summaryrefslogtreecommitdiff
path: root/tools
diff options
context:
space:
mode:
Diffstat (limited to 'tools')
-rw-r--r--tools/Makefile40
-rw-r--r--tools/arch/arm64/include/asm/cputype.h2
-rw-r--r--tools/arch/x86/include/asm/amd-ibs.h2
-rw-r--r--tools/arch/x86/include/asm/disabled-features.h8
-rw-r--r--tools/arch/x86/include/asm/msr-index.h4
-rw-r--r--tools/bpf/bpftool/gen.c22
-rw-r--r--tools/build/Makefile.feature1
-rw-r--r--tools/build/feature/Makefile13
-rw-r--r--tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c7
-rwxr-xr-xtools/certs/print-cert-tbs-hash.sh91
-rw-r--r--tools/include/linux/objtool.h10
-rw-r--r--tools/include/linux/slab.h8
-rw-r--r--tools/include/nolibc/Makefile42
-rw-r--r--tools/include/nolibc/arch-aarch64.h199
-rw-r--r--tools/include/nolibc/arch-arm.h204
-rw-r--r--tools/include/nolibc/arch-i386.h219
-rw-r--r--tools/include/nolibc/arch-mips.h215
-rw-r--r--tools/include/nolibc/arch-riscv.h204
-rw-r--r--tools/include/nolibc/arch-x86_64.h215
-rw-r--r--tools/include/nolibc/arch.h32
-rw-r--r--tools/include/nolibc/ctype.h99
-rw-r--r--tools/include/nolibc/errno.h27
-rw-r--r--tools/include/nolibc/nolibc.h2540
-rw-r--r--tools/include/nolibc/signal.h22
-rw-r--r--tools/include/nolibc/std.h49
-rw-r--r--tools/include/nolibc/stdio.h306
-rw-r--r--tools/include/nolibc/stdlib.h423
-rw-r--r--tools/include/nolibc/string.h285
-rw-r--r--tools/include/nolibc/sys.h1247
-rw-r--r--tools/include/nolibc/time.h28
-rw-r--r--tools/include/nolibc/types.h205
-rw-r--r--tools/include/nolibc/unistd.h54
-rw-r--r--tools/include/uapi/linux/kvm.h10
-rw-r--r--tools/include/uapi/linux/vhost.h7
-rw-r--r--tools/lib/perf/evlist.c3
-rw-r--r--tools/lib/subcmd/parse-options.c17
-rw-r--r--tools/lib/thermal/.gitignore2
-rw-r--r--tools/lib/thermal/Build5
-rw-r--r--tools/lib/thermal/Makefile165
-rw-r--r--tools/lib/thermal/commands.c349
-rw-r--r--tools/lib/thermal/events.c164
-rw-r--r--tools/lib/thermal/include/thermal.h142
-rw-r--r--tools/lib/thermal/libthermal.map25
-rw-r--r--tools/lib/thermal/libthermal.pc.template12
-rw-r--r--tools/lib/thermal/sampling.c75
-rw-r--r--tools/lib/thermal/thermal.c135
-rw-r--r--tools/lib/thermal/thermal_nl.c215
-rw-r--r--tools/lib/thermal/thermal_nl.h46
-rw-r--r--tools/memory-model/README3
-rw-r--r--tools/objtool/Build12
-rw-r--r--tools/objtool/Documentation/objtool.txt (renamed from tools/objtool/Documentation/stack-validation.txt)122
-rw-r--r--tools/objtool/Makefile10
-rw-r--r--tools/objtool/arch/x86/decode.c2
-rw-r--r--tools/objtool/arch/x86/special.c2
-rw-r--r--tools/objtool/builtin-check.c156
-rw-r--r--tools/objtool/builtin-orc.c73
-rw-r--r--tools/objtool/check.c565
-rw-r--r--tools/objtool/elf.c264
-rw-r--r--tools/objtool/include/objtool/builtin.h34
-rw-r--r--tools/objtool/include/objtool/elf.h16
-rw-r--r--tools/objtool/include/objtool/objtool.h2
-rw-r--r--tools/objtool/include/objtool/warn.h35
-rw-r--r--tools/objtool/objtool.c104
-rw-r--r--tools/objtool/weak.c9
-rw-r--r--tools/perf/Documentation/perf.txt2
-rw-r--r--tools/perf/Makefile.config13
-rw-r--r--tools/perf/arch/arm64/util/arm-spe.c16
-rw-r--r--tools/perf/arch/arm64/util/machine.c21
-rw-r--r--tools/perf/arch/powerpc/util/Build1
-rw-r--r--tools/perf/arch/powerpc/util/machine.c25
-rw-r--r--tools/perf/arch/s390/util/machine.c16
-rw-r--r--tools/perf/arch/x86/util/perf_regs.c12
-rw-r--r--tools/perf/bench/epoll-ctl.c25
-rw-r--r--tools/perf/bench/epoll-wait.c25
-rw-r--r--tools/perf/bench/futex-hash.c26
-rw-r--r--tools/perf/bench/futex-lock-pi.c21
-rw-r--r--tools/perf/bench/futex-requeue.c21
-rw-r--r--tools/perf/bench/futex-wake-parallel.c21
-rw-r--r--tools/perf/bench/futex-wake.c22
-rw-r--r--tools/perf/bench/numa.c140
-rw-r--r--tools/perf/builtin-record.c22
-rw-r--r--tools/perf/builtin-report.c14
-rw-r--r--tools/perf/builtin-script.c2
-rw-r--r--tools/perf/perf.c6
-rw-r--r--tools/perf/tests/attr/README1
-rw-r--r--tools/perf/tests/attr/test-record-spe-physical-address12
-rw-r--r--tools/perf/tests/bpf.c10
-rw-r--r--tools/perf/tests/builtin-test.c8
-rw-r--r--tools/perf/tests/dwarf-unwind.c2
-rw-r--r--tools/perf/tests/perf-time-to-tsc.c40
-rwxr-xr-xtools/perf/tests/shell/stat_all_pmu.sh10
-rwxr-xr-xtools/perf/tests/shell/test_arm_coresight.sh1
-rw-r--r--tools/perf/tests/topology.c11
-rw-r--r--tools/perf/util/annotate.c1
-rw-r--r--tools/perf/util/arm-spe.c5
-rw-r--r--tools/perf/util/arm64-frame-pointer-unwind-support.c2
-rw-r--r--tools/perf/util/bpf-event.c4
-rw-r--r--tools/perf/util/c++/clang.cpp4
-rw-r--r--tools/perf/util/header.c51
-rw-r--r--tools/perf/util/header.h1
-rw-r--r--tools/perf/util/machine.c2
-rw-r--r--tools/perf/util/parse-events.c5
-rw-r--r--tools/perf/util/session.c43
-rw-r--r--tools/perf/util/setup.py8
-rw-r--r--tools/perf/util/stat.c20
-rw-r--r--tools/perf/util/symbol-elf.c2
-rw-r--r--tools/perf/util/symbol.c37
-rw-r--r--tools/perf/util/symbol.h3
-rw-r--r--tools/perf/util/unwind-libdw.c10
-rw-r--r--tools/perf/util/unwind-libdw.h1
-rw-r--r--tools/perf/util/unwind-libunwind-local.c10
-rw-r--r--tools/perf/util/unwind-libunwind.c6
-rw-r--r--tools/perf/util/unwind.h13
-rw-r--r--tools/power/acpi/common/cmfsize.c2
-rw-r--r--tools/power/acpi/common/getopt.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/oslinuxtbl.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/osunixdir.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/osunixmap.c2
-rw-r--r--tools/power/acpi/os_specific/service_layers/osunixxf.c2
-rw-r--r--tools/power/acpi/tools/acpidump/acpidump.h2
-rw-r--r--tools/power/acpi/tools/acpidump/apdump.c2
-rw-r--r--tools/power/acpi/tools/acpidump/apfiles.c2
-rw-r--r--tools/power/acpi/tools/acpidump/apmain.c2
-rw-r--r--tools/power/x86/intel-speed-select/Makefile2
-rw-r--r--tools/power/x86/intel-speed-select/hfi-events.c2
-rw-r--r--tools/power/x86/intel-speed-select/isst-config.c6
-rw-r--r--tools/power/x86/turbostat/Makefile2
-rw-r--r--tools/power/x86/turbostat/turbostat.82
-rw-r--r--tools/power/x86/turbostat/turbostat.c594
-rw-r--r--tools/testing/nvdimm/test/nfit.c4
-rw-r--r--tools/testing/radix-tree/linux.c3
-rw-r--r--tools/testing/selftests/arm64/Makefile11
-rw-r--r--tools/testing/selftests/arm64/abi/.gitignore1
-rw-r--r--tools/testing/selftests/arm64/abi/Makefile9
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi-asm.S79
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi.c204
-rw-r--r--tools/testing/selftests/arm64/abi/syscall-abi.h15
-rw-r--r--tools/testing/selftests/arm64/abi/tpidr2.c298
-rw-r--r--tools/testing/selftests/arm64/bti/Makefile6
-rw-r--r--tools/testing/selftests/arm64/fp/.gitignore5
-rw-r--r--tools/testing/selftests/arm64/fp/Makefile46
-rw-r--r--tools/testing/selftests/arm64/fp/rdvl-sme.c14
-rw-r--r--tools/testing/selftests/arm64/fp/rdvl.S10
-rw-r--r--tools/testing/selftests/arm64/fp/rdvl.h1
-rw-r--r--tools/testing/selftests/arm64/fp/sme-inst.h51
-rw-r--r--tools/testing/selftests/arm64/fp/ssve-stress59
-rw-r--r--tools/testing/selftests/arm64/fp/sve-ptrace.c175
-rw-r--r--tools/testing/selftests/arm64/fp/sve-test.S20
-rw-r--r--tools/testing/selftests/arm64/fp/vec-syscfg.c10
-rw-r--r--tools/testing/selftests/arm64/fp/vlset.c10
-rw-r--r--tools/testing/selftests/arm64/fp/za-fork-asm.S61
-rw-r--r--tools/testing/selftests/arm64/fp/za-fork.c156
-rw-r--r--tools/testing/selftests/arm64/fp/za-ptrace.c356
-rw-r--r--tools/testing/selftests/arm64/fp/za-stress59
-rw-r--r--tools/testing/selftests/arm64/fp/za-test.S388
-rw-r--r--tools/testing/selftests/arm64/mte/.gitignore1
-rw-r--r--tools/testing/selftests/arm64/mte/check_child_memory.c8
-rw-r--r--tools/testing/selftests/arm64/mte/check_prctl.c119
-rw-r--r--tools/testing/selftests/arm64/mte/check_tags_inclusion.c54
-rw-r--r--tools/testing/selftests/arm64/mte/mte_common_util.c42
-rw-r--r--tools/testing/selftests/arm64/mte/mte_common_util.h15
-rw-r--r--tools/testing/selftests/arm64/signal/.gitignore3
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals.h4
-rw-r--r--tools/testing/selftests/arm64/signal/test_signals_utils.c6
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c92
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c38
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c45
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c36
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/sme_vl.c68
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/ssve_regs.c135
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/testcases.c36
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/testcases.h3
-rw-r--r--tools/testing/selftests/arm64/signal/testcases/za_regs.c128
-rw-r--r--tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c23
-rw-r--r--tools/testing/selftests/bpf/progs/map_ptr_kern.c4
-rw-r--r--tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c21
-rw-r--r--tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c78
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh17
-rwxr-xr-xtools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh17
-rwxr-xr-xtools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh2
-rw-r--r--tools/testing/selftests/kselftest_harness.h59
-rw-r--r--tools/testing/selftests/kvm/.gitignore2
-rw-r--r--tools/testing/selftests/kvm/Makefile1
-rw-r--r--tools/testing/selftests/kvm/aarch64/arch_timer.c15
-rw-r--r--tools/testing/selftests/kvm/aarch64/get-reg-list.c14
-rw-r--r--tools/testing/selftests/kvm/aarch64/vcpu_width_config.c122
-rw-r--r--tools/testing/selftests/kvm/dirty_log_perf_test.c34
-rw-r--r--tools/testing/selftests/kvm/include/riscv/processor.h4
-rw-r--r--tools/testing/selftests/kvm/include/x86_64/processor.h17
-rw-r--r--tools/testing/selftests/kvm/kvm_page_table_test.c2
-rw-r--r--tools/testing/selftests/kvm/lib/riscv/processor.c2
-rw-r--r--tools/testing/selftests/kvm/lib/x86_64/processor.c202
-rw-r--r--tools/testing/selftests/kvm/x86_64/amx_test.c1
-rw-r--r--tools/testing/selftests/kvm/x86_64/emulator_error_test.c1
-rw-r--r--tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c37
-rw-r--r--tools/testing/selftests/kvm/x86_64/smm_test.c2
-rw-r--r--tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c1
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c1
-rw-r--r--tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c1
-rw-r--r--tools/testing/selftests/landlock/base_test.c179
-rw-r--r--tools/testing/selftests/landlock/common.h66
-rw-r--r--tools/testing/selftests/landlock/fs_test.c1511
-rw-r--r--tools/testing/selftests/landlock/ptrace_test.c40
-rw-r--r--tools/testing/selftests/mqueue/mq_perf_tests.c25
-rw-r--r--tools/testing/selftests/net/Makefile6
-rw-r--r--tools/testing/selftests/net/bpf/Makefile14
-rw-r--r--tools/testing/selftests/net/bpf/nat6to4.c285
-rwxr-xr-xtools/testing/selftests/net/fcnal-test.sh12
-rwxr-xr-xtools/testing/selftests/net/fib_nexthops.sh14
-rw-r--r--tools/testing/selftests/net/forwarding/Makefile33
-rwxr-xr-xtools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh3
-rwxr-xr-xtools/testing/selftests/net/mptcp/mptcp_join.sh48
-rw-r--r--tools/testing/selftests/net/so_txtime.c4
-rwxr-xr-xtools/testing/selftests/net/udpgro_frglist.sh101
-rw-r--r--tools/testing/selftests/pid_namespace/Makefile6
-rw-r--r--tools/testing/selftests/pidfd/pidfd_wait.c1
-rw-r--r--tools/testing/selftests/proc/proc-pid-vm.c6
-rw-r--r--tools/testing/selftests/rcutorture/bin/functions.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-find-errors.sh2
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-recheck.sh7
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm-remote.sh14
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/kvm.sh10
-rwxr-xr-xtools/testing/selftests/rcutorture/bin/torture.sh29
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/RUDE012
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/SRCU-N2
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TASKS011
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TASKS024
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot1
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TASKS032
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE013
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TRACE022
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE045
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE071
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE092
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/TREE101
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh16
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon7
-rw-r--r--tools/testing/selftests/rcutorture/configs/rcuscale/TREE2
-rw-r--r--tools/testing/selftests/rcutorture/configs/refscale/CFcommon4
-rw-r--r--tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT2
-rw-r--r--tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT2
-rw-r--r--tools/testing/selftests/rcutorture/configs/scf/PREEMPT1
-rw-r--r--tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh3
-rw-r--r--tools/testing/selftests/seccomp/Makefile1
-rw-r--r--tools/testing/selftests/seccomp/seccomp_bpf.c437
-rw-r--r--tools/testing/selftests/vDSO/vdso_test_correctness.c9
-rw-r--r--tools/testing/selftests/vm/Makefile10
-rw-r--r--tools/testing/selftests/vm/mremap_test.c85
-rwxr-xr-xtools/testing/selftests/vm/run_vmtests.sh11
-rwxr-xr-xtools/testing/selftests/wireguard/netns.sh34
-rw-r--r--tools/testing/selftests/wireguard/qemu/.gitignore1
-rw-r--r--tools/testing/selftests/wireguard/qemu/Makefile205
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/aarch64.config5
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config5
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/arm.config5
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/armeb.config5
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/i686.config3
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/m68k.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/mips.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/mips64.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/mips64el.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/mipsel.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/powerpc.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/powerpc64.config13
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config2
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/riscv32.config12
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/riscv64.config12
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/s390x.config6
-rw-r--r--tools/testing/selftests/wireguard/qemu/arch/x86_64.config3
-rw-r--r--tools/testing/selftests/wireguard/qemu/init.c6
-rw-r--r--tools/testing/selftests/x86/Makefile4
-rw-r--r--tools/thermal/lib/Build3
-rw-r--r--tools/thermal/lib/Makefile158
-rw-r--r--tools/thermal/lib/libthermal_tools.pc.template12
-rw-r--r--tools/thermal/lib/log.c77
-rw-r--r--tools/thermal/lib/log.h31
-rw-r--r--tools/thermal/lib/mainloop.c120
-rw-r--r--tools/thermal/lib/mainloop.h15
-rw-r--r--tools/thermal/lib/thermal-tools.h10
-rw-r--r--tools/thermal/lib/uptimeofday.c40
-rw-r--r--tools/thermal/lib/uptimeofday.h12
-rw-r--r--tools/thermal/thermal-engine/Build1
-rw-r--r--tools/thermal/thermal-engine/Makefile28
-rw-r--r--tools/thermal/thermal-engine/thermal-engine.c341
-rw-r--r--tools/thermal/thermometer/Build1
-rw-r--r--tools/thermal/thermometer/Makefile26
-rw-r--r--tools/thermal/thermometer/thermometer.892
-rw-r--r--tools/thermal/thermometer/thermometer.c572
-rw-r--r--tools/thermal/thermometer/thermometer.conf5
289 files changed, 15148 insertions, 4333 deletions
diff --git a/tools/Makefile b/tools/Makefile
index db2f7b8ebed5..c074e42fd92f 100644
--- a/tools/Makefile
+++ b/tools/Makefile
@@ -24,6 +24,7 @@ help:
@echo ' intel-speed-select - Intel Speed Select tool'
@echo ' kvm_stat - top-like utility for displaying kvm statistics'
@echo ' leds - LEDs tools'
+ @echo ' nolibc - nolibc headers testing and installation'
@echo ' objtool - an ELF object analysis tool'
@echo ' pci - PCI tools'
@echo ' perf - Linux performance measurement and analysis tool'
@@ -31,6 +32,9 @@ help:
@echo ' bootconfig - boot config tool'
@echo ' spi - spi tools'
@echo ' tmon - thermal monitoring and tuning tool'
+ @echo ' thermometer - temperature capture tool'
+ @echo ' thermal-engine - thermal monitoring tool'
+ @echo ' thermal - thermal library'
@echo ' tracing - misc tracing tools'
@echo ' turbostat - Intel CPU idle stats and freq reporting tool'
@echo ' usb - USB testing tools'
@@ -74,6 +78,9 @@ bpf/%: FORCE
libapi: FORCE
$(call descend,lib/api)
+nolibc_%: FORCE
+ $(call descend,include/nolibc,$(patsubst nolibc_%,%,$@))
+
# The perf build does not follow the descend function setup,
# invoking it via it's own make rule.
PERF_O = $(if $(O),$(O)/tools/perf,)
@@ -85,12 +92,21 @@ perf: FORCE
selftests: FORCE
$(call descend,testing/$@)
+thermal: FORCE
+ $(call descend,lib/$@)
+
turbostat x86_energy_perf_policy intel-speed-select: FORCE
$(call descend,power/x86/$@)
tmon: FORCE
$(call descend,thermal/$@)
+thermometer: FORCE
+ $(call descend,thermal/$@)
+
+thermal-engine: FORCE thermal
+ $(call descend,thermal/$@)
+
freefall: FORCE
$(call descend,laptop/$@)
@@ -101,7 +117,7 @@ all: acpi cgroup counter cpupower gpio hv firewire \
perf selftests bootconfig spi turbostat usb \
virtio vm bpf x86_energy_perf_policy \
tmon freefall iio objtool kvm_stat wmi \
- pci debugging tracing
+ pci debugging tracing thermal thermometer thermal-engine
acpi_install:
$(call descend,power/$(@:_install=),install)
@@ -115,12 +131,21 @@ cgroup_install counter_install firewire_install gpio_install hv_install iio_inst
selftests_install:
$(call descend,testing/$(@:_install=),install)
+thermal_install:
+ $(call descend,lib/$(@:_install=),install)
+
turbostat_install x86_energy_perf_policy_install intel-speed-select_install:
$(call descend,power/x86/$(@:_install=),install)
tmon_install:
$(call descend,thermal/$(@:_install=),install)
+thermometer_install:
+ $(call descend,thermal/$(@:_install=),install)
+
+thermal-engine_install:
+ $(call descend,thermal/$(@:_install=),install)
+
freefall_install:
$(call descend,laptop/$(@:_install=),install)
@@ -133,7 +158,7 @@ install: acpi_install cgroup_install counter_install cpupower_install gpio_insta
virtio_install vm_install bpf_install x86_energy_perf_policy_install \
tmon_install freefall_install objtool_install kvm_stat_install \
wmi_install pci_install debugging_install intel-speed-select_install \
- tracing_install
+ tracing_install thermometer_install thermal-engine_install
acpi_clean:
$(call descend,power/acpi,clean)
@@ -160,9 +185,18 @@ perf_clean:
selftests_clean:
$(call descend,testing/$(@:_clean=),clean)
+thermal_clean:
+ $(call descend,lib/thermal,clean)
+
turbostat_clean x86_energy_perf_policy_clean intel-speed-select_clean:
$(call descend,power/x86/$(@:_clean=),clean)
+thermometer_clean:
+ $(call descend,thermal/thermometer,clean)
+
+thermal-engine_clean:
+ $(call descend,thermal/thermal-engine,clean)
+
tmon_clean:
$(call descend,thermal/tmon,clean)
@@ -177,6 +211,6 @@ clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_cl
vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
freefall_clean build_clean libbpf_clean libsubcmd_clean \
gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \
- intel-speed-select_clean tracing_clean
+ intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean
.PHONY: FORCE
diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h
index 9afcc6467a09..e09d6908a21d 100644
--- a/tools/arch/arm64/include/asm/cputype.h
+++ b/tools/arch/arm64/include/asm/cputype.h
@@ -75,6 +75,7 @@
#define ARM_CPU_PART_CORTEX_A77 0xD0D
#define ARM_CPU_PART_NEOVERSE_V1 0xD40
#define ARM_CPU_PART_CORTEX_A78 0xD41
+#define ARM_CPU_PART_CORTEX_A78AE 0xD42
#define ARM_CPU_PART_CORTEX_X1 0xD44
#define ARM_CPU_PART_CORTEX_A510 0xD46
#define ARM_CPU_PART_CORTEX_A710 0xD47
@@ -130,6 +131,7 @@
#define MIDR_CORTEX_A77 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A77)
#define MIDR_NEOVERSE_V1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V1)
#define MIDR_CORTEX_A78 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78)
+#define MIDR_CORTEX_A78AE MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78AE)
#define MIDR_CORTEX_X1 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1)
#define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510)
#define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710)
diff --git a/tools/arch/x86/include/asm/amd-ibs.h b/tools/arch/x86/include/asm/amd-ibs.h
index 174e7d83fcbd..765e9e752d03 100644
--- a/tools/arch/x86/include/asm/amd-ibs.h
+++ b/tools/arch/x86/include/asm/amd-ibs.h
@@ -49,7 +49,7 @@ union ibs_op_ctl {
};
};
-/* MSR 0xc0011035: IBS Op Data 2 */
+/* MSR 0xc0011035: IBS Op Data 1 */
union ibs_op_data {
__u64 val;
struct {
diff --git a/tools/arch/x86/include/asm/disabled-features.h b/tools/arch/x86/include/asm/disabled-features.h
index 1231d63f836d..1ae0fab7d902 100644
--- a/tools/arch/x86/include/asm/disabled-features.h
+++ b/tools/arch/x86/include/asm/disabled-features.h
@@ -10,12 +10,6 @@
* cpu_feature_enabled().
*/
-#ifdef CONFIG_X86_SMAP
-# define DISABLE_SMAP 0
-#else
-# define DISABLE_SMAP (1<<(X86_FEATURE_SMAP & 31))
-#endif
-
#ifdef CONFIG_X86_UMIP
# define DISABLE_UMIP 0
#else
@@ -80,7 +74,7 @@
#define DISABLED_MASK6 0
#define DISABLED_MASK7 (DISABLE_PTI)
#define DISABLED_MASK8 0
-#define DISABLED_MASK9 (DISABLE_SMAP|DISABLE_SGX)
+#define DISABLED_MASK9 (DISABLE_SGX)
#define DISABLED_MASK10 0
#define DISABLED_MASK11 0
#define DISABLED_MASK12 0
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 0eb90d21049e..ee15311b6be1 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -128,9 +128,9 @@
#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */
#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */
-/* SRBDS support */
#define MSR_IA32_MCU_OPT_CTRL 0x00000123
-#define RNGDS_MITG_DIS BIT(0)
+#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */
+#define RTM_ALLOW BIT(1) /* TSX development mode */
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 91af2850b505..7678af364793 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -828,8 +828,10 @@ codegen_maps_skeleton(struct bpf_object *obj, size_t map_cnt, bool mmaped)
s->map_cnt = %zu; \n\
s->map_skel_sz = sizeof(*s->maps); \n\
s->maps = (struct bpf_map_skeleton *)calloc(s->map_cnt, s->map_skel_sz);\n\
- if (!s->maps) \n\
+ if (!s->maps) { \n\
+ err = -ENOMEM; \n\
goto err; \n\
+ } \n\
",
map_cnt
);
@@ -870,8 +872,10 @@ codegen_progs_skeleton(struct bpf_object *obj, size_t prog_cnt, bool populate_li
s->prog_cnt = %zu; \n\
s->prog_skel_sz = sizeof(*s->progs); \n\
s->progs = (struct bpf_prog_skeleton *)calloc(s->prog_cnt, s->prog_skel_sz);\n\
- if (!s->progs) \n\
+ if (!s->progs) { \n\
+ err = -ENOMEM; \n\
goto err; \n\
+ } \n\
",
prog_cnt
);
@@ -1182,10 +1186,13 @@ static int do_skeleton(int argc, char **argv)
%1$s__create_skeleton(struct %1$s *obj) \n\
{ \n\
struct bpf_object_skeleton *s; \n\
+ int err; \n\
\n\
s = (struct bpf_object_skeleton *)calloc(1, sizeof(*s));\n\
- if (!s) \n\
+ if (!s) { \n\
+ err = -ENOMEM; \n\
goto err; \n\
+ } \n\
\n\
s->sz = sizeof(*s); \n\
s->name = \"%1$s\"; \n\
@@ -1206,7 +1213,7 @@ static int do_skeleton(int argc, char **argv)
return 0; \n\
err: \n\
bpf_object__destroy_skeleton(s); \n\
- return -ENOMEM; \n\
+ return err; \n\
} \n\
\n\
static inline const void *%2$s__elf_bytes(size_t *sz) \n\
@@ -1466,12 +1473,12 @@ static int do_subskeleton(int argc, char **argv)
\n\
obj = (struct %1$s *)calloc(1, sizeof(*obj)); \n\
if (!obj) { \n\
- errno = ENOMEM; \n\
+ err = -ENOMEM; \n\
goto err; \n\
} \n\
s = (struct bpf_object_subskeleton *)calloc(1, sizeof(*s));\n\
if (!s) { \n\
- errno = ENOMEM; \n\
+ err = -ENOMEM; \n\
goto err; \n\
} \n\
s->sz = sizeof(*s); \n\
@@ -1483,7 +1490,7 @@ static int do_subskeleton(int argc, char **argv)
s->var_cnt = %2$d; \n\
s->vars = (struct bpf_var_skeleton *)calloc(%2$d, sizeof(*s->vars));\n\
if (!s->vars) { \n\
- errno = ENOMEM; \n\
+ err = -ENOMEM; \n\
goto err; \n\
} \n\
",
@@ -1538,6 +1545,7 @@ static int do_subskeleton(int argc, char **argv)
return obj; \n\
err: \n\
%1$s__destroy(obj); \n\
+ errno = -err; \n\
return NULL; \n\
} \n\
\n\
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index ae61f464043a..c6a48d0ef9ff 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -98,6 +98,7 @@ FEATURE_TESTS_EXTRA := \
llvm-version \
clang \
libbpf \
+ libbpf-btf__load_from_kernel_by_id \
libpfm4 \
libdebuginfod \
clang-bpf-co-re
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 1480910c792e..cb4a2a4fa2e4 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -57,6 +57,7 @@ FILES= \
test-lzma.bin \
test-bpf.bin \
test-libbpf.bin \
+ test-libbpf-btf__load_from_kernel_by_id.bin \
test-get_cpuid.bin \
test-sdt.bin \
test-cxx.bin \
@@ -217,9 +218,16 @@ strip-libs = $(filter-out -l%,$(1))
PERL_EMBED_LDOPTS = $(shell perl -MExtUtils::Embed -e ldopts 2>/dev/null)
PERL_EMBED_LDFLAGS = $(call strip-libs,$(PERL_EMBED_LDOPTS))
PERL_EMBED_LIBADD = $(call grep-libs,$(PERL_EMBED_LDOPTS))
-PERL_EMBED_CCOPTS = `perl -MExtUtils::Embed -e ccopts 2>/dev/null`
+PERL_EMBED_CCOPTS = $(shell perl -MExtUtils::Embed -e ccopts 2>/dev/null)
FLAGS_PERL_EMBED=$(PERL_EMBED_CCOPTS) $(PERL_EMBED_LDOPTS)
+ifeq ($(CC_NO_CLANG), 0)
+ PERL_EMBED_LDOPTS := $(filter-out -specs=%,$(PERL_EMBED_LDOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -flto=auto -ffat-lto-objects, $(PERL_EMBED_CCOPTS))
+ PERL_EMBED_CCOPTS := $(filter-out -specs=%,$(PERL_EMBED_CCOPTS))
+ FLAGS_PERL_EMBED += -Wno-compound-token-split-by-macro
+endif
+
$(OUTPUT)test-libperl.bin:
$(BUILD) $(FLAGS_PERL_EMBED)
@@ -280,6 +288,9 @@ $(OUTPUT)test-bpf.bin:
$(OUTPUT)test-libbpf.bin:
$(BUILD) -lbpf
+$(OUTPUT)test-libbpf-btf__load_from_kernel_by_id.bin:
+ $(BUILD) -lbpf
+
$(OUTPUT)test-sdt.bin:
$(BUILD)
diff --git a/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c
new file mode 100644
index 000000000000..f7c084428735
--- /dev/null
+++ b/tools/build/feature/test-libbpf-btf__load_from_kernel_by_id.c
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <bpf/libbpf.h>
+
+int main(void)
+{
+ return btf__load_from_kernel_by_id(20151128, NULL);
+}
diff --git a/tools/certs/print-cert-tbs-hash.sh b/tools/certs/print-cert-tbs-hash.sh
new file mode 100755
index 000000000000..c93df5387ec9
--- /dev/null
+++ b/tools/certs/print-cert-tbs-hash.sh
@@ -0,0 +1,91 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright © 2020, Microsoft Corporation. All rights reserved.
+#
+# Author: Mickaël Salaün <mic@linux.microsoft.com>
+#
+# Compute and print the To Be Signed (TBS) hash of a certificate. This is used
+# as description of keys in the blacklist keyring to identify certificates.
+# This output should be redirected, without newline, in a file (hash0.txt) and
+# signed to create a PKCS#7 file (hash0.p7s). Both of these files can then be
+# loaded in the kernel with.
+#
+# Exemple on a workstation:
+# ./print-cert-tbs-hash.sh certificate-to-invalidate.pem > hash0.txt
+# openssl smime -sign -in hash0.txt -inkey builtin-private-key.pem \
+# -signer builtin-certificate.pem -certfile certificate-chain.pem \
+# -noattr -binary -outform DER -out hash0.p7s
+#
+# Exemple on a managed system:
+# keyctl padd blacklist "$(< hash0.txt)" %:.blacklist < hash0.p7s
+
+set -u -e -o pipefail
+
+CERT="${1:-}"
+BASENAME="$(basename -- "${BASH_SOURCE[0]}")"
+
+if [ $# -ne 1 ] || [ ! -f "${CERT}" ]; then
+ echo "usage: ${BASENAME} <certificate>" >&2
+ exit 1
+fi
+
+# Checks that it is indeed a certificate (PEM or DER encoded) and exclude the
+# optional PEM text header.
+if ! PEM="$(openssl x509 -inform DER -in "${CERT}" 2>/dev/null || openssl x509 -in "${CERT}")"; then
+ echo "ERROR: Failed to parse certificate" >&2
+ exit 1
+fi
+
+# TBSCertificate starts at the second entry.
+# Cf. https://tools.ietf.org/html/rfc3280#section-4.1
+#
+# Exemple of first lines printed by openssl asn1parse:
+# 0:d=0 hl=4 l= 763 cons: SEQUENCE
+# 4:d=1 hl=4 l= 483 cons: SEQUENCE
+# 8:d=2 hl=2 l= 3 cons: cont [ 0 ]
+# 10:d=3 hl=2 l= 1 prim: INTEGER :02
+# 13:d=2 hl=2 l= 20 prim: INTEGER :3CEB2CB8818D968AC00EEFE195F0DF9665328B7B
+# 35:d=2 hl=2 l= 13 cons: SEQUENCE
+# 37:d=3 hl=2 l= 9 prim: OBJECT :sha256WithRSAEncryption
+RANGE_AND_DIGEST_RE='
+2s/^\s*\([0-9]\+\):d=\s*[0-9]\+\s\+hl=\s*[0-9]\+\s\+l=\s*\([0-9]\+\)\s\+cons:\s*SEQUENCE\s*$/\1 \2/p;
+7s/^\s*[0-9]\+:d=\s*[0-9]\+\s\+hl=\s*[0-9]\+\s\+l=\s*[0-9]\+\s\+prim:\s*OBJECT\s*:\(.*\)$/\1/p;
+'
+
+RANGE_AND_DIGEST=($(echo "${PEM}" | \
+ openssl asn1parse -in - | \
+ sed -n -e "${RANGE_AND_DIGEST_RE}"))
+
+if [ "${#RANGE_AND_DIGEST[@]}" != 3 ]; then
+ echo "ERROR: Failed to parse TBSCertificate." >&2
+ exit 1
+fi
+
+OFFSET="${RANGE_AND_DIGEST[0]}"
+END="$(( OFFSET + RANGE_AND_DIGEST[1] ))"
+DIGEST="${RANGE_AND_DIGEST[2]}"
+
+# The signature hash algorithm is used by Linux to blacklist certificates.
+# Cf. crypto/asymmetric_keys/x509_cert_parser.c:x509_note_pkey_algo()
+DIGEST_MATCH=""
+while read -r DIGEST_ITEM; do
+ if [ -z "${DIGEST_ITEM}" ]; then
+ break
+ fi
+ if echo "${DIGEST}" | grep -qiF "${DIGEST_ITEM}"; then
+ DIGEST_MATCH="${DIGEST_ITEM}"
+ break
+ fi
+done < <(openssl list -digest-commands | tr ' ' '\n' | sort -ur)
+
+if [ -z "${DIGEST_MATCH}" ]; then
+ echo "ERROR: Unknown digest algorithm: ${DIGEST}" >&2
+ exit 1
+fi
+
+echo "${PEM}" | \
+ openssl x509 -in - -outform DER | \
+ dd "bs=1" "skip=${OFFSET}" "count=${END}" "status=none" | \
+ openssl dgst "-${DIGEST_MATCH}" - | \
+ awk '{printf "tbs:" $2}'
diff --git a/tools/include/linux/objtool.h b/tools/include/linux/objtool.h
index 586d35720f13..6491fa8fba6d 100644
--- a/tools/include/linux/objtool.h
+++ b/tools/include/linux/objtool.h
@@ -38,7 +38,9 @@ struct unwind_hint {
#define UNWIND_HINT_TYPE_REGS_PARTIAL 2
#define UNWIND_HINT_TYPE_FUNC 3
-#ifdef CONFIG_STACK_VALIDATION
+#ifdef CONFIG_OBJTOOL
+
+#include <asm/asm.h>
#ifndef __ASSEMBLY__
@@ -137,7 +139,7 @@ struct unwind_hint {
.macro STACK_FRAME_NON_STANDARD func:req
.pushsection .discard.func_stack_frame_non_standard, "aw"
- .long \func - .
+ _ASM_PTR \func
.popsection
.endm
@@ -157,7 +159,7 @@ struct unwind_hint {
#endif /* __ASSEMBLY__ */
-#else /* !CONFIG_STACK_VALIDATION */
+#else /* !CONFIG_OBJTOOL */
#ifndef __ASSEMBLY__
@@ -179,6 +181,6 @@ struct unwind_hint {
.endm
#endif
-#endif /* CONFIG_STACK_VALIDATION */
+#endif /* CONFIG_OBJTOOL */
#endif /* _LINUX_OBJTOOL_H */
diff --git a/tools/include/linux/slab.h b/tools/include/linux/slab.h
index f41d8a0eb1a4..0616409513eb 100644
--- a/tools/include/linux/slab.h
+++ b/tools/include/linux/slab.h
@@ -28,7 +28,13 @@ static inline void *kzalloc(size_t size, gfp_t gfp)
return kmalloc(size, gfp | __GFP_ZERO);
}
-void *kmem_cache_alloc(struct kmem_cache *cachep, int flags);
+struct list_lru;
+
+void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *, int flags);
+static inline void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
+{
+ return kmem_cache_alloc_lru(cachep, NULL, flags);
+}
void kmem_cache_free(struct kmem_cache *cachep, void *objp);
struct kmem_cache *kmem_cache_create(const char *name, unsigned int size,
diff --git a/tools/include/nolibc/Makefile b/tools/include/nolibc/Makefile
new file mode 100644
index 000000000000..7a16d917c185
--- /dev/null
+++ b/tools/include/nolibc/Makefile
@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for nolibc installation and tests
+include ../../scripts/Makefile.include
+
+# we're in ".../tools/include/nolibc"
+ifeq ($(srctree),)
+srctree := $(patsubst %/tools/include/,%,$(dir $(CURDIR)))
+endif
+
+nolibc_arch := $(patsubst arm64,aarch64,$(ARCH))
+arch_file := arch-$(nolibc_arch).h
+all_files := ctype.h errno.h nolibc.h signal.h std.h stdio.h stdlib.h string.h \
+ sys.h time.h types.h unistd.h
+
+# install all headers needed to support a bare-metal compiler
+all:
+
+# Note: when ARCH is "x86" we concatenate both x86_64 and i386
+headers:
+ $(Q)mkdir -p $(OUTPUT)sysroot
+ $(Q)mkdir -p $(OUTPUT)sysroot/include
+ $(Q)cp $(all_files) $(OUTPUT)sysroot/include/
+ $(Q)if [ "$(ARCH)" = "x86" ]; then \
+ sed -e \
+ 's,^#ifndef _NOLIBC_ARCH_X86_64_H,#if !defined(_NOLIBC_ARCH_X86_64_H) \&\& defined(__x86_64__),' \
+ arch-x86_64.h; \
+ sed -e \
+ 's,^#ifndef _NOLIBC_ARCH_I386_H,#if !defined(_NOLIBC_ARCH_I386_H) \&\& !defined(__x86_64__),' \
+ arch-i386.h; \
+ elif [ -e "$(arch_file)" ]; then \
+ cat $(arch_file); \
+ else \
+ echo "Fatal: architecture $(ARCH) not yet supported by nolibc." >&2; \
+ exit 1; \
+ fi > $(OUTPUT)sysroot/include/arch.h
+
+headers_standalone: headers
+ $(Q)$(MAKE) -C $(srctree) headers
+ $(Q)$(MAKE) -C $(srctree) headers_install INSTALL_HDR_PATH=$(OUTPUT)/sysroot
+
+clean:
+ $(call QUIET_CLEAN, nolibc) rm -rf "$(OUTPUT)sysroot"
diff --git a/tools/include/nolibc/arch-aarch64.h b/tools/include/nolibc/arch-aarch64.h
new file mode 100644
index 000000000000..f68baf8f395f
--- /dev/null
+++ b/tools/include/nolibc/arch-aarch64.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * AARCH64 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_AARCH64_H
+#define _NOLIBC_ARCH_AARCH64_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x4000
+
+/* The struct returned by the newfstatat() syscall. Differs slightly from the
+ * x86_64's stat one by field ordering, so be careful.
+ */
+struct sys_stat_struct {
+ unsigned long st_dev;
+ unsigned long st_ino;
+ unsigned int st_mode;
+ unsigned int st_nlink;
+ unsigned int st_uid;
+ unsigned int st_gid;
+
+ unsigned long st_rdev;
+ unsigned long __pad1;
+ long st_size;
+ int st_blksize;
+ int __pad2;
+
+ long st_blocks;
+ long st_atime;
+ unsigned long st_atime_nsec;
+ long st_mtime;
+
+ unsigned long st_mtime_nsec;
+ long st_ctime;
+ unsigned long st_ctime_nsec;
+ unsigned int __unused[2];
+};
+
+/* Syscalls for AARCH64 :
+ * - registers are 64-bit
+ * - stack is 16-byte aligned
+ * - syscall number is passed in x8
+ * - arguments are in x0, x1, x2, x3, x4, x5
+ * - the system call is performed by calling svc 0
+ * - syscall return comes in x0.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ *
+ * On aarch64, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0"); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ register long _arg4 __asm__ ("x3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ register long _arg4 __asm__ ("x3") = (long)(arg4); \
+ register long _arg5 __asm__ ("x4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("x8") = (num); \
+ register long _arg1 __asm__ ("x0") = (long)(arg1); \
+ register long _arg2 __asm__ ("x1") = (long)(arg2); \
+ register long _arg3 __asm__ ("x2") = (long)(arg3); \
+ register long _arg4 __asm__ ("x3") = (long)(arg4); \
+ register long _arg5 __asm__ ("x4") = (long)(arg5); \
+ register long _arg6 __asm__ ("x5") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+ ".weak _start\n"
+ "_start:\n"
+ "ldr x0, [sp]\n" // argc (x0) was in the stack
+ "add x1, sp, 8\n" // argv (x1) = sp
+ "lsl x2, x0, 3\n" // envp (x2) = 8*argc ...
+ "add x2, x2, 8\n" // + 8 (skip null)
+ "add x2, x2, x1\n" // + argv
+ "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee
+ "bl main\n" // main() returns the status code, we'll exit with it.
+ "mov x8, 93\n" // NR_exit == 93
+ "svc #0\n"
+ "");
+
+#endif // _NOLIBC_ARCH_AARCH64_H
diff --git a/tools/include/nolibc/arch-arm.h b/tools/include/nolibc/arch-arm.h
new file mode 100644
index 000000000000..f31be8e967d6
--- /dev/null
+++ b/tools/include/nolibc/arch-arm.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * ARM specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_ARM_H
+#define _NOLIBC_ARCH_ARM_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x4000
+
+/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
+ * exactly 56 bytes (stops before the unused array). In big endian, the format
+ * differs as devices are returned as short only.
+ */
+struct sys_stat_struct {
+#if defined(__ARMEB__)
+ unsigned short st_dev;
+ unsigned short __pad1;
+#else
+ unsigned long st_dev;
+#endif
+ unsigned long st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+
+#if defined(__ARMEB__)
+ unsigned short st_rdev;
+ unsigned short __pad2;
+#else
+ unsigned long st_rdev;
+#endif
+ unsigned long st_size;
+ unsigned long st_blksize;
+ unsigned long st_blocks;
+
+ unsigned long st_atime;
+ unsigned long st_atime_nsec;
+ unsigned long st_mtime;
+ unsigned long st_mtime_nsec;
+
+ unsigned long st_ctime;
+ unsigned long st_ctime_nsec;
+ unsigned long __unused[2];
+};
+
+/* Syscalls for ARM in ARM or Thumb modes :
+ * - registers are 32-bit
+ * - stack is 8-byte aligned
+ * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html)
+ * - syscall number is passed in r7
+ * - arguments are in r0, r1, r2, r3, r4, r5
+ * - the system call is performed by calling svc #0
+ * - syscall return comes in r0.
+ * - only lr is clobbered.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, ARM supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("r7") = (num); \
+ register long _arg1 __asm__ ("r0"); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("r7") = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("r7") = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("r7") = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("r7") = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ register long _arg4 __asm__ ("r3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r"(_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("r7") = (num); \
+ register long _arg1 __asm__ ("r0") = (long)(arg1); \
+ register long _arg2 __asm__ ("r1") = (long)(arg2); \
+ register long _arg3 __asm__ ("r2") = (long)(arg3); \
+ register long _arg4 __asm__ ("r3") = (long)(arg4); \
+ register long _arg5 __asm__ ("r4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "svc #0\n" \
+ : "=r" (_arg1) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc", "lr" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+ ".weak _start\n"
+ "_start:\n"
+#if defined(__THUMBEB__) || defined(__THUMBEL__)
+ /* We enter here in 32-bit mode but if some previous functions were in
+ * 16-bit mode, the assembler cannot know, so we need to tell it we're in
+ * 32-bit now, then switch to 16-bit (is there a better way to do it than
+ * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that
+ * it generates correct instructions. Note that we do not support thumb1.
+ */
+ ".code 32\n"
+ "add r0, pc, #1\n"
+ "bx r0\n"
+ ".code 16\n"
+#endif
+ "pop {%r0}\n" // argc was in the stack
+ "mov %r1, %sp\n" // argv = sp
+ "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ...
+ "add %r2, %r2, $4\n" // ... + 4
+ "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the
+ "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc)
+ "bl main\n" // main() returns the status code, we'll exit with it.
+ "movs r7, $1\n" // NR_exit == 1
+ "svc $0x00\n"
+ "");
+
+#endif // _NOLIBC_ARCH_ARM_H
diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h
new file mode 100644
index 000000000000..d7e7212346e2
--- /dev/null
+++ b/tools/include/nolibc/arch-i386.h
@@ -0,0 +1,219 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * i386 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_I386_H
+#define _NOLIBC_ARCH_I386_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
+
+/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
+ * exactly 56 bytes (stops before the unused array).
+ */
+struct sys_stat_struct {
+ unsigned long st_dev;
+ unsigned long st_ino;
+ unsigned short st_mode;
+ unsigned short st_nlink;
+ unsigned short st_uid;
+ unsigned short st_gid;
+
+ unsigned long st_rdev;
+ unsigned long st_size;
+ unsigned long st_blksize;
+ unsigned long st_blocks;
+
+ unsigned long st_atime;
+ unsigned long st_atime_nsec;
+ unsigned long st_mtime;
+ unsigned long st_mtime_nsec;
+
+ unsigned long st_ctime;
+ unsigned long st_ctime_nsec;
+ unsigned long __unused[2];
+};
+
+/* Syscalls for i386 :
+ * - mostly similar to x86_64
+ * - registers are 32-bit
+ * - syscall number is passed in eax
+ * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively
+ * - all registers are preserved (except eax of course)
+ * - the system call is performed by calling int $0x80
+ * - syscall return comes in eax
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ *
+ * Also, i386 supports the old_select syscall if newselect is not available
+ */
+#define __ARCH_WANT_SYS_OLD_SELECT
+
+#define my_syscall0(num) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ register long _arg3 __asm__ ("edx") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ register long _arg3 __asm__ ("edx") = (long)(arg3); \
+ register long _arg4 __asm__ ("esi") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("eax") = (num); \
+ register long _arg1 __asm__ ("ebx") = (long)(arg1); \
+ register long _arg2 __asm__ ("ecx") = (long)(arg2); \
+ register long _arg3 __asm__ ("edx") = (long)(arg3); \
+ register long _arg4 __asm__ ("esi") = (long)(arg4); \
+ register long _arg5 __asm__ ("edi") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "int $0x80\n" \
+ : "=a" (_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "0"(_num) \
+ : "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ long _eax = (long)(num); \
+ long _arg6 = (long)(arg6); /* Always in memory */ \
+ __asm__ volatile ( \
+ "pushl %[_arg6]\n\t" \
+ "pushl %%ebp\n\t" \
+ "movl 4(%%esp),%%ebp\n\t" \
+ "int $0x80\n\t" \
+ "popl %%ebp\n\t" \
+ "addl $4,%%esp\n\t" \
+ : "+a"(_eax) /* %eax */ \
+ : "b"(arg1), /* %ebx */ \
+ "c"(arg2), /* %ecx */ \
+ "d"(arg3), /* %edx */ \
+ "S"(arg4), /* %esi */ \
+ "D"(arg5), /* %edi */ \
+ [_arg6]"m"(_arg6) /* memory */ \
+ : "memory", "cc" \
+ ); \
+ _eax; \
+})
+
+/* startup code */
+/*
+ * i386 System V ABI mandates:
+ * 1) last pushed argument must be 16-byte aligned.
+ * 2) The deepest stack frame should be set to zero
+ *
+ */
+__asm__ (".section .text\n"
+ ".weak _start\n"
+ "_start:\n"
+ "pop %eax\n" // argc (first arg, %eax)
+ "mov %esp, %ebx\n" // argv[] (second arg, %ebx)
+ "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
+ "xor %ebp, %ebp\n" // zero the stack frame
+ "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before
+ "sub $4, %esp\n" // the call instruction (args are aligned)
+ "push %ecx\n" // push all registers on the stack so that we
+ "push %ebx\n" // support both regparm and plain stack modes
+ "push %eax\n"
+ "call main\n" // main() returns the status code in %eax
+ "mov %eax, %ebx\n" // retrieve exit code (32-bit int)
+ "movl $1, %eax\n" // NR_exit == 1
+ "int $0x80\n" // exit now
+ "hlt\n" // ensure it does not
+ "");
+
+#endif // _NOLIBC_ARCH_I386_H
diff --git a/tools/include/nolibc/arch-mips.h b/tools/include/nolibc/arch-mips.h
new file mode 100644
index 000000000000..5fc5b8029bff
--- /dev/null
+++ b/tools/include/nolibc/arch-mips.h
@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * MIPS specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_MIPS_H
+#define _NOLIBC_ARCH_MIPS_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_APPEND 0x0008
+#define O_NONBLOCK 0x0080
+#define O_CREAT 0x0100
+#define O_TRUNC 0x0200
+#define O_EXCL 0x0400
+#define O_NOCTTY 0x0800
+#define O_DIRECTORY 0x10000
+
+/* The struct returned by the stat() syscall. 88 bytes are returned by the
+ * syscall.
