100644
index 000000000000..46a447163b93
--- /dev/null
+++ b/tools/testing/selftests/x86/trivial_program.c
@@ -0,0 +1,10 @@
+/* Trivial program to check that compilation with certain flags is working. */
+
+#include <stdio.h>
+
+int
+main(void)
+{
+ puts("");
+ return 0;
+}
OpenPOWER on IntegriCloud