+ */
+struct sys_stat_struct {
+ unsigned int st_dev;
+ long st_pad1[3];
+ unsigned long st_ino;
+ unsigned int st_mode;
+ unsigned int st_nlink;
+ unsigned int st_uid;
+ unsigned int st_gid;
+ unsigned int st_rdev;
+ long st_pad2[2];
+ long st_size;
+ long st_pad3;
+
+ long st_atime;
+ long st_atime_nsec;
+ long st_mtime;
+ long st_mtime_nsec;
+
+ long st_ctime;
+ long st_ctime_nsec;
+ long st_blksize;
+ long st_blocks;
+ long st_pad4[14];
+};
+
+/* Syscalls for MIPS ABI O32 :
+ * - WARNING! there's always a delayed slot!
+ * - WARNING again, the syntax is different, registers take a '$' and numbers
+ * do not.
+ * - registers are 32-bit
+ * - stack is 8-byte aligned
+ * - syscall number is passed in v0 (starts at 0xfa0).
+ * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to
+ * leave some room in the stack for the callee to save a0..a3 if needed.
+ * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are
+ * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as
+ * scall32-o32.S in the kernel sources.
+ * - the system call is performed by calling "syscall"
+ * - syscall return comes in v0, and register a3 needs to be checked to know
+ * if an error occurred, in which case errno is in v0.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ */
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "r"(_num) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3"); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r"(_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "syscall\n" \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("v0") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "addiu $sp, $sp, -32\n" \
+ "sw %7, 16($sp)\n" \
+ "syscall\n " \
+ "addiu $sp, $sp, 32\n" \
+ : "=r" (_num), "=r"(_arg4) \
+ : "0"(_num), \
+ "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \
+ : "memory", "cc", "at", "v1", "hi", "lo", \
+ "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
+ ); \
+ _arg4 ? -_num : _num; \
+})
+
+/* startup code, note that it's called __start on MIPS */
+__asm__ (".section .text\n"
+ ".weak __start\n"
+ ".set nomips16\n"
+ ".set noreorder\n"
+ ".option pic0\n"
+ ".ent __start\n"
+ "__start:\n"
+ "lw $a0,($sp)\n" // argc was in the stack
+ "addiu $a1, $sp, 4\n" // argv = sp + 4
+ "sll $a2, $a0, 2\n" // a2 = argc * 4
+ "add $a2, $a2, $a1\n" // envp = argv + 4*argc ...
+ "addiu $a2, $a2, 4\n" // ... + 4
+ "li $t0, -8\n"
+ "and $sp, $sp, $t0\n" // sp must be 8-byte aligned
+ "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there!
+ "jal main\n" // main() returns the status code, we'll exit with it.
+ "nop\n" // delayed slot
+ "move $a0, $v0\n" // retrieve 32-bit exit code from v0
+ "li $v0, 4001\n" // NR_exit == 4001
+ "syscall\n"
+ ".end __start\n"
+ "");
+
+#endif // _NOLIBC_ARCH_MIPS_H
diff --git a/tools/include/nolibc/arch-riscv.h b/tools/include/nolibc/arch-riscv.h
new file mode 100644
index 000000000000..95e2b7924925
--- /dev/null
+++ b/tools/include/nolibc/arch-riscv.h
@@ -0,0 +1,204 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * RISCV (32 and 64) specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_RISCV_H
+#define _NOLIBC_ARCH_RISCV_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x100
+#define O_EXCL 0x200
+#define O_NOCTTY 0x400
+#define O_TRUNC 0x1000
+#define O_APPEND 0x2000
+#define O_NONBLOCK 0x4000
+#define O_DIRECTORY 0x200000
+
+struct sys_stat_struct {
+ unsigned long st_dev; /* Device. */
+ unsigned long st_ino; /* File serial number. */
+ unsigned int st_mode; /* File mode. */
+ unsigned int st_nlink; /* Link count. */
+ unsigned int st_uid; /* User ID of the file's owner. */
+ unsigned int st_gid; /* Group ID of the file's group. */
+ unsigned long st_rdev; /* Device number, if device. */
+ unsigned long __pad1;
+ long st_size; /* Size of file, in bytes. */
+ int st_blksize; /* Optimal block size for I/O. */
+ int __pad2;
+ long st_blocks; /* Number 512-byte blocks allocated. */
+ long st_atime; /* Time of last access. */
+ unsigned long st_atime_nsec;
+ long st_mtime; /* Time of last modification. */
+ unsigned long st_mtime_nsec;
+ long st_ctime; /* Time of last status change. */
+ unsigned long st_ctime_nsec;
+ unsigned int __unused4;
+ unsigned int __unused5;
+};
+
+#if __riscv_xlen == 64
+#define PTRLOG "3"
+#define SZREG "8"
+#elif __riscv_xlen == 32
+#define PTRLOG "2"
+#define SZREG "4"
+#endif
+
+/* Syscalls for RISCV :
+ * - stack is 16-byte aligned
+ * - syscall number is passed in a7
+ * - arguments are in a0, a1, a2, a3, a4, a5
+ * - the system call is performed by calling ecall
+ * - syscall return comes in a0
+ * - the arguments are cast to long and assigned into the target
+ * registers which are then simply passed as registers to the asm code,
+ * so that we don't have to experience issues with register constraints.
+ *
+ * On riscv, select() is not implemented so we have to use pselect6().
+ */
+#define __ARCH_WANT_SYS_PSELECT6
+
+#define my_syscall0(num) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0"); \
+ \
+ __asm__ volatile ( \
+ "ecall\n\t" \
+ : "=r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "ecall\n\t" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 __asm__ ("a4") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ register long _num __asm__ ("a7") = (num); \
+ register long _arg1 __asm__ ("a0") = (long)(arg1); \
+ register long _arg2 __asm__ ("a1") = (long)(arg2); \
+ register long _arg3 __asm__ ("a2") = (long)(arg3); \
+ register long _arg4 __asm__ ("a3") = (long)(arg4); \
+ register long _arg5 __asm__ ("a4") = (long)(arg5); \
+ register long _arg6 __asm__ ("a5") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "ecall\n" \
+ : "+r"(_arg1) \
+ : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \
+ "r"(_num) \
+ : "memory", "cc" \
+ ); \
+ _arg1; \
+})
+
+/* startup code */
+__asm__ (".section .text\n"
+ ".weak _start\n"
+ "_start:\n"
+ ".option push\n"
+ ".option norelax\n"
+ "lla gp, __global_pointer$\n"
+ ".option pop\n"
+ "ld a0, 0(sp)\n" // argc (a0) was in the stack
+ "add a1, sp, "SZREG"\n" // argv (a1) = sp
+ "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ...
+ "add a2, a2, "SZREG"\n" // + SZREG (skip null)
+ "add a2,a2,a1\n" // + argv
+ "andi sp,a1,-16\n" // sp must be 16-byte aligned
+ "call main\n" // main() returns the status code, we'll exit with it.
+ "li a7, 93\n" // NR_exit == 93
+ "ecall\n"
+ "");
+
+#endif // _NOLIBC_ARCH_RISCV_H
diff --git a/tools/include/nolibc/arch-x86_64.h b/tools/include/nolibc/arch-x86_64.h
new file mode 100644
index 000000000000..0e1e9eb8545d
--- /dev/null
+++ b/tools/include/nolibc/arch-x86_64.h
@@ -0,0 +1,215 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * x86_64 specific definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ARCH_X86_64_H
+#define _NOLIBC_ARCH_X86_64_H
+
+/* O_* macros for fcntl/open are architecture-specific */
+#define O_RDONLY 0
+#define O_WRONLY 1
+#define O_RDWR 2
+#define O_CREAT 0x40
+#define O_EXCL 0x80
+#define O_NOCTTY 0x100
+#define O_TRUNC 0x200
+#define O_APPEND 0x400
+#define O_NONBLOCK 0x800
+#define O_DIRECTORY 0x10000
+
+/* The struct returned by the stat() syscall, equivalent to stat64(). The
+ * syscall returns 116 bytes and stops in the middle of __unused.
+ */
+struct sys_stat_struct {
+ unsigned long st_dev;
+ unsigned long st_ino;
+ unsigned long st_nlink;
+ unsigned int st_mode;
+ unsigned int st_uid;
+
+ unsigned int st_gid;
+ unsigned int __pad0;
+ unsigned long st_rdev;
+ long st_size;
+ long st_blksize;
+
+ long st_blocks;
+ unsigned long st_atime;
+ unsigned long st_atime_nsec;
+ unsigned long st_mtime;
+
+ unsigned long st_mtime_nsec;
+ unsigned long st_ctime;
+ unsigned long st_ctime_nsec;
+ long __unused[3];
+};
+
+/* Syscalls for x86_64 :
+ * - registers are 64-bit
+ * - syscall number is passed in rax
+ * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
+ * - the system call is performed by calling the syscall instruction
+ * - syscall return comes in rax
+ * - rcx and r11 are clobbered, others are preserved.
+ * - the arguments are cast to long and assigned into the target registers
+ * which are then simply passed as registers to the asm code, so that we
+ * don't have to experience issues with register constraints.
+ * - the syscall number is always specified last in order to allow to force
+ * some registers before (gcc refuses a %-register at the last position).
+ * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
+ * Calling Conventions.
+ *
+ * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/home
+ *
+ */
+
+#define my_syscall0(num) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall1(num, arg1) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall2(num, arg1, arg2) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall3(num, arg1, arg2, arg3) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall4(num, arg1, arg2, arg3, arg4) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ register long _arg4 __asm__ ("r10") = (long)(arg4); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ register long _arg4 __asm__ ("r10") = (long)(arg4); \
+ register long _arg5 __asm__ ("r8") = (long)(arg5); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
+({ \
+ long _ret; \
+ register long _num __asm__ ("rax") = (num); \
+ register long _arg1 __asm__ ("rdi") = (long)(arg1); \
+ register long _arg2 __asm__ ("rsi") = (long)(arg2); \
+ register long _arg3 __asm__ ("rdx") = (long)(arg3); \
+ register long _arg4 __asm__ ("r10") = (long)(arg4); \
+ register long _arg5 __asm__ ("r8") = (long)(arg5); \
+ register long _arg6 __asm__ ("r9") = (long)(arg6); \
+ \
+ __asm__ volatile ( \
+ "syscall\n" \
+ : "=a"(_ret) \
+ : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
+ "r"(_arg6), "0"(_num) \
+ : "rcx", "r11", "memory", "cc" \
+ ); \
+ _ret; \
+})
+
+/* startup code */
+/*
+ * x86-64 System V ABI mandates:
+ * 1) %rsp must be 16-byte aligned right before the function call.
+ * 2) The deepest stack frame should be zero (the %rbp).
+ *
+ */
+__asm__ (".section .text\n"
+ ".weak _start\n"
+ "_start:\n"
+ "pop %rdi\n" // argc (first arg, %rdi)
+ "mov %rsp, %rsi\n" // argv[] (second arg, %rsi)
+ "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
+ "xor %ebp, %ebp\n" // zero the stack frame
+ "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call
+ "call main\n" // main() returns the status code, we'll exit with it.
+ "mov %eax, %edi\n" // retrieve exit code (32 bit)
+ "mov $60, %eax\n" // NR_exit == 60
+ "syscall\n" // really exit
+ "hlt\n" // ensure it does not return
+ "");
+
+#endif // _NOLIBC_ARCH_X86_64_H
diff --git a/tools/include/nolibc/arch.h b/tools/include/nolibc/arch.h
new file mode 100644
index 000000000000..4c6992321b0d
--- /dev/null
+++ b/tools/include/nolibc/arch.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+/* Below comes the architecture-specific code. For each architecture, we have
+ * the syscall declarations and the _start code definition. This is the only
+ * global part. On all architectures the kernel puts everything in the stack
+ * before jumping to _start just above us, without any return address (_start
+ * is not a function but an entry pint). So at the stack pointer we find argc.
+ * Then argv[] begins, and ends at the first NULL. Then we have envp which
+ * starts and ends with a NULL as well. So envp=argv+argc+1.
+ */
+
+#ifndef _NOLIBC_ARCH_H
+#define _NOLIBC_ARCH_H
+
+#if defined(__x86_64__)
+#include "arch-x86_64.h"
+#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
+#include "arch-i386.h"
+#elif defined(__ARM_EABI__)
+#include "arch-arm.h"
+#elif defined(__aarch64__)
+#include "arch-aarch64.h"
+#elif defined(__mips__) && defined(_ABIO32)
+#include "arch-mips.h"
+#elif defined(__riscv)
+#include "arch-riscv.h"
+#endif
+
+#endif /* _NOLIBC_ARCH_H */
diff --git a/tools/include/nolibc/ctype.h b/tools/include/nolibc/ctype.h
new file mode 100644
index 000000000000..e3000b2992d7
--- /dev/null
+++ b/tools/include/nolibc/ctype.h
@@ -0,0 +1,99 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * ctype function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_CTYPE_H
+#define _NOLIBC_CTYPE_H
+
+#include "std.h"
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+static __attribute__((unused))
+int isascii(int c)
+{
+ /* 0x00..0x7f */
+ return (unsigned int)c <= 0x7f;
+}
+
+static __attribute__((unused))
+int isblank(int c)
+{
+ return c == '\t' || c == ' ';
+}
+
+static __attribute__((unused))
+int iscntrl(int c)
+{
+ /* 0x00..0x1f, 0x7f */
+ return (unsigned int)c < 0x20 || c == 0x7f;
+}
+
+static __attribute__((unused))
+int isdigit(int c)
+{
+ return (unsigned int)(c - '0') < 10;
+}
+
+static __attribute__((unused))
+int isgraph(int c)
+{
+ /* 0x21..0x7e */
+ return (unsigned int)(c - 0x21) < 0x5e;
+}
+
+static __attribute__((unused))
+int islower(int c)
+{
+ return (unsigned int)(c - 'a') < 26;
+}
+
+static __attribute__((unused))
+int isprint(int c)
+{
+ /* 0x20..0x7e */
+ return (unsigned int)(c - 0x20) < 0x5f;
+}
+
+static __attribute__((unused))
+int isspace(int c)
+{
+ /* \t is 0x9, \n is 0xA, \v is 0xB, \f is 0xC, \r is 0xD */
+ return ((unsigned int)c == ' ') || (unsigned int)(c - 0x09) < 5;
+}
+
+static __attribute__((unused))
+int isupper(int c)
+{
+ return (unsigned int)(c - 'A') < 26;
+}
+
+static __attribute__((unused))
+int isxdigit(int c)
+{
+ return isdigit(c) || (unsigned int)(c - 'A') < 6 || (unsigned int)(c - 'a') < 6;
+}
+
+static __attribute__((unused))
+int isalpha(int c)
+{
+ return islower(c) || isupper(c);
+}
+
+static __attribute__((unused))
+int isalnum(int c)
+{
+ return isalpha(c) || isdigit(c);
+}
+
+static __attribute__((unused))
+int ispunct(int c)
+{
+ return isgraph(c) && !isalnum(c);
+}
+
+#endif /* _NOLIBC_CTYPE_H */
diff --git a/tools/include/nolibc/errno.h b/tools/include/nolibc/errno.h
new file mode 100644
index 000000000000..06893d6dfb7a
--- /dev/null
+++ b/tools/include/nolibc/errno.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Minimal errno definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_ERRNO_H
+#define _NOLIBC_ERRNO_H
+
+#include <asm/errno.h>
+
+/* this way it will be removed if unused */
+static int errno;
+
+#ifndef NOLIBC_IGNORE_ERRNO
+#define SET_ERRNO(v) do { errno = (v); } while (0)
+#else
+#define SET_ERRNO(v) do { } while (0)
+#endif
+
+
+/* errno codes all ensure that they will not conflict with a valid pointer
+ * because they all correspond to the highest addressable memory page.
+ */
+#define MAX_ERRNO 4095
+
+#endif /* _NOLIBC_ERRNO_H */
diff --git a/tools/include/nolibc/nolibc.h b/tools/include/nolibc/nolibc.h
index c1c285fe494a..b2bc48d3cfe4 100644
--- a/tools/include/nolibc/nolibc.h
+++ b/tools/include/nolibc/nolibc.h
@@ -57,22 +57,32 @@
* having to specify anything.
*
* Finally some very common libc-level functions are provided. It is the case
- * for a few functions usually found in string.h, ctype.h, or stdlib.h. Nothing
- * is currently provided regarding stdio emulation.
+ * for a few functions usually found in string.h, ctype.h, or stdlib.h.
*
- * The macro NOLIBC is always defined, so that it is possible for a program to
- * check this macro to know if it is being built against and decide to disable
- * some features or simply not to include some standard libc files.
- *
- * Ideally this file should be split in multiple files for easier long term
- * maintenance, but provided as a single file as it is now, it's quite
- * convenient to use. Maybe some variations involving a set of includes at the
- * top could work.
+ * The nolibc.h file is only a convenient entry point which includes all other
+ * files. It also defines the NOLIBC macro, so that it is possible for a
+ * program to check this macro to know if it is being built against and decide
+ * to disable some features or simply not to include some standard libc files.
*
* A simple static executable may be built this way :
* $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
* -static -include nolibc.h -o hello hello.c -lgcc
*
+ * Simple programs meant to be reasonably portable to various libc and using
+ * only a few common includes, may also be built by simply making the include
+ * path point to the nolibc directory:
+ * $ gcc -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ * -I../nolibc -o hello hello.c -lgcc
+ *
+ * The available standard (but limited) include files are:
+ * ctype.h, errno.h, signal.h, stdio.h, stdlib.h, string.h, time.h
+ *
+ * In addition, the following ones are expected to be provided by the compiler:
+ * float.h, stdarg.h, stddef.h
+ *
+ * The following ones which are part to the C standard are not provided:
+ * assert.h, locale.h, math.h, setjmp.h, limits.h
+ *
* A very useful calling convention table may be found here :
* http://man7.org/linux/man-pages/man2/syscall.2.html
*
@@ -80,2502 +90,22 @@
* https://w3challs.com/syscalls/
*
*/
+#ifndef _NOLIBC_H
+#define _NOLIBC_H
-#include <asm/unistd.h>
-#include <asm/ioctls.h>
-#include <asm/errno.h>
-#include <linux/fs.h>
-#include <linux/loop.h>
-#include <linux/time.h>
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+#include "ctype.h"
+#include "signal.h"
+#include "stdio.h"
+#include "stdlib.h"
+#include "string.h"
+#include "time.h"
+#include "unistd.h"
+/* Used by programs to avoid std includes */
#define NOLIBC
-/* this way it will be removed if unused */
-static int errno;
-
-#ifndef NOLIBC_IGNORE_ERRNO
-#define SET_ERRNO(v) do { errno = (v); } while (0)
-#else
-#define SET_ERRNO(v) do { } while (0)
-#endif
-
-/* errno codes all ensure that they will not conflict with a valid pointer
- * because they all correspond to the highest addressable memory page.
- */
-#define MAX_ERRNO 4095
-
-/* Declare a few quite common macros and types that usually are in stdlib.h,
- * stdint.h, ctype.h, unistd.h and a few other common locations.
- */
-
-#define NULL ((void *)0)
-
-/* stdint types */
-typedef unsigned char uint8_t;
-typedef signed char int8_t;
-typedef unsigned short uint16_t;
-typedef signed short int16_t;
-typedef unsigned int uint32_t;
-typedef signed int int32_t;
-typedef unsigned long long uint64_t;
-typedef signed long long int64_t;
-typedef unsigned long size_t;
-typedef signed long ssize_t;
-typedef unsigned long uintptr_t;
-typedef signed long intptr_t;
-typedef signed long ptrdiff_t;
-
-/* for stat() */
-typedef unsigned int dev_t;
-typedef unsigned long ino_t;
-typedef unsigned int mode_t;
-typedef signed int pid_t;
-typedef unsigned int uid_t;
-typedef unsigned int gid_t;
-typedef unsigned long nlink_t;
-typedef signed long off_t;
-typedef signed long blksize_t;
-typedef signed long blkcnt_t;
-typedef signed long time_t;
-
-/* for poll() */
-struct pollfd {
- int fd;
- short int events;
- short int revents;
-};
-
-/* for getdents64() */
-struct linux_dirent64 {
- uint64_t d_ino;
- int64_t d_off;
- unsigned short d_reclen;
- unsigned char d_type;
- char d_name[];
-};
-
-/* commonly an fd_set represents 256 FDs */
-#define FD_SETSIZE 256
-typedef struct { uint32_t fd32[FD_SETSIZE/32]; } fd_set;
-
-/* needed by wait4() */
-struct rusage {
- struct timeval ru_utime;
- struct timeval ru_stime;
- long ru_maxrss;
- long ru_ixrss;
- long ru_idrss;
- long ru_isrss;
- long ru_minflt;
- long ru_majflt;
- long ru_nswap;
- long ru_inblock;
- long ru_oublock;
- long ru_msgsnd;
- long ru_msgrcv;
- long ru_nsignals;
- long ru_nvcsw;
- long ru_nivcsw;
-};
-
-/* stat flags (WARNING, octal here) */
-#define S_IFDIR 0040000
-#define S_IFCHR 0020000
-#define S_IFBLK 0060000
-#define S_IFREG 0100000
-#define S_IFIFO 0010000
-#define S_IFLNK 0120000
-#define S_IFSOCK 0140000
-#define S_IFMT 0170000
-
-#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR)
-#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR)
-#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK)
-#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG)
-#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
-#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK)
-#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
-
-#define DT_UNKNOWN 0
-#define DT_FIFO 1
-#define DT_CHR 2
-#define DT_DIR 4
-#define DT_BLK 6
-#define DT_REG 8
-#define DT_LNK 10
-#define DT_SOCK 12
-
-/* all the *at functions */
-#ifndef AT_FDCWD
-#define AT_FDCWD -100
-#endif
-
-/* lseek */
-#define SEEK_SET 0
-#define SEEK_CUR 1
-#define SEEK_END 2
-
-/* reboot */
-#define LINUX_REBOOT_MAGIC1 0xfee1dead
-#define LINUX_REBOOT_MAGIC2 0x28121969
-#define LINUX_REBOOT_CMD_HALT 0xcdef0123
-#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc
-#define LINUX_REBOOT_CMD_RESTART 0x01234567
-#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2
-
-
-/* The format of the struct as returned by the libc to the application, which
- * significantly differs from the format returned by the stat() syscall flavours.
- */
-struct stat {
- dev_t st_dev; /* ID of device containing file */
- ino_t st_ino; /* inode number */
- mode_t st_mode; /* protection */
- nlink_t st_nlink; /* number of hard links */
- uid_t st_uid; /* user ID of owner */
- gid_t st_gid; /* group ID of owner */
- dev_t st_rdev; /* device ID (if special file) */
- off_t st_size; /* total size, in bytes */
- blksize_t st_blksize; /* blocksize for file system I/O */
- blkcnt_t st_blocks; /* number of 512B blocks allocated */
- time_t st_atime; /* time of last access */
- time_t st_mtime; /* time of last modification */
- time_t st_ctime; /* time of last status change */
-};
-
-#define WEXITSTATUS(status) (((status) & 0xff00) >> 8)
-#define WIFEXITED(status) (((status) & 0x7f) == 0)
-
-/* for SIGCHLD */
-#include <asm/signal.h>
-
-/* Below comes the architecture-specific code. For each architecture, we have
- * the syscall declarations and the _start code definition. This is the only
- * global part. On all architectures the kernel puts everything in the stack
- * before jumping to _start just above us, without any return address (_start
- * is not a function but an entry pint). So at the stack pointer we find argc.
- * Then argv[] begins, and ends at the first NULL. Then we have envp which
- * starts and ends with a NULL as well. So envp=argv+argc+1.
- */
-
-#if defined(__x86_64__)
-/* Syscalls for x86_64 :
- * - registers are 64-bit
- * - syscall number is passed in rax
- * - arguments are in rdi, rsi, rdx, r10, r8, r9 respectively
- * - the system call is performed by calling the syscall instruction
- * - syscall return comes in rax
- * - rcx and r11 are clobbered, others are preserved.
- * - the arguments are cast to long and assigned into the target registers
- * which are then simply passed as registers to the asm code, so that we
- * don't have to experience issues with register constraints.
- * - the syscall number is always specified last in order to allow to force
- * some registers before (gcc refuses a %-register at the last position).
- * - see also x86-64 ABI section A.2 AMD64 Linux Kernel Conventions, A.2.1
- * Calling Conventions.
- *
- * Link x86-64 ABI: https://gitlab.com/x86-psABIs/x86-64-ABI/-/wikis/x86-64-psABI
- *
- */
-
-#define my_syscall0(num) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall1(num, arg1) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- register long _arg1 asm("rdi") = (long)(arg1); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "r"(_arg1), \
- "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall2(num, arg1, arg2) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- register long _arg1 asm("rdi") = (long)(arg1); \
- register long _arg2 asm("rsi") = (long)(arg2); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "r"(_arg1), "r"(_arg2), \
- "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- register long _arg1 asm("rdi") = (long)(arg1); \
- register long _arg2 asm("rsi") = (long)(arg2); \
- register long _arg3 asm("rdx") = (long)(arg3); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
- "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- register long _arg1 asm("rdi") = (long)(arg1); \
- register long _arg2 asm("rsi") = (long)(arg2); \
- register long _arg3 asm("rdx") = (long)(arg3); \
- register long _arg4 asm("r10") = (long)(arg4); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
- "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- register long _arg1 asm("rdi") = (long)(arg1); \
- register long _arg2 asm("rsi") = (long)(arg2); \
- register long _arg3 asm("rdx") = (long)(arg3); \
- register long _arg4 asm("r10") = (long)(arg4); \
- register long _arg5 asm("r8") = (long)(arg5); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
-({ \
- long _ret; \
- register long _num asm("rax") = (num); \
- register long _arg1 asm("rdi") = (long)(arg1); \
- register long _arg2 asm("rsi") = (long)(arg2); \
- register long _arg3 asm("rdx") = (long)(arg3); \
- register long _arg4 asm("r10") = (long)(arg4); \
- register long _arg5 asm("r8") = (long)(arg5); \
- register long _arg6 asm("r9") = (long)(arg6); \
- \
- asm volatile ( \
- "syscall\n" \
- : "=a"(_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "r"(_arg6), "0"(_num) \
- : "rcx", "r11", "memory", "cc" \
- ); \
- _ret; \
-})
-
-/* startup code */
-/*
- * x86-64 System V ABI mandates:
- * 1) %rsp must be 16-byte aligned right before the function call.
- * 2) The deepest stack frame should be zero (the %rbp).
- *
- */
-asm(".section .text\n"
- ".global _start\n"
- "_start:\n"
- "pop %rdi\n" // argc (first arg, %rdi)
- "mov %rsp, %rsi\n" // argv[] (second arg, %rsi)
- "lea 8(%rsi,%rdi,8),%rdx\n" // then a NULL then envp (third arg, %rdx)
- "xor %ebp, %ebp\n" // zero the stack frame
- "and $-16, %rsp\n" // x86 ABI : esp must be 16-byte aligned before call
- "call main\n" // main() returns the status code, we'll exit with it.
- "mov %eax, %edi\n" // retrieve exit code (32 bit)
- "mov $60, %eax\n" // NR_exit == 60
- "syscall\n" // really exit
- "hlt\n" // ensure it does not return
- "");
-
-/* fcntl / open */
-#define O_RDONLY 0
-#define O_WRONLY 1
-#define O_RDWR 2
-#define O_CREAT 0x40
-#define O_EXCL 0x80
-#define O_NOCTTY 0x100
-#define O_TRUNC 0x200
-#define O_APPEND 0x400
-#define O_NONBLOCK 0x800
-#define O_DIRECTORY 0x10000
-
-/* The struct returned by the stat() syscall, equivalent to stat64(). The
- * syscall returns 116 bytes and stops in the middle of __unused.
- */
-struct sys_stat_struct {
- unsigned long st_dev;
- unsigned long st_ino;
- unsigned long st_nlink;
- unsigned int st_mode;
- unsigned int st_uid;
-
- unsigned int st_gid;
- unsigned int __pad0;
- unsigned long st_rdev;
- long st_size;
- long st_blksize;
-
- long st_blocks;
- unsigned long st_atime;
- unsigned long st_atime_nsec;
- unsigned long st_mtime;
-
- unsigned long st_mtime_nsec;
- unsigned long st_ctime;
- unsigned long st_ctime_nsec;
- long __unused[3];
-};
-
-#elif defined(__i386__) || defined(__i486__) || defined(__i586__) || defined(__i686__)
-/* Syscalls for i386 :
- * - mostly similar to x86_64
- * - registers are 32-bit
- * - syscall number is passed in eax
- * - arguments are in ebx, ecx, edx, esi, edi, ebp respectively
- * - all registers are preserved (except eax of course)
- * - the system call is performed by calling int $0x80
- * - syscall return comes in eax
- * - the arguments are cast to long and assigned into the target registers
- * which are then simply passed as registers to the asm code, so that we
- * don't have to experience issues with register constraints.
- * - the syscall number is always specified last in order to allow to force
- * some registers before (gcc refuses a %-register at the last position).
- *
- * Also, i386 supports the old_select syscall if newselect is not available
- */
-#define __ARCH_WANT_SYS_OLD_SELECT
-
-#define my_syscall0(num) \
-({ \
- long _ret; \
- register long _num asm("eax") = (num); \
- \
- asm volatile ( \
- "int $0x80\n" \
- : "=a" (_ret) \
- : "0"(_num) \
- : "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall1(num, arg1) \
-({ \
- long _ret; \
- register long _num asm("eax") = (num); \
- register long _arg1 asm("ebx") = (long)(arg1); \
- \
- asm volatile ( \
- "int $0x80\n" \
- : "=a" (_ret) \
- : "r"(_arg1), \
- "0"(_num) \
- : "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall2(num, arg1, arg2) \
-({ \
- long _ret; \
- register long _num asm("eax") = (num); \
- register long _arg1 asm("ebx") = (long)(arg1); \
- register long _arg2 asm("ecx") = (long)(arg2); \
- \
- asm volatile ( \
- "int $0x80\n" \
- : "=a" (_ret) \
- : "r"(_arg1), "r"(_arg2), \
- "0"(_num) \
- : "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3) \
-({ \
- long _ret; \
- register long _num asm("eax") = (num); \
- register long _arg1 asm("ebx") = (long)(arg1); \
- register long _arg2 asm("ecx") = (long)(arg2); \
- register long _arg3 asm("edx") = (long)(arg3); \
- \
- asm volatile ( \
- "int $0x80\n" \
- : "=a" (_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
- "0"(_num) \
- : "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4) \
-({ \
- long _ret; \
- register long _num asm("eax") = (num); \
- register long _arg1 asm("ebx") = (long)(arg1); \
- register long _arg2 asm("ecx") = (long)(arg2); \
- register long _arg3 asm("edx") = (long)(arg3); \
- register long _arg4 asm("esi") = (long)(arg4); \
- \
- asm volatile ( \
- "int $0x80\n" \
- : "=a" (_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
- "0"(_num) \
- : "memory", "cc" \
- ); \
- _ret; \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
-({ \
- long _ret; \
- register long _num asm("eax") = (num); \
- register long _arg1 asm("ebx") = (long)(arg1); \
- register long _arg2 asm("ecx") = (long)(arg2); \
- register long _arg3 asm("edx") = (long)(arg3); \
- register long _arg4 asm("esi") = (long)(arg4); \
- register long _arg5 asm("edi") = (long)(arg5); \
- \
- asm volatile ( \
- "int $0x80\n" \
- : "=a" (_ret) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "0"(_num) \
- : "memory", "cc" \
- ); \
- _ret; \
-})
-
-/* startup code */
-/*
- * i386 System V ABI mandates:
- * 1) last pushed argument must be 16-byte aligned.
- * 2) The deepest stack frame should be set to zero
- *
- */
-asm(".section .text\n"
- ".global _start\n"
- "_start:\n"
- "pop %eax\n" // argc (first arg, %eax)
- "mov %esp, %ebx\n" // argv[] (second arg, %ebx)
- "lea 4(%ebx,%eax,4),%ecx\n" // then a NULL then envp (third arg, %ecx)
- "xor %ebp, %ebp\n" // zero the stack frame
- "and $-16, %esp\n" // x86 ABI : esp must be 16-byte aligned before
- "sub $4, %esp\n" // the call instruction (args are aligned)
- "push %ecx\n" // push all registers on the stack so that we
- "push %ebx\n" // support both regparm and plain stack modes
- "push %eax\n"
- "call main\n" // main() returns the status code in %eax
- "mov %eax, %ebx\n" // retrieve exit code (32-bit int)
- "movl $1, %eax\n" // NR_exit == 1
- "int $0x80\n" // exit now
- "hlt\n" // ensure it does not
- "");
-
-/* fcntl / open */
-#define O_RDONLY 0
-#define O_WRONLY 1
-#define O_RDWR 2
-#define O_CREAT 0x40
-#define O_EXCL 0x80
-#define O_NOCTTY 0x100
-#define O_TRUNC 0x200
-#define O_APPEND 0x400
-#define O_NONBLOCK 0x800
-#define O_DIRECTORY 0x10000
-
-/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
- * exactly 56 bytes (stops before the unused array).
- */
-struct sys_stat_struct {
- unsigned long st_dev;
- unsigned long st_ino;
- unsigned short st_mode;
- unsigned short st_nlink;
- unsigned short st_uid;
- unsigned short st_gid;
-
- unsigned long st_rdev;
- unsigned long st_size;
- unsigned long st_blksize;
- unsigned long st_blocks;
-
- unsigned long st_atime;
- unsigned long st_atime_nsec;
- unsigned long st_mtime;
- unsigned long st_mtime_nsec;
-
- unsigned long st_ctime;
- unsigned long st_ctime_nsec;
- unsigned long __unused[2];
-};
-
-#elif defined(__ARM_EABI__)
-/* Syscalls for ARM in ARM or Thumb modes :
- * - registers are 32-bit
- * - stack is 8-byte aligned
- * ( http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.faqs/ka4127.html)
- * - syscall number is passed in r7
- * - arguments are in r0, r1, r2, r3, r4, r5
- * - the system call is performed by calling svc #0
- * - syscall return comes in r0.
- * - only lr is clobbered.
- * - the arguments are cast to long and assigned into the target registers
- * which are then simply passed as registers to the asm code, so that we
- * don't have to experience issues with register constraints.
- * - the syscall number is always specified last in order to allow to force
- * some registers before (gcc refuses a %-register at the last position).
- *
- * Also, ARM supports the old_select syscall if newselect is not available
- */
-#define __ARCH_WANT_SYS_OLD_SELECT
-
-#define my_syscall0(num) \
-({ \
- register long _num asm("r7") = (num); \
- register long _arg1 asm("r0"); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_num) \
- : "memory", "cc", "lr" \
- ); \
- _arg1; \
-})
-
-#define my_syscall1(num, arg1) \
-({ \
- register long _num asm("r7") = (num); \
- register long _arg1 asm("r0") = (long)(arg1); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), \
- "r"(_num) \
- : "memory", "cc", "lr" \
- ); \
- _arg1; \
-})
-
-#define my_syscall2(num, arg1, arg2) \
-({ \
- register long _num asm("r7") = (num); \
- register long _arg1 asm("r0") = (long)(arg1); \
- register long _arg2 asm("r1") = (long)(arg2); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), "r"(_arg2), \
- "r"(_num) \
- : "memory", "cc", "lr" \
- ); \
- _arg1; \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3) \
-({ \
- register long _num asm("r7") = (num); \
- register long _arg1 asm("r0") = (long)(arg1); \
- register long _arg2 asm("r1") = (long)(arg2); \
- register long _arg3 asm("r2") = (long)(arg3); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
- "r"(_num) \
- : "memory", "cc", "lr" \
- ); \
- _arg1; \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4) \
-({ \
- register long _num asm("r7") = (num); \
- register long _arg1 asm("r0") = (long)(arg1); \
- register long _arg2 asm("r1") = (long)(arg2); \
- register long _arg3 asm("r2") = (long)(arg3); \
- register long _arg4 asm("r3") = (long)(arg4); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
- "r"(_num) \
- : "memory", "cc", "lr" \
- ); \
- _arg1; \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
-({ \
- register long _num asm("r7") = (num); \
- register long _arg1 asm("r0") = (long)(arg1); \
- register long _arg2 asm("r1") = (long)(arg2); \
- register long _arg3 asm("r2") = (long)(arg3); \
- register long _arg4 asm("r3") = (long)(arg4); \
- register long _arg5 asm("r4") = (long)(arg5); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r" (_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "r"(_num) \
- : "memory", "cc", "lr" \
- ); \
- _arg1; \
-})
-
-/* startup code */
-asm(".section .text\n"
- ".global _start\n"
- "_start:\n"
-#if defined(__THUMBEB__) || defined(__THUMBEL__)
- /* We enter here in 32-bit mode but if some previous functions were in
- * 16-bit mode, the assembler cannot know, so we need to tell it we're in
- * 32-bit now, then switch to 16-bit (is there a better way to do it than
- * adding 1 by hand ?) and tell the asm we're now in 16-bit mode so that
- * it generates correct instructions. Note that we do not support thumb1.
- */
- ".code 32\n"
- "add r0, pc, #1\n"
- "bx r0\n"
- ".code 16\n"
-#endif
- "pop {%r0}\n" // argc was in the stack
- "mov %r1, %sp\n" // argv = sp
- "add %r2, %r1, %r0, lsl #2\n" // envp = argv + 4*argc ...
- "add %r2, %r2, $4\n" // ... + 4
- "and %r3, %r1, $-8\n" // AAPCS : sp must be 8-byte aligned in the
- "mov %sp, %r3\n" // callee, an bl doesn't push (lr=pc)
- "bl main\n" // main() returns the status code, we'll exit with it.
- "movs r7, $1\n" // NR_exit == 1
- "svc $0x00\n"
- "");
-
-/* fcntl / open */
-#define O_RDONLY 0
-#define O_WRONLY 1
-#define O_RDWR 2
-#define O_CREAT 0x40
-#define O_EXCL 0x80
-#define O_NOCTTY 0x100
-#define O_TRUNC 0x200
-#define O_APPEND 0x400
-#define O_NONBLOCK 0x800
-#define O_DIRECTORY 0x4000
-
-/* The struct returned by the stat() syscall, 32-bit only, the syscall returns
- * exactly 56 bytes (stops before the unused array). In big endian, the format
- * differs as devices are returned as short only.
- */
-struct sys_stat_struct {
-#if defined(__ARMEB__)
- unsigned short st_dev;
- unsigned short __pad1;
-#else
- unsigned long st_dev;
-#endif
- unsigned long st_ino;
- unsigned short st_mode;
- unsigned short st_nlink;
- unsigned short st_uid;
- unsigned short st_gid;
-#if defined(__ARMEB__)
- unsigned short st_rdev;
- unsigned short __pad2;
-#else
- unsigned long st_rdev;
-#endif
- unsigned long st_size;
- unsigned long st_blksize;
- unsigned long st_blocks;
- unsigned long st_atime;
- unsigned long st_atime_nsec;
- unsigned long st_mtime;
- unsigned long st_mtime_nsec;
- unsigned long st_ctime;
- unsigned long st_ctime_nsec;
- unsigned long __unused[2];
-};
-
-#elif defined(__aarch64__)
-/* Syscalls for AARCH64 :
- * - registers are 64-bit
- * - stack is 16-byte aligned
- * - syscall number is passed in x8
- * - arguments are in x0, x1, x2, x3, x4, x5
- * - the system call is performed by calling svc 0
- * - syscall return comes in x0.
- * - the arguments are cast to long and assigned into the target registers
- * which are then simply passed as registers to the asm code, so that we
- * don't have to experience issues with register constraints.
- *
- * On aarch64, select() is not implemented so we have to use pselect6().
- */
-#define __ARCH_WANT_SYS_PSELECT6
-
-#define my_syscall0(num) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0"); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall1(num, arg1) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0") = (long)(arg1); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall2(num, arg1, arg2) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0") = (long)(arg1); \
- register long _arg2 asm("x1") = (long)(arg2); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), "r"(_arg2), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0") = (long)(arg1); \
- register long _arg2 asm("x1") = (long)(arg2); \
- register long _arg3 asm("x2") = (long)(arg3); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0") = (long)(arg1); \
- register long _arg2 asm("x1") = (long)(arg2); \
- register long _arg3 asm("x2") = (long)(arg3); \
- register long _arg4 asm("x3") = (long)(arg4); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r"(_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0") = (long)(arg1); \
- register long _arg2 asm("x1") = (long)(arg2); \
- register long _arg3 asm("x2") = (long)(arg3); \
- register long _arg4 asm("x3") = (long)(arg4); \
- register long _arg5 asm("x4") = (long)(arg5); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r" (_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
-({ \
- register long _num asm("x8") = (num); \
- register long _arg1 asm("x0") = (long)(arg1); \
- register long _arg2 asm("x1") = (long)(arg2); \
- register long _arg3 asm("x2") = (long)(arg3); \
- register long _arg4 asm("x3") = (long)(arg4); \
- register long _arg5 asm("x4") = (long)(arg5); \
- register long _arg6 asm("x5") = (long)(arg6); \
- \
- asm volatile ( \
- "svc #0\n" \
- : "=r" (_arg1) \
- : "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "r"(_arg6), "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-/* startup code */
-asm(".section .text\n"
- ".global _start\n"
- "_start:\n"
- "ldr x0, [sp]\n" // argc (x0) was in the stack
- "add x1, sp, 8\n" // argv (x1) = sp
- "lsl x2, x0, 3\n" // envp (x2) = 8*argc ...
- "add x2, x2, 8\n" // + 8 (skip null)
- "add x2, x2, x1\n" // + argv
- "and sp, x1, -16\n" // sp must be 16-byte aligned in the callee
- "bl main\n" // main() returns the status code, we'll exit with it.
- "mov x8, 93\n" // NR_exit == 93
- "svc #0\n"
- "");
-
-/* fcntl / open */
-#define O_RDONLY 0
-#define O_WRONLY 1
-#define O_RDWR 2
-#define O_CREAT 0x40
-#define O_EXCL 0x80
-#define O_NOCTTY 0x100
-#define O_TRUNC 0x200
-#define O_APPEND 0x400
-#define O_NONBLOCK 0x800
-#define O_DIRECTORY 0x4000
-
-/* The struct returned by the newfstatat() syscall. Differs slightly from the
- * x86_64's stat one by field ordering, so be careful.
- */
-struct sys_stat_struct {
- unsigned long st_dev;
- unsigned long st_ino;
- unsigned int st_mode;
- unsigned int st_nlink;
- unsigned int st_uid;
- unsigned int st_gid;
-
- unsigned long st_rdev;
- unsigned long __pad1;
- long st_size;
- int st_blksize;
- int __pad2;
-
- long st_blocks;
- long st_atime;
- unsigned long st_atime_nsec;
- long st_mtime;
-
- unsigned long st_mtime_nsec;
- long st_ctime;
- unsigned long st_ctime_nsec;
- unsigned int __unused[2];
-};
-
-#elif defined(__mips__) && defined(_ABIO32)
-/* Syscalls for MIPS ABI O32 :
- * - WARNING! there's always a delayed slot!
- * - WARNING again, the syntax is different, registers take a '$' and numbers
- * do not.
- * - registers are 32-bit
- * - stack is 8-byte aligned
- * - syscall number is passed in v0 (starts at 0xfa0).
- * - arguments are in a0, a1, a2, a3, then the stack. The caller needs to
- * leave some room in the stack for the callee to save a0..a3 if needed.
- * - Many registers are clobbered, in fact only a0..a2 and s0..s8 are
- * preserved. See: https://www.linux-mips.org/wiki/Syscall as well as
- * scall32-o32.S in the kernel sources.
- * - the system call is performed by calling "syscall"
- * - syscall return comes in v0, and register a3 needs to be checked to know
- * if an error occurred, in which case errno is in v0.
- * - the arguments are cast to long and assigned into the target registers
- * which are then simply passed as registers to the asm code, so that we
- * don't have to experience issues with register constraints.
- */
-
-#define my_syscall0(num) \
-({ \
- register long _num asm("v0") = (num); \
- register long _arg4 asm("a3"); \
- \
- asm volatile ( \
- "addiu $sp, $sp, -32\n" \
- "syscall\n" \
- "addiu $sp, $sp, 32\n" \
- : "=r"(_num), "=r"(_arg4) \
- : "r"(_num) \
- : "memory", "cc", "at", "v1", "hi", "lo", \
- "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
- ); \
- _arg4 ? -_num : _num; \
-})
-
-#define my_syscall1(num, arg1) \
-({ \
- register long _num asm("v0") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg4 asm("a3"); \
- \
- asm volatile ( \
- "addiu $sp, $sp, -32\n" \
- "syscall\n" \
- "addiu $sp, $sp, 32\n" \
- : "=r"(_num), "=r"(_arg4) \
- : "0"(_num), \
- "r"(_arg1) \
- : "memory", "cc", "at", "v1", "hi", "lo", \
- "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
- ); \
- _arg4 ? -_num : _num; \
-})
-
-#define my_syscall2(num, arg1, arg2) \
-({ \
- register long _num asm("v0") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg4 asm("a3"); \
- \
- asm volatile ( \
- "addiu $sp, $sp, -32\n" \
- "syscall\n" \
- "addiu $sp, $sp, 32\n" \
- : "=r"(_num), "=r"(_arg4) \
- : "0"(_num), \
- "r"(_arg1), "r"(_arg2) \
- : "memory", "cc", "at", "v1", "hi", "lo", \
- "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
- ); \
- _arg4 ? -_num : _num; \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3) \
-({ \
- register long _num asm("v0") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- register long _arg4 asm("a3"); \
- \
- asm volatile ( \
- "addiu $sp, $sp, -32\n" \
- "syscall\n" \
- "addiu $sp, $sp, 32\n" \
- : "=r"(_num), "=r"(_arg4) \
- : "0"(_num), \
- "r"(_arg1), "r"(_arg2), "r"(_arg3) \
- : "memory", "cc", "at", "v1", "hi", "lo", \
- "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
- ); \
- _arg4 ? -_num : _num; \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4) \
-({ \
- register long _num asm("v0") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- register long _arg4 asm("a3") = (long)(arg4); \
- \
- asm volatile ( \
- "addiu $sp, $sp, -32\n" \
- "syscall\n" \
- "addiu $sp, $sp, 32\n" \
- : "=r" (_num), "=r"(_arg4) \
- : "0"(_num), \
- "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4) \
- : "memory", "cc", "at", "v1", "hi", "lo", \
- "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
- ); \
- _arg4 ? -_num : _num; \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
-({ \
- register long _num asm("v0") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- register long _arg4 asm("a3") = (long)(arg4); \
- register long _arg5 = (long)(arg5); \
- \
- asm volatile ( \
- "addiu $sp, $sp, -32\n" \
- "sw %7, 16($sp)\n" \
- "syscall\n " \
- "addiu $sp, $sp, 32\n" \
- : "=r" (_num), "=r"(_arg4) \
- : "0"(_num), \
- "r"(_arg1), "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5) \
- : "memory", "cc", "at", "v1", "hi", "lo", \
- "t0", "t1", "t2", "t3", "t4", "t5", "t6", "t7", "t8", "t9" \
- ); \
- _arg4 ? -_num : _num; \
-})
-
-/* startup code, note that it's called __start on MIPS */
-asm(".section .text\n"
- ".set nomips16\n"
- ".global __start\n"
- ".set noreorder\n"
- ".option pic0\n"
- ".ent __start\n"
- "__start:\n"
- "lw $a0,($sp)\n" // argc was in the stack
- "addiu $a1, $sp, 4\n" // argv = sp + 4
- "sll $a2, $a0, 2\n" // a2 = argc * 4
- "add $a2, $a2, $a1\n" // envp = argv + 4*argc ...
- "addiu $a2, $a2, 4\n" // ... + 4
- "li $t0, -8\n"
- "and $sp, $sp, $t0\n" // sp must be 8-byte aligned
- "addiu $sp,$sp,-16\n" // the callee expects to save a0..a3 there!
- "jal main\n" // main() returns the status code, we'll exit with it.
- "nop\n" // delayed slot
- "move $a0, $v0\n" // retrieve 32-bit exit code from v0
- "li $v0, 4001\n" // NR_exit == 4001
- "syscall\n"
- ".end __start\n"
- "");
-
-/* fcntl / open */
-#define O_RDONLY 0
-#define O_WRONLY 1
-#define O_RDWR 2
-#define O_APPEND 0x0008
-#define O_NONBLOCK 0x0080
-#define O_CREAT 0x0100
-#define O_TRUNC 0x0200
-#define O_EXCL 0x0400
-#define O_NOCTTY 0x0800
-#define O_DIRECTORY 0x10000
-
-/* The struct returned by the stat() syscall. 88 bytes are returned by the
- * syscall.
- */
-struct sys_stat_struct {
- unsigned int st_dev;
- long st_pad1[3];
- unsigned long st_ino;
- unsigned int st_mode;
- unsigned int st_nlink;
- unsigned int st_uid;
- unsigned int st_gid;
- unsigned int st_rdev;
- long st_pad2[2];
- long st_size;
- long st_pad3;
- long st_atime;
- long st_atime_nsec;
- long st_mtime;
- long st_mtime_nsec;
- long st_ctime;
- long st_ctime_nsec;
- long st_blksize;
- long st_blocks;
- long st_pad4[14];
-};
-
-#elif defined(__riscv)
-
-#if __riscv_xlen == 64
-#define PTRLOG "3"
-#define SZREG "8"
-#elif __riscv_xlen == 32
-#define PTRLOG "2"
-#define SZREG "4"
-#endif
-
-/* Syscalls for RISCV :
- * - stack is 16-byte aligned
- * - syscall number is passed in a7
- * - arguments are in a0, a1, a2, a3, a4, a5
- * - the system call is performed by calling ecall
- * - syscall return comes in a0
- * - the arguments are cast to long and assigned into the target
- * registers which are then simply passed as registers to the asm code,
- * so that we don't have to experience issues with register constraints.
- */
-
-#define my_syscall0(num) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0"); \
- \
- asm volatile ( \
- "ecall\n\t" \
- : "=r"(_arg1) \
- : "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall1(num, arg1) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- \
- asm volatile ( \
- "ecall\n" \
- : "+r"(_arg1) \
- : "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall2(num, arg1, arg2) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- \
- asm volatile ( \
- "ecall\n" \
- : "+r"(_arg1) \
- : "r"(_arg2), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall3(num, arg1, arg2, arg3) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- \
- asm volatile ( \
- "ecall\n\t" \
- : "+r"(_arg1) \
- : "r"(_arg2), "r"(_arg3), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall4(num, arg1, arg2, arg3, arg4) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- register long _arg4 asm("a3") = (long)(arg4); \
- \
- asm volatile ( \
- "ecall\n" \
- : "+r"(_arg1) \
- : "r"(_arg2), "r"(_arg3), "r"(_arg4), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall5(num, arg1, arg2, arg3, arg4, arg5) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- register long _arg4 asm("a3") = (long)(arg4); \
- register long _arg5 asm("a4") = (long)(arg5); \
- \
- asm volatile ( \
- "ecall\n" \
- : "+r"(_arg1) \
- : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-#define my_syscall6(num, arg1, arg2, arg3, arg4, arg5, arg6) \
-({ \
- register long _num asm("a7") = (num); \
- register long _arg1 asm("a0") = (long)(arg1); \
- register long _arg2 asm("a1") = (long)(arg2); \
- register long _arg3 asm("a2") = (long)(arg3); \
- register long _arg4 asm("a3") = (long)(arg4); \
- register long _arg5 asm("a4") = (long)(arg5); \
- register long _arg6 asm("a5") = (long)(arg6); \
- \
- asm volatile ( \
- "ecall\n" \
- : "+r"(_arg1) \
- : "r"(_arg2), "r"(_arg3), "r"(_arg4), "r"(_arg5), "r"(_arg6), \
- "r"(_num) \
- : "memory", "cc" \
- ); \
- _arg1; \
-})
-
-/* startup code */
-asm(".section .text\n"
- ".global _start\n"
- "_start:\n"
- ".option push\n"
- ".option norelax\n"
- "lla gp, __global_pointer$\n"
- ".option pop\n"
- "ld a0, 0(sp)\n" // argc (a0) was in the stack
- "add a1, sp, "SZREG"\n" // argv (a1) = sp
- "slli a2, a0, "PTRLOG"\n" // envp (a2) = SZREG*argc ...
- "add a2, a2, "SZREG"\n" // + SZREG (skip null)
- "add a2,a2,a1\n" // + argv
- "andi sp,a1,-16\n" // sp must be 16-byte aligned
- "call main\n" // main() returns the status code, we'll exit with it.
- "li a7, 93\n" // NR_exit == 93
- "ecall\n"
- "");
-
-/* fcntl / open */
-#define O_RDONLY 0
-#define O_WRONLY 1
-#define O_RDWR 2
-#define O_CREAT 0x100
-#define O_EXCL 0x200
-#define O_NOCTTY 0x400
-#define O_TRUNC 0x1000
-#define O_APPEND 0x2000
-#define O_NONBLOCK 0x4000
-#define O_DIRECTORY 0x200000
-
-struct sys_stat_struct {
- unsigned long st_dev; /* Device. */
- unsigned long st_ino; /* File serial number. */
- unsigned int st_mode; /* File mode. */
- unsigned int st_nlink; /* Link count. */
- unsigned int st_uid; /* User ID of the file's owner. */
- unsigned int st_gid; /* Group ID of the file's group. */
- unsigned long st_rdev; /* Device number, if device. */
- unsigned long __pad1;
- long st_size; /* Size of file, in bytes. */
- int st_blksize; /* Optimal block size for I/O. */
- int __pad2;
- long st_blocks; /* Number 512-byte blocks allocated. */
- long st_atime; /* Time of last access. */
- unsigned long st_atime_nsec;
- long st_mtime; /* Time of last modification. */
- unsigned long st_mtime_nsec;
- long st_ctime; /* Time of last status change. */
- unsigned long st_ctime_nsec;
- unsigned int __unused4;
- unsigned int __unused5;
-};
-
-#endif
-
-
-/* Below are the C functions used to declare the raw syscalls. They try to be
- * architecture-agnostic, and return either a success or -errno. Declaring them
- * static will lead to them being inlined in most cases, but it's still possible
- * to reference them by a pointer if needed.
- */
-static __attribute__((unused))
-void *sys_brk(void *addr)
-{
- return (void *)my_syscall1(__NR_brk, addr);
-}
-
-static __attribute__((noreturn,unused))
-void sys_exit(int status)
-{
- my_syscall1(__NR_exit, status & 255);
- while(1); // shut the "noreturn" warnings.
-}
-
-static __attribute__((unused))
-int sys_chdir(const char *path)
-{
- return my_syscall1(__NR_chdir, path);
-}
-
-static __attribute__((unused))
-int sys_chmod(const char *path, mode_t mode)
-{
-#ifdef __NR_fchmodat
- return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
-#elif defined(__NR_chmod)
- return my_syscall2(__NR_chmod, path, mode);
-#else
-#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod()
-#endif
-}
-
-static __attribute__((unused))
-int sys_chown(const char *path, uid_t owner, gid_t group)
-{
-#ifdef __NR_fchownat
- return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
-#elif defined(__NR_chown)
- return my_syscall3(__NR_chown, path, owner, group);
-#else
-#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown()
-#endif
-}
-
-static __attribute__((unused))
-int sys_chroot(const char *path)
-{
- return my_syscall1(__NR_chroot, path);
-}
-
-static __attribute__((unused))
-int sys_close(int fd)
-{
- return my_syscall1(__NR_close, fd);
-}
-
-static __attribute__((unused))
-int sys_dup(int fd)
-{
- return my_syscall1(__NR_dup, fd);
-}
-
-#ifdef __NR_dup3
-static __attribute__((unused))
-int sys_dup3(int old, int new, int flags)
-{
- return my_syscall3(__NR_dup3, old, new, flags);
-}
-#endif
-
-static __attribute__((unused))
-int sys_dup2(int old, int new)
-{
-#ifdef __NR_dup3
- return my_syscall3(__NR_dup3, old, new, 0);
-#elif defined(__NR_dup2)
- return my_syscall2(__NR_dup2, old, new);
-#else
-#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2()
-#endif
-}
-
-static __attribute__((unused))
-int sys_execve(const char *filename, char *const argv[], char *const envp[])
-{
- return my_syscall3(__NR_execve, filename, argv, envp);
-}
-
-static __attribute__((unused))
-pid_t sys_fork(void)
-{
-#ifdef __NR_clone
- /* note: some archs only have clone() and not fork(). Different archs
- * have a different API, but most archs have the flags on first arg and
- * will not use the rest with no other flag.
- */
- return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0);
-#elif defined(__NR_fork)
- return my_syscall0(__NR_fork);
-#else
-#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork()
-#endif
-}
-
-static __attribute__((unused))
-int sys_fsync(int fd)
-{
- return my_syscall1(__NR_fsync, fd);
-}
-
-static __attribute__((unused))
-int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
-{
- return my_syscall3(__NR_getdents64, fd, dirp, count);
-}
-
-static __attribute__((unused))
-pid_t sys_getpgid(pid_t pid)
-{
- return my_syscall1(__NR_getpgid, pid);
-}
-
-static __attribute__((unused))
-pid_t sys_getpgrp(void)
-{
- return sys_getpgid(0);
-}
-
-static __attribute__((unused))
-pid_t sys_getpid(void)
-{
- return my_syscall0(__NR_getpid);
-}
-
-static __attribute__((unused))
-pid_t sys_gettid(void)
-{
- return my_syscall0(__NR_gettid);
-}
-
-static __attribute__((unused))
-int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
- return my_syscall2(__NR_gettimeofday, tv, tz);
-}
-
-static __attribute__((unused))
-int sys_ioctl(int fd, unsigned long req, void *value)
-{
- return my_syscall3(__NR_ioctl, fd, req, value);
-}
-
-static __attribute__((unused))
-int sys_kill(pid_t pid, int signal)
-{
- return my_syscall2(__NR_kill, pid, signal);
-}
-
-static __attribute__((unused))
-int sys_link(const char *old, const char *new)
-{
-#ifdef __NR_linkat
- return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
-#elif defined(__NR_link)
- return my_syscall2(__NR_link, old, new);
-#else
-#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link()
-#endif
-}
-
-static __attribute__((unused))
-off_t sys_lseek(int fd, off_t offset, int whence)
-{
- return my_syscall3(__NR_lseek, fd, offset, whence);
-}
-
-static __attribute__((unused))
-int sys_mkdir(const char *path, mode_t mode)
-{
-#ifdef __NR_mkdirat
- return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
-#elif defined(__NR_mkdir)
- return my_syscall2(__NR_mkdir, path, mode);
-#else
-#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir()
-#endif
-}
-
-static __attribute__((unused))
-long sys_mknod(const char *path, mode_t mode, dev_t dev)
-{
-#ifdef __NR_mknodat
- return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
-#elif defined(__NR_mknod)
- return my_syscall3(__NR_mknod, path, mode, dev);
-#else
-#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod()
-#endif
-}
-
-static __attribute__((unused))
-int sys_mount(const char *src, const char *tgt, const char *fst,
- unsigned long flags, const void *data)
-{
- return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
-}
-
-static __attribute__((unused))
-int sys_open(const char *path, int flags, mode_t mode)
-{
-#ifdef __NR_openat
- return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
-#elif defined(__NR_open)
- return my_syscall3(__NR_open, path, flags, mode);
-#else
-#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open()
-#endif
-}
-
-static __attribute__((unused))
-int sys_pivot_root(const char *new, const char *old)
-{
- return my_syscall2(__NR_pivot_root, new, old);
-}
-
-static __attribute__((unused))
-int sys_poll(struct pollfd *fds, int nfds, int timeout)
-{
-#if defined(__NR_ppoll)
- struct timespec t;
-
- if (timeout >= 0) {
- t.tv_sec = timeout / 1000;
- t.tv_nsec = (timeout % 1000) * 1000000;
- }
- return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL);
-#elif defined(__NR_poll)
- return my_syscall3(__NR_poll, fds, nfds, timeout);
-#else
-#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll()
-#endif
-}
-
-static __attribute__((unused))
-ssize_t sys_read(int fd, void *buf, size_t count)
-{
- return my_syscall3(__NR_read, fd, buf, count);
-}
-
-static __attribute__((unused))
-ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
-{
- return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
-}
-
-static __attribute__((unused))
-int sys_sched_yield(void)
-{
- return my_syscall0(__NR_sched_yield);
-}
-
-static __attribute__((unused))
-int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
-{
-#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
- struct sel_arg_struct {
- unsigned long n;
- fd_set *r, *w, *e;
- struct timeval *t;
- } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
- return my_syscall1(__NR_select, &arg);
-#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
- struct timespec t;
-
- if (timeout) {
- t.tv_sec = timeout->tv_sec;
- t.tv_nsec = timeout->tv_usec * 1000;
- }
- return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
-#elif defined(__NR__newselect) || defined(__NR_select)
-#ifndef __NR__newselect
-#define __NR__newselect __NR_select
-#endif
- return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
-#else
-#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select()
-#endif
-}
-
-static __attribute__((unused))
-int sys_setpgid(pid_t pid, pid_t pgid)
-{
- return my_syscall2(__NR_setpgid, pid, pgid);
-}
-
-static __attribute__((unused))
-pid_t sys_setsid(void)
-{
- return my_syscall0(__NR_setsid);
-}
-
-static __attribute__((unused))
-int sys_stat(const char *path, struct stat *buf)
-{
- struct sys_stat_struct stat;
- long ret;
-
-#ifdef __NR_newfstatat
- /* only solution for arm64 */
- ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0);
-#elif defined(__NR_stat)
- ret = my_syscall2(__NR_stat, path, &stat);
-#else
-#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat()
-#endif
- buf->st_dev = stat.st_dev;
- buf->st_ino = stat.st_ino;
- buf->st_mode = stat.st_mode;
- buf->st_nlink = stat.st_nlink;
- buf->st_uid = stat.st_uid;
- buf->st_gid = stat.st_gid;
- buf->st_rdev = stat.st_rdev;
- buf->st_size = stat.st_size;
- buf->st_blksize = stat.st_blksize;
- buf->st_blocks = stat.st_blocks;
- buf->st_atime = stat.st_atime;
- buf->st_mtime = stat.st_mtime;
- buf->st_ctime = stat.st_ctime;
- return ret;
-}
-
-
-static __attribute__((unused))
-int sys_symlink(const char *old, const char *new)
-{
-#ifdef __NR_symlinkat
- return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
-#elif defined(__NR_symlink)
- return my_syscall2(__NR_symlink, old, new);
-#else
-#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink()
-#endif
-}
-
-static __attribute__((unused))
-mode_t sys_umask(mode_t mode)
-{
- return my_syscall1(__NR_umask, mode);
-}
-
-static __attribute__((unused))
-int sys_umount2(const char *path, int flags)
-{
- return my_syscall2(__NR_umount2, path, flags);
-}
-
-static __attribute__((unused))
-int sys_unlink(const char *path)
-{
-#ifdef __NR_unlinkat
- return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
-#elif defined(__NR_unlink)
- return my_syscall1(__NR_unlink, path);
-#else
-#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink()
-#endif
-}
-
-static __attribute__((unused))
-pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
-{
- return my_syscall4(__NR_wait4, pid, status, options, rusage);
-}
-
-static __attribute__((unused))
-pid_t sys_waitpid(pid_t pid, int *status, int options)
-{
- return sys_wait4(pid, status, options, 0);
-}
-
-static __attribute__((unused))
-pid_t sys_wait(int *status)
-{
- return sys_waitpid(-1, status, 0);
-}
-
-static __attribute__((unused))
-ssize_t sys_write(int fd, const void *buf, size_t count)
-{
- return my_syscall3(__NR_write, fd, buf, count);
-}
-
-
-/* Below are the libc-compatible syscalls which return x or -1 and set errno.
- * They rely on the functions above. Similarly they're marked static so that it
- * is possible to assign pointers to them if needed.
- */
-
-static __attribute__((unused))
-int brk(void *addr)
-{
- void *ret = sys_brk(addr);
-
- if (!ret) {
- SET_ERRNO(ENOMEM);
- return -1;
- }
- return 0;
-}
-
-static __attribute__((noreturn,unused))
-void exit(int status)
-{
- sys_exit(status);
-}
-
-static __attribute__((unused))
-int chdir(const char *path)
-{
- int ret = sys_chdir(path);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int chmod(const char *path, mode_t mode)
-{
- int ret = sys_chmod(path, mode);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int chown(const char *path, uid_t owner, gid_t group)
-{
- int ret = sys_chown(path, owner, group);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int chroot(const char *path)
-{
- int ret = sys_chroot(path);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int close(int fd)
-{
- int ret = sys_close(fd);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int dup(int fd)
-{
- int ret = sys_dup(fd);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int dup2(int old, int new)
-{
- int ret = sys_dup2(old, new);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-#ifdef __NR_dup3
-static __attribute__((unused))
-int dup3(int old, int new, int flags)
-{
- int ret = sys_dup3(old, new, flags);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-#endif
-
-static __attribute__((unused))
-int execve(const char *filename, char *const argv[], char *const envp[])
-{
- int ret = sys_execve(filename, argv, envp);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t fork(void)
-{
- pid_t ret = sys_fork();
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int fsync(int fd)
-{
- int ret = sys_fsync(fd);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int getdents64(int fd, struct linux_dirent64 *dirp, int count)
-{
- int ret = sys_getdents64(fd, dirp, count);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t getpgid(pid_t pid)
-{
- pid_t ret = sys_getpgid(pid);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t getpgrp(void)
-{
- pid_t ret = sys_getpgrp();
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t getpid(void)
-{
- pid_t ret = sys_getpid();
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t gettid(void)
-{
- pid_t ret = sys_gettid();
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int gettimeofday(struct timeval *tv, struct timezone *tz)
-{
- int ret = sys_gettimeofday(tv, tz);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int ioctl(int fd, unsigned long req, void *value)
-{
- int ret = sys_ioctl(fd, req, value);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int kill(pid_t pid, int signal)
-{
- int ret = sys_kill(pid, signal);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int link(const char *old, const char *new)
-{
- int ret = sys_link(old, new);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-off_t lseek(int fd, off_t offset, int whence)
-{
- off_t ret = sys_lseek(fd, offset, whence);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int mkdir(const char *path, mode_t mode)
-{
- int ret = sys_mkdir(path, mode);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int mknod(const char *path, mode_t mode, dev_t dev)
-{
- int ret = sys_mknod(path, mode, dev);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int mount(const char *src, const char *tgt,
- const char *fst, unsigned long flags,
- const void *data)
-{
- int ret = sys_mount(src, tgt, fst, flags, data);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int open(const char *path, int flags, mode_t mode)
-{
- int ret = sys_open(path, flags, mode);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int pivot_root(const char *new, const char *old)
-{
- int ret = sys_pivot_root(new, old);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int poll(struct pollfd *fds, int nfds, int timeout)
-{
- int ret = sys_poll(fds, nfds, timeout);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-ssize_t read(int fd, void *buf, size_t count)
-{
- ssize_t ret = sys_read(fd, buf, count);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int reboot(int cmd)
-{
- int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-void *sbrk(intptr_t inc)
-{
- void *ret;
-
- /* first call to find current end */
- if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc))
- return ret + inc;
-
- SET_ERRNO(ENOMEM);
- return (void *)-1;
-}
-
-static __attribute__((unused))
-int sched_yield(void)
-{
- int ret = sys_sched_yield();
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
-{
- int ret = sys_select(nfds, rfds, wfds, efds, timeout);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int setpgid(pid_t pid, pid_t pgid)
-{
- int ret = sys_setpgid(pid, pgid);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t setsid(void)
-{
- pid_t ret = sys_setsid();
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-unsigned int sleep(unsigned int seconds)
-{
- struct timeval my_timeval = { seconds, 0 };
-
- if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
- return my_timeval.tv_sec + !!my_timeval.tv_usec;
- else
- return 0;
-}
-
-static __attribute__((unused))
-int msleep(unsigned int msecs)
-{
- struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 };
-
- if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
- return (my_timeval.tv_sec * 1000) +
- (my_timeval.tv_usec / 1000) +
- !!(my_timeval.tv_usec % 1000);
- else
- return 0;
-}
-
-static __attribute__((unused))
-int stat(const char *path, struct stat *buf)
-{
- int ret = sys_stat(path, buf);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int symlink(const char *old, const char *new)
-{
- int ret = sys_symlink(old, new);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int tcsetpgrp(int fd, pid_t pid)
-{
- return ioctl(fd, TIOCSPGRP, &pid);
-}
-
-static __attribute__((unused))
-mode_t umask(mode_t mode)
-{
- return sys_umask(mode);
-}
-
-static __attribute__((unused))
-int umount2(const char *path, int flags)
-{
- int ret = sys_umount2(path, flags);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-int unlink(const char *path)
-{
- int ret = sys_unlink(path);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
-{
- pid_t ret = sys_wait4(pid, status, options, rusage);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t waitpid(pid_t pid, int *status, int options)
-{
- pid_t ret = sys_waitpid(pid, status, options);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-pid_t wait(int *status)
-{
- pid_t ret = sys_wait(status);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-static __attribute__((unused))
-ssize_t write(int fd, const void *buf, size_t count)
-{
- ssize_t ret = sys_write(fd, buf, count);
-
- if (ret < 0) {
- SET_ERRNO(-ret);
- ret = -1;
- }
- return ret;
-}
-
-/* some size-optimized reimplementations of a few common str* and mem*
- * functions. They're marked static, except memcpy() and raise() which are used
- * by libgcc on ARM, so they are marked weak instead in order not to cause an
- * error when building a program made of multiple files (not recommended).
- */
-
-static __attribute__((unused))
-void *memmove(void *dst, const void *src, size_t len)
-{
- ssize_t pos = (dst <= src) ? -1 : (long)len;
- void *ret = dst;
-
- while (len--) {
- pos += (dst <= src) ? 1 : -1;
- ((char *)dst)[pos] = ((char *)src)[pos];
- }
- return ret;
-}
-
-static __attribute__((unused))
-void *memset(void *dst, int b, size_t len)
-{
- char *p = dst;
-
- while (len--)
- *(p++) = b;
- return dst;
-}
-
-static __attribute__((unused))
-int memcmp(const void *s1, const void *s2, size_t n)
-{
- size_t ofs = 0;
- char c1 = 0;
-
- while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) {
- ofs++;
- }
- return c1;
-}
-
-static __attribute__((unused))
-char *strcpy(char *dst, const char *src)
-{
- char *ret = dst;
-
- while ((*dst++ = *src++));
- return ret;
-}
-
-static __attribute__((unused))
-char *strchr(const char *s, int c)
-{
- while (*s) {
- if (*s == (char)c)
- return (char *)s;
- s++;
- }
- return NULL;
-}
-
-static __attribute__((unused))
-char *strrchr(const char *s, int c)
-{
- const char *ret = NULL;
-
- while (*s) {
- if (*s == (char)c)
- ret = s;
- s++;
- }
- return (char *)ret;
-}
-
-static __attribute__((unused))
-size_t nolibc_strlen(const char *str)
-{
- size_t len;
-
- for (len = 0; str[len]; len++);
- return len;
-}
-
-#define strlen(str) ({ \
- __builtin_constant_p((str)) ? \
- __builtin_strlen((str)) : \
- nolibc_strlen((str)); \
-})
-
-static __attribute__((unused))
-int isdigit(int c)
-{
- return (unsigned int)(c - '0') <= 9;
-}
-
-static __attribute__((unused))
-long atol(const char *s)
-{
- unsigned long ret = 0;
- unsigned long d;
- int neg = 0;
-
- if (*s == '-') {
- neg = 1;
- s++;
- }
-
- while (1) {
- d = (*s++) - '0';
- if (d > 9)
- break;
- ret *= 10;
- ret += d;
- }
-
- return neg ? -ret : ret;
-}
-
-static __attribute__((unused))
-int atoi(const char *s)
-{
- return atol(s);
-}
-
-static __attribute__((unused))
-const char *ltoa(long in)
-{
- /* large enough for -9223372036854775808 */
- static char buffer[21];
- char *pos = buffer + sizeof(buffer) - 1;
- int neg = in < 0;
- unsigned long n = neg ? -in : in;
-
- *pos-- = '\0';
- do {
- *pos-- = '0' + n % 10;
- n /= 10;
- if (pos < buffer)
- return pos + 1;
- } while (n);
-
- if (neg)
- *pos-- = '-';
- return pos + 1;
-}
-
-__attribute__((weak,unused))
-void *memcpy(void *dst, const void *src, size_t len)
-{
- return memmove(dst, src, len);
-}
-
-/* needed by libgcc for divide by zero */
-__attribute__((weak,unused))
-int raise(int signal)
-{
- return kill(getpid(), signal);
-}
-
-/* Here come a few helper functions */
-
-static __attribute__((unused))
-void FD_ZERO(fd_set *set)
-{
- memset(set, 0, sizeof(*set));
-}
-
-static __attribute__((unused))
-void FD_SET(int fd, fd_set *set)
-{
- if (fd < 0 || fd >= FD_SETSIZE)
- return;
- set->fd32[fd / 32] |= 1 << (fd & 31);
-}
-
-/* WARNING, it only deals with the 4096 first majors and 256 first minors */
-static __attribute__((unused))
-dev_t makedev(unsigned int major, unsigned int minor)
-{
- return ((major & 0xfff) << 8) | (minor & 0xff);
-}
+#endif /* _NOLIBC_H */
diff --git a/tools/include/nolibc/signal.h b/tools/include/nolibc/signal.h
new file mode 100644
index 000000000000..ef47e71e2be3
--- /dev/null
+++ b/tools/include/nolibc/signal.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * signal function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SIGNAL_H
+#define _NOLIBC_SIGNAL_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+/* This one is not marked static as it's needed by libgcc for divide by zero */
+__attribute__((weak,unused,section(".text.nolibc_raise")))
+int raise(int signal)
+{
+ return sys_kill(sys_getpid(), signal);
+}
+
+#endif /* _NOLIBC_SIGNAL_H */
diff --git a/tools/include/nolibc/std.h b/tools/include/nolibc/std.h
new file mode 100644
index 000000000000..1747ae125392
--- /dev/null
+++ b/tools/include/nolibc/std.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Standard definitions and types for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STD_H
+#define _NOLIBC_STD_H
+
+/* Declare a few quite common macros and types that usually are in stdlib.h,
+ * stdint.h, ctype.h, unistd.h and a few other common locations. Please place
+ * integer type definitions and generic macros here, but avoid OS-specific and
+ * syscall-specific stuff, as this file is expected to be included very early.
+ */
+
+/* note: may already be defined */
+#ifndef NULL
+#define NULL ((void *)0)
+#endif
+
+/* stdint types */
+typedef unsigned char uint8_t;
+typedef signed char int8_t;
+typedef unsigned short uint16_t;
+typedef signed short int16_t;
+typedef unsigned int uint32_t;
+typedef signed int int32_t;
+typedef unsigned long long uint64_t;
+typedef signed long long int64_t;
+typedef unsigned long size_t;
+typedef signed long ssize_t;
+typedef unsigned long uintptr_t;
+typedef signed long intptr_t;
+typedef signed long ptrdiff_t;
+
+/* those are commonly provided by sys/types.h */
+typedef unsigned int dev_t;
+typedef unsigned long ino_t;
+typedef unsigned int mode_t;
+typedef signed int pid_t;
+typedef unsigned int uid_t;
+typedef unsigned int gid_t;
+typedef unsigned long nlink_t;
+typedef signed long off_t;
+typedef signed long blksize_t;
+typedef signed long blkcnt_t;
+typedef signed long time_t;
+
+#endif /* _NOLIBC_STD_H */
diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h
new file mode 100644
index 000000000000..15dedf8d0902
--- /dev/null
+++ b/tools/include/nolibc/stdio.h
@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * minimal stdio function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STDIO_H
+#define _NOLIBC_STDIO_H
+
+#include <stdarg.h>
+
+#include "std.h"
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+#include "sys.h"
+#include "stdlib.h"
+#include "string.h"
+
+#ifndef EOF
+#define EOF (-1)
+#endif
+
+/* just define FILE as a non-empty type */
+typedef struct FILE {
+ char dummy[1];
+} FILE;
+
+/* We define the 3 common stdio files as constant invalid pointers that
+ * are easily recognized.
+ */
+static __attribute__((unused)) FILE* const stdin = (FILE*)-3;
+static __attribute__((unused)) FILE* const stdout = (FILE*)-2;
+static __attribute__((unused)) FILE* const stderr = (FILE*)-1;
+
+/* getc(), fgetc(), getchar() */
+
+#define getc(stream) fgetc(stream)
+
+static __attribute__((unused))
+int fgetc(FILE* stream)
+{
+ unsigned char ch;
+ int fd;
+
+ if (stream < stdin || stream > stderr)
+ return EOF;
+
+ fd = 3 + (long)stream;
+
+ if (read(fd, &ch, 1) <= 0)
+ return EOF;
+ return ch;
+}
+
+static __attribute__((unused))
+int getchar(void)
+{
+ return fgetc(stdin);
+}
+
+
+/* putc(), fputc(), putchar() */
+
+#define putc(c, stream) fputc(c, stream)
+
+static __attribute__((unused))
+int fputc(int c, FILE* stream)
+{
+ unsigned char ch = c;
+ int fd;
+
+ if (stream < stdin || stream > stderr)
+ return EOF;
+
+ fd = 3 + (long)stream;
+
+ if (write(fd, &ch, 1) <= 0)
+ return EOF;
+ return ch;
+}
+
+static __attribute__((unused))
+int putchar(int c)
+{
+ return fputc(c, stdout);
+}
+
+
+/* fwrite(), puts(), fputs(). Note that puts() emits '\n' but not fputs(). */
+
+/* internal fwrite()-like function which only takes a size and returns 0 on
+ * success or EOF on error. It automatically retries on short writes.
+ */
+static __attribute__((unused))
+int _fwrite(const void *buf, size_t size, FILE *stream)
+{
+ ssize_t ret;
+ int fd;
+
+ if (stream < stdin || stream > stderr)
+ return EOF;
+
+ fd = 3 + (long)stream;
+
+ while (size) {
+ ret = write(fd, buf, size);
+ if (ret <= 0)
+ return EOF;
+ size -= ret;
+ buf += ret;
+ }
+ return 0;
+}
+
+static __attribute__((unused))
+size_t fwrite(const void *s, size_t size, size_t nmemb, FILE *stream)
+{
+ size_t written;
+
+ for (written = 0; written < nmemb; written++) {
+ if (_fwrite(s, size, stream) != 0)
+ break;
+ s += size;
+ }
+ return written;
+}
+
+static __attribute__((unused))
+int fputs(const char *s, FILE *stream)
+{
+ return _fwrite(s, strlen(s), stream);
+}
+
+static __attribute__((unused))
+int puts(const char *s)
+{
+ if (fputs(s, stdout) == EOF)
+ return EOF;
+ return putchar('\n');
+}
+
+
+/* fgets() */
+static __attribute__((unused))
+char *fgets(char *s, int size, FILE *stream)
+{
+ int ofs;
+ int c;
+
+ for (ofs = 0; ofs + 1 < size;) {
+ c = fgetc(stream);
+ if (c == EOF)
+ break;
+ s[ofs++] = c;
+ if (c == '\n')
+ break;
+ }
+ if (ofs < size)
+ s[ofs] = 0;
+ return ofs ? s : NULL;
+}
+
+
+/* minimal vfprintf(). It supports the following formats:
+ * - %[l*]{d,u,c,x,p}
+ * - %s
+ * - unknown modifiers are ignored.
+ */
+static __attribute__((unused))
+int vfprintf(FILE *stream, const char *fmt, va_list args)
+{
+ char escape, lpref, c;
+ unsigned long long v;
+ unsigned int written;
+ size_t len, ofs;
+ char tmpbuf[21];
+ const char *outstr;
+
+ written = ofs = escape = lpref = 0;
+ while (1) {
+ c = fmt[ofs++];
+
+ if (escape) {
+ /* we're in an escape sequence, ofs == 1 */
+ escape = 0;
+ if (c == 'c' || c == 'd' || c == 'u' || c == 'x' || c == 'p') {
+ char *out = tmpbuf;
+
+ if (c == 'p')
+ v = va_arg(args, unsigned long);
+ else if (lpref) {
+ if (lpref > 1)
+ v = va_arg(args, unsigned long long);
+ else
+ v = va_arg(args, unsigned long);
+ } else
+ v = va_arg(args, unsigned int);
+
+ if (c == 'd') {
+ /* sign-extend the value */
+ if (lpref == 0)
+ v = (long long)(int)v;
+ else if (lpref == 1)
+ v = (long long)(long)v;
+ }
+
+ switch (c) {
+ case 'c':
+ out[0] = v;
+ out[1] = 0;
+ break;
+ case 'd':
+ i64toa_r(v, out);
+ break;
+ case 'u':
+ u64toa_r(v, out);
+ break;
+ case 'p':
+ *(out++) = '0';
+ *(out++) = 'x';
+ /* fall through */
+ default: /* 'x' and 'p' above */
+ u64toh_r(v, out);
+ break;
+ }
+ outstr = tmpbuf;
+ }
+ else if (c == 's') {
+ outstr = va_arg(args, char *);
+ if (!outstr)
+ outstr="(null)";
+ }
+ else if (c == '%') {
+ /* queue it verbatim */
+ continue;
+ }
+ else {
+ /* modifiers or final 0 */
+ if (c == 'l') {
+ /* long format prefix, maintain the escape */
+ lpref++;
+ }
+ escape = 1;
+ goto do_escape;
+ }
+ len = strlen(outstr);
+ goto flush_str;
+ }
+
+ /* not an escape sequence */
+ if (c == 0 || c == '%') {
+ /* flush pending data on escape or end */
+ escape = 1;
+ lpref = 0;
+ outstr = fmt;
+ len = ofs - 1;
+ flush_str:
+ if (_fwrite(outstr, len, stream) != 0)
+ break;
+
+ written += len;
+ do_escape:
+ if (c == 0)
+ break;
+ fmt += ofs;
+ ofs = 0;
+ continue;
+ }
+
+ /* literal char, just queue it */
+ }
+ return written;
+}
+
+static __attribute__((unused))
+int fprintf(FILE *stream, const char *fmt, ...)
+{
+ va_list args;
+ int ret;
+
+ va_start(args, fmt);
+ ret = vfprintf(stream, fmt, args);
+ va_end(args);
+ return ret;
+}
+
+static __attribute__((unused))
+int printf(const char *fmt, ...)
+{
+ va_list args;
+ int ret;
+
+ va_start(args, fmt);
+ ret = vfprintf(stdout, fmt, args);
+ va_end(args);
+ return ret;
+}
+
+static __attribute__((unused))
+void perror(const char *msg)
+{
+ fprintf(stderr, "%s%serrno=%d\n", (msg && *msg) ? msg : "", (msg && *msg) ? ": " : "", errno);
+}
+
+#endif /* _NOLIBC_STDIO_H */
diff --git a/tools/include/nolibc/stdlib.h b/tools/include/nolibc/stdlib.h
new file mode 100644
index 000000000000..8fd32eaf8037
--- /dev/null
+++ b/tools/include/nolibc/stdlib.h
@@ -0,0 +1,423 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * stdlib function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STDLIB_H
+#define _NOLIBC_STDLIB_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+#include "string.h"
+
+struct nolibc_heap {
+ size_t len;
+ char user_p[] __attribute__((__aligned__));
+};
+
+/* Buffer used to store int-to-ASCII conversions. Will only be implemented if
+ * any of the related functions is implemented. The area is large enough to
+ * store "18446744073709551615" or "-9223372036854775808" and the final zero.
+ */
+static __attribute__((unused)) char itoa_buffer[21];
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+/* must be exported, as it's used by libgcc for various divide functions */
+__attribute__((weak,unused,noreturn,section(".text.nolibc_abort")))
+void abort(void)
+{
+ sys_kill(sys_getpid(), SIGABRT);
+ for (;;);
+}
+
+static __attribute__((unused))
+long atol(const char *s)
+{
+ unsigned long ret = 0;
+ unsigned long d;
+ int neg = 0;
+
+ if (*s == '-') {
+ neg = 1;
+ s++;
+ }
+
+ while (1) {
+ d = (*s++) - '0';
+ if (d > 9)
+ break;
+ ret *= 10;
+ ret += d;
+ }
+
+ return neg ? -ret : ret;
+}
+
+static __attribute__((unused))
+int atoi(const char *s)
+{
+ return atol(s);
+}
+
+static __attribute__((unused))
+void free(void *ptr)
+{
+ struct nolibc_heap *heap;
+
+ if (!ptr)
+ return;
+
+ heap = container_of(ptr, struct nolibc_heap, user_p);
+ munmap(heap, heap->len);
+}
+
+/* getenv() tries to find the environment variable named <name> in the
+ * environment array pointed to by global variable "environ" which must be
+ * declared as a char **, and must be terminated by a NULL (it is recommended
+ * to set this variable to the "envp" argument of main()). If the requested
+ * environment variable exists its value is returned otherwise NULL is
+ * returned. getenv() is forcefully inlined so that the reference to "environ"
+ * will be dropped if unused, even at -O0.
+ */
+static __attribute__((unused))
+char *_getenv(const char *name, char **environ)
+{
+ int idx, i;
+
+ if (environ) {
+ for (idx = 0; environ[idx]; idx++) {
+ for (i = 0; name[i] && name[i] == environ[idx][i];)
+ i++;
+ if (!name[i] && environ[idx][i] == '=')
+ return &environ[idx][i+1];
+ }
+ }
+ return NULL;
+}
+
+static inline __attribute__((unused,always_inline))
+char *getenv(const char *name)
+{
+ extern char **environ;
+ return _getenv(name, environ);
+}
+
+static __attribute__((unused))
+void *malloc(size_t len)
+{
+ struct nolibc_heap *heap;
+
+ /* Always allocate memory with size multiple of 4096. */
+ len = sizeof(*heap) + len;
+ len = (len + 4095UL) & -4096UL;
+ heap = mmap(NULL, len, PROT_READ|PROT_WRITE, MAP_ANONYMOUS|MAP_PRIVATE,
+ -1, 0);
+ if (__builtin_expect(heap == MAP_FAILED, 0))
+ return NULL;
+
+ heap->len = len;
+ return heap->user_p;
+}
+
+static __attribute__((unused))
+void *calloc(size_t size, size_t nmemb)
+{
+ void *orig;
+ size_t res = 0;
+
+ if (__builtin_expect(__builtin_mul_overflow(nmemb, size, &res), 0)) {
+ SET_ERRNO(ENOMEM);
+ return NULL;
+ }
+
+ /*
+ * No need to zero the heap, the MAP_ANONYMOUS in malloc()
+ * already does it.
+ */
+ return malloc(res);
+}
+
+static __attribute__((unused))
+void *realloc(void *old_ptr, size_t new_size)
+{
+ struct nolibc_heap *heap;
+ size_t user_p_len;
+ void *ret;
+
+ if (!old_ptr)
+ return malloc(new_size);
+
+ heap = container_of(old_ptr, struct nolibc_heap, user_p);
+ user_p_len = heap->len - sizeof(*heap);
+ /*
+ * Don't realloc() if @user_p_len >= @new_size, this block of
+ * memory is still enough to handle the @new_size. Just return
+ * the same pointer.
+ */
+ if (user_p_len >= new_size)
+ return old_ptr;
+
+ ret = malloc(new_size);
+ if (__builtin_expect(!ret, 0))
+ return NULL;
+
+ memcpy(ret, heap->user_p, heap->len);
+ munmap(heap, heap->len);
+ return ret;
+}
+
+/* Converts the unsigned long integer <in> to its hex representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (17 bytes for "ffffffffffffffff" or 9 for "ffffffff"). The
+ * buffer is filled from the first byte, and the number of characters emitted
+ * (not counting the trailing zero) is returned. The function is constructed
+ * in a way to optimize the code size and avoid any divide that could add a
+ * dependency on large external functions.
+ */
+static __attribute__((unused))
+int utoh_r(unsigned long in, char *buffer)
+{
+ signed char pos = (~0UL > 0xfffffffful) ? 60 : 28;
+ int digits = 0;
+ int dig;
+
+ do {
+ dig = in >> pos;
+ in -= (uint64_t)dig << pos;
+ pos -= 4;
+ if (dig || digits || pos < 0) {
+ if (dig > 9)
+ dig += 'a' - '0' - 10;
+ buffer[digits++] = '0' + dig;
+ }
+ } while (pos >= 0);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* converts unsigned long <in> to an hex string using the static itoa_buffer
+ * and returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *utoh(unsigned long in)
+{
+ utoh_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* Converts the unsigned long integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for 18446744073709551615 in 64-bit, 11 for
+ * 4294967295 in 32-bit). The buffer is filled from the first byte, and the
+ * number of characters emitted (not counting the trailing zero) is returned.
+ * The function is constructed in a way to optimize the code size and avoid
+ * any divide that could add a dependency on large external functions.
+ */
+static __attribute__((unused))
+int utoa_r(unsigned long in, char *buffer)
+{
+ unsigned long lim;
+ int digits = 0;
+ int pos = (~0UL > 0xfffffffful) ? 19 : 9;
+ int dig;
+
+ do {
+ for (dig = 0, lim = 1; dig < pos; dig++)
+ lim *= 10;
+
+ if (digits || in >= lim || !pos) {
+ for (dig = 0; in >= lim; dig++)
+ in -= lim;
+ buffer[digits++] = '0' + dig;
+ }
+ } while (pos--);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* Converts the signed long integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for -9223372036854775808 in 64-bit, 12 for
+ * -2147483648 in 32-bit). The buffer is filled from the first byte, and the
+ * number of characters emitted (not counting the trailing zero) is returned.
+ */
+static __attribute__((unused))
+int itoa_r(long in, char *buffer)
+{
+ char *ptr = buffer;
+ int len = 0;
+
+ if (in < 0) {
+ in = -in;
+ *(ptr++) = '-';
+ len++;
+ }
+ len += utoa_r(in, ptr);
+ return len;
+}
+
+/* for historical compatibility, same as above but returns the pointer to the
+ * buffer.
+ */
+static inline __attribute__((unused))
+char *ltoa_r(long in, char *buffer)
+{
+ itoa_r(in, buffer);
+ return buffer;
+}
+
+/* converts long integer <in> to a string using the static itoa_buffer and
+ * returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *itoa(long in)
+{
+ itoa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* converts long integer <in> to a string using the static itoa_buffer and
+ * returns the pointer to that string. Same as above, for compatibility.
+ */
+static inline __attribute__((unused))
+char *ltoa(long in)
+{
+ itoa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* converts unsigned long integer <in> to a string using the static itoa_buffer
+ * and returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *utoa(unsigned long in)
+{
+ utoa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* Converts the unsigned 64-bit integer <in> to its hex representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (17 bytes for "ffffffffffffffff"). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned. The function is constructed in a way to optimize
+ * the code size and avoid any divide that could add a dependency on large
+ * external functions.
+ */
+static __attribute__((unused))
+int u64toh_r(uint64_t in, char *buffer)
+{
+ signed char pos = 60;
+ int digits = 0;
+ int dig;
+
+ do {
+ if (sizeof(long) >= 8) {
+ dig = (in >> pos) & 0xF;
+ } else {
+ /* 32-bit platforms: avoid a 64-bit shift */
+ uint32_t d = (pos >= 32) ? (in >> 32) : in;
+ dig = (d >> (pos & 31)) & 0xF;
+ }
+ if (dig > 9)
+ dig += 'a' - '0' - 10;
+ pos -= 4;
+ if (dig || digits || pos < 0)
+ buffer[digits++] = '0' + dig;
+ } while (pos >= 0);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* converts uint64_t <in> to an hex string using the static itoa_buffer and
+ * returns the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *u64toh(uint64_t in)
+{
+ u64toh_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* Converts the unsigned 64-bit integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for 18446744073709551615). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned. The function is constructed in a way to optimize
+ * the code size and avoid any divide that could add a dependency on large
+ * external functions.
+ */
+static __attribute__((unused))
+int u64toa_r(uint64_t in, char *buffer)
+{
+ unsigned long long lim;
+ int digits = 0;
+ int pos = 19; /* start with the highest possible digit */
+ int dig;
+
+ do {
+ for (dig = 0, lim = 1; dig < pos; dig++)
+ lim *= 10;
+
+ if (digits || in >= lim || !pos) {
+ for (dig = 0; in >= lim; dig++)
+ in -= lim;
+ buffer[digits++] = '0' + dig;
+ }
+ } while (pos--);
+
+ buffer[digits] = 0;
+ return digits;
+}
+
+/* Converts the signed 64-bit integer <in> to its string representation into
+ * buffer <buffer>, which must be long enough to store the number and the
+ * trailing zero (21 bytes for -9223372036854775808). The buffer is filled from
+ * the first byte, and the number of characters emitted (not counting the
+ * trailing zero) is returned.
+ */
+static __attribute__((unused))
+int i64toa_r(int64_t in, char *buffer)
+{
+ char *ptr = buffer;
+ int len = 0;
+
+ if (in < 0) {
+ in = -in;
+ *(ptr++) = '-';
+ len++;
+ }
+ len += u64toa_r(in, ptr);
+ return len;
+}
+
+/* converts int64_t <in> to a string using the static itoa_buffer and returns
+ * the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *i64toa(int64_t in)
+{
+ i64toa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+/* converts uint64_t <in> to a string using the static itoa_buffer and returns
+ * the pointer to that string.
+ */
+static inline __attribute__((unused))
+char *u64toa(uint64_t in)
+{
+ u64toa_r(in, itoa_buffer);
+ return itoa_buffer;
+}
+
+#endif /* _NOLIBC_STDLIB_H */
diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
new file mode 100644
index 000000000000..bef35bee9c44
--- /dev/null
+++ b/tools/include/nolibc/string.h
@@ -0,0 +1,285 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * string function definitions for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_STRING_H
+#define _NOLIBC_STRING_H
+
+#include "std.h"
+
+static void *malloc(size_t len);
+
+/*
+ * As much as possible, please keep functions alphabetically sorted.
+ */
+
+static __attribute__((unused))
+int memcmp(const void *s1, const void *s2, size_t n)
+{
+ size_t ofs = 0;
+ char c1 = 0;
+
+ while (ofs < n && !(c1 = ((char *)s1)[ofs] - ((char *)s2)[ofs])) {
+ ofs++;
+ }
+ return c1;
+}
+
+static __attribute__((unused))
+void *_nolibc_memcpy_up(void *dst, const void *src, size_t len)
+{
+ size_t pos = 0;
+
+ while (pos < len) {
+ ((char *)dst)[pos] = ((const char *)src)[pos];
+ pos++;
+ }
+ return dst;
+}
+
+static __attribute__((unused))
+void *_nolibc_memcpy_down(void *dst, const void *src, size_t len)
+{
+ while (len) {
+ len--;
+ ((char *)dst)[len] = ((const char *)src)[len];
+ }
+ return dst;
+}
+
+/* might be ignored by the compiler without -ffreestanding, then found as
+ * missing.
+ */
+__attribute__((weak,unused,section(".text.nolibc_memmove")))
+void *memmove(void *dst, const void *src, size_t len)
+{
+ size_t dir, pos;
+
+ pos = len;
+ dir = -1;
+
+ if (dst < src) {
+ pos = -1;
+ dir = 1;
+ }
+
+ while (len) {
+ pos += dir;
+ ((char *)dst)[pos] = ((const char *)src)[pos];
+ len--;
+ }
+ return dst;
+}
+
+/* must be exported, as it's used by libgcc on ARM */
+__attribute__((weak,unused,section(".text.nolibc_memcpy")))
+void *memcpy(void *dst, const void *src, size_t len)
+{
+ return _nolibc_memcpy_up(dst, src, len);
+}
+
+/* might be ignored by the compiler without -ffreestanding, then found as
+ * missing.
+ */
+__attribute__((weak,unused,section(".text.nolibc_memset")))
+void *memset(void *dst, int b, size_t len)
+{
+ char *p = dst;
+
+ while (len--)
+ *(p++) = b;
+ return dst;
+}
+
+static __attribute__((unused))
+char *strchr(const char *s, int c)
+{
+ while (*s) {
+ if (*s == (char)c)
+ return (char *)s;
+ s++;
+ }
+ return NULL;
+}
+
+static __attribute__((unused))
+int strcmp(const char *a, const char *b)
+{
+ unsigned int c;
+ int diff;
+
+ while (!(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
+ ;
+ return diff;
+}
+
+static __attribute__((unused))
+char *strcpy(char *dst, const char *src)
+{
+ char *ret = dst;
+
+ while ((*dst++ = *src++));
+ return ret;
+}
+
+/* this function is only used with arguments that are not constants or when
+ * it's not known because optimizations are disabled.
+ */
+static __attribute__((unused))
+size_t nolibc_strlen(const char *str)
+{
+ size_t len;
+
+ for (len = 0; str[len]; len++);
+ return len;
+}
+
+/* do not trust __builtin_constant_p() at -O0, as clang will emit a test and
+ * the two branches, then will rely on an external definition of strlen().
+ */
+#if defined(__OPTIMIZE__)
+#define strlen(str) ({ \
+ __builtin_constant_p((str)) ? \
+ __builtin_strlen((str)) : \
+ nolibc_strlen((str)); \
+})
+#else
+#define strlen(str) nolibc_strlen((str))
+#endif
+
+static __attribute__((unused))
+size_t strnlen(const char *str, size_t maxlen)
+{
+ size_t len;
+
+ for (len = 0; (len < maxlen) && str[len]; len++);
+ return len;
+}
+
+static __attribute__((unused))
+char *strdup(const char *str)
+{
+ size_t len;
+ char *ret;
+
+ len = strlen(str);
+ ret = malloc(len + 1);
+ if (__builtin_expect(ret != NULL, 1))
+ memcpy(ret, str, len + 1);
+
+ return ret;
+}
+
+static __attribute__((unused))
+char *strndup(const char *str, size_t maxlen)
+{
+ size_t len;
+ char *ret;
+
+ len = strnlen(str, maxlen);
+ ret = malloc(len + 1);
+ if (__builtin_expect(ret != NULL, 1)) {
+ memcpy(ret, str, len);
+ ret[len] = '\0';
+ }
+
+ return ret;
+}
+
+static __attribute__((unused))
+size_t strlcat(char *dst, const char *src, size_t size)
+{
+ size_t len;
+ char c;
+
+ for (len = 0; dst[len]; len++)
+ ;
+
+ for (;;) {
+ c = *src;
+ if (len < size)
+ dst[len] = c;
+ if (!c)
+ break;
+ len++;
+ src++;
+ }
+
+ return len;
+}
+
+static __attribute__((unused))
+size_t strlcpy(char *dst, const char *src, size_t size)
+{
+ size_t len;
+ char c;
+
+ for (len = 0;;) {
+ c = src[len];
+ if (len < size)
+ dst[len] = c;
+ if (!c)
+ break;
+ len++;
+ }
+ return len;
+}
+
+static __attribute__((unused))
+char *strncat(char *dst, const char *src, size_t size)
+{
+ char *orig = dst;
+
+ while (*dst)
+ dst++;
+
+ while (size && (*dst = *src)) {
+ src++;
+ dst++;
+ size--;
+ }
+
+ *dst = 0;
+ return orig;
+}
+
+static __attribute__((unused))
+int strncmp(const char *a, const char *b, size_t size)
+{
+ unsigned int c;
+ int diff = 0;
+
+ while (size-- &&
+ !(diff = (unsigned char)*a++ - (c = (unsigned char)*b++)) && c)
+ ;
+
+ return diff;
+}
+
+static __attribute__((unused))
+char *strncpy(char *dst, const char *src, size_t size)
+{
+ size_t len;
+
+ for (len = 0; len < size; len++)
+ if ((dst[len] = *src))
+ src++;
+ return dst;
+}
+
+static __attribute__((unused))
+char *strrchr(const char *s, int c)
+{
+ const char *ret = NULL;
+
+ while (*s) {
+ if (*s == (char)c)
+ ret = s;
+ s++;
+ }
+ return (char *)ret;
+}
+
+#endif /* _NOLIBC_STRING_H */
diff --git a/tools/include/nolibc/sys.h b/tools/include/nolibc/sys.h
new file mode 100644
index 000000000000..08491070387b
--- /dev/null
+++ b/tools/include/nolibc/sys.h
@@ -0,0 +1,1247 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Syscall definitions for NOLIBC (those in man(2))
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_SYS_H
+#define _NOLIBC_SYS_H
+
+#include <stdarg.h>
+#include "std.h"
+
+/* system includes */
+#include <asm/unistd.h>
+#include <asm/signal.h> // for SIGCHLD
+#include <asm/ioctls.h>
+#include <asm/mman.h>
+#include <linux/fs.h>
+#include <linux/loop.h>
+#include <linux/time.h>
+
+#include "arch.h"
+#include "errno.h"
+#include "types.h"
+
+
+/* Functions in this file only describe syscalls. They're declared static so
+ * that the compiler usually decides to inline them while still being allowed
+ * to pass a pointer to one of their instances. Each syscall exists in two
+ * versions:
+ * - the "internal" ones, which matches the raw syscall interface at the
+ * kernel level, which may sometimes slightly differ from the documented
+ * libc-level ones. For example most of them return either a valid value
+ * or -errno. All of these are prefixed with "sys_". They may be called
+ * by non-portable applications if desired.
+ *
+ * - the "exported" ones, whose interface must closely match the one
+ * documented in man(2), that applications are supposed to expect. These
+ * ones rely on the internal ones, and set errno.
+ *
+ * Each syscall will be defined with the two functions, sorted in alphabetical
+ * order applied to the exported names.
+ *
+ * In case of doubt about the relevance of a function here, only those which
+ * set errno should be defined here. Wrappers like those appearing in man(3)
+ * should not be placed here.
+ */
+
+
+/*
+ * int brk(void *addr);
+ * void *sbrk(intptr_t inc)
+ */
+
+static __attribute__((unused))
+void *sys_brk(void *addr)
+{
+ return (void *)my_syscall1(__NR_brk, addr);
+}
+
+static __attribute__((unused))
+int brk(void *addr)
+{
+ void *ret = sys_brk(addr);
+
+ if (!ret) {
+ SET_ERRNO(ENOMEM);
+ return -1;
+ }
+ return 0;
+}
+
+static __attribute__((unused))
+void *sbrk(intptr_t inc)
+{
+ void *ret;
+
+ /* first call to find current end */
+ if ((ret = sys_brk(0)) && (sys_brk(ret + inc) == ret + inc))
+ return ret + inc;
+
+ SET_ERRNO(ENOMEM);
+ return (void *)-1;
+}
+
+
+/*
+ * int chdir(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chdir(const char *path)
+{
+ return my_syscall1(__NR_chdir, path);
+}
+
+static __attribute__((unused))
+int chdir(const char *path)
+{
+ int ret = sys_chdir(path);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int chmod(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_chmod(const char *path, mode_t mode)
+{
+#ifdef __NR_fchmodat
+ return my_syscall4(__NR_fchmodat, AT_FDCWD, path, mode, 0);
+#elif defined(__NR_chmod)
+ return my_syscall2(__NR_chmod, path, mode);
+#else
+#error Neither __NR_fchmodat nor __NR_chmod defined, cannot implement sys_chmod()
+#endif
+}
+
+static __attribute__((unused))
+int chmod(const char *path, mode_t mode)
+{
+ int ret = sys_chmod(path, mode);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int chown(const char *path, uid_t owner, gid_t group);
+ */
+
+static __attribute__((unused))
+int sys_chown(const char *path, uid_t owner, gid_t group)
+{
+#ifdef __NR_fchownat
+ return my_syscall5(__NR_fchownat, AT_FDCWD, path, owner, group, 0);
+#elif defined(__NR_chown)
+ return my_syscall3(__NR_chown, path, owner, group);
+#else
+#error Neither __NR_fchownat nor __NR_chown defined, cannot implement sys_chown()
+#endif
+}
+
+static __attribute__((unused))
+int chown(const char *path, uid_t owner, gid_t group)
+{
+ int ret = sys_chown(path, owner, group);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int chroot(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_chroot(const char *path)
+{
+ return my_syscall1(__NR_chroot, path);
+}
+
+static __attribute__((unused))
+int chroot(const char *path)
+{
+ int ret = sys_chroot(path);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int close(int fd);
+ */
+
+static __attribute__((unused))
+int sys_close(int fd)
+{
+ return my_syscall1(__NR_close, fd);
+}
+
+static __attribute__((unused))
+int close(int fd)
+{
+ int ret = sys_close(fd);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int dup(int fd);
+ */
+
+static __attribute__((unused))
+int sys_dup(int fd)
+{
+ return my_syscall1(__NR_dup, fd);
+}
+
+static __attribute__((unused))
+int dup(int fd)
+{
+ int ret = sys_dup(fd);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int dup2(int old, int new);
+ */
+
+static __attribute__((unused))
+int sys_dup2(int old, int new)
+{
+#ifdef __NR_dup3
+ return my_syscall3(__NR_dup3, old, new, 0);
+#elif defined(__NR_dup2)
+ return my_syscall2(__NR_dup2, old, new);
+#else
+#error Neither __NR_dup3 nor __NR_dup2 defined, cannot implement sys_dup2()
+#endif
+}
+
+static __attribute__((unused))
+int dup2(int old, int new)
+{
+ int ret = sys_dup2(old, new);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int dup3(int old, int new, int flags);
+ */
+
+#ifdef __NR_dup3
+static __attribute__((unused))
+int sys_dup3(int old, int new, int flags)
+{
+ return my_syscall3(__NR_dup3, old, new, flags);
+}
+
+static __attribute__((unused))
+int dup3(int old, int new, int flags)
+{
+ int ret = sys_dup3(old, new, flags);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+#endif
+
+
+/*
+ * int execve(const char *filename, char *const argv[], char *const envp[]);
+ */
+
+static __attribute__((unused))
+int sys_execve(const char *filename, char *const argv[], char *const envp[])
+{
+ return my_syscall3(__NR_execve, filename, argv, envp);
+}
+
+static __attribute__((unused))
+int execve(const char *filename, char *const argv[], char *const envp[])
+{
+ int ret = sys_execve(filename, argv, envp);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * void exit(int status);
+ */
+
+static __attribute__((noreturn,unused))
+void sys_exit(int status)
+{
+ my_syscall1(__NR_exit, status & 255);
+ while(1); // shut the "noreturn" warnings.
+}
+
+static __attribute__((noreturn,unused))
+void exit(int status)
+{
+ sys_exit(status);
+}
+
+
+/*
+ * pid_t fork(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_fork(void)
+{
+#ifdef __NR_clone
+ /* note: some archs only have clone() and not fork(). Different archs
+ * have a different API, but most archs have the flags on first arg and
+ * will not use the rest with no other flag.
+ */
+ return my_syscall5(__NR_clone, SIGCHLD, 0, 0, 0, 0);
+#elif defined(__NR_fork)
+ return my_syscall0(__NR_fork);
+#else
+#error Neither __NR_clone nor __NR_fork defined, cannot implement sys_fork()
+#endif
+}
+
+static __attribute__((unused))
+pid_t fork(void)
+{
+ pid_t ret = sys_fork();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int fsync(int fd);
+ */
+
+static __attribute__((unused))
+int sys_fsync(int fd)
+{
+ return my_syscall1(__NR_fsync, fd);
+}
+
+static __attribute__((unused))
+int fsync(int fd)
+{
+ int ret = sys_fsync(fd);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int getdents64(int fd, struct linux_dirent64 *dirp, int count);
+ */
+
+static __attribute__((unused))
+int sys_getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+ return my_syscall3(__NR_getdents64, fd, dirp, count);
+}
+
+static __attribute__((unused))
+int getdents64(int fd, struct linux_dirent64 *dirp, int count)
+{
+ int ret = sys_getdents64(fd, dirp, count);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * pid_t getpgid(pid_t pid);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgid(pid_t pid)
+{
+ return my_syscall1(__NR_getpgid, pid);
+}
+
+static __attribute__((unused))
+pid_t getpgid(pid_t pid)
+{
+ pid_t ret = sys_getpgid(pid);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * pid_t getpgrp(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpgrp(void)
+{
+ return sys_getpgid(0);
+}
+
+static __attribute__((unused))
+pid_t getpgrp(void)
+{
+ return sys_getpgrp();
+}
+
+
+/*
+ * pid_t getpid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getpid(void)
+{
+ return my_syscall0(__NR_getpid);
+}
+
+static __attribute__((unused))
+pid_t getpid(void)
+{
+ return sys_getpid();
+}
+
+
+/*
+ * pid_t getppid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_getppid(void)
+{
+ return my_syscall0(__NR_getppid);
+}
+
+static __attribute__((unused))
+pid_t getppid(void)
+{
+ return sys_getppid();
+}
+
+
+/*
+ * pid_t gettid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_gettid(void)
+{
+ return my_syscall0(__NR_gettid);
+}
+
+static __attribute__((unused))
+pid_t gettid(void)
+{
+ return sys_gettid();
+}
+
+
+/*
+ * int gettimeofday(struct timeval *tv, struct timezone *tz);
+ */
+
+static __attribute__((unused))
+int sys_gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ return my_syscall2(__NR_gettimeofday, tv, tz);
+}
+
+static __attribute__((unused))
+int gettimeofday(struct timeval *tv, struct timezone *tz)
+{
+ int ret = sys_gettimeofday(tv, tz);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int ioctl(int fd, unsigned long req, void *value);
+ */
+
+static __attribute__((unused))
+int sys_ioctl(int fd, unsigned long req, void *value)
+{
+ return my_syscall3(__NR_ioctl, fd, req, value);
+}
+
+static __attribute__((unused))
+int ioctl(int fd, unsigned long req, void *value)
+{
+ int ret = sys_ioctl(fd, req, value);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+/*
+ * int kill(pid_t pid, int signal);
+ */
+
+static __attribute__((unused))
+int sys_kill(pid_t pid, int signal)
+{
+ return my_syscall2(__NR_kill, pid, signal);
+}
+
+static __attribute__((unused))
+int kill(pid_t pid, int signal)
+{
+ int ret = sys_kill(pid, signal);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int link(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_link(const char *old, const char *new)
+{
+#ifdef __NR_linkat
+ return my_syscall5(__NR_linkat, AT_FDCWD, old, AT_FDCWD, new, 0);
+#elif defined(__NR_link)
+ return my_syscall2(__NR_link, old, new);
+#else
+#error Neither __NR_linkat nor __NR_link defined, cannot implement sys_link()
+#endif
+}
+
+static __attribute__((unused))
+int link(const char *old, const char *new)
+{
+ int ret = sys_link(old, new);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * off_t lseek(int fd, off_t offset, int whence);
+ */
+
+static __attribute__((unused))
+off_t sys_lseek(int fd, off_t offset, int whence)
+{
+ return my_syscall3(__NR_lseek, fd, offset, whence);
+}
+
+static __attribute__((unused))
+off_t lseek(int fd, off_t offset, int whence)
+{
+ off_t ret = sys_lseek(fd, offset, whence);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int mkdir(const char *path, mode_t mode);
+ */
+
+static __attribute__((unused))
+int sys_mkdir(const char *path, mode_t mode)
+{
+#ifdef __NR_mkdirat
+ return my_syscall3(__NR_mkdirat, AT_FDCWD, path, mode);
+#elif defined(__NR_mkdir)
+ return my_syscall2(__NR_mkdir, path, mode);
+#else
+#error Neither __NR_mkdirat nor __NR_mkdir defined, cannot implement sys_mkdir()
+#endif
+}
+
+static __attribute__((unused))
+int mkdir(const char *path, mode_t mode)
+{
+ int ret = sys_mkdir(path, mode);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int mknod(const char *path, mode_t mode, dev_t dev);
+ */
+
+static __attribute__((unused))
+long sys_mknod(const char *path, mode_t mode, dev_t dev)
+{
+#ifdef __NR_mknodat
+ return my_syscall4(__NR_mknodat, AT_FDCWD, path, mode, dev);
+#elif defined(__NR_mknod)
+ return my_syscall3(__NR_mknod, path, mode, dev);
+#else
+#error Neither __NR_mknodat nor __NR_mknod defined, cannot implement sys_mknod()
+#endif
+}
+
+static __attribute__((unused))
+int mknod(const char *path, mode_t mode, dev_t dev)
+{
+ int ret = sys_mknod(path, mode, dev);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+#ifndef MAP_SHARED
+#define MAP_SHARED 0x01 /* Share changes */
+#define MAP_PRIVATE 0x02 /* Changes are private */
+#define MAP_SHARED_VALIDATE 0x03 /* share + validate extension flags */
+#endif
+
+#ifndef MAP_FAILED
+#define MAP_FAILED ((void *)-1)
+#endif
+
+static __attribute__((unused))
+void *sys_mmap(void *addr, size_t length, int prot, int flags, int fd,
+ off_t offset)
+{
+#ifndef my_syscall6
+ /* Function not implemented. */
+ return -ENOSYS;
+#else
+
+ int n;
+
+#if defined(__i386__)
+ n = __NR_mmap2;
+ offset >>= 12;
+#else
+ n = __NR_mmap;
+#endif
+
+ return (void *)my_syscall6(n, addr, length, prot, flags, fd, offset);
+#endif
+}
+
+static __attribute__((unused))
+void *mmap(void *addr, size_t length, int prot, int flags, int fd, off_t offset)
+{
+ void *ret = sys_mmap(addr, length, prot, flags, fd, offset);
+
+ if ((unsigned long)ret >= -4095UL) {
+ SET_ERRNO(-(long)ret);
+ ret = MAP_FAILED;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+int sys_munmap(void *addr, size_t length)
+{
+ return my_syscall2(__NR_munmap, addr, length);
+}
+
+static __attribute__((unused))
+int munmap(void *addr, size_t length)
+{
+ int ret = sys_munmap(addr, length);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+/*
+ * int mount(const char *source, const char *target,
+ * const char *fstype, unsigned long flags,
+ * const void *data);
+ */
+static __attribute__((unused))
+int sys_mount(const char *src, const char *tgt, const char *fst,
+ unsigned long flags, const void *data)
+{
+ return my_syscall5(__NR_mount, src, tgt, fst, flags, data);
+}
+
+static __attribute__((unused))
+int mount(const char *src, const char *tgt,
+ const char *fst, unsigned long flags,
+ const void *data)
+{
+ int ret = sys_mount(src, tgt, fst, flags, data);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int open(const char *path, int flags[, mode_t mode]);
+ */
+
+static __attribute__((unused))
+int sys_open(const char *path, int flags, mode_t mode)
+{
+#ifdef __NR_openat
+ return my_syscall4(__NR_openat, AT_FDCWD, path, flags, mode);
+#elif defined(__NR_open)
+ return my_syscall3(__NR_open, path, flags, mode);
+#else
+#error Neither __NR_openat nor __NR_open defined, cannot implement sys_open()
+#endif
+}
+
+static __attribute__((unused))
+int open(const char *path, int flags, ...)
+{
+ mode_t mode = 0;
+ int ret;
+
+ if (flags & O_CREAT) {
+ va_list args;
+
+ va_start(args, flags);
+ mode = va_arg(args, mode_t);
+ va_end(args);
+ }
+
+ ret = sys_open(path, flags, mode);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int pivot_root(const char *new, const char *old);
+ */
+
+static __attribute__((unused))
+int sys_pivot_root(const char *new, const char *old)
+{
+ return my_syscall2(__NR_pivot_root, new, old);
+}
+
+static __attribute__((unused))
+int pivot_root(const char *new, const char *old)
+{
+ int ret = sys_pivot_root(new, old);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int poll(struct pollfd *fds, int nfds, int timeout);
+ */
+
+static __attribute__((unused))
+int sys_poll(struct pollfd *fds, int nfds, int timeout)
+{
+#if defined(__NR_ppoll)
+ struct timespec t;
+
+ if (timeout >= 0) {
+ t.tv_sec = timeout / 1000;
+ t.tv_nsec = (timeout % 1000) * 1000000;
+ }
+ return my_syscall4(__NR_ppoll, fds, nfds, (timeout >= 0) ? &t : NULL, NULL);
+#elif defined(__NR_poll)
+ return my_syscall3(__NR_poll, fds, nfds, timeout);
+#else
+#error Neither __NR_ppoll nor __NR_poll defined, cannot implement sys_poll()
+#endif
+}
+
+static __attribute__((unused))
+int poll(struct pollfd *fds, int nfds, int timeout)
+{
+ int ret = sys_poll(fds, nfds, timeout);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * ssize_t read(int fd, void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_read(int fd, void *buf, size_t count)
+{
+ return my_syscall3(__NR_read, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t read(int fd, void *buf, size_t count)
+{
+ ssize_t ret = sys_read(fd, buf, count);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int reboot(int cmd);
+ * <cmd> is among LINUX_REBOOT_CMD_*
+ */
+
+static __attribute__((unused))
+ssize_t sys_reboot(int magic1, int magic2, int cmd, void *arg)
+{
+ return my_syscall4(__NR_reboot, magic1, magic2, cmd, arg);
+}
+
+static __attribute__((unused))
+int reboot(int cmd)
+{
+ int ret = sys_reboot(LINUX_REBOOT_MAGIC1, LINUX_REBOOT_MAGIC2, cmd, 0);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int sched_yield(void);
+ */
+
+static __attribute__((unused))
+int sys_sched_yield(void)
+{
+ return my_syscall0(__NR_sched_yield);
+}
+
+static __attribute__((unused))
+int sched_yield(void)
+{
+ int ret = sys_sched_yield();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int select(int nfds, fd_set *read_fds, fd_set *write_fds,
+ * fd_set *except_fds, struct timeval *timeout);
+ */
+
+static __attribute__((unused))
+int sys_select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+#if defined(__ARCH_WANT_SYS_OLD_SELECT) && !defined(__NR__newselect)
+ struct sel_arg_struct {
+ unsigned long n;
+ fd_set *r, *w, *e;
+ struct timeval *t;
+ } arg = { .n = nfds, .r = rfds, .w = wfds, .e = efds, .t = timeout };
+ return my_syscall1(__NR_select, &arg);
+#elif defined(__ARCH_WANT_SYS_PSELECT6) && defined(__NR_pselect6)
+ struct timespec t;
+
+ if (timeout) {
+ t.tv_sec = timeout->tv_sec;
+ t.tv_nsec = timeout->tv_usec * 1000;
+ }
+ return my_syscall6(__NR_pselect6, nfds, rfds, wfds, efds, timeout ? &t : NULL, NULL);
+#elif defined(__NR__newselect) || defined(__NR_select)
+#ifndef __NR__newselect
+#define __NR__newselect __NR_select
+#endif
+ return my_syscall5(__NR__newselect, nfds, rfds, wfds, efds, timeout);
+#else
+#error None of __NR_select, __NR_pselect6, nor __NR__newselect defined, cannot implement sys_select()
+#endif
+}
+
+static __attribute__((unused))
+int select(int nfds, fd_set *rfds, fd_set *wfds, fd_set *efds, struct timeval *timeout)
+{
+ int ret = sys_select(nfds, rfds, wfds, efds, timeout);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int setpgid(pid_t pid, pid_t pgid);
+ */
+
+static __attribute__((unused))
+int sys_setpgid(pid_t pid, pid_t pgid)
+{
+ return my_syscall2(__NR_setpgid, pid, pgid);
+}
+
+static __attribute__((unused))
+int setpgid(pid_t pid, pid_t pgid)
+{
+ int ret = sys_setpgid(pid, pgid);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * pid_t setsid(void);
+ */
+
+static __attribute__((unused))
+pid_t sys_setsid(void)
+{
+ return my_syscall0(__NR_setsid);
+}
+
+static __attribute__((unused))
+pid_t setsid(void)
+{
+ pid_t ret = sys_setsid();
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int stat(const char *path, struct stat *buf);
+ * Warning: the struct stat's layout is arch-dependent.
+ */
+
+static __attribute__((unused))
+int sys_stat(const char *path, struct stat *buf)
+{
+ struct sys_stat_struct stat;
+ long ret;
+
+#ifdef __NR_newfstatat
+ /* only solution for arm64 */
+ ret = my_syscall4(__NR_newfstatat, AT_FDCWD, path, &stat, 0);
+#elif defined(__NR_stat)
+ ret = my_syscall2(__NR_stat, path, &stat);
+#else
+#error Neither __NR_newfstatat nor __NR_stat defined, cannot implement sys_stat()
+#endif
+ buf->st_dev = stat.st_dev;
+ buf->st_ino = stat.st_ino;
+ buf->st_mode = stat.st_mode;
+ buf->st_nlink = stat.st_nlink;
+ buf->st_uid = stat.st_uid;
+ buf->st_gid = stat.st_gid;
+ buf->st_rdev = stat.st_rdev;
+ buf->st_size = stat.st_size;
+ buf->st_blksize = stat.st_blksize;
+ buf->st_blocks = stat.st_blocks;
+ buf->st_atime = stat.st_atime;
+ buf->st_mtime = stat.st_mtime;
+ buf->st_ctime = stat.st_ctime;
+ return ret;
+}
+
+static __attribute__((unused))
+int stat(const char *path, struct stat *buf)
+{
+ int ret = sys_stat(path, buf);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int symlink(const char *old, const char *new);
+ */
+
+static __attribute__((unused))
+int sys_symlink(const char *old, const char *new)
+{
+#ifdef __NR_symlinkat
+ return my_syscall3(__NR_symlinkat, old, AT_FDCWD, new);
+#elif defined(__NR_symlink)
+ return my_syscall2(__NR_symlink, old, new);
+#else
+#error Neither __NR_symlinkat nor __NR_symlink defined, cannot implement sys_symlink()
+#endif
+}
+
+static __attribute__((unused))
+int symlink(const char *old, const char *new)
+{
+ int ret = sys_symlink(old, new);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * mode_t umask(mode_t mode);
+ */
+
+static __attribute__((unused))
+mode_t sys_umask(mode_t mode)
+{
+ return my_syscall1(__NR_umask, mode);
+}
+
+static __attribute__((unused))
+mode_t umask(mode_t mode)
+{
+ return sys_umask(mode);
+}
+
+
+/*
+ * int umount2(const char *path, int flags);
+ */
+
+static __attribute__((unused))
+int sys_umount2(const char *path, int flags)
+{
+ return my_syscall2(__NR_umount2, path, flags);
+}
+
+static __attribute__((unused))
+int umount2(const char *path, int flags)
+{
+ int ret = sys_umount2(path, flags);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * int unlink(const char *path);
+ */
+
+static __attribute__((unused))
+int sys_unlink(const char *path)
+{
+#ifdef __NR_unlinkat
+ return my_syscall3(__NR_unlinkat, AT_FDCWD, path, 0);
+#elif defined(__NR_unlink)
+ return my_syscall1(__NR_unlink, path);
+#else
+#error Neither __NR_unlinkat nor __NR_unlink defined, cannot implement sys_unlink()
+#endif
+}
+
+static __attribute__((unused))
+int unlink(const char *path)
+{
+ int ret = sys_unlink(path);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * pid_t wait(int *status);
+ * pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage);
+ * pid_t waitpid(pid_t pid, int *status, int options);
+ */
+
+static __attribute__((unused))
+pid_t sys_wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+ return my_syscall4(__NR_wait4, pid, status, options, rusage);
+}
+
+static __attribute__((unused))
+pid_t wait(int *status)
+{
+ pid_t ret = sys_wait4(-1, status, 0, NULL);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+static __attribute__((unused))
+pid_t wait4(pid_t pid, int *status, int options, struct rusage *rusage)
+{
+ pid_t ret = sys_wait4(pid, status, options, rusage);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+static __attribute__((unused))
+pid_t waitpid(pid_t pid, int *status, int options)
+{
+ pid_t ret = sys_wait4(pid, status, options, NULL);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+/*
+ * ssize_t write(int fd, const void *buf, size_t count);
+ */
+
+static __attribute__((unused))
+ssize_t sys_write(int fd, const void *buf, size_t count)
+{
+ return my_syscall3(__NR_write, fd, buf, count);
+}
+
+static __attribute__((unused))
+ssize_t write(int fd, const void *buf, size_t count)
+{
+ ssize_t ret = sys_write(fd, buf, count);
+
+ if (ret < 0) {
+ SET_ERRNO(-ret);
+ ret = -1;
+ }
+ return ret;
+}
+
+
+#endif /* _NOLIBC_SYS_H */
diff --git a/tools/include/nolibc/time.h b/tools/include/nolibc/time.h
new file mode 100644
index 000000000000..d18b7661fdd7
--- /dev/null
+++ b/tools/include/nolibc/time.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * time function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_TIME_H
+#define _NOLIBC_TIME_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+static __attribute__((unused))
+time_t time(time_t *tptr)
+{
+ struct timeval tv;
+
+ /* note, cannot fail here */
+ sys_gettimeofday(&tv, NULL);
+
+ if (tptr)
+ *tptr = tv.tv_sec;
+ return tv.tv_sec;
+}
+
+#endif /* _NOLIBC_TIME_H */
diff --git a/tools/include/nolibc/types.h b/tools/include/nolibc/types.h
new file mode 100644
index 000000000000..959997034e55
--- /dev/null
+++ b/tools/include/nolibc/types.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * Special types used by various syscalls for NOLIBC
+ * Copyright (C) 2017-2021 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_TYPES_H
+#define _NOLIBC_TYPES_H
+
+#include "std.h"
+#include <linux/time.h>
+
+
+/* Only the generic macros and types may be defined here. The arch-specific
+ * ones such as the O_RDONLY and related macros used by fcntl() and open(), or
+ * the layout of sys_stat_struct must not be defined here.
+ */
+
+/* stat flags (WARNING, octal here) */
+#define S_IFDIR 0040000
+#define S_IFCHR 0020000
+#define S_IFBLK 0060000
+#define S_IFREG 0100000
+#define S_IFIFO 0010000
+#define S_IFLNK 0120000
+#define S_IFSOCK 0140000
+#define S_IFMT 0170000
+
+#define S_ISDIR(mode) (((mode) & S_IFDIR) == S_IFDIR)
+#define S_ISCHR(mode) (((mode) & S_IFCHR) == S_IFCHR)
+#define S_ISBLK(mode) (((mode) & S_IFBLK) == S_IFBLK)
+#define S_ISREG(mode) (((mode) & S_IFREG) == S_IFREG)
+#define S_ISFIFO(mode) (((mode) & S_IFIFO) == S_IFIFO)
+#define S_ISLNK(mode) (((mode) & S_IFLNK) == S_IFLNK)
+#define S_ISSOCK(mode) (((mode) & S_IFSOCK) == S_IFSOCK)
+
+/* dirent types */
+#define DT_UNKNOWN 0x0
+#define DT_FIFO 0x1
+#define DT_CHR 0x2
+#define DT_DIR 0x4
+#define DT_BLK 0x6
+#define DT_REG 0x8
+#define DT_LNK 0xa
+#define DT_SOCK 0xc
+
+/* commonly an fd_set represents 256 FDs */
+#ifndef FD_SETSIZE
+#define FD_SETSIZE 256
+#endif
+
+/* PATH_MAX and MAXPATHLEN are often used and found with plenty of different
+ * values.
+ */
+#ifndef PATH_MAX
+#define PATH_MAX 4096
+#endif
+
+#ifndef MAXPATHLEN
+#define MAXPATHLEN (PATH_MAX)
+#endif
+
+/* Special FD used by all the *at functions */
+#ifndef AT_FDCWD
+#define AT_FDCWD (-100)
+#endif
+
+/* whence values for lseek() */
+#define SEEK_SET 0
+#define SEEK_CUR 1
+#define SEEK_END 2
+
+/* cmd for reboot() */
+#define LINUX_REBOOT_MAGIC1 0xfee1dead
+#define LINUX_REBOOT_MAGIC2 0x28121969
+#define LINUX_REBOOT_CMD_HALT 0xcdef0123
+#define LINUX_REBOOT_CMD_POWER_OFF 0x4321fedc
+#define LINUX_REBOOT_CMD_RESTART 0x01234567
+#define LINUX_REBOOT_CMD_SW_SUSPEND 0xd000fce2
+
+/* Macros used on waitpid()'s return status */
+#define WEXITSTATUS(status) (((status) & 0xff00) >> 8)
+#define WIFEXITED(status) (((status) & 0x7f) == 0)
+
+/* waitpid() flags */
+#define WNOHANG 1
+
+/* standard exit() codes */
+#define EXIT_SUCCESS 0
+#define EXIT_FAILURE 1
+
+/* for select() */
+typedef struct {
+ uint32_t fd32[(FD_SETSIZE + 31) / 32];
+} fd_set;
+
+#define FD_CLR(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fd32[__fd / 32] &= ~(1U << (__fd & 31)); \
+ } while (0)
+
+#define FD_SET(fd, set) do { \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ if (__fd >= 0) \
+ __set->fd32[__fd / 32] |= 1U << (__fd & 31); \
+ } while (0)
+
+#define FD_ISSET(fd, set) ({ \
+ fd_set *__set = (set); \
+ int __fd = (fd); \
+ int __r = 0; \
+ if (__fd >= 0) \
+ __r = !!(__set->fd32[__fd / 32] & 1U << (__fd & 31)); \
+ __r; \
+ })
+
+#define FD_ZERO(set) do { \
+ fd_set *__set = (set); \
+ int __idx; \
+ for (__idx = 0; __idx < (FD_SETSIZE+31) / 32; __idx ++) \
+ __set->fd32[__idx] = 0; \
+ } while (0)
+
+/* for poll() */
+#define POLLIN 0x0001
+#define POLLPRI 0x0002
+#define POLLOUT 0x0004
+#define POLLERR 0x0008
+#define POLLHUP 0x0010
+#define POLLNVAL 0x0020
+
+struct pollfd {
+ int fd;
+ short int events;
+ short int revents;
+};
+
+/* for getdents64() */
+struct linux_dirent64 {
+ uint64_t d_ino;
+ int64_t d_off;
+ unsigned short d_reclen;
+ unsigned char d_type;
+ char d_name[];
+};
+
+/* needed by wait4() */
+struct rusage {
+ struct timeval ru_utime;
+ struct timeval ru_stime;
+ long ru_maxrss;
+ long ru_ixrss;
+ long ru_idrss;
+ long ru_isrss;
+ long ru_minflt;
+ long ru_majflt;
+ long ru_nswap;
+ long ru_inblock;
+ long ru_oublock;
+ long ru_msgsnd;
+ long ru_msgrcv;
+ long ru_nsignals;
+ long ru_nvcsw;
+ long ru_nivcsw;
+};
+
+/* The format of the struct as returned by the libc to the application, which
+ * significantly differs from the format returned by the stat() syscall flavours.
+ */
+struct stat {
+ dev_t st_dev; /* ID of device containing file */
+ ino_t st_ino; /* inode number */
+ mode_t st_mode; /* protection */
+ nlink_t st_nlink; /* number of hard links */
+ uid_t st_uid; /* user ID of owner */
+ gid_t st_gid; /* group ID of owner */
+ dev_t st_rdev; /* device ID (if special file) */
+ off_t st_size; /* total size, in bytes */
+ blksize_t st_blksize; /* blocksize for file system I/O */
+ blkcnt_t st_blocks; /* number of 512B blocks allocated */
+ time_t st_atime; /* time of last access */
+ time_t st_mtime; /* time of last modification */
+ time_t st_ctime; /* time of last status change */
+};
+
+/* WARNING, it only deals with the 4096 first majors and 256 first minors */
+#define makedev(major, minor) ((dev_t)((((major) & 0xfff) << 8) | ((minor) & 0xff)))
+#define major(dev) ((unsigned int)(((dev) >> 8) & 0xfff))
+#define minor(dev) ((unsigned int)(((dev) & 0xff))
+
+#ifndef offsetof
+#define offsetof(TYPE, FIELD) ((size_t) &((TYPE *)0)->FIELD)
+#endif
+
+#ifndef container_of
+#define container_of(PTR, TYPE, FIELD) ({ \
+ __typeof__(((TYPE *)0)->FIELD) *__FIELD_PTR = (PTR); \
+ (TYPE *)((char *) __FIELD_PTR - offsetof(TYPE, FIELD)); \
+})
+#endif
+
+#endif /* _NOLIBC_TYPES_H */
diff --git a/tools/include/nolibc/unistd.h b/tools/include/nolibc/unistd.h
new file mode 100644
index 000000000000..1c25e20ee360
--- /dev/null
+++ b/tools/include/nolibc/unistd.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * unistd function definitions for NOLIBC
+ * Copyright (C) 2017-2022 Willy Tarreau <w@1wt.eu>
+ */
+
+#ifndef _NOLIBC_UNISTD_H
+#define _NOLIBC_UNISTD_H
+
+#include "std.h"
+#include "arch.h"
+#include "types.h"
+#include "sys.h"
+
+
+static __attribute__((unused))
+int msleep(unsigned int msecs)
+{
+ struct timeval my_timeval = { msecs / 1000, (msecs % 1000) * 1000 };
+
+ if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+ return (my_timeval.tv_sec * 1000) +
+ (my_timeval.tv_usec / 1000) +
+ !!(my_timeval.tv_usec % 1000);
+ else
+ return 0;
+}
+
+static __attribute__((unused))
+unsigned int sleep(unsigned int seconds)
+{
+ struct timeval my_timeval = { seconds, 0 };
+
+ if (sys_select(0, 0, 0, 0, &my_timeval) < 0)
+ return my_timeval.tv_sec + !!my_timeval.tv_usec;
+ else
+ return 0;
+}
+
+static __attribute__((unused))
+int usleep(unsigned int usecs)
+{
+ struct timeval my_timeval = { usecs / 1000000, usecs % 1000000 };
+
+ return sys_select(0, 0, 0, 0, &my_timeval);
+}
+
+static __attribute__((unused))
+int tcsetpgrp(int fd, pid_t pid)
+{
+ return ioctl(fd, TIOCSPGRP, &pid);
+}
+
+#endif /* _NOLIBC_UNISTD_H */
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 91a6fe4e02c0..6a184d260c7f 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -445,7 +445,13 @@ struct kvm_run {
#define KVM_SYSTEM_EVENT_RESET 2
#define KVM_SYSTEM_EVENT_CRASH 3
__u32 type;
- __u64 flags;
+ __u32 ndata;
+ union {
+#ifndef __KERNEL__
+ __u64 flags;
+#endif
+ __u64 data[16];
+ };
} system_event;
/* KVM_EXIT_S390_STSI */
struct {
@@ -1144,6 +1150,8 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_S390_MEM_OP_EXTENSION 211
#define KVM_CAP_PMU_CAPABILITY 212
#define KVM_CAP_DISABLE_QUIRKS2 213
+/* #define KVM_CAP_VM_TSC_CONTROL 214 */
+#define KVM_CAP_SYSTEM_EVENT_DATA 215
#ifdef KVM_CAP_IRQ_ROUTING
diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h
index c998860d7bbc..5d99e7c242a2 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/include/uapi/linux/vhost.h
@@ -150,4 +150,11 @@
/* Get the valid iova range */
#define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \
struct vhost_vdpa_iova_range)
+
+/* Get the config size */
+#define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32)
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32)
+
#endif
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index 1b15ba13c477..a09315538a30 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -577,7 +577,6 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
{
struct perf_evsel *evsel;
const struct perf_cpu_map *cpus = evlist->user_requested_cpus;
- const struct perf_thread_map *threads = evlist->threads;
if (!ops || !ops->get || !ops->mmap)
return -EINVAL;
@@ -589,7 +588,7 @@ int perf_evlist__mmap_ops(struct perf_evlist *evlist,
perf_evlist__for_each_entry(evlist, evsel) {
if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
evsel->sample_id == NULL &&
- perf_evsel__alloc_id(evsel, perf_cpu_map__nr(cpus), threads->nr) < 0)
+ perf_evsel__alloc_id(evsel, evsel->fd->max_x, evsel->fd->max_y) < 0)
return -ENOMEM;
}
diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
index 39ebf6192016..9fa75943f2ed 100644
--- a/tools/lib/subcmd/parse-options.c
+++ b/tools/lib/subcmd/parse-options.c
@@ -806,9 +806,9 @@ static int option__cmp(const void *va, const void *vb)
static struct option *options__order(const struct option *opts)
{
- int nr_opts = 0, len;
+ int nr_opts = 0, nr_group = 0, len;
const struct option *o = opts;
- struct option *ordered;
+ struct option *opt, *ordered, *group;
for (o = opts; o->type != OPTION_END; o++)
++nr_opts;
@@ -819,7 +819,18 @@ static struct option *options__order(const struct option *opts)
goto out;
memcpy(ordered, opts, len);
- qsort(ordered, nr_opts, sizeof(*o), option__cmp);
+ /* sort each option group individually */
+ for (opt = group = ordered; opt->type != OPTION_END; opt++) {
+ if (opt->type == OPTION_GROUP) {
+ qsort(group, nr_group, sizeof(*opt), option__cmp);
+ group = opt + 1;
+ nr_group = 0;
+ continue;
+ }
+ nr_group++;
+ }
+ qsort(group, nr_group, sizeof(*opt), option__cmp);
+
out:
return ordered;
}
diff --git a/tools/lib/thermal/.gitignore b/tools/lib/thermal/.gitignore
new file mode 100644
index 000000000000..5d2aeda80fea
--- /dev/null
+++ b/tools/lib/thermal/.gitignore
@@ -0,0 +1,2 @@
+libthermal.so*
+libthermal.pc
diff --git a/tools/lib/thermal/Build b/tools/lib/thermal/Build
new file mode 100644
index 000000000000..4a892d9e24f9
--- /dev/null
+++ b/tools/lib/thermal/Build
@@ -0,0 +1,5 @@
+libthermal-y += commands.o
+libthermal-y += events.o
+libthermal-y += thermal_nl.o
+libthermal-y += sampling.o
+libthermal-y += thermal.o
diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile
new file mode 100644
index 000000000000..2d0d255fd0e1
--- /dev/null
+++ b/tools/lib/thermal/Makefile
@@ -0,0 +1,165 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Most of this file is copied from tools/lib/perf/Makefile
+
+LIBTHERMAL_VERSION = 0
+LIBTHERMAL_PATCHLEVEL = 0
+LIBTHERMAL_EXTRAVERSION = 1
+
+MAKEFLAGS += --no-print-directory
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+# $(info Determined 'srctree' to be $(srctree))
+endif
+
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+include $(srctree)/tools/scripts/Makefile.include
+include $(srctree)/tools/scripts/Makefile.arch
+
+ifeq ($(LP64), 1)
+ libdir_relative = lib64
+else
+ libdir_relative = lib
+endif
+
+prefix ?=
+libdir = $(prefix)/$(libdir_relative)
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
+
+ifeq ("$(origin V)", "command line")
+ VERBOSE = $(V)
+endif
+ifndef VERBOSE
+ VERBOSE = 0
+endif
+
+ifeq ($(VERBOSE),1)
+ Q =
+else
+ Q = @
+endif
+
+# Set compile option CFLAGS
+ifdef EXTRA_CFLAGS
+ CFLAGS := $(EXTRA_CFLAGS)
+else
+ CFLAGS := -g -Wall
+endif
+
+INCLUDES = \
+-I/usr/include/libnl3 \
+-I$(srctree)/tools/lib/thermal/include \
+-I$(srctree)/tools/lib/ \
+-I$(srctree)/tools/include \
+-I$(srctree)/tools/arch/$(SRCARCH)/include/ \
+-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \
+-I$(srctree)/tools/include/uapi
+
+# Append required CFLAGS
+override CFLAGS += $(EXTRA_WARNINGS)
+override CFLAGS += -Werror -Wall
+override CFLAGS += -fPIC
+override CFLAGS += $(INCLUDES)
+override CFLAGS += -fvisibility=hidden
+override CFGLAS += -Wl,-L.
+override CFGLAS += -Wl,-lthermal
+
+all:
+
+export srctree OUTPUT CC LD CFLAGS V
+export DESTDIR DESTDIR_SQ
+
+include $(srctree)/tools/build/Makefile.include
+
+VERSION_SCRIPT := libthermal.map
+
+PATCHLEVEL = $(LIBTHERMAL_PATCHLEVEL)
+EXTRAVERSION = $(LIBTHERMAL_EXTRAVERSION)
+VERSION = $(LIBTHERMAL_VERSION).$(LIBTHERMAL_PATCHLEVEL).$(LIBTHERMAL_EXTRAVERSION)
+
+LIBTHERMAL_SO := $(OUTPUT)libthermal.so.$(VERSION)
+LIBTHERMAL_A := $(OUTPUT)libthermal.a
+LIBTHERMAL_IN := $(OUTPUT)libthermal-in.o
+LIBTHERMAL_PC := $(OUTPUT)libthermal.pc
+LIBTHERMAL_ALL := $(LIBTHERMAL_A) $(OUTPUT)libthermal.so*
+
+THERMAL_UAPI := include/uapi/linux/thermal.h
+
+$(THERMAL_UAPI): FORCE
+ ln -sf $(srctree)/$@ $(srctree)/tools/$@
+
+$(LIBTHERMAL_IN): FORCE
+ $(Q)$(MAKE) $(build)=libthermal
+
+$(LIBTHERMAL_A): $(LIBTHERMAL_IN)
+ $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBTHERMAL_IN)
+
+$(LIBTHERMAL_SO): $(LIBTHERMAL_IN)
+ $(QUIET_LINK)$(CC) --shared -Wl,-soname,libthermal.so \
+ -Wl,--version-script=$(VERSION_SCRIPT) $^ -o $@
+ @ln -sf $(@F) $(OUTPUT)libthermal.so
+ @ln -sf $(@F) $(OUTPUT)libthermal.so.$(LIBTHERMAL_VERSION)
+
+
+libs: $(THERMAL_UAPI) $(LIBTHERMAL_A) $(LIBTHERMAL_SO) $(LIBTHERMAL_PC)
+
+all: fixdep
+ $(Q)$(MAKE) libs
+
+clean:
+ $(call QUIET_CLEAN, libthermal) $(RM) $(LIBTHERMAL_A) \
+ *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_VERSION) .*.d .*.cmd LIBTHERMAL-CFLAGS $(LIBTHERMAL_PC)
+
+$(LIBTHERMAL_PC):
+ $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+ -e "s|@LIBDIR@|$(libdir_SQ)|" \
+ -e "s|@VERSION@|$(VERSION)|" \
+ < libthermal.pc.template > $@
+
+define do_install_mkdir
+ if [ ! -d '$(DESTDIR_SQ)$1' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+ fi
+endef
+
+define do_install
+ if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
+ fi; \
+ $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: libs
+ $(call QUIET_INSTALL, $(LIBTHERMAL_ALL)) \
+ $(call do_install_mkdir,$(libdir_SQ)); \
+ cp -fpR $(LIBTHERMAL_ALL) $(DESTDIR)$(libdir_SQ)
+
+install_headers:
+ $(call QUIET_INSTALL, headers) \
+ $(call do_install,include/thermal.h,$(prefix)/include/thermal,644); \
+
+install_pkgconfig: $(LIBTHERMAL_PC)
+ $(call QUIET_INSTALL, $(LIBTHERMAL_PC)) \
+ $(call do_install,$(LIBTHERMAL_PC),$(libdir_SQ)/pkgconfig,644)
+
+install_doc:
+ $(Q)$(MAKE) -C Documentation install-man install-html install-examples
+
+install: install_lib install_headers install_pkgconfig
+
+FORCE:
+
+.PHONY: all install clean FORCE
diff --git a/tools/lib/thermal/commands.c b/tools/lib/thermal/commands.c
new file mode 100644
index 000000000000..73d4d4e8d6ec
--- /dev/null
+++ b/tools/lib/thermal/commands.c
@@ -0,0 +1,349 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <thermal.h>
+#include "thermal_nl.h"
+
+static struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = {
+ /* Thermal zone */
+ [THERMAL_GENL_ATTR_TZ] = { .type = NLA_NESTED },
+ [THERMAL_GENL_ATTR_TZ_ID] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_TEMP] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_TRIP] = { .type = NLA_NESTED },
+ [THERMAL_GENL_ATTR_TZ_TRIP_ID] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_TRIP_TEMP] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_TRIP_TYPE] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_TRIP_HYST] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_MODE] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_TZ_NAME] = { .type = NLA_STRING },
+
+ /* Governor(s) */
+ [THERMAL_GENL_ATTR_TZ_GOV] = { .type = NLA_NESTED },
+ [THERMAL_GENL_ATTR_TZ_GOV_NAME] = { .type = NLA_STRING },
+
+ /* Cooling devices */
+ [THERMAL_GENL_ATTR_CDEV] = { .type = NLA_NESTED },
+ [THERMAL_GENL_ATTR_CDEV_ID] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_CDEV_CUR_STATE] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_CDEV_MAX_STATE] = { .type = NLA_U32 },
+ [THERMAL_GENL_ATTR_CDEV_NAME] = { .type = NLA_STRING },
+};
+
+static int parse_tz_get(struct genl_info *info, struct thermal_zone **tz)
+{
+ struct nlattr *attr;
+ struct thermal_zone *__tz = NULL;
+ size_t size = 0;
+ int rem;
+
+ nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ], rem) {
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_ID) {
+
+ size++;
+
+ __tz = realloc(__tz, sizeof(*__tz) * (size + 2));
+ if (!__tz)
+ return THERMAL_ERROR;
+
+ __tz[size - 1].id = nla_get_u32(attr);
+ }
+
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_NAME)
+ nla_strlcpy(__tz[size - 1].name, attr,
+ THERMAL_NAME_LENGTH);
+ }
+
+ if (__tz)
+ __tz[size].id = -1;
+
+ *tz = __tz;
+
+ return THERMAL_SUCCESS;
+}
+
+static int parse_cdev_get(struct genl_info *info, struct thermal_cdev **cdev)
+{
+ struct nlattr *attr;
+ struct thermal_cdev *__cdev = NULL;
+ size_t size = 0;
+ int rem;
+
+ nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_CDEV], rem) {
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_ID) {
+
+ size++;
+
+ __cdev = realloc(__cdev, sizeof(*__cdev) * (size + 2));
+ if (!__cdev)
+ return THERMAL_ERROR;
+
+ __cdev[size - 1].id = nla_get_u32(attr);
+ }
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_NAME) {
+ nla_strlcpy(__cdev[size - 1].name, attr,
+ THERMAL_NAME_LENGTH);
+ }
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_CUR_STATE)
+ __cdev[size - 1].cur_state = nla_get_u32(attr);
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_CDEV_MAX_STATE)
+ __cdev[size - 1].max_state = nla_get_u32(attr);
+ }
+
+ if (__cdev)
+ __cdev[size].id = -1;
+
+ *cdev = __cdev;
+
+ return THERMAL_SUCCESS;
+}
+
+static int parse_tz_get_trip(struct genl_info *info, struct thermal_zone *tz)
+{
+ struct nlattr *attr;
+ struct thermal_trip *__tt = NULL;
+ size_t size = 0;
+ int rem;
+
+ nla_for_each_nested(attr, info->attrs[THERMAL_GENL_ATTR_TZ_TRIP], rem) {
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_ID) {
+
+ size++;
+
+ __tt = realloc(__tt, sizeof(*__tt) * (size + 2));
+ if (!__tt)
+ return THERMAL_ERROR;
+
+ __tt[size - 1].id = nla_get_u32(attr);
+ }
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TYPE)
+ __tt[size - 1].type = nla_get_u32(attr);
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_TEMP)
+ __tt[size - 1].temp = nla_get_u32(attr);
+
+ if (nla_type(attr) == THERMAL_GENL_ATTR_TZ_TRIP_HYST)
+ __tt[size - 1].hyst = nla_get_u32(attr);
+ }
+
+ if (__tt)
+ __tt[size].id = -1;
+
+ tz->trip = __tt;
+
+ return THERMAL_SUCCESS;
+}
+
+static int parse_tz_get_temp(struct genl_info *info, struct thermal_zone *tz)
+{
+ int id = -1;
+
+ if (info->attrs[THERMAL_GENL_ATTR_TZ_ID])
+ id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]);
+
+ if (tz->id != id)
+ return THERMAL_ERROR;
+
+ if (info->attrs[THERMAL_GENL_ATTR_TZ_TEMP])
+ tz->temp = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_TEMP]);
+
+ return THERMAL_SUCCESS;
+}
+
+static int parse_tz_get_gov(struct genl_info *info, struct thermal_zone *tz)
+{
+ int id = -1;
+
+ if (info->attrs[THERMAL_GENL_ATTR_TZ_ID])
+ id = nla_get_u32(info->attrs[THERMAL_GENL_ATTR_TZ_ID]);
+
+ if (tz->id != id)
+ return THERMAL_ERROR;
+
+ if (info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME]) {
+ nla_strlcpy(tz->governor,
+ info->attrs[THERMAL_GENL_ATTR_TZ_GOV_NAME],
+ THERMAL_NAME_LENGTH);
+ }
+
+ return THERMAL_SUCCESS;
+}
+
+static int handle_netlink(struct nl_cache_ops *unused,
+ struct genl_cmd *cmd,
+ struct genl_info *info, void *arg)
+{
+ int ret;
+
+ switch (cmd->c_id) {
+
+ case THERMAL_GENL_CMD_TZ_GET_ID:
+ ret = parse_tz_get(info, arg);
+ break;
+
+ case THERMAL_GENL_CMD_CDEV_GET:
+ ret = parse_cdev_get(info, arg);
+ break;
+
+ case THERMAL_GENL_CMD_TZ_GET_TEMP:
+ ret = parse_tz_get_temp(info, arg);
+ break;
+
+ case THERMAL_GENL_CMD_TZ_GET_TRIP:
+ ret = parse_tz_get_trip(info, arg);
+ break;
+
+ case THERMAL_GENL_CMD_TZ_GET_GOV:
+ ret = parse_tz_get_gov(info, arg);
+ break;
+
+ default:
+ return THERMAL_ERROR;
+ }
+
+ return ret;
+}
+
+static struct genl_cmd thermal_cmds[] = {
+ {
+ .c_id = THERMAL_GENL_CMD_TZ_GET_ID,
+ .c_name = (char *)"List thermal zones",
+ .c_msg_parser = handle_netlink,
+ .c_maxattr = THERMAL_GENL_ATTR_MAX,
+ .c_attr_policy = thermal_genl_policy,
+ },
+ {
+ .c_id = THERMAL_GENL_CMD_TZ_GET_GOV,
+ .c_name = (char *)"Get governor",
+ .c_msg_parser = handle_netlink,
+ .c_maxattr = THERMAL_GENL_ATTR_MAX,
+ .c_attr_policy = thermal_genl_policy,
+ },
+ {
+ .c_id = THERMAL_GENL_CMD_TZ_GET_TEMP,
+ .c_name = (char *)"Get thermal zone temperature",
+ .c_msg_parser = handle_netlink,
+ .c_maxattr = THERMAL_GENL_ATTR_MAX,
+ .c_attr_policy = thermal_genl_policy,
+ },
+ {
+ .c_id = THERMAL_GENL_CMD_TZ_GET_TRIP,
+ .c_name = (char *)"Get thermal zone trip points",
+ .c_msg_parser = handle_netlink,
+ .c_maxattr = THERMAL_GENL_ATTR_MAX,
+ .c_attr_policy = thermal_genl_policy,
+ },
+ {
+ .c_id = THERMAL_GENL_CMD_CDEV_GET,
+ .c_name = (char *)"Get cooling devices",
+ .c_msg_parser = handle_netlink,
+ .c_maxattr = THERMAL_GENL_ATTR_MAX,
+ .c_attr_policy = thermal_genl_policy,
+ },
+};
+
+static struct genl_ops thermal_cmd_ops = {
+ .o_name = (char *)"thermal",
+ .o_cmds = thermal_cmds,
+ .o_ncmds = ARRAY_SIZE(thermal_cmds),
+};
+
+static thermal_error_t thermal_genl_auto(struct thermal_handler *th, int id, int cmd,
+ int flags, void *arg)
+{
+ struct nl_msg *msg;
+ void *hdr;
+
+ msg = nlmsg_alloc();
+ if (!msg)
+ return THERMAL_ERROR;
+
+ hdr = genlmsg_put(msg, NL_AUTO_PORT, NL_AUTO_SEQ, thermal_cmd_ops.o_id,
+ 0, flags, cmd, THERMAL_GENL_VERSION);
+ if (!hdr)
+ return THERMAL_ERROR;
+
+ if (id >= 0 && nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id))
+ return THERMAL_ERROR;
+
+ if (nl_send_msg(th->sk_cmd, th->cb_cmd, msg, genl_handle_msg, arg))
+ return THERMAL_ERROR;
+
+ nlmsg_free(msg);
+
+ return THERMAL_SUCCESS;
+}
+
+thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th, struct thermal_zone **tz)
+{
+ return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_TZ_GET_ID,
+ NLM_F_DUMP | NLM_F_ACK, tz);
+}
+
+thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th, struct thermal_cdev **tc)
+{
+ return thermal_genl_auto(th, -1, THERMAL_GENL_CMD_CDEV_GET,
+ NLM_F_DUMP | NLM_F_ACK, tc);
+}
+
+thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th, struct thermal_zone *tz)
+{
+ return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TRIP,
+ 0, tz);
+}
+
+thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th, struct thermal_zone *tz)
+{
+ return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_GOV, 0, tz);
+}
+
+thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th, struct thermal_zone *tz)
+{
+ return thermal_genl_auto(th, tz->id, THERMAL_GENL_CMD_TZ_GET_TEMP, 0, tz);
+}
+
+thermal_error_t thermal_cmd_exit(struct thermal_handler *th)
+{
+ if (genl_unregister_family(&thermal_cmd_ops))
+ return THERMAL_ERROR;
+
+ nl_thermal_disconnect(th->sk_cmd, th->cb_cmd);
+
+ return THERMAL_SUCCESS;
+}
+
+thermal_error_t thermal_cmd_init(struct thermal_handler *th)
+{
+ int ret;
+ int family;
+
+ if (nl_thermal_connect(&th->sk_cmd, &th->cb_cmd))
+ return THERMAL_ERROR;
+
+ ret = genl_register_family(&thermal_cmd_ops);
+ if (ret)
+ return THERMAL_ERROR;
+
+ ret = genl_ops_resolve(th->sk_cmd, &thermal_cmd_ops);
+ if (ret)
+ return THERMAL_ERROR;
+
+ family = genl_ctrl_resolve(th->sk_cmd, "nlctrl");
+ if (family != GENL_ID_CTRL)
+ return THERMAL_ERROR;
+
+ return THERMAL_SUCCESS;
+}
diff --git a/tools/lib/thermal/events.c b/tools/lib/thermal/events.c
new file mode 100644
index 000000000000..a7a55d1a0c4c
--- /dev/null
+++ b/tools/lib/thermal/events.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <linux/netlink.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+
+#include <thermal.h>
+#include "thermal_nl.h"
+
+/*
+ * Optimization: fill this array to tell which event we do want to pay
+ * attention to. That happens at init time with the ops
+ * structure. Each ops will enable the event and the general handler
+ * will be able to discard the event if there is not ops associated
+ * with it.
+ */
+static int enabled_ops[__THERMAL_GENL_EVENT_MAX];
+
+static int handle_thermal_event(struct nl_msg *n, void *arg)
+{
+ struct nlmsghdr *nlh = nlmsg_hdr(n);
+ struct genlmsghdr *genlhdr = genlmsg_hdr(nlh);
+ struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1];
+ struct thermal_handler_param *thp = arg;
+ struct thermal_events_ops *ops = &thp->th->ops->events;
+
+ genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL);
+
+ arg = thp->arg;
+
+ /*
+ * This is an event we don't care of, bail out.
+ */
+ if (!enabled_ops[genlhdr->cmd])
+ return THERMAL_SUCCESS;
+
+ switch (genlhdr->cmd) {
+
+ case THERMAL_GENL_EVENT_TZ_CREATE:
+ return ops->tz_create(nla_get_string(attrs[THERMAL_GENL_ATTR_TZ_NAME]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_DELETE:
+ return ops->tz_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_ENABLE:
+ return ops->tz_enable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_DISABLE:
+ return ops->tz_disable(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_TRIP_CHANGE:
+ return ops->trip_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_TRIP_ADD:
+ return ops->trip_add(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TYPE]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_TEMP]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_HYST]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_TRIP_DELETE:
+ return ops->trip_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_TRIP_UP:
+ return ops->trip_high(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_TRIP_DOWN:
+ return ops->trip_low(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TRIP_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg);
+
+ case THERMAL_GENL_EVENT_CDEV_ADD:
+ return ops->cdev_add(nla_get_string(attrs[THERMAL_GENL_ATTR_CDEV_NAME]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_MAX_STATE]), arg);
+
+ case THERMAL_GENL_EVENT_CDEV_DELETE:
+ return ops->cdev_delete(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]), arg);
+
+ case THERMAL_GENL_EVENT_CDEV_STATE_UPDATE:
+ return ops->cdev_update(nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_CDEV_CUR_STATE]), arg);
+
+ case THERMAL_GENL_EVENT_TZ_GOV_CHANGE:
+ return ops->gov_change(nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_string(attrs[THERMAL_GENL_ATTR_GOV_NAME]), arg);
+ default:
+ return -1;
+ }
+}
+
+static void thermal_events_ops_init(struct thermal_events_ops *ops)
+{
+ enabled_ops[THERMAL_GENL_EVENT_TZ_CREATE] = !!ops->tz_create;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_DELETE] = !!ops->tz_delete;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_DISABLE] = !!ops->tz_disable;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_ENABLE] = !!ops->tz_enable;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_UP] = !!ops->trip_high;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DOWN] = !!ops->trip_low;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_CHANGE] = !!ops->trip_change;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_ADD] = !!ops->trip_add;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_TRIP_DELETE] = !!ops->trip_delete;
+ enabled_ops[THERMAL_GENL_EVENT_CDEV_ADD] = !!ops->cdev_add;
+ enabled_ops[THERMAL_GENL_EVENT_CDEV_DELETE] = !!ops->cdev_delete;
+ enabled_ops[THERMAL_GENL_EVENT_CDEV_STATE_UPDATE] = !!ops->cdev_update;
+ enabled_ops[THERMAL_GENL_EVENT_TZ_GOV_CHANGE] = !!ops->gov_change;
+}
+
+thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg)
+{
+ struct thermal_handler_param thp = { .th = th, .arg = arg };
+
+ if (!th)
+ return THERMAL_ERROR;
+
+ if (nl_cb_set(th->cb_event, NL_CB_VALID, NL_CB_CUSTOM,
+ handle_thermal_event, &thp))
+ return THERMAL_ERROR;
+
+ return nl_recvmsgs(th->sk_event, th->cb_event);
+}
+
+int thermal_events_fd(struct thermal_handler *th)
+{
+ if (!th)
+ return -1;
+
+ return nl_socket_get_fd(th->sk_event);
+}
+
+thermal_error_t thermal_events_exit(struct thermal_handler *th)
+{
+ if (nl_unsubscribe_thermal(th->sk_event, th->cb_event,
+ THERMAL_GENL_EVENT_GROUP_NAME))
+ return THERMAL_ERROR;
+
+ nl_thermal_disconnect(th->sk_event, th->cb_event);
+
+ return THERMAL_SUCCESS;
+}
+
+thermal_error_t thermal_events_init(struct thermal_handler *th)
+{
+ thermal_events_ops_init(&th->ops->events);
+
+ if (nl_thermal_connect(&th->sk_event, &th->cb_event))
+ return THERMAL_ERROR;
+
+ if (nl_subscribe_thermal(th->sk_event, th->cb_event,
+ THERMAL_GENL_EVENT_GROUP_NAME))
+ return THERMAL_ERROR;
+
+ return THERMAL_SUCCESS;
+}
diff --git a/tools/lib/thermal/include/thermal.h b/tools/lib/thermal/include/thermal.h
new file mode 100644
index 000000000000..1abc560602cf
--- /dev/null
+++ b/tools/lib/thermal/include/thermal.h
@@ -0,0 +1,142 @@
+/* SPDX-License-Identifier: LGPL-2.1+ */
+/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */
+#ifndef __LIBTHERMAL_H
+#define __LIBTHERMAL_H
+
+#include <linux/thermal.h>
+
+#ifndef LIBTHERMAL_API
+#define LIBTHERMAL_API __attribute__((visibility("default")))
+#endif
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+struct thermal_sampling_ops {
+ int (*tz_temp)(int tz_id, int temp, void *arg);
+};
+
+struct thermal_events_ops {
+ int (*tz_create)(const char *name, int tz_id, void *arg);
+ int (*tz_delete)(int tz_id, void *arg);
+ int (*tz_enable)(int tz_id, void *arg);
+ int (*tz_disable)(int tz_id, void *arg);
+ int (*trip_high)(int tz_id, int trip_id, int temp, void *arg);
+ int (*trip_low)(int tz_id, int trip_id, int temp, void *arg);
+ int (*trip_add)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg);
+ int (*trip_change)(int tz_id, int trip_id, int type, int temp, int hyst, void *arg);
+ int (*trip_delete)(int tz_id, int trip_id, void *arg);
+ int (*cdev_add)(const char *name, int cdev_id, int max_state, void *arg);
+ int (*cdev_delete)(int cdev_id, void *arg);
+ int (*cdev_update)(int cdev_id, int cur_state, void *arg);
+ int (*gov_change)(int tz_id, const char *gov_name, void *arg);
+};
+
+struct thermal_ops {
+ struct thermal_sampling_ops sampling;
+ struct thermal_events_ops events;
+};
+
+struct thermal_trip {
+ int id;
+ int type;
+ int temp;
+ int hyst;
+};
+
+struct thermal_zone {
+ int id;
+ int temp;
+ char name[THERMAL_NAME_LENGTH];
+ char governor[THERMAL_NAME_LENGTH];
+ struct thermal_trip *trip;
+};
+
+struct thermal_cdev {
+ int id;
+ char name[THERMAL_NAME_LENGTH];
+ int max_state;
+ int min_state;
+ int cur_state;
+};
+
+typedef enum {
+ THERMAL_ERROR = -1,
+ THERMAL_SUCCESS = 0,
+} thermal_error_t;
+
+struct thermal_handler;
+
+typedef int (*cb_tz_t)(struct thermal_zone *, void *);
+
+typedef int (*cb_tt_t)(struct thermal_trip *, void *);
+
+typedef int (*cb_tc_t)(struct thermal_cdev *, void *);
+
+LIBTHERMAL_API int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg);
+
+LIBTHERMAL_API int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg);
+
+LIBTHERMAL_API int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg);
+
+LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz,
+ const char *name);
+
+LIBTHERMAL_API struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id);
+
+LIBTHERMAL_API struct thermal_zone *thermal_zone_discover(struct thermal_handler *th);
+
+LIBTHERMAL_API struct thermal_handler *thermal_init(struct thermal_ops *ops);
+
+LIBTHERMAL_API void thermal_exit(struct thermal_handler *th);
+
+/*
+ * Netlink thermal events
+ */
+LIBTHERMAL_API thermal_error_t thermal_events_exit(struct thermal_handler *th);
+
+LIBTHERMAL_API thermal_error_t thermal_events_init(struct thermal_handler *th);
+
+LIBTHERMAL_API thermal_error_t thermal_events_handle(struct thermal_handler *th, void *arg);
+
+LIBTHERMAL_API int thermal_events_fd(struct thermal_handler *th);
+
+/*
+ * Netlink thermal commands
+ */
+LIBTHERMAL_API thermal_error_t thermal_cmd_exit(struct thermal_handler *th);
+
+LIBTHERMAL_API thermal_error_t thermal_cmd_init(struct thermal_handler *th);
+
+LIBTHERMAL_API thermal_error_t thermal_cmd_get_tz(struct thermal_handler *th,
+ struct thermal_zone **tz);
+
+LIBTHERMAL_API thermal_error_t thermal_cmd_get_cdev(struct thermal_handler *th,
+ struct thermal_cdev **tc);
+
+LIBTHERMAL_API thermal_error_t thermal_cmd_get_trip(struct thermal_handler *th,
+ struct thermal_zone *tz);
+
+LIBTHERMAL_API thermal_error_t thermal_cmd_get_governor(struct thermal_handler *th,
+ struct thermal_zone *tz);
+
+LIBTHERMAL_API thermal_error_t thermal_cmd_get_temp(struct thermal_handler *th,
+ struct thermal_zone *tz);
+
+/*
+ * Netlink thermal samples
+ */
+LIBTHERMAL_API thermal_error_t thermal_sampling_exit(struct thermal_handler *th);
+
+LIBTHERMAL_API thermal_error_t thermal_sampling_init(struct thermal_handler *th);
+
+LIBTHERMAL_API thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg);
+
+LIBTHERMAL_API int thermal_sampling_fd(struct thermal_handler *th);
+
+#endif /* __LIBTHERMAL_H */
+
+#ifdef __cplusplus
+}
+#endif
diff --git a/tools/lib/thermal/libthermal.map b/tools/lib/thermal/libthermal.map
new file mode 100644
index 000000000000..d5e77738c7a4
--- /dev/null
+++ b/tools/lib/thermal/libthermal.map
@@ -0,0 +1,25 @@
+LIBTHERMAL_0.0.1 {
+ global:
+ thermal_init;
+ for_each_thermal_zone;
+ for_each_thermal_trip;
+ for_each_thermal_cdev;
+ thermal_zone_find_by_name;
+ thermal_zone_find_by_id;
+ thermal_zone_discover;
+ thermal_init;
+ thermal_events_init;
+ thermal_events_handle;
+ thermal_events_fd;
+ thermal_cmd_init;
+ thermal_cmd_get_tz;
+ thermal_cmd_get_cdev;
+ thermal_cmd_get_trip;
+ thermal_cmd_get_governor;
+ thermal_cmd_get_temp;
+ thermal_sampling_init;
+ thermal_sampling_handle;
+ thermal_sampling_fd;
+local:
+ *;
+};
diff --git a/tools/lib/thermal/libthermal.pc.template b/tools/lib/thermal/libthermal.pc.template
new file mode 100644
index 000000000000..6f3769731b59
--- /dev/null
+++ b/tools/lib/thermal/libthermal.pc.template
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=${prefix}/include
+
+Name: libthermal
+Description: thermal library
+Requires: libnl-3.0 libnl-genl-3.0
+Version: @VERSION@
+Libs: -L${libdir} -lnl-genl-3 -lnl-3
+Cflags: -I${includedir} -I{include}/libnl3
diff --git a/tools/lib/thermal/sampling.c b/tools/lib/thermal/sampling.c
new file mode 100644
index 000000000000..ee818f4e9654
--- /dev/null
+++ b/tools/lib/thermal/sampling.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <thermal.h>
+#include "thermal_nl.h"
+
+static int handle_thermal_sample(struct nl_msg *n, void *arg)
+{
+ struct nlmsghdr *nlh = nlmsg_hdr(n);
+ struct genlmsghdr *genlhdr = genlmsg_hdr(nlh);
+ struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1];
+ struct thermal_handler_param *thp = arg;
+ struct thermal_handler *th = thp->th;
+
+ genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL);
+
+ switch (genlhdr->cmd) {
+
+ case THERMAL_GENL_SAMPLING_TEMP:
+ return th->ops->sampling.tz_temp(
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_ID]),
+ nla_get_u32(attrs[THERMAL_GENL_ATTR_TZ_TEMP]), arg);
+ default:
+ return THERMAL_ERROR;
+ }
+}
+
+thermal_error_t thermal_sampling_handle(struct thermal_handler *th, void *arg)
+{
+ struct thermal_handler_param thp = { .th = th, .arg = arg };
+
+ if (!th)
+ return THERMAL_ERROR;
+
+ if (nl_cb_set(th->cb_sampling, NL_CB_VALID, NL_CB_CUSTOM,
+ handle_thermal_sample, &thp))
+ return THERMAL_ERROR;
+
+ return nl_recvmsgs(th->sk_sampling, th->cb_sampling);
+}
+
+int thermal_sampling_fd(struct thermal_handler *th)
+{
+ if (!th)
+ return -1;
+
+ return nl_socket_get_fd(th->sk_sampling);
+}
+
+thermal_error_t thermal_sampling_exit(struct thermal_handler *th)
+{
+ if (nl_unsubscribe_thermal(th->sk_sampling, th->cb_sampling,
+ THERMAL_GENL_EVENT_GROUP_NAME))
+ return THERMAL_ERROR;
+
+ nl_thermal_disconnect(th->sk_sampling, th->cb_sampling);
+
+ return THERMAL_SUCCESS;
+}
+
+thermal_error_t thermal_sampling_init(struct thermal_handler *th)
+{
+ if (nl_thermal_connect(&th->sk_sampling, &th->cb_sampling))
+ return THERMAL_ERROR;
+
+ if (nl_subscribe_thermal(th->sk_sampling, th->cb_sampling,
+ THERMAL_GENL_SAMPLING_GROUP_NAME))
+ return THERMAL_ERROR;
+
+ return THERMAL_SUCCESS;
+}
diff --git a/tools/lib/thermal/thermal.c b/tools/lib/thermal/thermal.c
new file mode 100644
index 000000000000..72a76dc205bc
--- /dev/null
+++ b/tools/lib/thermal/thermal.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <stdio.h>
+#include <thermal.h>
+
+#include "thermal_nl.h"
+
+int for_each_thermal_cdev(struct thermal_cdev *cdev, cb_tc_t cb, void *arg)
+{
+ int i, ret = 0;
+
+ if (!cdev)
+ return 0;
+
+ for (i = 0; cdev[i].id != -1; i++)
+ ret |= cb(&cdev[i], arg);
+
+ return ret;
+}
+
+int for_each_thermal_trip(struct thermal_trip *tt, cb_tt_t cb, void *arg)
+{
+ int i, ret = 0;
+
+ if (!tt)
+ return 0;
+
+ for (i = 0; tt[i].id != -1; i++)
+ ret |= cb(&tt[i], arg);
+
+ return ret;
+}
+
+int for_each_thermal_zone(struct thermal_zone *tz, cb_tz_t cb, void *arg)
+{
+ int i, ret = 0;
+
+ if (!tz)
+ return 0;
+
+ for (i = 0; tz[i].id != -1; i++)
+ ret |= cb(&tz[i], arg);
+
+ return ret;
+}
+
+struct thermal_zone *thermal_zone_find_by_name(struct thermal_zone *tz,
+ const char *name)
+{
+ int i;
+
+ if (!tz || !name)
+ return NULL;
+
+ for (i = 0; tz[i].id != -1; i++) {
+ if (!strcmp(tz[i].name, name))
+ return &tz[i];
+ }
+
+ return NULL;
+}
+
+struct thermal_zone *thermal_zone_find_by_id(struct thermal_zone *tz, int id)
+{
+ int i;
+
+ if (!tz || id < 0)
+ return NULL;
+
+ for (i = 0; tz[i].id != -1; i++) {
+ if (tz[i].id == id)
+ return &tz[i];
+ }
+
+ return NULL;
+}
+
+static int __thermal_zone_discover(struct thermal_zone *tz, void *th)
+{
+ if (thermal_cmd_get_trip(th, tz) < 0)
+ return -1;
+
+ if (thermal_cmd_get_governor(th, tz))
+ return -1;
+
+ return 0;
+}
+
+struct thermal_zone *thermal_zone_discover(struct thermal_handler *th)
+{
+ struct thermal_zone *tz;
+
+ if (thermal_cmd_get_tz(th, &tz) < 0)
+ return NULL;
+
+ if (for_each_thermal_zone(tz, __thermal_zone_discover, th))
+ return NULL;
+
+ return tz;
+}
+
+void thermal_exit(struct thermal_handler *th)
+{
+ thermal_cmd_exit(th);
+ thermal_events_exit(th);
+ thermal_sampling_exit(th);
+
+ free(th);
+}
+
+struct thermal_handler *thermal_init(struct thermal_ops *ops)
+{
+ struct thermal_handler *th;
+
+ th = malloc(sizeof(*th));
+ if (!th)
+ return NULL;
+ th->ops = ops;
+
+ if (thermal_events_init(th))
+ goto out_free;
+
+ if (thermal_sampling_init(th))
+ goto out_free;
+
+ if (thermal_cmd_init(th))
+ goto out_free;
+
+ return th;
+
+out_free:
+ free(th);
+
+ return NULL;
+}
diff --git a/tools/lib/thermal/thermal_nl.c b/tools/lib/thermal/thermal_nl.c
new file mode 100644
index 000000000000..b05cf9569858
--- /dev/null
+++ b/tools/lib/thermal/thermal_nl.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <thermal.h>
+#include "thermal_nl.h"
+
+struct handler_args {
+ const char *group;
+ int id;
+};
+
+static __thread int err;
+static __thread int done;
+
+static int nl_seq_check_handler(struct nl_msg *msg, void *arg)
+{
+ return NL_OK;
+}
+
+static int nl_error_handler(struct sockaddr_nl *nla, struct nlmsgerr *nl_err,
+ void *arg)
+{
+ int *ret = arg;
+
+ if (ret)
+ *ret = nl_err->error;
+
+ return NL_STOP;
+}
+
+static int nl_finish_handler(struct nl_msg *msg, void *arg)
+{
+ int *ret = arg;
+
+ if (ret)
+ *ret = 1;
+
+ return NL_OK;
+}
+
+static int nl_ack_handler(struct nl_msg *msg, void *arg)
+{
+ int *ret = arg;
+
+ if (ret)
+ *ret = 1;
+
+ return NL_OK;
+}
+
+int nl_send_msg(struct nl_sock *sock, struct nl_cb *cb, struct nl_msg *msg,
+ int (*rx_handler)(struct nl_msg *, void *), void *data)
+{
+ if (!rx_handler)
+ return THERMAL_ERROR;
+
+ err = nl_send_auto_complete(sock, msg);
+ if (err < 0)
+ return err;
+
+ nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, rx_handler, data);
+
+ err = done = 0;
+
+ while (err == 0 && done == 0)
+ nl_recvmsgs(sock, cb);
+
+ return err;
+}
+
+static int nl_family_handler(struct nl_msg *msg, void *arg)
+{
+ struct handler_args *grp = arg;
+ struct nlattr *tb[CTRL_ATTR_MAX + 1];
+ struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+ struct nlattr *mcgrp;
+ int rem_mcgrp;
+
+ nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0),
+ genlmsg_attrlen(gnlh, 0), NULL);
+
+ if (!tb[CTRL_ATTR_MCAST_GROUPS])
+ return THERMAL_ERROR;
+
+ nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) {
+
+ struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1];
+
+ nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX,
+ nla_data(mcgrp), nla_len(mcgrp), NULL);
+
+ if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] ||
+ !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID])
+ continue;
+
+ if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]),
+ grp->group,
+ nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME])))
+ continue;
+
+ grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]);
+
+ break;
+ }
+
+ return THERMAL_SUCCESS;
+}
+
+static int nl_get_multicast_id(struct nl_sock *sock, struct nl_cb *cb,
+ const char *family, const char *group)
+{
+ struct nl_msg *msg;
+ int ret = 0, ctrlid;
+ struct handler_args grp = {
+ .group = group,
+ .id = -ENOENT,
+ };
+
+ msg = nlmsg_alloc();
+ if (!msg)
+ return THERMAL_ERROR;
+
+ ctrlid = genl_ctrl_resolve(sock, "nlctrl");
+
+ genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0);
+
+ nla_put_string(msg, CTRL_ATTR_FAMILY_NAME, family);
+
+ ret = nl_send_msg(sock, cb, msg, nl_family_handler, &grp);
+ if (ret)
+ goto nla_put_failure;
+
+ ret = grp.id;
+
+nla_put_failure:
+ nlmsg_free(msg);
+ return ret;
+}
+
+int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb)
+{
+ struct nl_cb *cb;
+ struct nl_sock *sock;
+
+ cb = nl_cb_alloc(NL_CB_DEFAULT);
+ if (!cb)
+ return THERMAL_ERROR;
+
+ sock = nl_socket_alloc();
+ if (!sock)
+ goto out_cb_free;
+
+ if (genl_connect(sock))
+ goto out_socket_free;
+
+ if (nl_cb_err(cb, NL_CB_CUSTOM, nl_error_handler, &err) ||
+ nl_cb_set(cb, NL_CB_FINISH, NL_CB_CUSTOM, nl_finish_handler, &done) ||
+ nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, nl_ack_handler, &done) ||
+ nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check_handler, &done))
+ return THERMAL_ERROR;
+
+ *nl_sock = sock;
+ *nl_cb = cb;
+
+ return THERMAL_SUCCESS;
+
+out_socket_free:
+ nl_socket_free(sock);
+out_cb_free:
+ nl_cb_put(cb);
+ return THERMAL_ERROR;
+}
+
+void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb)
+{
+ nl_close(nl_sock);
+ nl_socket_free(nl_sock);
+ nl_cb_put(nl_cb);
+}
+
+int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb,
+ const char *group)
+{
+ int mcid;
+
+ mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME,
+ group);
+ if (mcid < 0)
+ return THERMAL_ERROR;
+
+ if (nl_socket_drop_membership(nl_sock, mcid))
+ return THERMAL_ERROR;
+
+ return THERMAL_SUCCESS;
+}
+
+int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb,
+ const char *group)
+{
+ int mcid;
+
+ mcid = nl_get_multicast_id(nl_sock, nl_cb, THERMAL_GENL_FAMILY_NAME,
+ group);
+ if (mcid < 0)
+ return THERMAL_ERROR;
+
+ if (nl_socket_add_membership(nl_sock, mcid))
+ return THERMAL_ERROR;
+
+ return THERMAL_SUCCESS;
+}
diff --git a/tools/lib/thermal/thermal_nl.h b/tools/lib/thermal/thermal_nl.h
new file mode 100644
index 000000000000..ddf635642f07
--- /dev/null
+++ b/tools/lib/thermal/thermal_nl.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: LGPL-2.1+ */
+/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */
+#ifndef __THERMAL_H
+#define __THERMAL_H
+
+#include <netlink/netlink.h>
+#include <netlink/genl/genl.h>
+#include <netlink/genl/mngt.h>
+#include <netlink/genl/ctrl.h>
+
+struct thermal_handler {
+ int done;
+ int error;
+ struct thermal_ops *ops;
+ struct nl_msg *msg;
+ struct nl_sock *sk_event;
+ struct nl_sock *sk_sampling;
+ struct nl_sock *sk_cmd;
+ struct nl_cb *cb_cmd;
+ struct nl_cb *cb_event;
+ struct nl_cb *cb_sampling;
+};
+
+struct thermal_handler_param {
+ struct thermal_handler *th;
+ void *arg;
+};
+
+/*
+ * Low level netlink
+ */
+extern int nl_subscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb,
+ const char *group);
+
+extern int nl_unsubscribe_thermal(struct nl_sock *nl_sock, struct nl_cb *nl_cb,
+ const char *group);
+
+extern int nl_thermal_connect(struct nl_sock **nl_sock, struct nl_cb **nl_cb);
+
+extern void nl_thermal_disconnect(struct nl_sock *nl_sock, struct nl_cb *nl_cb);
+
+extern int nl_send_msg(struct nl_sock *sock, struct nl_cb *nl_cb, struct nl_msg *msg,
+ int (*rx_handler)(struct nl_msg *, void *),
+ void *data);
+
+#endif /* __THERMAL_H */
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 9edd402704c4..dab38904206a 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -54,7 +54,8 @@ klitmus7 Compatibility Table
-- 4.14 7.48 --
4.15 -- 4.19 7.49 --
4.20 -- 5.5 7.54 --
- 5.6 -- 7.56 --
+ 5.6 -- 5.16 7.56 --
+ 5.17 -- 7.56.1 --
============ ==========
diff --git a/tools/objtool/Build b/tools/objtool/Build
index b7222d5cc7bc..33f2ee5a46d3 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -2,17 +2,15 @@ objtool-y += arch/$(SRCARCH)/
objtool-y += weak.o
-objtool-$(SUBCMD_CHECK) += check.o
-objtool-$(SUBCMD_CHECK) += special.o
-objtool-$(SUBCMD_ORC) += check.o
-objtool-$(SUBCMD_ORC) += orc_gen.o
-objtool-$(SUBCMD_ORC) += orc_dump.o
-
+objtool-y += check.o
+objtool-y += special.o
objtool-y += builtin-check.o
-objtool-y += builtin-orc.o
objtool-y += elf.o
objtool-y += objtool.o
+objtool-$(BUILD_ORC) += orc_gen.o
+objtool-$(BUILD_ORC) += orc_dump.o
+
objtool-y += libstring.o
objtool-y += libctype.o
objtool-y += str_error_r.o
diff --git a/tools/objtool/Documentation/stack-validation.txt b/tools/objtool/Documentation/objtool.txt
index 30f38fdc0d56..8a671902a187 100644
--- a/tools/objtool/Documentation/stack-validation.txt
+++ b/tools/objtool/Documentation/objtool.txt
@@ -1,15 +1,103 @@
-Compile-time stack metadata validation
-======================================
+Objtool
+=======
+The kernel CONFIG_OBJTOOL option enables a host tool named 'objtool'
+which runs at compile time. It can do various validations and
+transformations on .o files.
-Overview
+Objtool has become an integral part of the x86-64 kernel toolchain. The
+kernel depends on it for a variety of security and performance features
+(and other types of features as well).
+
+
+Features
--------
-The kernel CONFIG_STACK_VALIDATION option enables a host tool named
-objtool which runs at compile time. It has a "check" subcommand which
-analyzes every .o file and ensures the validity of its stack metadata.
-It enforces a set of rules on asm code and C inline assembly code so
-that stack traces can be reliable.
+Objtool has the following features:
+
+- Stack unwinding metadata validation -- useful for helping to ensure
+ stack traces are reliable for live patching
+
+- ORC unwinder metadata generation -- a faster and more precise
+ alternative to frame pointer based unwinding
+
+- Retpoline validation -- ensures that all indirect calls go through
+ retpoline thunks, for Spectre v2 mitigations
+
+- Retpoline call site annotation -- annotates all retpoline thunk call
+ sites, enabling the kernel to patch them inline, to prevent "thunk
+ funneling" for both security and performance reasons
+
+- Non-instrumentation validation -- validates non-instrumentable
+ ("noinstr") code rules, preventing instrumentation in low-level C
+ entry code
+
+- Static call annotation -- annotates static call sites, enabling the
+ kernel to implement inline static calls, a faster alternative to some
+ indirect branches
+
+- Uaccess validation -- validates uaccess rules for a proper
+ implementation of Supervisor Mode Access Protection (SMAP)
+
+- Straight Line Speculation validation -- validates certain SLS
+ mitigations
+
+- Indirect Branch Tracking validation -- validates Intel CET IBT rules
+ to ensure that all functions referenced by function pointers have
+ corresponding ENDBR instructions
+
+- Indirect Branch Tracking annotation -- annotates unused ENDBR
+ instruction sites, enabling the kernel to "seal" them (replace them
+ with NOPs) to further harden IBT
+
+- Function entry annotation -- annotates function entries, enabling
+ kernel function tracing
+
+- Other toolchain hacks which will go unmentioned at this time...
+
+Each feature can be enabled individually or in combination using the
+objtool cmdline.
+
+
+Objects
+-------
+
+Typically, objtool runs on every translation unit (TU, aka ".o file") in
+the kernel. If a TU is part of a kernel module, the '--module' option
+is added.
+
+However:
+
+- If noinstr validation is enabled, it also runs on vmlinux.o, with all
+ options removed and '--noinstr' added.
+
+- If IBT or LTO is enabled, it doesn't run on TUs at all. Instead it
+ runs on vmlinux.o and linked modules, with all options.
+
+In summary:
+
+ A) Legacy mode:
+ TU: objtool [--module] <options>
+ vmlinux: N/A
+ module: N/A
+
+ B) CONFIG_NOINSTR_VALIDATION=y && !(CONFIG_X86_KERNEL_IBT=y || CONFIG_LTO=y):
+ TU: objtool [--module] <options> // no --noinstr
+ vmlinux: objtool --noinstr // other options removed
+ module: N/A
+
+ C) CONFIG_X86_KERNEL_IBT=y || CONFIG_LTO=y:
+ TU: N/A
+ vmlinux: objtool --noinstr <options>
+ module: objtool --module --noinstr <options>
+
+
+Stack validation
+----------------
+
+Objtool's stack validation feature analyzes every .o file and ensures
+the validity of its stack metadata. It enforces a set of rules on asm
+code and C inline assembly code so that stack traces can be reliable.
For each function, it recursively follows all possible code paths and
validates the correct frame pointer state at each instruction.
@@ -20,14 +108,6 @@ alternative execution paths to a given instruction (or set of
instructions). Similarly, it knows how to follow switch statements, for
which gcc sometimes uses jump tables.
-(Objtool also has an 'orc generate' subcommand which generates debuginfo
-for the ORC unwinder. See Documentation/x86/orc-unwinder.rst in the
-kernel tree for more details.)
-
-
-Why do we need stack metadata validation?
------------------------------------------
-
Here are some of the benefits of validating stack metadata:
a) More reliable stack traces for frame pointer enabled kernels
@@ -113,9 +193,6 @@ c) Higher live patching compatibility rate
For more details, see the livepatch documentation in the Linux kernel
source tree at Documentation/livepatch/livepatch.rst.
-Rules
------
-
To achieve the validation, objtool enforces the following rules:
1. Each callable function must be annotated as such with the ELF
@@ -177,7 +254,8 @@ Another possible cause for errors in C code is if the Makefile removes
-fno-omit-frame-pointer or adds -fomit-frame-pointer to the gcc options.
Here are some examples of common warnings reported by objtool, what
-they mean, and suggestions for how to fix them.
+they mean, and suggestions for how to fix them. When in doubt, ping
+the objtool maintainers.
1. file.o: warning: objtool: func()+0x128: call without frame pointer save/setup
@@ -358,3 +436,7 @@ ignore it:
OBJECT_FILES_NON_STANDARD := y
to the Makefile.
+
+NOTE: OBJECT_FILES_NON_STANDARD doesn't work for link time validation of
+vmlinux.o or a linked module. So it should only be used for files which
+aren't linked into vmlinux or a module.
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 0dbd397f319d..e66d717c245d 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -39,15 +39,13 @@ CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
AWK = awk
-SUBCMD_CHECK := n
-SUBCMD_ORC := n
+BUILD_ORC := n
ifeq ($(SRCARCH),x86)
- SUBCMD_CHECK := y
- SUBCMD_ORC := y
+ BUILD_ORC := y
endif
-export SUBCMD_CHECK SUBCMD_ORC
+export BUILD_ORC
export srctree OUTPUT CFLAGS SRCARCH AWK
include $(srctree)/tools/build/Makefile.include
@@ -65,7 +63,7 @@ $(LIBSUBCMD): fixdep FORCE
clean:
$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
- $(Q)$(RM) $(OUTPUT)arch/x86/inat-tables.c $(OUTPUT)fixdep
+ $(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep $(LIBSUBCMD)
FORCE:
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index 943cb41cddf7..8b990a52aada 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -581,7 +581,7 @@ int arch_decode_instruction(struct objtool_file *file, const struct section *sec
break;
case 0xc7: /* mov imm, r/m */
- if (!noinstr)
+ if (!opts.noinstr)
break;
if (insn.length == 3+4+4 && !strncmp(sec->name, ".init.text", 10)) {
diff --git a/tools/objtool/arch/x86/special.c b/tools/objtool/arch/x86/special.c
index e707d9bcd161..7c97b7391279 100644
--- a/tools/objtool/arch/x86/special.c
+++ b/tools/objtool/arch/x86/special.c
@@ -20,7 +20,7 @@ void arch_handle_alternative(unsigned short feature, struct special_alt *alt)
* find paths that see the STAC but take the NOP instead of
* CLAC and the other way around.
*/
- if (uaccess)
+ if (opts.uaccess)
alt->skip_orig = true;
else
alt->skip_alt = true;
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index fc6975ab8b06..f4c3a5091737 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -3,28 +3,21 @@
* Copyright (C) 2015-2017 Josh Poimboeuf <jpoimboe@redhat.com>
*/
-/*
- * objtool check:
- *
- * This command analyzes every .o file and ensures the validity of its stack
- * trace metadata. It enforces a set of rules on asm code and C inline
- * assembly code so that stack traces can be reliable.
- *
- * For more information, see tools/objtool/Documentation/stack-validation.txt.
- */
-
#include <subcmd/parse-options.h>
#include <string.h>
#include <stdlib.h>
#include <objtool/builtin.h>
#include <objtool/objtool.h>
-bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats,
- lto, vmlinux, mcount, noinstr, backup, sls, dryrun,
- ibt;
+#define ERROR(format, ...) \
+ fprintf(stderr, \
+ "error: objtool: " format "\n", \
+ ##__VA_ARGS__)
+
+struct opts opts;
static const char * const check_usage[] = {
- "objtool check [<options>] file.o",
+ "objtool <actions> [<options>] file.o",
NULL,
};
@@ -33,22 +26,64 @@ static const char * const env_usage[] = {
NULL,
};
+static int parse_dump(const struct option *opt, const char *str, int unset)
+{
+ if (!str || !strcmp(str, "orc")) {
+ opts.dump_orc = true;
+ return 0;
+ }
+
+ return -1;
+}
+
+static int parse_hacks(const struct option *opt, const char *str, int unset)
+{
+ bool found = false;
+
+ /*
+ * Use strstr() as a lazy method of checking for comma-separated
+ * options.
+ *
+ * No string provided == enable all options.
+ */
+
+ if (!str || strstr(str, "jump_label")) {
+ opts.hack_jump_label = true;
+ found = true;
+ }
+
+ if (!str || strstr(str, "noinstr")) {
+ opts.hack_noinstr = true;
+ found = true;
+ }
+
+ return found ? 0 : -1;
+}
+
const struct option check_options[] = {
- OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"),
- OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
- OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
- OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
- OPT_BOOLEAN('b', "backtrace", &backtrace, "unwind on error"),
- OPT_BOOLEAN('a', "uaccess", &uaccess, "enable uaccess checking"),
- OPT_BOOLEAN('s', "stats", &stats, "print statistics"),
- OPT_BOOLEAN(0, "lto", &lto, "whole-archive like runs"),
- OPT_BOOLEAN('n', "noinstr", &noinstr, "noinstr validation for vmlinux.o"),
- OPT_BOOLEAN('l', "vmlinux", &vmlinux, "vmlinux.o validation"),
- OPT_BOOLEAN('M', "mcount", &mcount, "generate __mcount_loc"),
- OPT_BOOLEAN('B', "backup", &backup, "create .orig files before modification"),
- OPT_BOOLEAN('S', "sls", &sls, "validate straight-line-speculation"),
- OPT_BOOLEAN(0, "dry-run", &dryrun, "don't write the modifications"),
- OPT_BOOLEAN(0, "ibt", &ibt, "validate ENDBR placement"),
+ OPT_GROUP("Actions:"),
+ OPT_CALLBACK_OPTARG('h', "hacks", NULL, NULL, "jump_label,noinstr", "patch toolchain bugs/limitations", parse_hacks),
+ OPT_BOOLEAN('i', "ibt", &opts.ibt, "validate and annotate IBT"),
+ OPT_BOOLEAN('m', "mcount", &opts.mcount, "annotate mcount/fentry calls for ftrace"),
+ OPT_BOOLEAN('n', "noinstr", &opts.noinstr, "validate noinstr rules"),
+ OPT_BOOLEAN('o', "orc", &opts.orc, "generate ORC metadata"),
+ OPT_BOOLEAN('r', "retpoline", &opts.retpoline, "validate and annotate retpoline usage"),
+ OPT_BOOLEAN('l', "sls", &opts.sls, "validate straight-line-speculation mitigations"),
+ OPT_BOOLEAN('s', "stackval", &opts.stackval, "validate frame pointer rules"),
+ OPT_BOOLEAN('t', "static-call", &opts.static_call, "annotate static calls"),
+ OPT_BOOLEAN('u', "uaccess", &opts.uaccess, "validate uaccess rules for SMAP"),
+ OPT_CALLBACK_OPTARG(0, "dump", NULL, NULL, "orc", "dump metadata", parse_dump),
+
+ OPT_GROUP("Options:"),
+ OPT_BOOLEAN(0, "backtrace", &opts.backtrace, "unwind on error"),
+ OPT_BOOLEAN(0, "backup", &opts.backup, "create .orig files before modification"),
+ OPT_BOOLEAN(0, "dry-run", &opts.dryrun, "don't write modifications"),
+ OPT_BOOLEAN(0, "link", &opts.link, "object is a linked object"),
+ OPT_BOOLEAN(0, "module", &opts.module, "object is part of a kernel module"),
+ OPT_BOOLEAN(0, "no-unreachable", &opts.no_unreachable, "skip 'unreachable instruction' warnings"),
+ OPT_BOOLEAN(0, "sec-address", &opts.sec_address, "print section addresses in warnings"),
+ OPT_BOOLEAN(0, "stats", &opts.stats, "print statistics"),
+
OPT_END(),
};
@@ -79,7 +114,59 @@ int cmd_parse_options(int argc, const char **argv, const char * const usage[])
return argc;
}
-int cmd_check(int argc, const char **argv)
+static bool opts_valid(void)
+{
+ if (opts.hack_jump_label ||
+ opts.hack_noinstr ||
+ opts.ibt ||
+ opts.mcount ||
+ opts.noinstr ||
+ opts.orc ||
+ opts.retpoline ||
+ opts.sls ||
+ opts.stackval ||
+ opts.static_call ||
+ opts.uaccess) {
+ if (opts.dump_orc) {
+ ERROR("--dump can't be combined with other options");
+ return false;
+ }
+
+ return true;
+ }
+
+ if (opts.dump_orc)
+ return true;
+
+ ERROR("At least one command required");
+ return false;
+}
+
+static bool link_opts_valid(struct objtool_file *file)
+{
+ if (opts.link)
+ return true;
+
+ if (has_multiple_files(file->elf)) {
+ ERROR("Linked object detected, forcing --link");
+ opts.link = true;
+ return true;
+ }
+
+ if (opts.noinstr) {
+ ERROR("--noinstr requires --link");
+ return false;
+ }
+
+ if (opts.ibt) {
+ ERROR("--ibt requires --link");
+ return false;
+ }
+
+ return true;
+}
+
+int objtool_run(int argc, const char **argv)
{
const char *objname;
struct objtool_file *file;
@@ -88,10 +175,19 @@ int cmd_check(int argc, const char **argv)
argc = cmd_parse_options(argc, argv, check_usage);
objname = argv[0];
+ if (!opts_valid())
+ return 1;
+
+ if (opts.dump_orc)
+ return orc_dump(objname);
+
file = objtool_open_read(objname);
if (!file)
return 1;
+ if (!link_opts_valid(file))
+ return 1;
+
ret = check(file);
if (ret)
return ret;
diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c
deleted file mode 100644
index 17f8b9307738..000000000000
--- a/tools/objtool/builtin-orc.c
+++ /dev/null
@@ -1,73 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
- */
-
-/*
- * objtool orc:
- *
- * This command analyzes a .o file and adds .orc_unwind and .orc_unwind_ip
- * sections to it, which is used by the in-kernel ORC unwinder.
- *
- * This command is a superset of "objtool check".
- */
-
-#include <string.h>
-#include <objtool/builtin.h>
-#include <objtool/objtool.h>
-
-static const char *orc_usage[] = {
- "objtool orc generate [<options>] file.o",
- "objtool orc dump file.o",
- NULL,
-};
-
-int cmd_orc(int argc, const char **argv)
-{
- const char *objname;
-
- argc--; argv++;
- if (argc <= 0)
- usage_with_options(orc_usage, check_options);
-
- if (!strncmp(argv[0], "gen", 3)) {
- struct objtool_file *file;
- int ret;
-
- argc = cmd_parse_options(argc, argv, orc_usage);
- objname = argv[0];
-
- file = objtool_open_read(objname);
- if (!file)
- return 1;
-
- ret = check(file);
- if (ret)
- return ret;
-
- if (list_empty(&file->insn_list))
- return 0;
-
- ret = orc_create(file);
- if (ret)
- return ret;
-
- if (!file->elf->changed)
- return 0;
-
- return elf_write(file->elf);
- }
-
- if (!strcmp(argv[0], "dump")) {
- if (argc != 2)
- usage_with_options(orc_usage, check_options);
-
- objname = argv[1];
-
- return orc_dump(objname);
- }
-
- usage_with_options(orc_usage, check_options);
-
- return 0;
-}
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 6de5085e3e5a..190b2f6e360a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -5,6 +5,7 @@
#include <string.h>
#include <stdlib.h>
+#include <inttypes.h>
#include <sys/mman.h>
#include <arch/elf.h>
@@ -184,6 +185,7 @@ static bool __dead_end_function(struct objtool_file *file, struct symbol *func,
"do_group_exit",
"stop_this_cpu",
"__invalid_creds",
+ "cpu_startup_entry",
};
if (!func)
@@ -262,7 +264,8 @@ static void init_cfi_state(struct cfi_state *cfi)
cfi->drap_offset = -1;
}
-static void init_insn_state(struct insn_state *state, struct section *sec)
+static void init_insn_state(struct objtool_file *file, struct insn_state *state,
+ struct section *sec)
{
memset(state, 0, sizeof(*state));
init_cfi_state(&state->cfi);
@@ -272,7 +275,7 @@ static void init_insn_state(struct insn_state *state, struct section *sec)
* not correctly determine insn->call_dest->sec (external symbols do
* not have a section).
*/
- if (vmlinux && noinstr && sec)
+ if (opts.link && opts.noinstr && sec)
state->noinstr = sec->noinstr;
}
@@ -338,7 +341,7 @@ static void *cfi_hash_alloc(unsigned long size)
if (cfi_hash == (void *)-1L) {
WARN("mmap fail cfi_hash");
cfi_hash = NULL;
- } else if (stats) {
+ } else if (opts.stats) {
printf("cfi_bits: %d\n", cfi_bits);
}
@@ -433,7 +436,7 @@ static int decode_instructions(struct objtool_file *file)
}
}
- if (stats)
+ if (opts.stats)
printf("nr_insns: %lu\n", nr_insns);
return 0;
@@ -496,7 +499,7 @@ static int init_pv_ops(struct objtool_file *file)
struct symbol *sym;
int idx, nr;
- if (!noinstr)
+ if (!opts.noinstr)
return 0;
file->pv_ops = NULL;
@@ -559,12 +562,12 @@ static int add_dead_ends(struct objtool_file *file)
else if (reloc->addend == reloc->sym->sec->sh.sh_size) {
insn = find_last_insn(file, reloc->sym->sec);
if (!insn) {
- WARN("can't find unreachable insn at %s+0x%x",
+ WARN("can't find unreachable insn at %s+0x%" PRIx64,
reloc->sym->sec->name, reloc->addend);
return -1;
}
} else {
- WARN("can't find unreachable insn at %s+0x%x",
+ WARN("can't find unreachable insn at %s+0x%" PRIx64,
reloc->sym->sec->name, reloc->addend);
return -1;
}
@@ -594,12 +597,12 @@ reachable:
else if (reloc->addend == reloc->sym->sec->sh.sh_size) {
insn = find_last_insn(file, reloc->sym->sec);
if (!insn) {
- WARN("can't find reachable insn at %s+0x%x",
+ WARN("can't find reachable insn at %s+0x%" PRIx64,
reloc->sym->sec->name, reloc->addend);
return -1;
}
} else {
- WARN("can't find reachable insn at %s+0x%x",
+ WARN("can't find reachable insn at %s+0x%" PRIx64,
reloc->sym->sec->name, reloc->addend);
return -1;
}
@@ -667,7 +670,7 @@ static int create_static_call_sections(struct objtool_file *file)
key_sym = find_symbol_by_name(file->elf, tmp);
if (!key_sym) {
- if (!module) {
+ if (!opts.module) {
WARN("static_call: can't find static_call_key symbol: %s", tmp);
return -1;
}
@@ -760,7 +763,7 @@ static int create_ibt_endbr_seal_sections(struct objtool_file *file)
list_for_each_entry(insn, &file->endbr_list, call_node)
idx++;
- if (stats) {
+ if (opts.stats) {
printf("ibt: ENDBR at function start: %d\n", file->nr_endbr);
printf("ibt: ENDBR inside functions: %d\n", file->nr_endbr_int);
printf("ibt: superfluous ENDBR: %d\n", idx);
@@ -1027,7 +1030,7 @@ static void add_uaccess_safe(struct objtool_file *file)
struct symbol *func;
const char **name;
- if (!uaccess)
+ if (!opts.uaccess)
return;
for (name = uaccess_safe_builtin; *name; name++) {
@@ -1143,7 +1146,7 @@ static void annotate_call_site(struct objtool_file *file,
* attribute so they need a little help, NOP out any such calls from
* noinstr text.
*/
- if (insn->sec->noinstr && sym->profiling_func) {
+ if (opts.hack_noinstr && insn->sec->noinstr && sym->profiling_func) {
if (reloc) {
reloc->type = R_NONE;
elf_write_reloc(file->elf, reloc);
@@ -1155,10 +1158,21 @@ static void annotate_call_site(struct objtool_file *file,
: arch_nop_insn(insn->len));
insn->type = sibling ? INSN_RETURN : INSN_NOP;
+
+ if (sibling) {
+ /*
+ * We've replaced the tail-call JMP insn by two new
+ * insn: RET; INT3, except we only have a single struct
+ * insn here. Mark it retpoline_safe to avoid the SLS
+ * warning, instead of adding another insn.
+ */
+ insn->retpoline_safe = true;
+ }
+
return;
}
- if (mcount && sym->fentry) {
+ if (opts.mcount && sym->fentry) {
if (sibling)
WARN_FUNC("Tail call to __fentry__ !?!?", insn->sec, insn->offset);
@@ -1239,11 +1253,20 @@ static bool same_function(struct instruction *insn1, struct instruction *insn2)
return insn1->func->pfunc == insn2->func->pfunc;
}
-static bool is_first_func_insn(struct instruction *insn)
+static bool is_first_func_insn(struct objtool_file *file, struct instruction *insn)
{
- return insn->offset == insn->func->offset ||
- (insn->type == INSN_ENDBR &&
- insn->offset == insn->func->offset + insn->len);
+ if (insn->offset == insn->func->offset)
+ return true;
+
+ if (opts.ibt) {
+ struct instruction *prev = prev_insn_same_sym(file, insn);
+
+ if (prev && prev->type == INSN_ENDBR &&
+ insn->offset == insn->func->offset + prev->len)
+ return true;
+ }
+
+ return false;
}
/*
@@ -1251,12 +1274,19 @@ static bool is_first_func_insn(struct instruction *insn)
*/
static int add_jump_destinations(struct objtool_file *file)
{
- struct instruction *insn;
+ struct instruction *insn, *jump_dest;
struct reloc *reloc;
struct section *dest_sec;
unsigned long dest_off;
for_each_insn(file, insn) {
+ if (insn->jump_dest) {
+ /*
+ * handle_group_alt() may have previously set
+ * 'jump_dest' for some alternatives.
+ */
+ continue;
+ }
if (!is_static_jump(insn))
continue;
@@ -1271,7 +1301,10 @@ static int add_jump_destinations(struct objtool_file *file)
add_retpoline_call(file, insn);
continue;
} else if (insn->func) {
- /* internal or external sibling call (with reloc) */
+ /*
+ * External sibling call or internal sibling call with
+ * STT_FUNC reloc.
+ */
add_call_dest(file, insn, reloc->sym, true);
continue;
} else if (reloc->sym->sec->idx) {
@@ -1283,17 +1316,8 @@ static int add_jump_destinations(struct objtool_file *file)
continue;
}
- insn->jump_dest = find_insn(file, dest_sec, dest_off);
- if (!insn->jump_dest) {
-
- /*
- * This is a special case where an alt instruction
- * jumps past the end of the section. These are
- * handled later in handle_group_alt().
- */
- if (!strcmp(insn->sec->name, ".altinstr_replacement"))
- continue;
-
+ jump_dest = find_insn(file, dest_sec, dest_off);
+ if (!jump_dest) {
WARN_FUNC("can't find jump dest instruction at %s+0x%lx",
insn->sec, insn->offset, dest_sec->name,
dest_off);
@@ -1303,8 +1327,8 @@ static int add_jump_destinations(struct objtool_file *file)
/*
* Cross-function jump.
*/
- if (insn->func && insn->jump_dest->func &&
- insn->func != insn->jump_dest->func) {
+ if (insn->func && jump_dest->func &&
+ insn->func != jump_dest->func) {
/*
* For GCC 8+, create parent/child links for any cold
@@ -1322,16 +1346,22 @@ static int add_jump_destinations(struct objtool_file *file)
* subfunction is through a jump table.
*/
if (!strstr(insn->func->name, ".cold") &&
- strstr(insn->jump_dest->func->name, ".cold")) {
- insn->func->cfunc = insn->jump_dest->func;
- insn->jump_dest->func->pfunc = insn->func;
+ strstr(jump_dest->func->name, ".cold")) {
+ insn->func->cfunc = jump_dest->func;
+ jump_dest->func->pfunc = insn->func;
- } else if (!same_function(insn, insn->jump_dest) &&
- is_first_func_insn(insn->jump_dest)) {
- /* internal sibling call (without reloc) */
- add_call_dest(file, insn, insn->jump_dest->func, true);
+ } else if (!same_function(insn, jump_dest) &&
+ is_first_func_insn(file, jump_dest)) {
+ /*
+ * Internal sibling call without reloc or with
+ * STT_SECTION reloc.
+ */
+ add_call_dest(file, insn, jump_dest->func, true);
+ continue;
}
}
+
+ insn->jump_dest = jump_dest;
}
return 0;
@@ -1520,13 +1550,13 @@ static int handle_group_alt(struct objtool_file *file,
continue;
dest_off = arch_jump_destination(insn);
- if (dest_off == special_alt->new_off + special_alt->new_len)
+ if (dest_off == special_alt->new_off + special_alt->new_len) {
insn->jump_dest = next_insn_same_sec(file, last_orig_insn);
-
- if (!insn->jump_dest) {
- WARN_FUNC("can't find alternative jump destination",
- insn->sec, insn->offset);
- return -1;
+ if (!insn->jump_dest) {
+ WARN_FUNC("can't find alternative jump destination",
+ insn->sec, insn->offset);
+ return -1;
+ }
}
}
@@ -1564,7 +1594,7 @@ static int handle_jump_alt(struct objtool_file *file,
return -1;
}
- if (special_alt->key_addend & 2) {
+ if (opts.hack_jump_label && special_alt->key_addend & 2) {
struct reloc *reloc = insn_reloc(file, orig_insn);
if (reloc) {
@@ -1671,7 +1701,7 @@ static int add_special_section_alts(struct objtool_file *file)
free(special_alt);
}
- if (stats) {
+ if (opts.stats) {
printf("jl\\\tNOP\tJMP\n");
printf("short:\t%ld\t%ld\n", file->jl_nop_short, file->jl_short);
printf("long:\t%ld\t%ld\n", file->jl_nop_long, file->jl_long);
@@ -1917,7 +1947,7 @@ static int read_unwind_hints(struct objtool_file *file)
insn->hint = true;
- if (ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) {
+ if (opts.ibt && hint->type == UNWIND_HINT_TYPE_REGS_PARTIAL) {
struct symbol *sym = find_symbol_by_offset(insn->sec, insn->offset);
if (sym && sym->bind == STB_GLOBAL &&
@@ -2225,14 +2255,14 @@ static int decode_sections(struct objtool_file *file)
return ret;
/*
- * Must be before add_special_section_alts() as that depends on
- * jump_dest being set.
+ * Must be before add_jump_destinations(), which depends on 'func'
+ * being set for alternatives, to enable proper sibling call detection.
*/
- ret = add_jump_destinations(file);
+ ret = add_special_section_alts(file);
if (ret)
return ret;
- ret = add_special_section_alts(file);
+ ret = add_jump_destinations(file);
if (ret)
return ret;
@@ -2778,7 +2808,7 @@ static int update_cfi_state(struct instruction *insn,
}
/* detect when asm code uses rbp as a scratch register */
- if (!no_fp && insn->func && op->src.reg == CFI_BP &&
+ if (opts.stackval && insn->func && op->src.reg == CFI_BP &&
cfa->base != CFI_BP)
cfi->bp_scratch = true;
break;
@@ -3154,115 +3184,6 @@ static struct instruction *next_insn_to_validate(struct objtool_file *file,
return next_insn_same_sec(file, insn);
}
-static struct instruction *
-validate_ibt_reloc(struct objtool_file *file, struct reloc *reloc)
-{
- struct instruction *dest;
- struct section *sec;
- unsigned long off;
-
- sec = reloc->sym->sec;
- off = reloc->sym->offset;
-
- if ((reloc->sec->base->sh.sh_flags & SHF_EXECINSTR) &&
- (reloc->type == R_X86_64_PC32 || reloc->type == R_X86_64_PLT32))
- off += arch_dest_reloc_offset(reloc->addend);
- else
- off += reloc->addend;
-
- dest = find_insn(file, sec, off);
- if (!dest)
- return NULL;
-
- if (dest->type == INSN_ENDBR) {
- if (!list_empty(&dest->call_node))
- list_del_init(&dest->call_node);
-
- return NULL;
- }
-
- if (reloc->sym->static_call_tramp)
- return NULL;
-
- return dest;
-}
-
-static void warn_noendbr(const char *msg, struct section *sec, unsigned long offset,
- struct instruction *dest)
-{
- WARN_FUNC("%srelocation to !ENDBR: %s+0x%lx", sec, offset, msg,
- dest->func ? dest->func->name : dest->sec->name,
- dest->func ? dest->offset - dest->func->offset : dest->offset);
-}
-
-static void validate_ibt_dest(struct objtool_file *file, struct instruction *insn,
- struct instruction *dest)
-{
- if (dest->func && dest->func == insn->func) {
- /*
- * Anything from->to self is either _THIS_IP_ or IRET-to-self.
- *
- * There is no sane way to annotate _THIS_IP_ since the compiler treats the
- * relocation as a constant and is happy to fold in offsets, skewing any
- * annotation we do, leading to vast amounts of false-positives.
- *
- * There's also compiler generated _THIS_IP_ through KCOV and
- * such which we have no hope of annotating.
- *
- * As such, blanket accept self-references without issue.
- */
- return;
- }
-
- if (dest->noendbr)
- return;
-
- warn_noendbr("", insn->sec, insn->offset, dest);
-}
-
-static void validate_ibt_insn(struct objtool_file *file, struct instruction *insn)
-{
- struct instruction *dest;
- struct reloc *reloc;
-
- switch (insn->type) {
- case INSN_CALL:
- case INSN_CALL_DYNAMIC:
- case INSN_JUMP_CONDITIONAL:
- case INSN_JUMP_UNCONDITIONAL:
- case INSN_JUMP_DYNAMIC:
- case INSN_JUMP_DYNAMIC_CONDITIONAL:
- case INSN_RETURN:
- /*
- * We're looking for code references setting up indirect code
- * flow. As such, ignore direct code flow and the actual
- * dynamic branches.
- */
- return;
-
- case INSN_NOP:
- /*
- * handle_group_alt() will create INSN_NOP instruction that
- * don't belong to any section, ignore all NOP since they won't
- * carry a (useful) relocation anyway.
- */
- return;
-
- default:
- break;
- }
-
- for (reloc = insn_reloc(file, insn);
- reloc;
- reloc = find_reloc_by_dest_range(file->elf, insn->sec,
- reloc->offset + 1,
- (insn->offset + insn->len) - (reloc->offset + 1))) {
- dest = validate_ibt_reloc(file, reloc);
- if (dest)
- validate_ibt_dest(file, insn, dest);
- }
-}
-
/*
* Follow the branch starting at the given instruction, and recursively follow
* any other branches (jumps). Meanwhile, track the frame pointer state at
@@ -3283,7 +3204,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
while (1) {
next_insn = next_insn_to_validate(file, insn);
- if (file->c_file && func && insn->func && func != insn->func->pfunc) {
+ if (func && insn->func && func != insn->func->pfunc) {
WARN("%s() falls through to next function %s()",
func->name, insn->func->name);
return 1;
@@ -3336,7 +3257,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
ret = validate_branch(file, func, alt->insn, state);
if (ret) {
- if (backtrace)
+ if (opts.backtrace)
BT_FUNC("(alt)", insn);
return ret;
}
@@ -3352,11 +3273,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
switch (insn->type) {
case INSN_RETURN:
- if (sls && !insn->retpoline_safe &&
- next_insn && next_insn->type != INSN_TRAP) {
- WARN_FUNC("missing int3 after ret",
- insn->sec, insn->offset);
- }
return validate_return(func, insn, &state);
case INSN_CALL:
@@ -3365,7 +3281,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
if (ret)
return ret;
- if (!no_fp && func && !is_fentry_call(insn) &&
+ if (opts.stackval && func && !is_fentry_call(insn) &&
!has_valid_stack_frame(&state)) {
WARN_FUNC("call without frame pointer save/setup",
sec, insn->offset);
@@ -3388,7 +3304,7 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
ret = validate_branch(file, func,
insn->jump_dest, state);
if (ret) {
- if (backtrace)
+ if (opts.backtrace)
BT_FUNC("(branch)", insn);
return ret;
}
@@ -3400,13 +3316,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
break;
case INSN_JUMP_DYNAMIC:
- if (sls && !insn->retpoline_safe &&
- next_insn && next_insn->type != INSN_TRAP) {
- WARN_FUNC("missing int3 after indirect jump",
- insn->sec, insn->offset);
- }
-
- /* fallthrough */
case INSN_JUMP_DYNAMIC_CONDITIONAL:
if (is_sibling_call(insn)) {
ret = validate_sibling_call(file, insn, &state);
@@ -3472,9 +3381,6 @@ static int validate_branch(struct objtool_file *file, struct symbol *func,
break;
}
- if (ibt)
- validate_ibt_insn(file, insn);
-
if (insn->dead_end)
return 0;
@@ -3501,7 +3407,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec)
if (!file->hints)
return 0;
- init_insn_state(&state, sec);
+ init_insn_state(file, &state, sec);
if (sec) {
insn = find_insn(file, sec, 0);
@@ -3514,7 +3420,7 @@ static int validate_unwind_hints(struct objtool_file *file, struct section *sec)
while (&insn->list != &file->insn_list && (!sec || insn->sec == sec)) {
if (insn->hint && !insn->visited && !insn->ignore) {
ret = validate_branch(file, insn->func, insn, state);
- if (ret && backtrace)
+ if (ret && opts.backtrace)
BT_FUNC("<=== (hint)", insn);
warnings += ret;
}
@@ -3544,7 +3450,7 @@ static int validate_retpoline(struct objtool_file *file)
* loaded late, they very much do need retpoline in their
* .init.text
*/
- if (!strcmp(insn->sec->name, ".init.text") && !module)
+ if (!strcmp(insn->sec->name, ".init.text") && !opts.module)
continue;
WARN_FUNC("indirect %s found in RETPOLINE build",
@@ -3587,14 +3493,14 @@ static bool ignore_unreachable_insn(struct objtool_file *file, struct instructio
return true;
/*
- * Whole archive runs might encounder dead code from weak symbols.
+ * Whole archive runs might encounter dead code from weak symbols.
* This is where the linker will have dropped the weak symbol in
* favour of a regular symbol, but leaves the code in place.
*
* In this case we'll find a piece of code (whole function) that is not
* covered by a !section symbol. Ignore them.
*/
- if (!insn->func && lto) {
+ if (opts.link && !insn->func) {
int size = find_symbol_hole_containing(insn->sec, insn->offset);
unsigned long end = insn->offset + size;
@@ -3701,7 +3607,7 @@ static int validate_symbol(struct objtool_file *file, struct section *sec,
state->uaccess = sym->uaccess_safe;
ret = validate_branch(file, insn->func, insn, *state);
- if (ret && backtrace)
+ if (ret && opts.backtrace)
BT_FUNC("<=== (sym)", insn);
return ret;
}
@@ -3716,7 +3622,7 @@ static int validate_section(struct objtool_file *file, struct section *sec)
if (func->type != STT_FUNC)
continue;
- init_insn_state(&state, sec);
+ init_insn_state(file, &state, sec);
set_func_state(&state.cfi);
warnings += validate_symbol(file, sec, func, &state);
@@ -3725,7 +3631,7 @@ static int validate_section(struct objtool_file *file, struct section *sec)
return warnings;
}
-static int validate_vmlinux_functions(struct objtool_file *file)
+static int validate_noinstr_sections(struct objtool_file *file)
{
struct section *sec;
int warnings = 0;
@@ -3760,51 +3666,208 @@ static int validate_functions(struct objtool_file *file)
return warnings;
}
+static void mark_endbr_used(struct instruction *insn)
+{
+ if (!list_empty(&insn->call_node))
+ list_del_init(&insn->call_node);
+}
+
+static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn)
+{
+ struct instruction *dest;
+ struct reloc *reloc;
+ unsigned long off;
+ int warnings = 0;
+
+ /*
+ * Looking for function pointer load relocations. Ignore
+ * direct/indirect branches:
+ */
+ switch (insn->type) {
+ case INSN_CALL:
+ case INSN_CALL_DYNAMIC:
+ case INSN_JUMP_CONDITIONAL:
+ case INSN_JUMP_UNCONDITIONAL:
+ case INSN_JUMP_DYNAMIC:
+ case INSN_JUMP_DYNAMIC_CONDITIONAL:
+ case INSN_RETURN:
+ case INSN_NOP:
+ return 0;
+ default:
+ break;
+ }
+
+ for (reloc = insn_reloc(file, insn);
+ reloc;
+ reloc = find_reloc_by_dest_range(file->elf, insn->sec,
+ reloc->offset + 1,
+ (insn->offset + insn->len) - (reloc->offset + 1))) {
+
+ /*
+ * static_call_update() references the trampoline, which
+ * doesn't have (or need) ENDBR. Skip warning in that case.
+ */
+ if (reloc->sym->static_call_tramp)
+ continue;
+
+ off = reloc->sym->offset;
+ if (reloc->type == R_X86_64_PC32 || reloc->type == R_X86_64_PLT32)
+ off += arch_dest_reloc_offset(reloc->addend);
+ else
+ off += reloc->addend;
+
+ dest = find_insn(file, reloc->sym->sec, off);
+ if (!dest)
+ continue;
+
+ if (dest->type == INSN_ENDBR) {
+ mark_endbr_used(dest);
+ continue;
+ }
+
+ if (dest->func && dest->func == insn->func) {
+ /*
+ * Anything from->to self is either _THIS_IP_ or
+ * IRET-to-self.
+ *
+ * There is no sane way to annotate _THIS_IP_ since the
+ * compiler treats the relocation as a constant and is
+ * happy to fold in offsets, skewing any annotation we
+ * do, leading to vast amounts of false-positives.
+ *
+ * There's also compiler generated _THIS_IP_ through
+ * KCOV and such which we have no hope of annotating.
+ *
+ * As such, blanket accept self-references without
+ * issue.
+ */
+ continue;
+ }
+
+ if (dest->noendbr)
+ continue;
+
+ WARN_FUNC("relocation to !ENDBR: %s",
+ insn->sec, insn->offset,
+ offstr(dest->sec, dest->offset));
+
+ warnings++;
+ }
+
+ return warnings;
+}
+
+static int validate_ibt_data_reloc(struct objtool_file *file,
+ struct reloc *reloc)
+{
+ struct instruction *dest;
+
+ dest = find_insn(file, reloc->sym->sec,
+ reloc->sym->offset + reloc->addend);
+ if (!dest)
+ return 0;
+
+ if (dest->type == INSN_ENDBR) {
+ mark_endbr_used(dest);
+ return 0;
+ }
+
+ if (dest->noendbr)
+ return 0;
+
+ WARN_FUNC("data relocation to !ENDBR: %s",
+ reloc->sec->base, reloc->offset,
+ offstr(dest->sec, dest->offset));
+
+ return 1;
+}
+
+/*
+ * Validate IBT rules and remove used ENDBR instructions from the seal list.
+ * Unused ENDBR instructions will be annotated for sealing (i.e., replaced with
+ * NOPs) later, in create_ibt_endbr_seal_sections().
+ */
static int validate_ibt(struct objtool_file *file)
{
struct section *sec;
struct reloc *reloc;
+ struct instruction *insn;
+ int warnings = 0;
+
+ for_each_insn(file, insn)
+ warnings += validate_ibt_insn(file, insn);
for_each_sec(file, sec) {
- bool is_data;
- /* already done in validate_branch() */
+ /* Already done by validate_ibt_insn() */
if (sec->sh.sh_flags & SHF_EXECINSTR)
continue;
if (!sec->reloc)
continue;
- if (!strncmp(sec->name, ".orc", 4))
+ /*
+ * These sections can reference text addresses, but not with
+ * the intent to indirect branch to them.
+ */
+ if (!strncmp(sec->name, ".discard", 8) ||
+ !strncmp(sec->name, ".debug", 6) ||
+ !strcmp(sec->name, ".altinstructions") ||
+ !strcmp(sec->name, ".ibt_endbr_seal") ||
+ !strcmp(sec->name, ".orc_unwind_ip") ||
+ !strcmp(sec->name, ".parainstructions") ||
+ !strcmp(sec->name, ".retpoline_sites") ||
+ !strcmp(sec->name, ".smp_locks") ||
+ !strcmp(sec->name, ".static_call_sites") ||
+ !strcmp(sec->name, "_error_injection_whitelist") ||
+ !strcmp(sec->name, "_kprobe_blacklist") ||
+ !strcmp(sec->name, "__bug_table") ||
+ !strcmp(sec->name, "__ex_table") ||
+ !strcmp(sec->name, "__jump_table") ||
+ !strcmp(sec->name, "__mcount_loc") ||
+ !strcmp(sec->name, "__tracepoints"))
continue;
- if (!strncmp(sec->name, ".discard", 8))
- continue;
+ list_for_each_entry(reloc, &sec->reloc->reloc_list, list)
+ warnings += validate_ibt_data_reloc(file, reloc);
+ }
- if (!strncmp(sec->name, ".debug", 6))
- continue;
+ return warnings;
+}
- if (!strcmp(sec->name, "_error_injection_whitelist"))
- continue;
+static int validate_sls(struct objtool_file *file)
+{
+ struct instruction *insn, *next_insn;
+ int warnings = 0;
- if (!strcmp(sec->name, "_kprobe_blacklist"))
- continue;
+ for_each_insn(file, insn) {
+ next_insn = next_insn_same_sec(file, insn);
- is_data = strstr(sec->name, ".data") || strstr(sec->name, ".rodata");
+ if (insn->retpoline_safe)
+ continue;
- list_for_each_entry(reloc, &sec->reloc->reloc_list, list) {
- struct instruction *dest;
+ switch (insn->type) {
+ case INSN_RETURN:
+ if (!next_insn || next_insn->type != INSN_TRAP) {
+ WARN_FUNC("missing int3 after ret",
+ insn->sec, insn->offset);
+ warnings++;
+ }
- dest = validate_ibt_reloc(file, reloc);
- if (is_data && dest && !dest->noendbr) {
- warn_noendbr("data ", reloc->sym->sec,
- reloc->sym->offset + reloc->addend,
- dest);
+ break;
+ case INSN_JUMP_DYNAMIC:
+ if (!next_insn || next_insn->type != INSN_TRAP) {
+ WARN_FUNC("missing int3 after indirect jump",
+ insn->sec, insn->offset);
+ warnings++;
}
+ break;
+ default:
+ break;
}
}
- return 0;
+ return warnings;
}
static int validate_reachable_instructions(struct objtool_file *file)
@@ -3829,16 +3892,6 @@ int check(struct objtool_file *file)
{
int ret, warnings = 0;
- if (lto && !(vmlinux || module)) {
- fprintf(stderr, "--lto requires: --vmlinux or --module\n");
- return 1;
- }
-
- if (ibt && !lto) {
- fprintf(stderr, "--ibt requires: --lto\n");
- return 1;
- }
-
arch_initial_func_cfi_state(&initial_func_cfi);
init_cfi_state(&init_cfi);
init_cfi_state(&func_cfi);
@@ -3859,73 +3912,89 @@ int check(struct objtool_file *file)
if (list_empty(&file->insn_list))
goto out;
- if (vmlinux && !lto) {
- ret = validate_vmlinux_functions(file);
+ if (opts.retpoline) {
+ ret = validate_retpoline(file);
if (ret < 0)
- goto out;
-
+ return ret;
warnings += ret;
- goto out;
}
- if (retpoline) {
- ret = validate_retpoline(file);
+ if (opts.stackval || opts.orc || opts.uaccess) {
+ ret = validate_functions(file);
if (ret < 0)
- return ret;
+ goto out;
warnings += ret;
- }
- ret = validate_functions(file);
- if (ret < 0)
- goto out;
- warnings += ret;
+ ret = validate_unwind_hints(file, NULL);
+ if (ret < 0)
+ goto out;
+ warnings += ret;
- ret = validate_unwind_hints(file, NULL);
- if (ret < 0)
- goto out;
- warnings += ret;
+ if (!warnings) {
+ ret = validate_reachable_instructions(file);
+ if (ret < 0)
+ goto out;
+ warnings += ret;
+ }
- if (ibt) {
+ } else if (opts.noinstr) {
+ ret = validate_noinstr_sections(file);
+ if (ret < 0)
+ goto out;
+ warnings += ret;
+ }
+
+ if (opts.ibt) {
ret = validate_ibt(file);
if (ret < 0)
goto out;
warnings += ret;
}
- if (!warnings) {
- ret = validate_reachable_instructions(file);
+ if (opts.sls) {
+ ret = validate_sls(file);
if (ret < 0)
goto out;
warnings += ret;
}
- ret = create_static_call_sections(file);
- if (ret < 0)
- goto out;
- warnings += ret;
+ if (opts.static_call) {
+ ret = create_static_call_sections(file);
+ if (ret < 0)
+ goto out;
+ warnings += ret;
+ }
- if (retpoline) {
+ if (opts.retpoline) {
ret = create_retpoline_sites_sections(file);
if (ret < 0)
goto out;
warnings += ret;
}
- if (mcount) {
+ if (opts.mcount) {
ret = create_mcount_loc_sections(file);
if (ret < 0)
goto out;
warnings += ret;
}
- if (ibt) {
+ if (opts.ibt) {
ret = create_ibt_endbr_seal_sections(file);
if (ret < 0)
goto out;
warnings += ret;
}
- if (stats) {
+ if (opts.orc && !list_empty(&file->insn_list)) {
+ ret = orc_create(file);
+ if (ret < 0)
+ goto out;
+ warnings += ret;
+ }
+
+
+ if (opts.stats) {
printf("nr_insns_visited: %ld\n", nr_insns_visited);
printf("nr_cfi: %ld\n", nr_cfi);
printf("nr_cfi_reused: %ld\n", nr_cfi_reused);
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index d7b99a737496..c25e957c1e52 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -355,7 +355,7 @@ static int read_sections(struct elf *elf)
elf_hash_add(section_name, &sec->name_hash, str_hash(sec->name));
}
- if (stats) {
+ if (opts.stats) {
printf("nr_sections: %lu\n", (unsigned long)sections_nr);
printf("section_bits: %d\n", elf->section_bits);
}
@@ -374,9 +374,15 @@ static void elf_add_symbol(struct elf *elf, struct symbol *sym)
struct list_head *entry;
struct rb_node *pnode;
+ INIT_LIST_HEAD(&sym->pv_target);
+ sym->alias = sym;
+
sym->type = GELF_ST_TYPE(sym->sym.st_info);
sym->bind = GELF_ST_BIND(sym->sym.st_info);
+ if (sym->type == STT_FILE)
+ elf->num_files++;
+
sym->offset = sym->sym.st_value;
sym->len = sym->sym.st_size;
@@ -435,8 +441,6 @@ static int read_symbols(struct elf *elf)
return -1;
}
memset(sym, 0, sizeof(*sym));
- INIT_LIST_HEAD(&sym->pv_target);
- sym->alias = sym;
sym->idx = i;
@@ -475,7 +479,7 @@ static int read_symbols(struct elf *elf)
elf_add_symbol(elf, sym);
}
- if (stats) {
+ if (opts.stats) {
printf("nr_symbols: %lu\n", (unsigned long)symbols_nr);
printf("symbol_bits: %d\n", elf->symbol_bits);
}
@@ -546,7 +550,7 @@ static struct section *elf_create_reloc_section(struct elf *elf,
int reltype);
int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
- unsigned int type, struct symbol *sym, int addend)
+ unsigned int type, struct symbol *sym, s64 addend)
{
struct reloc *reloc;
@@ -575,37 +579,239 @@ int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
return 0;
}
+/*
+ * Ensure that any reloc section containing references to @sym is marked
+ * changed such that it will get re-generated in elf_rebuild_reloc_sections()
+ * with the new symbol index.
+ */
+static void elf_dirty_reloc_sym(struct elf *elf, struct symbol *sym)
+{
+ struct section *sec;
+
+ list_for_each_entry(sec, &elf->sections, list) {
+ struct reloc *reloc;
+
+ if (sec->changed)
+ continue;
+
+ list_for_each_entry(reloc, &sec->reloc_list, list) {
+ if (reloc->sym == sym) {
+ sec->changed = true;
+ break;
+ }
+ }
+ }
+}
+
+/*
+ * The libelf API is terrible; gelf_update_sym*() takes a data block relative
+ * index value, *NOT* the symbol index. As such, iterate the data blocks and
+ * adjust index until it fits.
+ *
+ * If no data block is found, allow adding a new data block provided the index
+ * is only one past the end.
+ */
+static int elf_update_symbol(struct elf *elf, struct section *symtab,
+ struct section *symtab_shndx, struct symbol *sym)
+{
+ Elf32_Word shndx = sym->sec ? sym->sec->idx : SHN_UNDEF;
+ Elf_Data *symtab_data = NULL, *shndx_data = NULL;
+ Elf64_Xword entsize = symtab->sh.sh_entsize;
+ int max_idx, idx = sym->idx;
+ Elf_Scn *s, *t = NULL;
+
+ s = elf_getscn(elf->elf, symtab->idx);
+ if (!s) {
+ WARN_ELF("elf_getscn");
+ return -1;
+ }
+
+ if (symtab_shndx) {
+ t = elf_getscn(elf->elf, symtab_shndx->idx);
+ if (!t) {
+ WARN_ELF("elf_getscn");
+ return -1;
+ }
+ }
+
+ for (;;) {
+ /* get next data descriptor for the relevant sections */
+ symtab_data = elf_getdata(s, symtab_data);
+ if (t)
+ shndx_data = elf_getdata(t, shndx_data);
+
+ /* end-of-list */
+ if (!symtab_data) {
+ void *buf;
+
+ if (idx) {
+ /* we don't do holes in symbol tables */
+ WARN("index out of range");
+ return -1;
+ }
+
+ /* if @idx == 0, it's the next contiguous entry, create it */
+ symtab_data = elf_newdata(s);
+ if (t)
+ shndx_data = elf_newdata(t);
+
+ buf = calloc(1, entsize);
+ if (!buf) {
+ WARN("malloc");
+ return -1;
+ }
+
+ symtab_data->d_buf = buf;
+ symtab_data->d_size = entsize;
+ symtab_data->d_align = 1;
+ symtab_data->d_type = ELF_T_SYM;
+
+ symtab->sh.sh_size += entsize;
+ symtab->changed = true;
+
+ if (t) {
+ shndx_data->d_buf = &sym->sec->idx;
+ shndx_data->d_size = sizeof(Elf32_Word);
+ shndx_data->d_align = sizeof(Elf32_Word);
+ shndx_data->d_type = ELF_T_WORD;
+
+ symtab_shndx->sh.sh_size += sizeof(Elf32_Word);
+ symtab_shndx->changed = true;
+ }
+
+ break;
+ }
+
+ /* empty blocks should not happen */
+ if (!symtab_data->d_size) {
+ WARN("zero size data");
+ return -1;
+ }
+
+ /* is this the right block? */
+ max_idx = symtab_data->d_size / entsize;
+ if (idx < max_idx)
+ break;
+
+ /* adjust index and try again */
+ idx -= max_idx;
+ }
+
+ /* something went side-ways */
+ if (idx < 0) {
+ WARN("negative index");
+ return -1;
+ }
+
+ /* setup extended section index magic and write the symbol */
+ if (shndx >= SHN_UNDEF && shndx < SHN_LORESERVE) {
+ sym->sym.st_shndx = shndx;
+ if (!shndx_data)
+ shndx = 0;
+ } else {
+ sym->sym.st_shndx = SHN_XINDEX;
+ if (!shndx_data) {
+ WARN("no .symtab_shndx");
+ return -1;
+ }
+ }
+
+ if (!gelf_update_symshndx(symtab_data, shndx_data, idx, &sym->sym, shndx)) {
+ WARN_ELF("gelf_update_symshndx");
+ return -1;
+ }
+
+ return 0;
+}
+
+static struct symbol *
+elf_create_section_symbol(struct elf *elf, struct section *sec)
+{
+ struct section *symtab, *symtab_shndx;
+ Elf32_Word first_non_local, new_idx;
+ struct symbol *sym, *old;
+
+ symtab = find_section_by_name(elf, ".symtab");
+ if (symtab) {
+ symtab_shndx = find_section_by_name(elf, ".symtab_shndx");
+ } else {
+ WARN("no .symtab");
+ return NULL;
+ }
+
+ sym = calloc(1, sizeof(*sym));
+ if (!sym) {
+ perror("malloc");
+ return NULL;
+ }
+
+ sym->name = sec->name;
+ sym->sec = sec;
+
+ // st_name 0
+ sym->sym.st_info = GELF_ST_INFO(STB_LOCAL, STT_SECTION);
+ // st_other 0
+ // st_value 0
+ // st_size 0
+
+ /*
+ * Move the first global symbol, as per sh_info, into a new, higher
+ * symbol index. This fees up a spot for a new local symbol.
+ */
+ first_non_local = symtab->sh.sh_info;
+ new_idx = symtab->sh.sh_size / symtab->sh.sh_entsize;
+ old = find_symbol_by_index(elf, first_non_local);
+ if (old) {
+ old->idx = new_idx;
+
+ hlist_del(&old->hash);
+ elf_hash_add(symbol, &old->hash, old->idx);
+
+ elf_dirty_reloc_sym(elf, old);
+
+ if (elf_update_symbol(elf, symtab, symtab_shndx, old)) {
+ WARN("elf_update_symbol move");
+ return NULL;
+ }
+
+ new_idx = first_non_local;
+ }
+
+ sym->idx = new_idx;
+ if (elf_update_symbol(elf, symtab, symtab_shndx, sym)) {
+ WARN("elf_update_symbol");
+ return NULL;
+ }
+
+ /*
+ * Either way, we added a LOCAL symbol.
+ */
+ symtab->sh.sh_info += 1;
+
+ elf_add_symbol(elf, sym);
+
+ return sym;
+}
+
int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
unsigned long offset, unsigned int type,
struct section *insn_sec, unsigned long insn_off)
{
- struct symbol *sym;
- int addend;
-
- if (insn_sec->sym) {
- sym = insn_sec->sym;
- addend = insn_off;
+ struct symbol *sym = insn_sec->sym;
+ int addend = insn_off;
- } else {
+ if (!sym) {
/*
- * The Clang assembler strips section symbols, so we have to
- * reference the function symbol instead:
+ * Due to how weak functions work, we must use section based
+ * relocations. Symbol based relocations would result in the
+ * weak and non-weak function annotations being overlaid on the
+ * non-weak function after linking.
*/
- sym = find_symbol_containing(insn_sec, insn_off);
- if (!sym) {
- /*
- * Hack alert. This happens when we need to reference
- * the NOP pad insn immediately after the function.
- */
- sym = find_symbol_containing(insn_sec, insn_off - 1);
- }
-
- if (!sym) {
- WARN("can't find symbol containing %s+0x%lx", insn_sec->name, insn_off);
+ sym = elf_create_section_symbol(elf, insn_sec);
+ if (!sym)
return -1;
- }
- addend = insn_off - sym->offset;
+ insn_sec->sym = sym;
}
return elf_add_reloc(elf, sec, offset, type, sym, addend);
@@ -700,7 +906,7 @@ static int read_relocs(struct elf *elf)
tot_reloc += nr_reloc;
}
- if (stats) {
+ if (opts.stats) {
printf("max_reloc: %lu\n", max_reloc);
printf("tot_reloc: %lu\n", tot_reloc);
printf("reloc_bits: %d\n", elf->reloc_bits);
@@ -1079,7 +1285,7 @@ int elf_write(struct elf *elf)
struct section *sec;
Elf_Scn *s;
- if (dryrun)
+ if (opts.dryrun)
return 0;
/* Update changed relocation sections and section headers: */
diff --git a/tools/objtool/include/objtool/builtin.h b/tools/objtool/include/objtool/builtin.h
index c39dbfaef6dc..280ea18b7f2b 100644
--- a/tools/objtool/include/objtool/builtin.h
+++ b/tools/objtool/include/objtool/builtin.h
@@ -8,13 +8,37 @@
#include <subcmd/parse-options.h>
extern const struct option check_options[];
-extern bool no_fp, no_unreachable, retpoline, module, backtrace, uaccess, stats,
- lto, vmlinux, mcount, noinstr, backup, sls, dryrun,
- ibt;
+
+struct opts {
+ /* actions: */
+ bool dump_orc;
+ bool hack_jump_label;
+ bool hack_noinstr;
+ bool ibt;
+ bool mcount;
+ bool noinstr;
+ bool orc;
+ bool retpoline;
+ bool sls;
+ bool stackval;
+ bool static_call;
+ bool uaccess;
+
+ /* options: */
+ bool backtrace;
+ bool backup;
+ bool dryrun;
+ bool link;
+ bool module;
+ bool no_unreachable;
+ bool sec_address;
+ bool stats;
+};
+
+extern struct opts opts;
extern int cmd_parse_options(int argc, const char **argv, const char * const usage[]);
-extern int cmd_check(int argc, const char **argv);
-extern int cmd_orc(int argc, const char **argv);
+extern int objtool_run(int argc, const char **argv);
#endif /* _BUILTIN_H */
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 22ba7e2b816e..adebfbc2b518 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -73,7 +73,7 @@ struct reloc {
struct symbol *sym;
unsigned long offset;
unsigned int type;
- int addend;
+ s64 addend;
int idx;
bool jump_table_start;
};
@@ -86,7 +86,7 @@ struct elf {
int fd;
bool changed;
char *name;
- unsigned int text_size;
+ unsigned int text_size, num_files;
struct list_head sections;
int symbol_bits;
@@ -131,11 +131,21 @@ static inline u32 reloc_hash(struct reloc *reloc)
return sec_offset_hash(reloc->sec, reloc->offset);
}
+/*
+ * Try to see if it's a whole archive (vmlinux.o or module).
+ *
+ * Note this will miss the case where a module only has one source file.
+ */
+static inline bool has_multiple_files(struct elf *elf)
+{
+ return elf->num_files > 1;
+}
+
struct elf *elf_open_read(const char *name, int flags);
struct section *elf_create_section(struct elf *elf, const char *name, unsigned int sh_flags, size_t entsize, int nr);
int elf_add_reloc(struct elf *elf, struct section *sec, unsigned long offset,
- unsigned int type, struct symbol *sym, int addend);
+ unsigned int type, struct symbol *sym, s64 addend);
int elf_add_reloc_to_insn(struct elf *elf, struct section *sec,
unsigned long offset, unsigned int type,
struct section *insn_sec, unsigned long insn_off);
diff --git a/tools/objtool/include/objtool/objtool.h b/tools/objtool/include/objtool/objtool.h
index 7a5c13a78f87..a6e72d916807 100644
--- a/tools/objtool/include/objtool/objtool.h
+++ b/tools/objtool/include/objtool/objtool.h
@@ -27,7 +27,7 @@ struct objtool_file {
struct list_head static_call_list;
struct list_head mcount_loc_list;
struct list_head endbr_list;
- bool ignore_unreachables, c_file, hints, rodata;
+ bool ignore_unreachables, hints, rodata;
unsigned int nr_endbr;
unsigned int nr_endbr_int;
diff --git a/tools/objtool/include/objtool/warn.h b/tools/objtool/include/objtool/warn.h
index 802cfda0a6f6..a3e79ae75f2e 100644
--- a/tools/objtool/include/objtool/warn.h
+++ b/tools/objtool/include/objtool/warn.h
@@ -11,34 +11,33 @@
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
+#include <objtool/builtin.h>
#include <objtool/elf.h>
extern const char *objname;
static inline char *offstr(struct section *sec, unsigned long offset)
{
- struct symbol *func;
- char *name, *str;
- unsigned long name_off;
+ bool is_text = (sec->sh.sh_flags & SHF_EXECINSTR);
+ struct symbol *sym = NULL;
+ char *str;
+ int len;
- func = find_func_containing(sec, offset);
- if (!func)
- func = find_symbol_containing(sec, offset);
- if (func) {
- name = func->name;
- name_off = offset - func->offset;
+ if (is_text)
+ sym = find_func_containing(sec, offset);
+ if (!sym)
+ sym = find_symbol_containing(sec, offset);
+
+ if (sym) {
+ str = malloc(strlen(sym->name) + strlen(sec->name) + 40);
+ len = sprintf(str, "%s+0x%lx", sym->name, offset - sym->offset);
+ if (opts.sec_address)
+ sprintf(str+len, " (%s+0x%lx)", sec->name, offset);
} else {
- name = sec->name;
- name_off = offset;
+ str = malloc(strlen(sec->name) + 20);
+ sprintf(str, "%s+0x%lx", sec->name, offset);
}
- str = malloc(strlen(name) + 20);
-
- if (func)
- sprintf(str, "%s()+0x%lx", name, name_off);
- else
- sprintf(str, "%s+0x%lx", name, name_off);
-
return str;
}
diff --git a/tools/objtool/objtool.c b/tools/objtool/objtool.c
index b09946f4e1d6..512669ce064c 100644
--- a/tools/objtool/objtool.c
+++ b/tools/objtool/objtool.c
@@ -3,16 +3,6 @@
* Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
*/
-/*
- * objtool:
- *
- * The 'check' subcmd analyzes every .o file and ensures the validity of its
- * stack trace metadata. It enforces a set of rules on asm code and C inline
- * assembly code so that stack traces can be reliable.
- *
- * For more information, see tools/objtool/Documentation/stack-validation.txt.
- */
-
#include <stdio.h>
#include <stdbool.h>
#include <string.h>
@@ -26,20 +16,6 @@
#include <objtool/objtool.h>
#include <objtool/warn.h>
-struct cmd_struct {
- const char *name;
- int (*fn)(int, const char **);
- const char *help;
-};
-
-static const char objtool_usage_string[] =
- "objtool COMMAND [ARGS]";
-
-static struct cmd_struct objtool_cmds[] = {
- {"check", cmd_check, "Perform stack metadata validation on an object file" },
- {"orc", cmd_orc, "Generate in-place ORC unwind tables for an object file" },
-};
-
bool help;
const char *objname;
@@ -118,7 +94,7 @@ struct objtool_file *objtool_open_read(const char *_objname)
if (!file.elf)
return NULL;
- if (backup && !objtool_create_backup(objname)) {
+ if (opts.backup && !objtool_create_backup(objname)) {
WARN("can't create backup file");
return NULL;
}
@@ -129,8 +105,7 @@ struct objtool_file *objtool_open_read(const char *_objname)
INIT_LIST_HEAD(&file.static_call_list);
INIT_LIST_HEAD(&file.mcount_loc_list);
INIT_LIST_HEAD(&file.endbr_list);
- file.c_file = !vmlinux && find_section_by_name(file.elf, ".comment");
- file.ignore_unreachables = no_unreachable;
+ file.ignore_unreachables = opts.no_unreachable;
file.hints = false;
return &file;
@@ -138,7 +113,7 @@ struct objtool_file *objtool_open_read(const char *_objname)
void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func)
{
- if (!noinstr)
+ if (!opts.noinstr)
return;
if (!f->pv_ops) {
@@ -162,70 +137,6 @@ void objtool_pv_add(struct objtool_file *f, int idx, struct symbol *func)
f->pv_ops[idx].clean = false;
}
-static void cmd_usage(void)
-{
- unsigned int i, longest = 0;
-
- printf("\n usage: %s\n\n", objtool_usage_string);
-
- for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) {
- if (longest < strlen(objtool_cmds[i].name))
- longest = strlen(objtool_cmds[i].name);
- }
-
- puts(" Commands:");
- for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) {
- printf(" %-*s ", longest, objtool_cmds[i].name);
- puts(objtool_cmds[i].help);
- }
-
- printf("\n");
-
- if (!help)
- exit(129);
- exit(0);
-}
-
-static void handle_options(int *argc, const char ***argv)
-{
- while (*argc > 0) {
- const char *cmd = (*argv)[0];
-
- if (cmd[0] != '-')
- break;
-
- if (!strcmp(cmd, "--help") || !strcmp(cmd, "-h")) {
- help = true;
- break;
- } else {
- fprintf(stderr, "Unknown option: %s\n", cmd);
- cmd_usage();
- }
-
- (*argv)++;
- (*argc)--;
- }
-}
-
-static void handle_internal_command(int argc, const char **argv)
-{
- const char *cmd = argv[0];
- unsigned int i, ret;
-
- for (i = 0; i < ARRAY_SIZE(objtool_cmds); i++) {
- struct cmd_struct *p = objtool_cmds+i;
-
- if (strcmp(p->name, cmd))
- continue;
-
- ret = p->fn(argc, argv);
-
- exit(ret);
- }
-
- cmd_usage();
-}
-
int main(int argc, const char **argv)
{
static const char *UNUSED = "OBJTOOL_NOT_IMPLEMENTED";
@@ -234,14 +145,7 @@ int main(int argc, const char **argv)
exec_cmd_init("objtool", UNUSED, UNUSED, UNUSED);
pager_init(UNUSED);
- argv++;
- argc--;
- handle_options(&argc, &argv);
-
- if (!argc || help)
- cmd_usage();
-
- handle_internal_command(argc, argv);
+ objtool_run(argc, argv);
return 0;
}
diff --git a/tools/objtool/weak.c b/tools/objtool/weak.c
index 8314e824db4a..d83f607733b0 100644
--- a/tools/objtool/weak.c
+++ b/tools/objtool/weak.c
@@ -15,17 +15,12 @@
return ENOSYS; \
})
-int __weak check(struct objtool_file *file)
-{
- UNSUPPORTED("check subcommand");
-}
-
int __weak orc_dump(const char *_objname)
{
- UNSUPPORTED("orc");
+ UNSUPPORTED("ORC");
}
int __weak orc_create(struct objtool_file *file)
{
- UNSUPPORTED("orc");
+ UNSUPPORTED("ORC");
}
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt
index 9c330cdfa973..71ebdf8125de 100644
--- a/tools/perf/Documentation/perf.txt
+++ b/tools/perf/Documentation/perf.txt
@@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1],
linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1],
linkperf:perf-evlist[1], linkperf:perf-ftrace[1],
linkperf:perf-help[1], linkperf:perf-inject[1],
-linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1],
+linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1],
linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1],
linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1],
linkperf:perf-script[1], linkperf:perf-test[1],
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 96ad944ca6a8..1bd64e7404b9 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG
PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil
PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null)
FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS)
+ ifeq ($(CC_NO_CLANG), 0)
+ PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS))
+ endif
endif
FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS)
@@ -550,9 +553,16 @@ ifndef NO_LIBELF
ifeq ($(feature-libbpf), 1)
EXTLIBS += -lbpf
$(call detected,CONFIG_LIBBPF_DYNAMIC)
+
+ $(call feature_check,libbpf-btf__load_from_kernel_by_id)
+ ifeq ($(feature-libbpf-btf__load_from_kernel_by_id), 1)
+ CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+ endif
else
dummy := $(error Error: No libbpf devel library found, please install libbpf-devel);
endif
+ else
+ CFLAGS += -DHAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
endif
endif
@@ -790,6 +800,9 @@ else
LDFLAGS += $(PERL_EMBED_LDFLAGS)
EXTLIBS += $(PERL_EMBED_LIBADD)
CFLAGS += -DHAVE_LIBPERL_SUPPORT
+ ifeq ($(CC_NO_CLANG), 0)
+ CFLAGS += -Wno-compound-token-split-by-macro
+ endif
$(call detected,CONFIG_LIBPERL)
endif
endif
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 86e2e926aa0e..e8b577d33e53 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
bool privileged = perf_event_paranoid_check(-1);
struct evsel *tracking_evsel;
int err;
+ u64 bit;
sper->evlist = evlist;
@@ -239,6 +240,21 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
arm_spe_set_timestamp(itr, arm_spe_evsel);
}
+ /*
+ * Set this only so that perf report knows that SPE generates memory info. It has no effect
+ * on the opening of the event or the SPE data produced.
+ */
+ evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
+
+ /*
+ * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+ * inform that the resulting output's SPE samples contain physical addresses
+ * where applicable.
+ */
+ bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable");
+ if (arm_spe_evsel->core.attr.config & bit)
+ evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
+
/* Add dummy event to keep tracking */
err = parse_events(evlist, "dummy:u", NULL);
if (err)
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index d2ce31e28cd7..41c1596e5207 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -8,27 +8,6 @@
#include "callchain.h"
#include "record.h"
-/* On arm64, kernel text segment starts at high memory address,
- * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
- * address, like 0xffff 0000 00ax xxxx. When only small amount of
- * memory is used by modules, gap between end of module's text segment
- * and start of kernel text segment may reach 2G.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-#define SYMBOL_LIMIT (1 << 12) /* 4K */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) ||
- (strchr(p->name, '[') == NULL && strchr(c->name, '[')))
- /* Limit range of last symbol in module and kernel */
- p->end += SYMBOL_LIMIT;
- else
- p->end = c->start;
- pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
-
void arch__add_leaf_frame_record_opts(struct record_opts *opts)
{
opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 8a79c4126e5b..0115f3166568 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -1,5 +1,4 @@
perf-y += header.o
-perf-y += machine.o
perf-y += kvm-stat.o
perf-y += perf_regs.o
perf-y += mem-events.o
diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c
deleted file mode 100644
index e652a1aa8132..000000000000
--- a/tools/perf/arch/powerpc/util/machine.c
+++ /dev/null
@@ -1,25 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <string.h>
-#include <internal/lib.h> // page_size
-#include "debug.h"
-#include "symbol.h"
-
-/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000
- * whereas the modules are located at very high memory addresses,
- * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very high.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
- /* Limit the range of last kernel symbol */
- p->end += page_size;
- else
- p->end = c->start;
- pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c
index 7644a4f6d4a4..98bc3f39d5f3 100644
--- a/tools/perf/arch/s390/util/machine.c
+++ b/tools/perf/arch/s390/util/machine.c
@@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name)
return 0;
}
-
-/* On s390 kernel text segment start is located at very low memory addresses,
- * for example 0x10000. Modules are located at very high memory addresses,
- * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment
- * and beginning of first module's text segment is very big.
- * Therefore do not fill this gap and do not assign it to the kernel dso map.
- */
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- if (strchr(p->name, '[') == NULL && strchr(c->name, '['))
- /* Last kernel symbol mapped to end of page */
- p->end = roundup(p->end, page_size);
- else
- p->end = c->start;
- pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
-}
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 207c56805c55..0ed177991ad0 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -9,6 +9,8 @@
#include "../../../util/perf_regs.h"
#include "../../../util/debug.h"
#include "../../../util/event.h"
+#include "../../../util/pmu.h"
+#include "../../../util/pmu-hybrid.h"
const struct sample_reg sample_reg_masks[] = {
SMPL_REG(AX, PERF_REG_X86_AX),
@@ -284,12 +286,22 @@ uint64_t arch__intr_reg_mask(void)
.disabled = 1,
.exclude_kernel = 1,
};
+ struct perf_pmu *pmu;
int fd;
/*
* In an unnamed union, init it here to build on older gcc versions
*/
attr.sample_period = 1;
+ if (perf_pmu__has_hybrid()) {
+ /*
+ * The same register set is supported among different hybrid PMUs.
+ * Only check the first available one.
+ */
+ pmu = list_first_entry(&perf_pmu__hybrid_pmus, typeof(*pmu), hybrid_list);
+ attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
+ }
+
event_attr_init(&attr);
fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index 134612bde0cb..4256dc5d6236 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct)
static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
{
pthread_attr_t thread_attr, *attrp = NULL;
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
unsigned int i, j;
int ret = 0;
+ int nrcpus;
+ size_t size;
if (!noaffinity)
pthread_attr_init(&thread_attr);
+ nrcpus = perf_cpu_map__nr(cpu);
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
for (i = 0; i < nthreads; i++) {
struct worker *w = &worker[i];
@@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
init_fdmaps(w, 50);
if (!noaffinity) {
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
+ size, cpuset);
- ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
- if (ret)
+ ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+ if (ret) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+ }
attrp = &thread_attr;
}
ret = pthread_create(&w->thread, attrp, workerfn,
(void *)(struct worker *) w);
- if (ret)
+ if (ret) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
if (!noaffinity)
pthread_attr_destroy(&thread_attr);
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 37de970c9743..2728b0140853 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -291,9 +291,11 @@ static void print_summary(void)
static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
{
pthread_attr_t thread_attr, *attrp = NULL;
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
unsigned int i, j;
int ret = 0, events = EPOLLIN;
+ int nrcpus;
+ size_t size;
if (oneshot)
events |= EPOLLONESHOT;
@@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
if (!noaffinity)
pthread_attr_init(&thread_attr);
+ nrcpus = perf_cpu_map__nr(cpu);
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
for (i = 0; i < nthreads; i++) {
struct worker *w = &worker[i];
@@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
}
if (!noaffinity) {
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu,
+ size, cpuset);
- ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
- if (ret)
+ ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+ if (ret) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+ }
attrp = &thread_attr;
}
ret = pthread_create(&w->thread, attrp, workerfn,
(void *)(struct worker *) w);
- if (ret)
+ if (ret) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
if (!noaffinity)
pthread_attr_destroy(&thread_attr);
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index dbcecec4eeda..f05db4cf983d 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -122,12 +122,14 @@ static void print_summary(void)
int bench_futex_hash(int argc, const char **argv)
{
int ret = 0;
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
struct sigaction act;
unsigned int i;
pthread_attr_t thread_attr;
struct worker *worker = NULL;
struct perf_cpu_map *cpu;
+ int nrcpus;
+ size_t size;
argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0);
if (argc) {
@@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv)
threads_starting = params.nthreads;
pthread_attr_init(&thread_attr);
gettimeofday(&bench__start, NULL);
+
+ nrcpus = perf_cpu_map__nr(cpu);
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
for (i = 0; i < params.nthreads; i++) {
worker[i].tid = i;
worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex));
if (!worker[i].futex)
goto errmem;
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
- ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
- if (ret)
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
+ ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset);
+ if (ret) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
-
+ }
ret = pthread_create(&worker[i].thread, &thread_attr, workerfn,
(void *)(struct worker *) &worker[i]);
- if (ret)
+ if (ret) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
pthread_attr_destroy(&thread_attr);
pthread_mutex_lock(&thread_lock);
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 6fc9a3d55c1f..0abb3f7ee24f 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -120,11 +120,17 @@ static void *workerfn(void *arg)
static void create_threads(struct worker *w, pthread_attr_t thread_attr,
struct perf_cpu_map *cpu)
{
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
unsigned int i;
+ int nrcpus = perf_cpu_map__nr(cpu);
+ size_t size;
threads_starting = params.nthreads;
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
for (i = 0; i < params.nthreads; i++) {
worker[i].tid = i;
@@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
} else
worker[i].futex = &global_futex;
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+ if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+ }
- if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i]))
+ if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
}
int bench_futex_lock_pi(int argc, const char **argv)
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index 2f59d5d1c509..b6faabfafb8e 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused)
static void block_threads(pthread_t *w,
pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
{
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
unsigned int i;
+ int nrcpus = perf_cpu_map__nr(cpu);
+ size_t size;
threads_starting = params.nthreads;
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+ if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+ }
- if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+ if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
}
static void toggle_done(int sig __maybe_unused,
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 861deb934745..e47f46a3a47e 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused)
static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
struct perf_cpu_map *cpu)
{
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
unsigned int i;
+ int nrcpus = perf_cpu_map__nr(cpu);
+ size_t size;
threads_starting = params.nthreads;
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+ if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+ }
- if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL))
+ if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
}
static void print_run(struct thread_data *waking_worker, unsigned int run_num)
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index cfda48bef1d7..201a3555f09a 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -97,22 +97,32 @@ static void print_summary(void)
static void block_threads(pthread_t *w,
pthread_attr_t thread_attr, struct perf_cpu_map *cpu)
{
- cpu_set_t cpuset;
+ cpu_set_t *cpuset;
unsigned int i;
-
+ size_t size;
+ int nrcpus = perf_cpu_map__nr(cpu);
threads_starting = params.nthreads;
+ cpuset = CPU_ALLOC(nrcpus);
+ BUG_ON(!cpuset);
+ size = CPU_ALLOC_SIZE(nrcpus);
+
/* create and block all threads */
for (i = 0; i < params.nthreads; i++) {
- CPU_ZERO(&cpuset);
- CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
+ CPU_ZERO_S(size, cpuset);
+ CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset);
- if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
+ if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
+ }
- if (pthread_create(&w[i], &thread_attr, workerfn, NULL))
+ if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) {
+ CPU_FREE(cpuset);
err(EXIT_FAILURE, "pthread_create");
+ }
}
+ CPU_FREE(cpuset);
}
static void toggle_done(int sig __maybe_unused,
diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
index f2640179ada9..20eed1e53f80 100644
--- a/tools/perf/bench/numa.c
+++ b/tools/perf/bench/numa.c
@@ -34,6 +34,7 @@
#include <linux/numa.h>
#include <linux/zalloc.h>
+#include "../util/header.h"
#include <numa.h>
#include <numaif.h>
@@ -54,7 +55,7 @@
struct thread_data {
int curr_cpu;
- cpu_set_t bind_cpumask;
+ cpu_set_t *bind_cpumask;
int bind_node;
u8 *process_data;
int process_nr;
@@ -266,71 +267,117 @@ static bool node_has_cpus(int node)
return ret;
}
-static cpu_set_t bind_to_cpu(int target_cpu)
+static cpu_set_t *bind_to_cpu(int target_cpu)
{
- cpu_set_t orig_mask, mask;
- int ret;
+ int nrcpus = numa_num_possible_cpus();
+ cpu_set_t *orig_mask, *mask;
+ size_t size;
- ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
- BUG_ON(ret);
+ orig_mask = CPU_ALLOC(nrcpus);
+ BUG_ON(!orig_mask);
+ size = CPU_ALLOC_SIZE(nrcpus);
+ CPU_ZERO_S(size, orig_mask);
+
+ if (sched_getaffinity(0, size, orig_mask))
+ goto err_out;
- CPU_ZERO(&mask);
+ mask = CPU_ALLOC(nrcpus);
+ if (!mask)
+ goto err_out;
+
+ CPU_ZERO_S(size, mask);
if (target_cpu == -1) {
int cpu;
for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
- CPU_SET(cpu, &mask);
+ CPU_SET_S(cpu, size, mask);
} else {
- BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus);
- CPU_SET(target_cpu, &mask);
+ if (target_cpu < 0 || target_cpu >= g->p.nr_cpus)
+ goto err;
+
+ CPU_SET_S(target_cpu, size, mask);
}
- ret = sched_setaffinity(0, sizeof(mask), &mask);
- BUG_ON(ret);
+ if (sched_setaffinity(0, size, mask))
+ goto err;
return orig_mask;
+
+err:
+ CPU_FREE(mask);
+err_out:
+ CPU_FREE(orig_mask);
+
+ /* BUG_ON due to failure in allocation of orig_mask/mask */
+ BUG_ON(-1);
+ return NULL;
}
-static cpu_set_t bind_to_node(int target_node)
+static cpu_set_t *bind_to_node(int target_node)
{
- cpu_set_t orig_mask, mask;
+ int nrcpus = numa_num_possible_cpus();
+ size_t size;
+ cpu_set_t *orig_mask, *mask;
int cpu;
- int ret;
- ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
- BUG_ON(ret);
+ orig_mask = CPU_ALLOC(nrcpus);
+ BUG_ON(!orig_mask);
+ size = CPU_ALLOC_SIZE(nrcpus);
+ CPU_ZERO_S(size, orig_mask);
- CPU_ZERO(&mask);
+ if (sched_getaffinity(0, size, orig_mask))
+ goto err_out;
+
+ mask = CPU_ALLOC(nrcpus);
+ if (!mask)
+ goto err_out;
+
+ CPU_ZERO_S(size, mask);
if (target_node == NUMA_NO_NODE) {
for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
- CPU_SET(cpu, &mask);
+ CPU_SET_S(cpu, size, mask);
} else {
struct bitmask *cpumask = numa_allocate_cpumask();
- BUG_ON(!cpumask);
+ if (!cpumask)
+ goto err;
+
if (!numa_node_to_cpus(target_node, cpumask)) {
for (cpu = 0; cpu < (int)cpumask->size; cpu++) {
if (numa_bitmask_isbitset(cpumask, cpu))
- CPU_SET(cpu, &mask);
+ CPU_SET_S(cpu, size, mask);
}
}
numa_free_cpumask(cpumask);
}
- ret = sched_setaffinity(0, sizeof(mask), &mask);
- BUG_ON(ret);
+ if (sched_setaffinity(0, size, mask))
+ goto err;
return orig_mask;
+
+err:
+ CPU_FREE(mask);
+err_out:
+ CPU_FREE(orig_mask);
+
+ /* BUG_ON due to failure in allocation of orig_mask/mask */
+ BUG_ON(-1);
+ return NULL;
}
-static void bind_to_cpumask(cpu_set_t mask)
+static void bind_to_cpumask(cpu_set_t *mask)
{
int ret;
+ size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus());
- ret = sched_setaffinity(0, sizeof(mask), &mask);
- BUG_ON(ret);
+ ret = sched_setaffinity(0, size, mask);
+ if (ret) {
+ CPU_FREE(mask);
+ BUG_ON(ret);
+ }
}
static void mempol_restore(void)
@@ -376,7 +423,7 @@ do { \
static u8 *alloc_data(ssize_t bytes0, int map_flags,
int init_zero, int init_cpu0, int thp, int init_random)
{
- cpu_set_t orig_mask;
+ cpu_set_t *orig_mask = NULL;
ssize_t bytes;
u8 *buf;
int ret;
@@ -434,6 +481,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags,
/* Restore affinity: */
if (init_cpu0) {
bind_to_cpumask(orig_mask);
+ CPU_FREE(orig_mask);
mempol_restore();
}
@@ -585,10 +633,16 @@ static int parse_setup_cpu_list(void)
return -1;
}
+ if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) {
+ printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n");
+ return -1;
+ }
+
BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0);
BUG_ON(bind_cpu_0 > bind_cpu_1);
for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) {
+ size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus);
int i;
for (i = 0; i < mul; i++) {
@@ -608,10 +662,15 @@ static int parse_setup_cpu_list(void)
tprintf("%2d", bind_cpu);
}
- CPU_ZERO(&td->bind_cpumask);
+ td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus);
+ BUG_ON(!td->bind_cpumask);
+ CPU_ZERO_S(size, td->bind_cpumask);
for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) {
- BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus);
- CPU_SET(cpu, &td->bind_cpumask);
+ if (cpu < 0 || cpu >= g->p.nr_cpus) {
+ CPU_FREE(td->bind_cpumask);
+ BUG_ON(-1);
+ }
+ CPU_SET_S(cpu, size, td->bind_cpumask);
}
t++;
}
@@ -752,8 +811,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused,
return parse_node_list(arg);
}
-#define BIT(x) (1ul << x)
-
static inline uint32_t lfsr_32(uint32_t lfsr)
{
const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31);
@@ -1241,7 +1298,7 @@ static void *worker_thread(void *__tdata)
* by migrating to CPU#0:
*/
if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) {
- cpu_set_t orig_mask;
+ cpu_set_t *orig_mask;
int target_cpu;
int this_cpu;
@@ -1265,6 +1322,7 @@ static void *worker_thread(void *__tdata)
printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu);
bind_to_cpumask(orig_mask);
+ CPU_FREE(orig_mask);
}
if (details >= 3) {
@@ -1398,21 +1456,31 @@ static void init_thread_data(void)
for (t = 0; t < g->p.nr_tasks; t++) {
struct thread_data *td = g->threads + t;
+ size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus);
int cpu;
/* Allow all nodes by default: */
td->bind_node = NUMA_NO_NODE;
/* Allow all CPUs by default: */
- CPU_ZERO(&td->bind_cpumask);
+ td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus);
+ BUG_ON(!td->bind_cpumask);
+ CPU_ZERO_S(cpuset_size, td->bind_cpumask);
for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
- CPU_SET(cpu, &td->bind_cpumask);
+ CPU_SET_S(cpu, cpuset_size, td->bind_cpumask);
}
}
static void deinit_thread_data(void)
{
ssize_t size = sizeof(*g->threads)*g->p.nr_tasks;
+ int t;
+
+ /* Free the bind_cpumask allocated for thread_data */
+ for (t = 0; t < g->p.nr_tasks; t++) {
+ struct thread_data *td = g->threads + t;
+ CPU_FREE(td->bind_cpumask);
+ }
free_data(g->threads, size);
}
@@ -1672,7 +1740,7 @@ static int __bench_numa(const char *name)
"GB/sec,", "total-speed", "GB/sec total speed");
if (g->p.show_details >= 2) {
- char tname[14 + 2 * 10 + 1];
+ char tname[14 + 2 * 11 + 1];
struct thread_data *td;
for (p = 0; p < g->p.nr_proc; p++) {
for (t = 0; t < g->p.nr_threads; t++) {
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ba74fab02e62..069825c48d40 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -989,8 +989,11 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
struct mmap *overwrite_mmap = evlist->overwrite_mmap;
struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
- thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
- thread_data->mask->maps.nbits);
+ if (cpu_map__is_dummy(cpus))
+ thread_data->nr_mmaps = nr_mmaps;
+ else
+ thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits,
+ thread_data->mask->maps.nbits);
if (mmap) {
thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *));
if (!thread_data->maps)
@@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru
thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps);
for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) {
- if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) {
+ if (cpu_map__is_dummy(cpus) ||
+ test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) {
if (thread_data->maps) {
thread_data->maps[tm] = &mmap[m];
pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n",
- thread_data, cpus->map[m].cpu, tm, m);
+ thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m);
}
if (thread_data->overwrite_maps) {
thread_data->overwrite_maps[tm] = &overwrite_mmap[m];
pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n",
- thread_data, cpus->map[m].cpu, tm, m);
+ thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m);
}
tm++;
}
@@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c
{
int c;
+ if (cpu_map__is_dummy(cpus))
+ return;
+
for (c = 0; c < cpus->nr; c++)
set_bit(cpus->map[c].cpu, mask->bits);
}
@@ -3680,6 +3687,11 @@ static int record__init_thread_masks(struct record *rec)
if (!record__threads_enabled(rec))
return record__init_thread_default_masks(rec, cpus);
+ if (cpu_map__is_dummy(cpus)) {
+ pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n");
+ return -EINVAL;
+ }
+
switch (rec->opts.threads_spec) {
case THREAD_SPEC__CPU:
ret = record__init_thread_cpu_masks(rec, cpus);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 1ad75c7ba074..afe4a5539ecc 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -353,6 +353,7 @@ static int report__setup_sample_type(struct report *rep)
struct perf_session *session = rep->session;
u64 sample_type = evlist__combined_sample_type(session->evlist);
bool is_pipe = perf_data__is_pipe(session->data);
+ struct evsel *evsel;
if (session->itrace_synth_opts->callchain ||
session->itrace_synth_opts->add_callchain ||
@@ -407,6 +408,19 @@ static int report__setup_sample_type(struct report *rep)
}
if (sort__mode == SORT_MODE__MEMORY) {
+ /*
+ * FIXUP: prior to kernel 5.18, Arm SPE missed to set
+ * PERF_SAMPLE_DATA_SRC bit in sample type. For backward
+ * compatibility, set the bit if it's an old perf data file.
+ */
+ evlist__for_each_entry(session->evlist, evsel) {
+ if (strstr(evsel->name, "arm_spe") &&
+ !(sample_type & PERF_SAMPLE_DATA_SRC)) {
+ evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC;
+ sample_type |= PERF_SAMPLE_DATA_SRC;
+ }
+ }
+
if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) {
ui__error("Selected --mem-mode but no mem data. "
"Did you call perf record without -d?\n");
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index a2f117936188..cf5eab5431b4 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
return -EINVAL;
if (PRINT_FIELD(DATA_SRC) &&
- evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC))
+ evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set))
return -EINVAL;
if (PRINT_FIELD(WEIGHT) &&
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 2f6b67189b42..0170cb0819d6 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -55,6 +55,7 @@ struct cmd_struct {
};
static struct cmd_struct commands[] = {
+ { "archive", NULL, 0 },
{ "buildid-cache", cmd_buildid_cache, 0 },
{ "buildid-list", cmd_buildid_list, 0 },
{ "config", cmd_config, 0 },
@@ -62,6 +63,7 @@ static struct cmd_struct commands[] = {
{ "diff", cmd_diff, 0 },
{ "evlist", cmd_evlist, 0 },
{ "help", cmd_help, 0 },
+ { "iostat", NULL, 0 },
{ "kallsyms", cmd_kallsyms, 0 },
{ "list", cmd_list, 0 },
{ "record", cmd_record, 0 },
@@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv)
for (i = 0; i < ARRAY_SIZE(commands); i++) {
struct cmd_struct *p = commands+i;
+ if (p->fn == NULL)
+ continue;
if (strcmp(p->cmd, cmd))
continue;
exit(run_builtin(p, argc, argv));
@@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void)
static int libperf_print(enum libperf_print_level level,
const char *fmt, va_list ap)
{
- return eprintf(level, verbose, fmt, ap);
+ return veprintf(level, verbose, fmt, ap);
}
int main(int argc, const char **argv)
diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README
index 454505d343fa..eb3f7d4bb324 100644
--- a/tools/perf/tests/attr/README
+++ b/tools/perf/tests/attr/README
@@ -60,6 +60,7 @@ Following tests are defined (with perf commands):
perf record -R kill (test-record-raw)
perf record -c 2 -e arm_spe_0// -- kill (test-record-spe-period)
perf record -e arm_spe_0/period=3/ -- kill (test-record-spe-period-term)
+ perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address)
perf stat -e cycles kill (test-stat-basic)
perf stat kill (test-stat-default)
perf stat -d kill (test-stat-detailed-1)
diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address
new file mode 100644
index 000000000000..7ebcf5012ce3
--- /dev/null
+++ b/tools/perf/tests/attr/test-record-spe-physical-address
@@ -0,0 +1,12 @@
+[config]
+command = record
+args = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1
+ret = 1
+arch = aarch64
+
+[event-10:base-record-spe]
+# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR
+sample_type=622727
+
+# dummy event
+[event-1:base-record-spe] \ No newline at end of file
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index 57b9591f7cbb..17c023823713 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -222,11 +222,11 @@ static int __test__bpf(int idx)
ret = test_llvm__fetch_bpf_obj(&obj_buf, &obj_buf_sz,
bpf_testcase_table[idx].prog_id,
- true, NULL);
+ false, NULL);
if (ret != TEST_OK || !obj_buf || !obj_buf_sz) {
pr_debug("Unable to get BPF object, %s\n",
bpf_testcase_table[idx].msg_compile_fail);
- if (idx == 0)
+ if ((idx == 0) || (ret == TEST_SKIP))
return TEST_SKIP;
else
return TEST_FAIL;
@@ -364,9 +364,11 @@ static int test__bpf_prologue_test(struct test_suite *test __maybe_unused,
static struct test_case bpf_tests[] = {
#ifdef HAVE_LIBBPF_SUPPORT
TEST_CASE("Basic BPF filtering", basic_bpf_test),
- TEST_CASE("BPF pinning", bpf_pinning),
+ TEST_CASE_REASON("BPF pinning", bpf_pinning,
+ "clang isn't installed or environment missing BPF support"),
#ifdef HAVE_BPF_PROLOGUE
- TEST_CASE("BPF prologue generation", bpf_prologue_test),
+ TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test,
+ "clang isn't installed or environment missing BPF support"),
#else
TEST_CASE_REASON("BPF prologue generation", bpf_prologue_test, "not compiled in"),
#endif
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index fac3717d9ba1..d336cda94a11 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -279,6 +279,7 @@ static const char *shell_test__description(char *description, size_t size,
{
FILE *fp;
char filename[PATH_MAX];
+ int ch;
path__join(filename, sizeof(filename), path, name);
fp = fopen(filename, "r");
@@ -286,7 +287,9 @@ static const char *shell_test__description(char *description, size_t size,
return NULL;
/* Skip shebang */
- while (fgetc(fp) != '\n');
+ do {
+ ch = fgetc(fp);
+ } while (ch != EOF && ch != '\n');
description = fgets(description, size, fp);
fclose(fp);
@@ -417,7 +420,8 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
.priv = &st,
};
- if (!perf_test__matches(test_suite.desc, curr, argc, argv))
+ if (test_suite.desc == NULL ||
+ !perf_test__matches(test_suite.desc, curr, argc, argv))
continue;
st.file = ent->d_name;
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 2dab2d262060..afdca7f2959f 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr
}
err = unwind__get_entries(unwind_entry, &cnt, thread,
- &sample, MAX_STACK);
+ &sample, MAX_STACK, false);
if (err)
pr_debug("unwind failed\n");
else if (cnt != MAX_STACK) {
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index d12d0ad81801..4ad0dfbc8b21 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -47,6 +47,17 @@
} \
}
+static int test__tsc_is_supported(struct test_suite *test __maybe_unused,
+ int subtest __maybe_unused)
+{
+ if (!TSC_IS_SUPPORTED) {
+ pr_debug("Test not supported on this architecture\n");
+ return TEST_SKIP;
+ }
+
+ return TEST_OK;
+}
+
/**
* test__perf_time_to_tsc - test converting perf time to TSC.
*
@@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
struct perf_cpu_map *cpus = NULL;
struct evlist *evlist = NULL;
struct evsel *evsel = NULL;
- int err = -1, ret, i;
+ int err = TEST_FAIL, ret, i;
const char *comm1, *comm2;
struct perf_tsc_conversion tc;
struct perf_event_mmap_page *pc;
@@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
u64 test_time, comm1_time = 0, comm2_time = 0;
struct mmap *md;
- if (!TSC_IS_SUPPORTED) {
- pr_debug("Test not supported on this architecture");
- return TEST_SKIP;
- }
threads = thread_map__new(-1, getpid(), UINT_MAX);
CHECK_NOT_NULL__(threads);
@@ -116,6 +123,10 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
evsel->core.attr.enable_on_exec = 0;
}
+ if (evlist__open(evlist) == -ENOENT) {
+ err = TEST_SKIP;
+ goto out_err;
+ }
CHECK__(evlist__open(evlist));
CHECK__(evlist__mmap(evlist, UINT_MAX));
@@ -124,8 +135,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su
ret = perf_read_tsc_conversion(pc, &tc);
if (ret) {
if (ret == -EOPNOTSUPP) {
- fprintf(stderr, " (not supported)");
- return 0;
+ pr_debug("perf_read_tsc_conversion is not supported in current kernel\n");
+ err = TEST_SKIP;
}
goto out_err;
}
@@ -191,7 +202,7 @@ next_event:
test_tsc >= comm2_tsc)
goto out_err;
- err = 0;
+ err = TEST_OK;
out_err:
evlist__delete(evlist);
@@ -200,4 +211,15 @@ out_err:
return err;
}
-DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc);
+static struct test_case time_to_tsc_tests[] = {
+ TEST_CASE_REASON("TSC support", tsc_is_supported,
+ "This architecture does not support"),
+ TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc,
+ "perf_read_tsc_conversion is not supported"),
+ { .name = NULL, }
+};
+
+struct test_suite suite__perf_time_to_tsc = {
+ .desc = "Convert perf time to TSC",
+ .test_cases = time_to_tsc_tests,
+};
diff --git a/tools/perf/tests/shell/stat_all_pmu.sh b/tools/perf/tests/shell/stat_all_pmu.sh
index b30dba455f36..9c9ef33e0b3c 100755
--- a/tools/perf/tests/shell/stat_all_pmu.sh
+++ b/tools/perf/tests/shell/stat_all_pmu.sh
@@ -5,6 +5,16 @@
set -e
for p in $(perf list --raw-dump pmu); do
+ # In powerpc, skip the events for hv_24x7 and hv_gpci.
+ # These events needs input values to be filled in for
+ # core, chip, partition id based on system.
+ # Example: hv_24x7/CPM_ADJUNCT_INST,domain=?,core=?/
+ # hv_gpci/event,partition_id=?/
+ # Hence skip these events for ppc.
+ if echo "$p" |grep -Eq 'hv_24x7|hv_gpci' ; then
+ echo "Skipping: Event '$p' in powerpc"
+ continue
+ fi
echo "Testing $p"
result=$(perf stat -e "$p" true 2>&1)
if ! echo "$result" | grep -q "$p" && ! echo "$result" | grep -q "<not supported>" ; then
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 6de53b7ef5ff..e4cb4f1806ff 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -29,7 +29,6 @@ cleanup_files()
rm -f ${file}
rm -f "${perfdata}.old"
trap - exit term int
- kill -2 $$
exit $glb_err
}
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index ee1e3dcbc0bd..d23a9e322ff5 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -109,6 +109,17 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
&& strncmp(session->header.env.arch, "aarch64", 7))
return TEST_SKIP;
+ /*
+ * In powerpc pSeries platform, not all the topology information
+ * are exposed via sysfs. Due to restriction, detail like
+ * physical_package_id will be set to -1. Hence skip this
+ * test if physical_package_id returns -1 for cpu from perf_cpu_map.
+ */
+ if (strncmp(session->header.env.arch, "powerpc", 7)) {
+ if (cpu__get_socket_id(perf_cpu_map__cpu(map, 0)) == -1)
+ return TEST_SKIP;
+ }
+
TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e4c641b240df..82cc396ef516 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
objdump_process.argv = objdump_argv;
objdump_process.out = -1;
objdump_process.err = -1;
+ objdump_process.no_stderr = 1;
if (start_command(&objdump_process)) {
pr_err("Failure starting to run %s\n", command);
err = -1;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index d2b64e3f588b..1a80151baed9 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
memset(&attr, 0, sizeof(struct perf_event_attr));
attr.size = sizeof(struct perf_event_attr);
attr.type = PERF_TYPE_HARDWARE;
- attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
+ attr.sample_type = evsel->core.attr.sample_type &
+ (PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR);
attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
- PERF_SAMPLE_WEIGHT;
+ PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR;
if (spe->timeless_decoding)
attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
else
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
index 2242a885fbd7..4940be4a0569 100644
--- a/tools/perf/util/arm64-frame-pointer-unwind-support.c
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr
sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
}
- ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+ ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true);
sample->user_regs = old_regs;
if (ret || entries.length != 2)
diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 94624733af7e..8271ab764eb5 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -22,7 +22,8 @@
#include "record.h"
#include "util/synthetic-events.h"
-struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
+#ifndef HAVE_LIBBPF_BTF__LOAD_FROM_KERNEL_BY_ID
+struct btf *btf__load_from_kernel_by_id(__u32 id)
{
struct btf *btf;
#pragma GCC diagnostic push
@@ -32,6 +33,7 @@ struct btf * __weak btf__load_from_kernel_by_id(__u32 id)
return err ? ERR_PTR(err) : btf;
}
+#endif
int __weak bpf_prog_load(enum bpf_prog_type prog_type,
const char *prog_name __maybe_unused,
diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp
index df7b18fb6b6e..1aad7d6d34aa 100644
--- a/tools/perf/util/c++/clang.cpp
+++ b/tools/perf/util/c++/clang.cpp
@@ -20,7 +20,11 @@
#include "llvm/Option/Option.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/ManagedStatic.h"
+#if CLANG_VERSION_MAJOR >= 14
+#include "llvm/MC/TargetRegistry.h"
+#else
#include "llvm/Support/TargetRegistry.h"
+#endif
#include "llvm/Support/TargetSelect.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Target/TargetOptions.h"
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index d546ff724dbe..a27132e5a5ef 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff,
return do_write(ff, &data->dir.version, sizeof(data->dir.version));
}
+/*
+ * Check whether a CPU is online
+ *
+ * Returns:
+ * 1 -> if CPU is online
+ * 0 -> if CPU is offline
+ * -1 -> error case
+ */
+int is_cpu_online(unsigned int cpu)
+{
+ char *str;
+ size_t strlen;
+ char buf[256];
+ int status = -1;
+ struct stat statbuf;
+
+ snprintf(buf, sizeof(buf),
+ "/sys/devices/system/cpu/cpu%d", cpu);
+ if (stat(buf, &statbuf) != 0)
+ return 0;
+
+ /*
+ * Check if /sys/devices/system/cpu/cpux/online file
+ * exists. Some cases cpu0 won't have online file since
+ * it is not expected to be turned off generally.
+ * In kernels without CONFIG_HOTPLUG_CPU, this
+ * file won't exist
+ */
+ snprintf(buf, sizeof(buf),
+ "/sys/devices/system/cpu/cpu%d/online", cpu);
+ if (stat(buf, &statbuf) != 0)
+ return 1;
+
+ /*
+ * Read online file using sysfs__read_str.
+ * If read or open fails, return -1.
+ * If read succeeds, return value from file
+ * which gets stored in "str"
+ */
+ snprintf(buf, sizeof(buf),
+ "devices/system/cpu/cpu%d/online", cpu);
+
+ if (sysfs__read_str(buf, &str, &strlen) < 0)
+ return status;
+
+ status = atoi(str);
+
+ free(str);
+ return status;
+}
+
#ifdef HAVE_LIBBPF_SUPPORT
static int write_bpf_prog_info(struct feat_fd *ff,
struct evlist *evlist __maybe_unused)
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index c9e3265832d9..0eb4bc29a5a4 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size);
int write_padded(struct feat_fd *fd, const void *bf,
size_t count, size_t count_aligned);
+int is_cpu_online(unsigned int cpu);
/*
* arch specific callback
*/
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b80048546451..95391236f5f6 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread,
return 0;
return unwind__get_entries(unwind_entry, cursor,
- thread, sample, max_stack);
+ thread, sample, max_stack, false);
}
int thread__resolve_callchain(struct thread *thread,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 24997925ae00..dd84fed698a3 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
bool use_uncore_alias;
LIST_HEAD(config_terms);
- if (verbose > 1) {
+ pmu = parse_state->fake_pmu ?: perf_pmu__find(name);
+
+ if (verbose > 1 && !(pmu && pmu->selectable)) {
fprintf(stderr, "Attempting to add event pmu '%s' with '",
name);
if (head_config) {
@@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
fprintf(stderr, "' that may result in non-fatal errors\n");
}
- pmu = parse_state->fake_pmu ?: perf_pmu__find(name);
if (!pmu) {
char *err_str;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 3b8dfe603e50..a7f93f5a1ac8 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1151,9 +1151,20 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
struct branch_entry *entries = perf_sample__branch_entries(sample);
uint64_t i;
- printf("%s: nr:%" PRIu64 "\n",
- !callstack ? "... branch stack" : "... branch callstack",
- sample->branch_stack->nr);
+ if (!callstack) {
+ printf("%s: nr:%" PRIu64 "\n", "... branch stack", sample->branch_stack->nr);
+ } else {
+ /* the reason of adding 1 to nr is because after expanding
+ * branch stack it generates nr + 1 callstack records. e.g.,
+ * B()->C()
+ * A()->B()
+ * the final callstack should be:
+ * C()
+ * B()
+ * A()
+ */
+ printf("%s: nr:%" PRIu64 "\n", "... branch callstack", sample->branch_stack->nr+1);
+ }
for (i = 0; i < sample->branch_stack->nr; i++) {
struct branch_entry *e = &entries[i];
@@ -1169,8 +1180,13 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
(unsigned)e->flags.reserved,
e->flags.type ? branch_type_name(e->flags.type) : "");
} else {
- printf("..... %2"PRIu64": %016" PRIx64 "\n",
- i, i > 0 ? e->from : e->to);
+ if (i == 0) {
+ printf("..... %2"PRIu64": %016" PRIx64 "\n"
+ "..... %2"PRIu64": %016" PRIx64 "\n",
+ i, e->to, i+1, e->from);
+ } else {
+ printf("..... %2"PRIu64": %016" PRIx64 "\n", i+1, e->from);
+ }
}
}
}
@@ -2095,6 +2111,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
bool needs_swap, union perf_event *error)
{
union perf_event *event;
+ u16 event_size;
/*
* Ensure we have enough space remaining to read
@@ -2107,15 +2124,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size,
if (needs_swap)
perf_event_header__bswap(&event->header);
- if (head + event->header.size <= mmap_size)
+ event_size = event->header.size;
+ if (head + event_size <= mmap_size)
return event;
/* We're not fetching the event so swap back again */
if (needs_swap)
perf_event_header__bswap(&event->header);
- pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:"
- " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size);
+ /* Check if the event fits into the next mmapped buf. */
+ if (event_size <= mmap_size - head % page_size) {
+ /* Remap buf and fetch again. */
+ return NULL;
+ }
+
+ /* Invalid input. Event size should never exceed mmap_size. */
+ pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:"
+ " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size);
return error;
}
@@ -2567,7 +2592,7 @@ int perf_session__process_events(struct perf_session *session)
if (perf_data__is_pipe(session->data))
return __perf_session__process_pipe_events(session);
- if (perf_data__is_dir(session->data))
+ if (perf_data__is_dir(session->data) && session->data->dir.nr)
return __perf_session__process_dir_events(session);
return __perf_session__process_events(session);
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index 483f05004e68..c255a2c90cd6 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,12 +1,14 @@
-from os import getenv
+from os import getenv, path
from subprocess import Popen, PIPE
from re import sub
cc = getenv("CC")
cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline()
+src_feature_tests = getenv('srctree') + '/tools/build/feature'
def clang_has_option(option):
- return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ]
+ cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines()
+ return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ]
if cc_is_clang:
from distutils.sysconfig import get_config_vars
@@ -23,6 +25,8 @@ if cc_is_clang:
vars[var] = sub("-fstack-protector-strong", "", vars[var])
if not clang_has_option("-fno-semantic-interposition"):
vars[var] = sub("-fno-semantic-interposition", "", vars[var])
+ if not clang_has_option("-ffat-lto-objects"):
+ vars[var] = sub("-ffat-lto-objects", "", vars[var])
from distutils.core import setup, Extension
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index ee6f03481215..c1af37e11f98 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <errno.h>
+#include <linux/err.h>
#include <inttypes.h>
#include <math.h>
#include <string.h>
@@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
if (!mask) {
mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL);
- if (!mask)
+ if (IS_ERR(mask))
return -ENOMEM;
counter->per_pkg_mask = mask;
@@ -471,9 +472,10 @@ int perf_stat_process_counter(struct perf_stat_config *config,
int perf_event__process_stat_event(struct perf_session *session,
union perf_event *event)
{
- struct perf_counts_values count;
+ struct perf_counts_values count, *ptr;
struct perf_record_stat *st = &event->stat;
struct evsel *counter;
+ int cpu_map_idx;
count.val = st->val;
count.ena = st->ena;
@@ -484,8 +486,18 @@ int perf_event__process_stat_event(struct perf_session *session,
pr_err("Failed to resolve counter for stat event.\n");
return -EINVAL;
}
-
- *perf_counts(counter->counts, st->cpu, st->thread) = count;
+ cpu_map_idx = perf_cpu_map__idx(evsel__cpus(counter), (struct perf_cpu){.cpu = st->cpu});
+ if (cpu_map_idx == -1) {
+ pr_err("Invalid CPU %d for event %s.\n", st->cpu, evsel__name(counter));
+ return -EINVAL;
+ }
+ ptr = perf_counts(counter->counts, cpu_map_idx, st->thread);
+ if (ptr == NULL) {
+ pr_err("Failed to find perf count for CPU %d thread %d on event %s.\n",
+ st->cpu, st->thread, evsel__name(counter));
+ return -EINVAL;
+ }
+ *ptr = count;
counter->supported = true;
return 0;
}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 31cd59a2b66e..ecd377938eea 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss,
* For misannotated, zeroed, ASM function sizes.
*/
if (nr > 0) {
- symbols__fixup_end(&dso->symbols);
+ symbols__fixup_end(&dso->symbols, false);
symbols__fixup_duplicate(&dso->symbols);
if (kmap) {
/*
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index dea0fc495185..f72baf636724 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str)
return tail - str;
}
-void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
-{
- p->end = c->start;
-}
-
const char * __weak arch__normalize_symbol_name(const char *name)
{
return name;
@@ -217,7 +212,8 @@ again:
}
}
-void symbols__fixup_end(struct rb_root_cached *symbols)
+/* Update zero-sized symbols using the address of the next symbol */
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms)
{
struct rb_node *nd, *prevnd = rb_first_cached(symbols);
struct symbol *curr, *prev;
@@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols)
prev = curr;
curr = rb_entry(nd, struct symbol, rb_node);
- if (prev->end == prev->start || prev->end != curr->start)
- arch__symbols__fixup_end(prev, curr);
+ /*
+ * On some architecture kernel text segment start is located at
+ * some low memory address, while modules are located at high
+ * memory addresses (or vice versa). The gap between end of
+ * kernel text segment and beginning of first module's text
+ * segment is very big. Therefore do not fill this gap and do
+ * not assign it to the kernel dso map (kallsyms).
+ *
+ * In kallsyms, it determines module symbols using '[' character
+ * like in:
+ * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi]
+ */
+ if (prev->end == prev->start) {
+ /* Last kernel/module symbol mapped to end of page */
+ if (is_kallsyms && (!strchr(prev->name, '[') !=
+ !strchr(curr->name, '[')))
+ prev->end = roundup(prev->end + 4096, 4096);
+ else
+ prev->end = curr->start;
+
+ pr_debug4("%s sym:%s end:%#" PRIx64 "\n",
+ __func__, prev->name, prev->end);
+ }
}
/* Last entry */
@@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename,
if (kallsyms__delta(kmap, filename, &delta))
return -1;
- symbols__fixup_end(&dso->symbols);
+ symbols__fixup_end(&dso->symbols, true);
symbols__fixup_duplicate(&dso->symbols);
if (dso->kernel == DSO_SPACE__KERNEL_GUEST)
@@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
#undef bfd_asymbol_section
#endif
- symbols__fixup_end(&dso->symbols);
+ symbols__fixup_end(&dso->symbols, false);
symbols__fixup_duplicate(&dso->symbols);
dso->adjust_symbols = 1;
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index fbf866d82dcc..0b893dcc8ea6 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym,
bool kernel);
void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym);
void symbols__fixup_duplicate(struct rb_root_cached *symbols);
-void symbols__fixup_end(struct rb_root_cached *symbols);
+void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms);
void maps__fixup_end(struct maps *maps);
typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data);
@@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name);
#define SYMBOL_A 0
#define SYMBOL_B 1
-void arch__symbols__fixup_end(struct symbol *p, struct symbol *c);
int arch__compare_symbol_names(const char *namea, const char *nameb);
int arch__compare_symbol_names_n(const char *namea, const char *nameb,
unsigned int n);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index a74b517f7497..94aa40f6e348 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
bool isactivation;
if (!dwfl_frame_pc(state, &pc, NULL)) {
- pr_err("%s", dwfl_errmsg(-1));
+ if (!ui->best_effort)
+ pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}
@@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
report_module(pc, ui);
if (!dwfl_frame_pc(state, &pc, &isactivation)) {
- pr_err("%s", dwfl_errmsg(-1));
+ if (!ui->best_effort)
+ pr_err("%s", dwfl_errmsg(-1));
return DWARF_CB_ABORT;
}
@@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg)
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
struct perf_sample *data,
- int max_stack)
+ int max_stack,
+ bool best_effort)
{
struct unwind_info *ui, ui_buf = {
.sample = data,
@@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
.cb = cb,
.arg = arg,
.max_stack = max_stack,
+ .best_effort = best_effort
};
Dwarf_Word ip;
int err = -EINVAL, i;
diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h
index 0cbd2650e280..8c88bc4f2304 100644
--- a/tools/perf/util/unwind-libdw.h
+++ b/tools/perf/util/unwind-libdw.h
@@ -20,6 +20,7 @@ struct unwind_info {
void *arg;
int max_stack;
int idx;
+ bool best_effort;
struct unwind_entry entries[];
};
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 71a353349181..41e29fc7648a 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -96,6 +96,7 @@ struct unwind_info {
struct perf_sample *sample;
struct machine *machine;
struct thread *thread;
+ bool best_effort;
};
#define dw_read(ptr, type, end) ({ \
@@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as,
ret = perf_reg_value(&val, &ui->sample->user_regs, id);
if (ret) {
- pr_err("unwind: can't read reg %d\n", regnum);
+ if (!ui->best_effort)
+ pr_err("unwind: can't read reg %d\n", regnum);
return ret;
}
@@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
return -1;
ret = unw_init_remote(&c, addr_space, ui);
- if (ret)
+ if (ret && !ui->best_effort)
display_error(ret);
while (!ret && (unw_step(&c) > 0) && i < max_stack) {
@@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack)
+ struct perf_sample *data, int max_stack,
+ bool best_effort)
{
struct unwind_info ui = {
.sample = data,
.thread = thread,
.machine = thread->maps->machine,
+ .best_effort = best_effort
};
if (!data->user_regs.regs)
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index e89a5479b361..509c287ee762 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps)
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack)
+ struct perf_sample *data, int max_stack,
+ bool best_effort)
{
if (thread->maps->unwind_libunwind_ops)
- return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack);
+ return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data,
+ max_stack, best_effort);
return 0;
}
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index ab8ad469c8de..b2a03fa5289b 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -23,13 +23,19 @@ struct unwind_libunwind_ops {
void (*finish_access)(struct maps *maps);
int (*get_entries)(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack);
+ struct perf_sample *data, int max_stack, bool best_effort);
};
#ifdef HAVE_DWARF_UNWIND_SUPPORT
+/*
+ * When best_effort is set, don't report errors and fail silently. This could
+ * be expanded in the future to be more permissive about things other than
+ * error messages.
+ */
int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
struct thread *thread,
- struct perf_sample *data, int max_stack);
+ struct perf_sample *data, int max_stack,
+ bool best_effort);
/* libunwind specific */
#ifdef HAVE_LIBUNWIND_SUPPORT
#ifndef LIBUNWIND__ARCH_REG_ID
@@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
void *arg __maybe_unused,
struct thread *thread __maybe_unused,
struct perf_sample *data __maybe_unused,
- int max_stack __maybe_unused)
+ int max_stack __maybe_unused,
+ bool best_effort __maybe_unused)
{
return 0;
}
diff --git a/tools/power/acpi/common/cmfsize.c b/tools/power/acpi/common/cmfsize.c
index 185b8c588e1d..38f9b9da8170 100644
--- a/tools/power/acpi/common/cmfsize.c
+++ b/tools/power/acpi/common/cmfsize.c
@@ -3,7 +3,7 @@
*
* Module Name: cmfsize - Common get file size function
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/common/getopt.c b/tools/power/acpi/common/getopt.c
index 3c265bc917a1..96fd6cec78e2 100644
--- a/tools/power/acpi/common/getopt.c
+++ b/tools/power/acpi/common/getopt.c
@@ -3,7 +3,7 @@
*
* Module Name: getopt
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
index ccabdbaae6a4..bd08f36df4a7 100644
--- a/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
+++ b/tools/power/acpi/os_specific/service_layers/oslinuxtbl.c
@@ -3,7 +3,7 @@
*
* Module Name: oslinuxtbl - Linux OSL for obtaining ACPI tables
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/os_specific/service_layers/osunixdir.c b/tools/power/acpi/os_specific/service_layers/osunixdir.c
index edd99274cd12..5107892d054b 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixdir.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixdir.c
@@ -3,7 +3,7 @@
*
* Module Name: osunixdir - Unix directory access interfaces
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/os_specific/service_layers/osunixmap.c b/tools/power/acpi/os_specific/service_layers/osunixmap.c
index fee0022560d5..6ff4edd8dc3b 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixmap.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixmap.c
@@ -3,7 +3,7 @@
*
* Module Name: osunixmap - Unix OSL for file mappings
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/os_specific/service_layers/osunixxf.c b/tools/power/acpi/os_specific/service_layers/osunixxf.c
index 0861728da562..b3651a04d68c 100644
--- a/tools/power/acpi/os_specific/service_layers/osunixxf.c
+++ b/tools/power/acpi/os_specific/service_layers/osunixxf.c
@@ -3,7 +3,7 @@
*
* Module Name: osunixxf - UNIX OSL interfaces
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/tools/acpidump/acpidump.h b/tools/power/acpi/tools/acpidump/acpidump.h
index e0ebc1dab1cc..153249c87fd7 100644
--- a/tools/power/acpi/tools/acpidump/acpidump.h
+++ b/tools/power/acpi/tools/acpidump/acpidump.h
@@ -3,7 +3,7 @@
*
* Module Name: acpidump.h - Include file for acpi_dump utility
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/tools/acpidump/apdump.c b/tools/power/acpi/tools/acpidump/apdump.c
index 444e3d78bd89..d54dde02b87d 100644
--- a/tools/power/acpi/tools/acpidump/apdump.c
+++ b/tools/power/acpi/tools/acpidump/apdump.c
@@ -3,7 +3,7 @@
*
* Module Name: apdump - Dump routines for ACPI tables (acpidump)
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/tools/acpidump/apfiles.c b/tools/power/acpi/tools/acpidump/apfiles.c
index da0c6e13042b..2d9b45a9b526 100644
--- a/tools/power/acpi/tools/acpidump/apfiles.c
+++ b/tools/power/acpi/tools/acpidump/apfiles.c
@@ -3,7 +3,7 @@
*
* Module Name: apfiles - File-related functions for acpidump utility
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/acpi/tools/acpidump/apmain.c b/tools/power/acpi/tools/acpidump/apmain.c
index a4cf6042fcfd..44b23fc53dd9 100644
--- a/tools/power/acpi/tools/acpidump/apmain.c
+++ b/tools/power/acpi/tools/acpidump/apmain.c
@@ -3,7 +3,7 @@
*
* Module Name: apmain - Main module for the acpidump utility
*
- * Copyright (C) 2000 - 2021, Intel Corp.
+ * Copyright (C) 2000 - 2022, Intel Corp.
*
*****************************************************************************/
diff --git a/tools/power/x86/intel-speed-select/Makefile b/tools/power/x86/intel-speed-select/Makefile
index 846f785e278d..7221f2f55e8b 100644
--- a/tools/power/x86/intel-speed-select/Makefile
+++ b/tools/power/x86/intel-speed-select/Makefile
@@ -42,7 +42,7 @@ ISST_IN := $(OUTPUT)intel-speed-select-in.o
$(ISST_IN): prepare FORCE
$(Q)$(MAKE) $(build)=intel-speed-select
$(OUTPUT)intel-speed-select: $(ISST_IN)
- $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $< -o $@
+ $(QUIET_LINK)$(CC) $(CFLAGS) $< $(LDFLAGS) -o $@
clean:
rm -f $(ALL_PROGRAMS)
diff --git a/tools/power/x86/intel-speed-select/hfi-events.c b/tools/power/x86/intel-speed-select/hfi-events.c
index e85676711372..761375062505 100644
--- a/tools/power/x86/intel-speed-select/hfi-events.c
+++ b/tools/power/x86/intel-speed-select/hfi-events.c
@@ -190,7 +190,7 @@ static int handle_event(struct nl_msg *n, void *arg)
struct genlmsghdr *genlhdr = genlmsg_hdr(nlh);
struct nlattr *attrs[THERMAL_GENL_ATTR_MAX + 1];
int ret;
- struct perf_cap perf_cap;
+ struct perf_cap perf_cap = {0};
ret = genlmsg_parse(nlh, 0, attrs, THERMAL_GENL_ATTR_MAX, NULL);
diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c
index 060390e88e37..9d35614995ee 100644
--- a/tools/power/x86/intel-speed-select/isst-config.c
+++ b/tools/power/x86/intel-speed-select/isst-config.c
@@ -1892,6 +1892,12 @@ static void set_fact_for_cpu(int cpu, void *arg1, void *arg2, void *arg3,
int ret;
int status = *(int *)arg4;
+ if (status && no_turbo()) {
+ isst_display_error_info_message(1, "Turbo mode is disabled", 0, 0);
+ ret = -1;
+ goto disp_results;
+ }
+
ret = isst_get_ctdp_levels(cpu, &pkg_dev);
if (ret) {
isst_display_error_info_message(1, "Failed to get number of levels", 0, 0);
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index f3e3c94ab9bd..92e139b9c792 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -9,7 +9,7 @@ ifeq ("$(origin O)", "command line")
endif
turbostat : turbostat.c
-override CFLAGS += -O2 -Wall -I../../../include
+override CFLAGS += -O2 -Wall -Wextra -I../../../include
override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"'
override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"'
override CFLAGS += -D_FILE_OFFSET_BITS=64
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index 9b17097bc3d7..1e7d3de55a94 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -292,7 +292,7 @@ starts a new interval.
must be run as root.
Alternatively, non-root users can be enabled to run turbostat this way:
-# setcap cap_sys_rawio=ep ./turbostat
+# setcap cap_sys_admin,cap_sys_rawio,cap_sys_nice=+ep ./turbostat
# chmod +r /dev/cpu/*/msr
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bc5ae0872fed..ede31a4287a0 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -3,7 +3,7 @@
* turbostat -- show CPU frequency and C-state residency
* on modern Intel and AMD processors.
*
- * Copyright (c) 2021 Intel Corporation.
+ * Copyright (c) 2022 Intel Corporation.
* Len Brown <len.brown@intel.com>
*/
@@ -37,6 +37,171 @@
#include <asm/unistd.h>
#include <stdbool.h>
+#define UNUSED(x) (void)(x)
+
+/*
+ * This list matches the column headers, except
+ * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time
+ * 2. Core and CPU are moved to the end, we can't have strings that contain them
+ * matching on them for --show and --hide.
+ */
+
+/*
+ * buffer size used by sscanf() for added column names
+ * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters
+ */
+#define NAME_BYTES 20
+#define PATH_BYTES 128
+
+enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
+enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC };
+enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT };
+
+struct msr_counter {
+ unsigned int msr_num;
+ char name[NAME_BYTES];
+ char path[PATH_BYTES];
+ unsigned int width;
+ enum counter_type type;
+ enum counter_format format;
+ struct msr_counter *next;
+ unsigned int flags;
+#define FLAGS_HIDE (1 << 0)
+#define FLAGS_SHOW (1 << 1)
+#define SYSFS_PERCPU (1 << 1)
+};
+
+struct msr_counter bic[] = {
+ { 0x0, "usec", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Time_Of_Day_Seconds", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Package", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Node", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Avg_MHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Busy%", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Bzy_MHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "TSC_MHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "IRQ", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL, 0 },
+ { 0x0, "sysfs", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPU%c1", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPU%c3", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPU%c6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPU%c7", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "ThreadC", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CoreTmp", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CoreCnt", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "PkgTmp", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "GFX%rc6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "GFXMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg%pc2", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg%pc3", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg%pc6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg%pc7", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg%pc8", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg%pc9", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pk%pc10", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPU%LPI", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "SYS%LPI", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "PkgWatt", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CorWatt", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "GFXWatt", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "PkgCnt", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "RAMWatt", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "PKG_%", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "RAM_%", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Pkg_J", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Cor_J", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "GFX_J", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "RAM_J", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Mod%c6", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Totl%C0", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Any%C0", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "GFX%C0", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPUGFX%", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Core", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CPU", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "APIC", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "X2APIC", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "Die", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "GFXAMHz", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "IPC", "", 0, 0, 0, NULL, 0 },
+ { 0x0, "CoreThr", "", 0, 0, 0, NULL, 0 },
+};
+
+#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
+#define BIC_USEC (1ULL << 0)
+#define BIC_TOD (1ULL << 1)
+#define BIC_Package (1ULL << 2)
+#define BIC_Node (1ULL << 3)
+#define BIC_Avg_MHz (1ULL << 4)
+#define BIC_Busy (1ULL << 5)
+#define BIC_Bzy_MHz (1ULL << 6)
+#define BIC_TSC_MHz (1ULL << 7)
+#define BIC_IRQ (1ULL << 8)
+#define BIC_SMI (1ULL << 9)
+#define BIC_sysfs (1ULL << 10)
+#define BIC_CPU_c1 (1ULL << 11)
+#define BIC_CPU_c3 (1ULL << 12)
+#define BIC_CPU_c6 (1ULL << 13)
+#define BIC_CPU_c7 (1ULL << 14)
+#define BIC_ThreadC (1ULL << 15)
+#define BIC_CoreTmp (1ULL << 16)
+#define BIC_CoreCnt (1ULL << 17)
+#define BIC_PkgTmp (1ULL << 18)
+#define BIC_GFX_rc6 (1ULL << 19)
+#define BIC_GFXMHz (1ULL << 20)
+#define BIC_Pkgpc2 (1ULL << 21)
+#define BIC_Pkgpc3 (1ULL << 22)
+#define BIC_Pkgpc6 (1ULL << 23)
+#define BIC_Pkgpc7 (1ULL << 24)
+#define BIC_Pkgpc8 (1ULL << 25)
+#define BIC_Pkgpc9 (1ULL << 26)
+#define BIC_Pkgpc10 (1ULL << 27)
+#define BIC_CPU_LPI (1ULL << 28)
+#define BIC_SYS_LPI (1ULL << 29)
+#define BIC_PkgWatt (1ULL << 30)
+#define BIC_CorWatt (1ULL << 31)
+#define BIC_GFXWatt (1ULL << 32)
+#define BIC_PkgCnt (1ULL << 33)
+#define BIC_RAMWatt (1ULL << 34)
+#define BIC_PKG__ (1ULL << 35)
+#define BIC_RAM__ (1ULL << 36)
+#define BIC_Pkg_J (1ULL << 37)
+#define BIC_Cor_J (1ULL << 38)
+#define BIC_GFX_J (1ULL << 39)
+#define BIC_RAM_J (1ULL << 40)
+#define BIC_Mod_c6 (1ULL << 41)
+#define BIC_Totl_c0 (1ULL << 42)
+#define BIC_Any_c0 (1ULL << 43)
+#define BIC_GFX_c0 (1ULL << 44)
+#define BIC_CPUGFX (1ULL << 45)
+#define BIC_Core (1ULL << 46)
+#define BIC_CPU (1ULL << 47)
+#define BIC_APIC (1ULL << 48)
+#define BIC_X2APIC (1ULL << 49)
+#define BIC_Die (1ULL << 50)
+#define BIC_GFXACTMHz (1ULL << 51)
+#define BIC_IPC (1ULL << 52)
+#define BIC_CORE_THROT_CNT (1ULL << 53)
+
+#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
+#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
+#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz )
+#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX)
+#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
+
+#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
+
+unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
+
+#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME)
+#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
+#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
+#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
+#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT)
+
char *proc_stat = "/proc/stat";
FILE *outf;
int *fd_percpu;
@@ -48,6 +213,7 @@ struct timespec interval_ts = { 5, 0 };
unsigned int model_orig;
unsigned int num_iterations;
+unsigned int header_iterations;
unsigned int debug;
unsigned int quiet;
unsigned int shown;
@@ -159,13 +325,6 @@ int ignore_stdin;
#define MAX(a, b) ((a) > (b) ? (a) : (b))
-/*
- * buffer size used by sscanf() for added column names
- * Usually truncated to 7 characters, but also handles 18 columns for raw 64-bit counters
- */
-#define NAME_BYTES 20
-#define PATH_BYTES 128
-
int backwards_count;
char *progname;
@@ -205,6 +364,7 @@ struct core_data {
unsigned int core_temp_c;
unsigned int core_energy; /* MSR_CORE_ENERGY_STAT */
unsigned int core_id;
+ unsigned long long core_throt_cnt;
unsigned long long counter[MAX_ADDED_COUNTERS];
} *core_even, *core_odd;
@@ -255,24 +415,6 @@ struct pkg_data {
#define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
-enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE };
-enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC };
-enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT };
-
-struct msr_counter {
- unsigned int msr_num;
- char name[NAME_BYTES];
- char path[PATH_BYTES];
- unsigned int width;
- enum counter_type type;
- enum counter_format format;
- struct msr_counter *next;
- unsigned int flags;
-#define FLAGS_HIDE (1 << 0)
-#define FLAGS_SHOW (1 << 1)
-#define SYSFS_PERCPU (1 << 1)
-};
-
/*
* The accumulated sum of MSR is defined as a monotonic
* increasing MSR, it will be accumulated periodically,
@@ -522,8 +664,10 @@ static int perf_instr_count_open(int cpu_num)
/* counter for cpu_num, including user + kernel and all processes */
fd = perf_event_open(&pea, -1, cpu_num, -1, 0);
- if (fd == -1)
- err(-1, "cpu%d: perf instruction counter\n", cpu_num);
+ if (fd == -1) {
+ warn("cpu%d: perf instruction counter", cpu_num);
+ BIC_NOT_PRESENT(BIC_IPC);
+ }
return fd;
}
@@ -550,143 +694,10 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
return 0;
}
-/*
- * This list matches the column headers, except
- * 1. built-in only, the sysfs counters are not here -- we learn of those at run-time
- * 2. Core and CPU are moved to the end, we can't have strings that contain them
- * matching on them for --show and --hide.
- */
-struct msr_counter bic[] = {
- { 0x0, "usec" },
- { 0x0, "Time_Of_Day_Seconds" },
- { 0x0, "Package" },
- { 0x0, "Node" },
- { 0x0, "Avg_MHz" },
- { 0x0, "Busy%" },
- { 0x0, "Bzy_MHz" },
- { 0x0, "TSC_MHz" },
- { 0x0, "IRQ" },
- { 0x0, "SMI", "", 32, 0, FORMAT_DELTA, NULL },
- { 0x0, "sysfs" },
- { 0x0, "CPU%c1" },
- { 0x0, "CPU%c3" },
- { 0x0, "CPU%c6" },
- { 0x0, "CPU%c7" },
- { 0x0, "ThreadC" },
- { 0x0, "CoreTmp" },
- { 0x0, "CoreCnt" },
- { 0x0, "PkgTmp" },
- { 0x0, "GFX%rc6" },
- { 0x0, "GFXMHz" },
- { 0x0, "Pkg%pc2" },
- { 0x0, "Pkg%pc3" },
- { 0x0, "Pkg%pc6" },
- { 0x0, "Pkg%pc7" },
- { 0x0, "Pkg%pc8" },
- { 0x0, "Pkg%pc9" },
- { 0x0, "Pk%pc10" },
- { 0x0, "CPU%LPI" },
- { 0x0, "SYS%LPI" },
- { 0x0, "PkgWatt" },
- { 0x0, "CorWatt" },
- { 0x0, "GFXWatt" },
- { 0x0, "PkgCnt" },
- { 0x0, "RAMWatt" },
- { 0x0, "PKG_%" },
- { 0x0, "RAM_%" },
- { 0x0, "Pkg_J" },
- { 0x0, "Cor_J" },
- { 0x0, "GFX_J" },
- { 0x0, "RAM_J" },
- { 0x0, "Mod%c6" },
- { 0x0, "Totl%C0" },
- { 0x0, "Any%C0" },
- { 0x0, "GFX%C0" },
- { 0x0, "CPUGFX%" },
- { 0x0, "Core" },
- { 0x0, "CPU" },
- { 0x0, "APIC" },
- { 0x0, "X2APIC" },
- { 0x0, "Die" },
- { 0x0, "GFXAMHz" },
- { 0x0, "IPC" },
-};
-
-#define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
-#define BIC_USEC (1ULL << 0)
-#define BIC_TOD (1ULL << 1)
-#define BIC_Package (1ULL << 2)
-#define BIC_Node (1ULL << 3)
-#define BIC_Avg_MHz (1ULL << 4)
-#define BIC_Busy (1ULL << 5)
-#define BIC_Bzy_MHz (1ULL << 6)
-#define BIC_TSC_MHz (1ULL << 7)
-#define BIC_IRQ (1ULL << 8)
-#define BIC_SMI (1ULL << 9)
-#define BIC_sysfs (1ULL << 10)
-#define BIC_CPU_c1 (1ULL << 11)
-#define BIC_CPU_c3 (1ULL << 12)
-#define BIC_CPU_c6 (1ULL << 13)
-#define BIC_CPU_c7 (1ULL << 14)
-#define BIC_ThreadC (1ULL << 15)
-#define BIC_CoreTmp (1ULL << 16)
-#define BIC_CoreCnt (1ULL << 17)
-#define BIC_PkgTmp (1ULL << 18)
-#define BIC_GFX_rc6 (1ULL << 19)
-#define BIC_GFXMHz (1ULL << 20)
-#define BIC_Pkgpc2 (1ULL << 21)
-#define BIC_Pkgpc3 (1ULL << 22)
-#define BIC_Pkgpc6 (1ULL << 23)
-#define BIC_Pkgpc7 (1ULL << 24)
-#define BIC_Pkgpc8 (1ULL << 25)
-#define BIC_Pkgpc9 (1ULL << 26)
-#define BIC_Pkgpc10 (1ULL << 27)
-#define BIC_CPU_LPI (1ULL << 28)
-#define BIC_SYS_LPI (1ULL << 29)
-#define BIC_PkgWatt (1ULL << 30)
-#define BIC_CorWatt (1ULL << 31)
-#define BIC_GFXWatt (1ULL << 32)
-#define BIC_PkgCnt (1ULL << 33)
-#define BIC_RAMWatt (1ULL << 34)
-#define BIC_PKG__ (1ULL << 35)
-#define BIC_RAM__ (1ULL << 36)
-#define BIC_Pkg_J (1ULL << 37)
-#define BIC_Cor_J (1ULL << 38)
-#define BIC_GFX_J (1ULL << 39)
-#define BIC_RAM_J (1ULL << 40)
-#define BIC_Mod_c6 (1ULL << 41)
-#define BIC_Totl_c0 (1ULL << 42)
-#define BIC_Any_c0 (1ULL << 43)
-#define BIC_GFX_c0 (1ULL << 44)
-#define BIC_CPUGFX (1ULL << 45)
-#define BIC_Core (1ULL << 46)
-#define BIC_CPU (1ULL << 47)
-#define BIC_APIC (1ULL << 48)
-#define BIC_X2APIC (1ULL << 49)
-#define BIC_Die (1ULL << 50)
-#define BIC_GFXACTMHz (1ULL << 51)
-#define BIC_IPC (1ULL << 52)
-
-#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die )
-#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__)
-#define BIC_FREQUENCY ( BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz )
-#define BIC_IDLE ( BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX)
-#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC)
-
-#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC)
-
-unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
-unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC;
-
-#define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
-#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME)
-#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
-#define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
-#define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
-#define BIC_IS_ENABLED(COUNTER_BIT) (bic_enabled & COUNTER_BIT)
-
#define MAX_DEFERRED 16
+char *deferred_add_names[MAX_DEFERRED];
char *deferred_skip_names[MAX_DEFERRED];
+int deferred_add_index;
int deferred_skip_index;
/*
@@ -720,6 +731,8 @@ void help(void)
" -l, --list list column headers only\n"
" -n, --num_iterations num\n"
" number of the measurement iterations\n"
+ " -N, --header_iterations num\n"
+ " print header every num iterations\n"
" -o, --out file\n"
" create or truncate \"file\" for all output\n"
" -q, --quiet skip decoding system configuration header\n"
@@ -741,7 +754,7 @@ void help(void)
*/
unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
{
- int i;
+ unsigned int i;
unsigned long long retval = 0;
while (name_list) {
@@ -752,40 +765,51 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
if (comma)
*comma = '\0';
- if (!strcmp(name_list, "all"))
- return ~0;
- if (!strcmp(name_list, "topology"))
- return BIC_TOPOLOGY;
- if (!strcmp(name_list, "power"))
- return BIC_THERMAL_PWR;
- if (!strcmp(name_list, "idle"))
- return BIC_IDLE;
- if (!strcmp(name_list, "frequency"))
- return BIC_FREQUENCY;
- if (!strcmp(name_list, "other"))
- return BIC_OTHER;
- if (!strcmp(name_list, "all"))
- return 0;
-
for (i = 0; i < MAX_BIC; ++i) {
if (!strcmp(name_list, bic[i].name)) {
retval |= (1ULL << i);
break;
}
+ if (!strcmp(name_list, "all")) {
+ retval |= ~0;
+ break;
+ } else if (!strcmp(name_list, "topology")) {
+ retval |= BIC_TOPOLOGY;
+ break;
+ } else if (!strcmp(name_list, "power")) {
+ retval |= BIC_THERMAL_PWR;
+ break;
+ } else if (!strcmp(name_list, "idle")) {
+ retval |= BIC_IDLE;
+ break;
+ } else if (!strcmp(name_list, "frequency")) {
+ retval |= BIC_FREQUENCY;
+ break;
+ } else if (!strcmp(name_list, "other")) {
+ retval |= BIC_OTHER;
+ break;
+ }
+
}
if (i == MAX_BIC) {
if (mode == SHOW_LIST) {
- fprintf(stderr, "Invalid counter name: %s\n", name_list);
- exit(-1);
- }
- deferred_skip_names[deferred_skip_index++] = name_list;
- if (debug)
- fprintf(stderr, "deferred \"%s\"\n", name_list);
- if (deferred_skip_index >= MAX_DEFERRED) {
- fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n",
- MAX_DEFERRED, name_list);
- help();
- exit(1);
+ deferred_add_names[deferred_add_index++] = name_list;
+ if (deferred_add_index >= MAX_DEFERRED) {
+ fprintf(stderr, "More than max %d un-recognized --add options '%s'\n",
+ MAX_DEFERRED, name_list);
+ help();
+ exit(1);
+ }
+ } else {
+ deferred_skip_names[deferred_skip_index++] = name_list;
+ if (debug)
+ fprintf(stderr, "deferred \"%s\"\n", name_list);
+ if (deferred_skip_index >= MAX_DEFERRED) {
+ fprintf(stderr, "More than max %d un-recognized --skip options '%s'\n",
+ MAX_DEFERRED, name_list);
+ help();
+ exit(1);
+ }
}
}
@@ -872,6 +896,9 @@ void print_header(char *delim)
if (DO_BIC(BIC_CoreTmp))
outp += sprintf(outp, "%sCoreTmp", (printed++ ? delim : ""));
+ if (DO_BIC(BIC_CORE_THROT_CNT))
+ outp += sprintf(outp, "%sCoreThr", (printed++ ? delim : ""));
+
if (do_rapl && !rapl_joules) {
if (DO_BIC(BIC_CorWatt) && (do_rapl & RAPL_PER_CORE_ENERGY))
outp += sprintf(outp, "%sCorWatt", (printed++ ? delim : ""));
@@ -1011,6 +1038,7 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p
outp += sprintf(outp, "c6: %016llX\n", c->c6);
outp += sprintf(outp, "c7: %016llX\n", c->c7);
outp += sprintf(outp, "DTS: %dC\n", c->core_temp_c);
+ outp += sprintf(outp, "cpu_throt_count: %016llX\n", c->core_throt_cnt);
outp += sprintf(outp, "Joules: %0X\n", c->core_energy);
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
@@ -1225,6 +1253,10 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_CoreTmp))
outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_temp_c);
+ /* Core throttle count */
+ if (DO_BIC(BIC_CORE_THROT_CNT))
+ outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), c->core_throt_cnt);
+
for (i = 0, mp = sys.cp; mp; i++, mp = mp->next) {
if (mp->format == FORMAT_RAW) {
if (mp->width == 32)
@@ -1311,6 +1343,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data
if (DO_BIC(BIC_PkgWatt))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_pkg * rapl_energy_units / interval_float);
+
if (DO_BIC(BIC_CorWatt) && !(do_rapl & RAPL_PER_CORE_ENERGY))
outp +=
sprintf(outp, fmt8, (printed++ ? delim : ""), p->energy_cores * rapl_energy_units / interval_float);
@@ -1386,14 +1419,14 @@ void flush_output_stderr(void)
void format_all_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
- static int printed;
+ static int count;
- if (!printed || !summary_only)
+ if ((!count || (header_iterations && !(count % header_iterations))) || !summary_only)
print_header("\t");
format_counters(&average.threads, &average.cores, &average.packages);
- printed = 1;
+ count++;
if (summary_only)
return;
@@ -1467,6 +1500,7 @@ void delta_core(struct core_data *new, struct core_data *old)
old->c6 = new->c6 - old->c6;
old->c7 = new->c7 - old->c7;
old->core_temp_c = new->core_temp_c;
+ old->core_throt_cnt = new->core_throt_cnt;
old->mc6_us = new->mc6_us - old->mc6_us;
DELTA_WRAP32(new->core_energy, old->core_energy);
@@ -1626,6 +1660,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
c->mc6_us = 0;
c->core_temp_c = 0;
c->core_energy = 0;
+ c->core_throt_cnt = 0;
p->pkg_wtd_core_c0 = 0;
p->pkg_any_core_c0 = 0;
@@ -1710,6 +1745,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
average.cores.mc6_us += c->mc6_us;
average.cores.core_temp_c = MAX(average.cores.core_temp_c, c->core_temp_c);
+ average.cores.core_throt_cnt = MAX(average.cores.core_throt_cnt, c->core_throt_cnt);
average.cores.core_energy += c->core_energy;
@@ -1987,6 +2023,26 @@ void get_apic_id(struct thread_data *t)
fprintf(outf, "cpu%d: BIOS BUG: apic 0x%x x2apic 0x%x\n", t->cpu_id, t->apic_id, t->x2apic_id);
}
+int get_core_throt_cnt(int cpu, unsigned long long *cnt)
+{
+ char path[128 + PATH_BYTES];
+ unsigned long long tmp;
+ FILE *fp;
+ int ret;
+
+ sprintf(path, "/sys/devices/system/cpu/cpu%d/thermal_throttle/core_throttle_count", cpu);
+ fp = fopen(path, "r");
+ if (!fp)
+ return -1;
+ ret = fscanf(fp, "%lld", &tmp);
+ if (ret != 1)
+ return -1;
+ fclose(fp);
+ *cnt = tmp;
+
+ return 0;
+}
+
/*
* get_counters(...)
* migrate to cpu
@@ -2129,6 +2185,9 @@ retry:
c->core_temp_c = tj_max - ((msr >> 16) & 0x7F);
}
+ if (DO_BIC(BIC_CORE_THROT_CNT))
+ get_core_throt_cnt(cpu, &c->core_throt_cnt);
+
if (do_rapl & RAPL_AMD_F17H) {
if (get_msr(cpu, MSR_CORE_ENERGY_STAT, &msr))
return -14;
@@ -2428,6 +2487,9 @@ int has_turbo_ratio_group_limits(int family, int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ATOM_GOLDMONT:
case INTEL_FAM6_SKYLAKE_X:
@@ -2435,8 +2497,9 @@ int has_turbo_ratio_group_limits(int family, int model)
case INTEL_FAM6_ATOM_GOLDMONT_D:
case INTEL_FAM6_ATOM_TREMONT_D:
return 1;
+ default:
+ return 0;
}
- return 0;
}
static void dump_turbo_ratio_limits(int family, int model)
@@ -3027,6 +3090,8 @@ void set_max_cpu_num(void)
*/
int count_cpus(int cpu)
{
+ UNUSED(cpu);
+
topo.num_cpus++;
return 0;
}
@@ -3361,6 +3426,9 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg
int i, ret;
int cpu = t->cpu_id;
+ UNUSED(c);
+ UNUSED(p);
+
for (i = IDX_PKG_ENERGY; i < IDX_COUNT; i++) {
unsigned long long msr_cur, msr_last;
off_t offset;
@@ -3387,6 +3455,8 @@ static int update_msr_sum(struct thread_data *t, struct core_data *c, struct pkg
static void msr_record_handler(union sigval v)
{
+ UNUSED(v);
+
for_all_cpus(update_msr_sum, EVEN_COUNTERS);
}
@@ -3439,6 +3509,9 @@ release_msr:
/*
* set_my_sched_priority(pri)
* return previous
+ *
+ * if non-root, do this:
+ * # /sbin/setcap cap_sys_rawio,cap_sys_nice=+ep /usr/bin/turbostat
*/
int set_my_sched_priority(int priority)
{
@@ -3457,7 +3530,7 @@ int set_my_sched_priority(int priority)
errno = 0;
retval = getpriority(PRIO_PROCESS, 0);
if (retval != priority)
- err(-1, "getpriority(%d) != setpriority(%d)", retval, priority);
+ err(retval, "getpriority(%d) != setpriority(%d)", retval, priority);
return original_priority;
}
@@ -3466,7 +3539,7 @@ void turbostat_loop()
{
int retval;
int restarted = 0;
- int done_iters = 0;
+ unsigned int done_iters = 0;
setup_signal_handler();
@@ -3678,6 +3751,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
break;
case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */
no_MSR_MISC_PWR_MGMT = 1;
+ /* FALLTHRU */
case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */
pkg_cstate_limits = slv_pkg_cstate_limits;
break;
@@ -3721,6 +3795,9 @@ int has_slv_msrs(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ATOM_SILVERMONT:
case INTEL_FAM6_ATOM_SILVERMONT_MID:
@@ -3736,6 +3813,9 @@ int is_dnv(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ATOM_GOLDMONT_D:
return 1;
@@ -3749,6 +3829,9 @@ int is_bdx(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_BROADWELL_X:
return 1;
@@ -3762,6 +3845,9 @@ int is_skx(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_SKYLAKE_X:
return 1;
@@ -3775,6 +3861,9 @@ int is_icx(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ICELAKE_X:
return 1;
@@ -3787,6 +3876,9 @@ int is_ehl(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ATOM_TREMONT:
return 1;
@@ -3799,6 +3891,9 @@ int is_jvl(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ATOM_TREMONT_D:
return 1;
@@ -3811,6 +3906,9 @@ int has_turbo_ratio_limit(unsigned int family, unsigned int model)
if (has_slv_msrs(family, model))
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
/* Nehalem compatible, but do not include turbo-ratio limit support */
case INTEL_FAM6_NEHALEM_EX: /* Nehalem-EX Xeon - Beckton */
@@ -4125,6 +4223,9 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p)
char *epb_string;
int cpu, epb;
+ UNUSED(c);
+ UNUSED(p);
+
if (!has_epb)
return 0;
@@ -4171,6 +4272,9 @@ int print_hwp(struct thread_data *t, struct core_data *c, struct pkg_data *p)
unsigned long long msr;
int cpu;
+ UNUSED(c);
+ UNUSED(p);
+
if (!has_hwp)
return 0;
@@ -4254,6 +4358,9 @@ int print_perf_limit(struct thread_data *t, struct core_data *c, struct pkg_data
unsigned long long msr;
int cpu;
+ UNUSED(c);
+ UNUSED(p);
+
cpu = t->cpu_id;
/* per-package */
@@ -4359,6 +4466,8 @@ double get_tdp_intel(unsigned int model)
double get_tdp_amd(unsigned int family)
{
+ UNUSED(family);
+
/* This is the max stock TDP of HEDT/Server Fam17h+ chips */
return 280.0;
}
@@ -4376,6 +4485,7 @@ static double rapl_dram_energy_units_probe(int model, double rapl_energy_units)
case INTEL_FAM6_BROADWELL_X: /* BDX */
case INTEL_FAM6_SKYLAKE_X: /* SKX */
case INTEL_FAM6_XEON_PHI_KNL: /* KNL */
+ case INTEL_FAM6_ICELAKE_X: /* ICX */
return (rapl_dram_energy_units = 15.3 / 1000000);
default:
return (rapl_energy_units);
@@ -4559,6 +4669,8 @@ void rapl_probe_amd(unsigned int family, unsigned int model)
unsigned int has_rapl = 0;
double tdp;
+ UNUSED(model);
+
if (max_extended_level >= 0x80000007) {
__cpuid(0x80000007, eax, ebx, ecx, edx);
/* RAPL (Fam 17h+) */
@@ -4617,6 +4729,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
case INTEL_FAM6_HASWELL_L: /* HSW */
case INTEL_FAM6_HASWELL_G: /* HSW */
do_gfx_perf_limit_reasons = 1;
+ /* FALLTHRU */
case INTEL_FAM6_HASWELL_X: /* HSX */
do_core_perf_limit_reasons = 1;
do_ring_perf_limit_reasons = 1;
@@ -4643,6 +4756,9 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
unsigned int dts, dts2;
int cpu;
+ UNUSED(c);
+ UNUSED(p);
+
if (!(do_dts || do_ptm))
return 0;
@@ -4698,7 +4814,7 @@ int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p
void print_power_limit_msr(int cpu, unsigned long long msr, char *label)
{
- fprintf(outf, "cpu%d: %s: %sabled (%f Watts, %f sec, clamp %sabled)\n",
+ fprintf(outf, "cpu%d: %s: %sabled (%0.3f Watts, %f sec, clamp %sabled)\n",
cpu, label,
((msr >> 15) & 1) ? "EN" : "DIS",
((msr >> 0) & 0x7FFF) * rapl_power_units,
@@ -4714,6 +4830,9 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
const char *msr_name;
int cpu;
+ UNUSED(c);
+ UNUSED(p);
+
if (!do_rapl)
return 0;
@@ -4762,12 +4881,19 @@ int print_rapl(struct thread_data *t, struct core_data *c, struct pkg_data *p)
cpu, msr, (msr >> 63) & 1 ? "" : "UN");
print_power_limit_msr(cpu, msr, "PKG Limit #1");
- fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%f Watts, %f* sec, clamp %sabled)\n",
+ fprintf(outf, "cpu%d: PKG Limit #2: %sabled (%0.3f Watts, %f* sec, clamp %sabled)\n",
cpu,
((msr >> 47) & 1) ? "EN" : "DIS",
((msr >> 32) & 0x7FFF) * rapl_power_units,
(1.0 + (((msr >> 54) & 0x3) / 4.0)) * (1 << ((msr >> 49) & 0x1F)) * rapl_time_units,
((msr >> 48) & 1) ? "EN" : "DIS");
+
+ if (get_msr(cpu, MSR_VR_CURRENT_CONFIG, &msr))
+ return -9;
+
+ fprintf(outf, "cpu%d: MSR_VR_CURRENT_CONFIG: 0x%08llx\n", cpu, msr);
+ fprintf(outf, "cpu%d: PKG Limit #4: %f Watts (%slocked)\n",
+ cpu, ((msr >> 0) & 0x1FFF) * rapl_power_units, (msr >> 31) & 1 ? "" : "UN");
}
if (do_rapl & RAPL_DRAM_POWER_INFO) {
@@ -4830,6 +4956,9 @@ int has_snb_msrs(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_SANDYBRIDGE:
case INTEL_FAM6_SANDYBRIDGE_X:
@@ -4873,6 +5002,9 @@ int has_c8910_msrs(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_HASWELL_L: /* HSW */
case INTEL_FAM6_BROADWELL: /* BDW */
@@ -4899,6 +5031,9 @@ int has_skl_msrs(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_SKYLAKE_L: /* SKL */
case INTEL_FAM6_CANNONLAKE_L: /* CNL */
@@ -4911,6 +5046,10 @@ int is_slm(unsigned int family, unsigned int model)
{
if (!genuine_intel)
return 0;
+
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_ATOM_SILVERMONT: /* BYT */
case INTEL_FAM6_ATOM_SILVERMONT_D: /* AVN */
@@ -4923,6 +5062,10 @@ int is_knl(unsigned int family, unsigned int model)
{
if (!genuine_intel)
return 0;
+
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_XEON_PHI_KNL: /* KNL */
return 1;
@@ -4935,6 +5078,9 @@ int is_cnl(unsigned int family, unsigned int model)
if (!genuine_intel)
return 0;
+ if (family != 6)
+ return 0;
+
switch (model) {
case INTEL_FAM6_CANNONLAKE_L: /* CNL */
return 1;
@@ -4989,6 +5135,9 @@ int get_cpu_type(struct thread_data *t, struct core_data *c, struct pkg_data *p)
{
unsigned int eax, ebx, ecx, edx;
+ UNUSED(c);
+ UNUSED(p);
+
if (!genuine_intel)
return 0;
@@ -5025,6 +5174,9 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk
unsigned int tcc_default, tcc_offset;
int cpu;
+ UNUSED(c);
+ UNUSED(p);
+
/* tj_max is used only for dts or ptm */
if (!(do_dts || do_ptm))
return 0;
@@ -5572,6 +5724,11 @@ void process_cpuid()
else
BIC_NOT_PRESENT(BIC_CPU_LPI);
+ if (!access("/sys/devices/system/cpu/cpu0/thermal_throttle/core_throttle_count", R_OK))
+ BIC_PRESENT(BIC_CORE_THROT_CNT);
+ else
+ BIC_NOT_PRESENT(BIC_CORE_THROT_CNT);
+
if (!access(sys_lpi_file_sysfs, R_OK)) {
sys_lpi_file = sys_lpi_file_sysfs;
BIC_PRESENT(BIC_SYS_LPI);
@@ -5601,11 +5758,6 @@ int dir_filter(const struct dirent *dirp)
return 0;
}
-int open_dev_cpu_msr(int dummy1)
-{
- return 0;
-}
-
void topology_probe()
{
int i;
@@ -5896,6 +6048,9 @@ void turbostat_init()
if (!quiet && do_irtl_snb)
print_irtl();
+
+ if (DO_BIC(BIC_IPC))
+ (void)get_instr_count_fd(base_cpu);
}
int fork_it(char **argv)
@@ -5973,7 +6128,7 @@ int get_and_dump_counters(void)
void print_version()
{
- fprintf(outf, "turbostat version 21.05.04" " - Len Brown <lenb@kernel.org>\n");
+ fprintf(outf, "turbostat version 2022.04.16 - Len Brown <lenb@kernel.org>\n");
}
int add_counter(unsigned int msr_num, char *path, char *name,
@@ -6138,6 +6293,16 @@ next:
}
}
+int is_deferred_add(char *name)
+{
+ int i;
+
+ for (i = 0; i < deferred_add_index; ++i)
+ if (!strcmp(name, deferred_add_names[i]))
+ return 1;
+ return 0;
+}
+
int is_deferred_skip(char *name)
{
int i;
@@ -6156,9 +6321,6 @@ void probe_sysfs(void)
int state;
char *sp;
- if (!DO_BIC(BIC_sysfs))
- return;
-
for (state = 10; state >= 0; --state) {
sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name", base_cpu, state);
@@ -6181,6 +6343,9 @@ void probe_sysfs(void)
sprintf(path, "cpuidle/state%d/time", state);
+ if (!DO_BIC(BIC_sysfs) && !is_deferred_add(name_buf))
+ continue;
+
if (is_deferred_skip(name_buf))
continue;
@@ -6206,6 +6371,9 @@ void probe_sysfs(void)
sprintf(path, "cpuidle/state%d/usage", state);
+ if (!DO_BIC(BIC_sysfs) && !is_deferred_add(name_buf))
+ continue;
+
if (is_deferred_skip(name_buf))
continue;
@@ -6313,6 +6481,7 @@ void cmdline(int argc, char **argv)
{ "interval", required_argument, 0, 'i' },
{ "IPC", no_argument, 0, 'I' },
{ "num_iterations", required_argument, 0, 'n' },
+ { "header_iterations", required_argument, 0, 'N' },
{ "help", no_argument, 0, 'h' },
{ "hide", required_argument, 0, 'H' }, // meh, -h taken by --help
{ "Joules", no_argument, 0, 'J' },
@@ -6394,6 +6563,14 @@ void cmdline(int argc, char **argv)
exit(2);
}
break;
+ case 'N':
+ header_iterations = strtod(optarg, NULL);
+
+ if (header_iterations <= 0) {
+ fprintf(outf, "iterations %d should be positive number\n", header_iterations);
+ exit(2);
+ }
+ break;
case 's':
/*
* --show: show only those specified
@@ -6432,6 +6609,8 @@ int main(int argc, char **argv)
turbostat_init();
+ msr_sum_record();
+
/* dump counters and exit */
if (dump_only)
return get_and_dump_counters();
@@ -6443,7 +6622,6 @@ int main(int argc, char **argv)
return 0;
}
- msr_sum_record();
/*
* if any params left, it must be a command to fork
*/
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 65dbdda3a054..1da76ccde448 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -1842,7 +1842,7 @@ static int nfit_test_dimm_init(struct nfit_test *t)
return 0;
}
-static void security_init(struct nfit_test *t)
+static void nfit_security_init(struct nfit_test *t)
{
int i;
@@ -1938,7 +1938,7 @@ static int nfit_test0_alloc(struct nfit_test *t)
if (nfit_test_dimm_init(t))
return -ENOMEM;
smart_init(t);
- security_init(t);
+ nfit_security_init(t);
return ars_state_init(&t->pdev.dev, &t->ars_state);
}
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index 81539f543954..d5c1bcba86fe 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -25,7 +25,8 @@ struct kmem_cache {
void (*ctor)(void *);
};
-void *kmem_cache_alloc(struct kmem_cache *cachep, int gfp)
+void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
+ int gfp)
{
void *p;
diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index 1e8d9a8f59df..9460cbe81bcc 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -17,16 +17,7 @@ top_srcdir = $(realpath ../../../../)
# Additional include paths needed by kselftest.h and local headers
CFLAGS += -I$(top_srcdir)/tools/testing/selftests/
-# Guessing where the Kernel headers could have been installed
-# depending on ENV config
-ifeq ($(KBUILD_OUTPUT),)
-khdr_dir = $(top_srcdir)/usr/include
-else
-# the KSFT preferred location when KBUILD_OUTPUT is set
-khdr_dir = $(KBUILD_OUTPUT)/kselftest/usr/include
-endif
-
-CFLAGS += -I$(khdr_dir)
+CFLAGS += $(KHDR_INCLUDES)
export CFLAGS
export top_srcdir
diff --git a/tools/testing/selftests/arm64/abi/.gitignore b/tools/testing/selftests/arm64/abi/.gitignore
index b79cf5814c23..b9e54417250d 100644
--- a/tools/testing/selftests/arm64/abi/.gitignore
+++ b/tools/testing/selftests/arm64/abi/.gitignore
@@ -1 +1,2 @@
syscall-abi
+tpidr2
diff --git a/tools/testing/selftests/arm64/abi/Makefile b/tools/testing/selftests/arm64/abi/Makefile
index 96eba974ac8d..c8d7f2495eb2 100644
--- a/tools/testing/selftests/arm64/abi/Makefile
+++ b/tools/testing/selftests/arm64/abi/Makefile
@@ -1,8 +1,15 @@
# SPDX-License-Identifier: GPL-2.0
# Copyright (C) 2021 ARM Limited
-TEST_GEN_PROGS := syscall-abi
+TEST_GEN_PROGS := syscall-abi tpidr2
include ../../lib.mk
$(OUTPUT)/syscall-abi: syscall-abi.c syscall-abi-asm.S
+
+# Build with nolibc since TPIDR2 is intended to be actively managed by
+# libc and we're trying to test the functionality that it depends on here.
+$(OUTPUT)/tpidr2: tpidr2.c
+ $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ -static -include ../../../../include/nolibc/nolibc.h \
+ -ffreestanding -Wall $^ -o $@ -lgcc
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
index 983467cfcee0..b523c21c2278 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
+++ b/tools/testing/selftests/arm64/abi/syscall-abi-asm.S
@@ -9,15 +9,42 @@
// invoked is configured in x8 of the input GPR data.
//
// x0: SVE VL, 0 for FP only
+// x1: SME VL
//
// GPRs: gpr_in, gpr_out
// FPRs: fpr_in, fpr_out
// Zn: z_in, z_out
// Pn: p_in, p_out
// FFR: ffr_in, ffr_out
+// ZA: za_in, za_out
+// SVCR: svcr_in, svcr_out
+
+#include "syscall-abi.h"
.arch_extension sve
+/*
+ * LDR (vector to ZA array):
+ * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _ldr_za nw, nxbase, offset=0
+ .inst 0xe1000000 \
+ | (((\nw) & 3) << 13) \
+ | ((\nxbase) << 5) \
+ | ((\offset) & 7)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _str_za nw, nxbase, offset=0
+ .inst 0xe1200000 \
+ | (((\nw) & 3) << 13) \
+ | ((\nxbase) << 5) \
+ | ((\offset) & 7)
+.endm
+
.globl do_syscall
do_syscall:
// Store callee saved registers x19-x29 (80 bytes) plus x0 and x1
@@ -30,6 +57,24 @@ do_syscall:
stp x25, x26, [sp, #80]
stp x27, x28, [sp, #96]
+ // Set SVCR if we're doing SME
+ cbz x1, 1f
+ adrp x2, svcr_in
+ ldr x2, [x2, :lo12:svcr_in]
+ msr S3_3_C4_C2_2, x2
+1:
+
+ // Load ZA if it's enabled - uses x12 as scratch due to SME LDR
+ tbz x2, #SVCR_ZA_SHIFT, 1f
+ mov w12, #0
+ ldr x2, =za_in
+2: _ldr_za 12, 2
+ add x2, x2, x1
+ add x12, x12, #1
+ cmp x1, x12
+ bne 2b
+1:
+
// Load GPRs x8-x28, and save our SP/FP for later comparison
ldr x2, =gpr_in
add x2, x2, #64
@@ -68,7 +113,7 @@ do_syscall:
ldp q30, q31, [x2, #16 * 30]
1:
- // Load the SVE registers if we're doing SVE
+ // Load the SVE registers if we're doing SVE/SME
cbz x0, 1f
ldr x2, =z_in
@@ -105,9 +150,14 @@ do_syscall:
ldr z30, [x2, #30, MUL VL]
ldr z31, [x2, #31, MUL VL]
+ // Only set a non-zero FFR, test patterns must be zero since the
+ // syscall should clear it - this lets us handle FA64.
ldr x2, =ffr_in
ldr p0, [x2, #0]
+ ldr x2, [x2, #0]
+ cbz x2, 2f
wrffr p0.b
+2:
ldr x2, =p_in
ldr p0, [x2, #0, MUL VL]
@@ -169,6 +219,24 @@ do_syscall:
stp q28, q29, [x2, #16 * 28]
stp q30, q31, [x2, #16 * 30]
+ // Save SVCR if we're doing SME
+ cbz x1, 1f
+ mrs x2, S3_3_C4_C2_2
+ adrp x3, svcr_out
+ str x2, [x3, :lo12:svcr_out]
+1:
+
+ // Save ZA if it's enabled - uses x12 as scratch due to SME STR
+ tbz x2, #SVCR_ZA_SHIFT, 1f
+ mov w12, #0
+ ldr x2, =za_out
+2: _str_za 12, 2
+ add x2, x2, x1
+ add x12, x12, #1
+ cmp x1, x12
+ bne 2b
+1:
+
// Save the SVE state if we have some
cbz x0, 1f
@@ -224,6 +292,10 @@ do_syscall:
str p14, [x2, #14, MUL VL]
str p15, [x2, #15, MUL VL]
+ // Only save FFR if we wrote a value for SME
+ ldr x2, =ffr_in
+ ldr x2, [x2, #0]
+ cbz x2, 1f
ldr x2, =ffr_out
rdffr p0.b
str p0, [x2, #0]
@@ -237,4 +309,9 @@ do_syscall:
ldp x27, x28, [sp, #96]
ldp x29, x30, [sp], #112
+ // Clear SVCR if we were doing SME so future tests don't have ZA
+ cbz x1, 1f
+ msr S3_3_C4_C2_2, xzr
+1:
+
ret
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.c b/tools/testing/selftests/arm64/abi/syscall-abi.c
index 1e13b7523918..b632bfe9e022 100644
--- a/tools/testing/selftests/arm64/abi/syscall-abi.c
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.c
@@ -18,9 +18,13 @@
#include "../../kselftest.h"
+#include "syscall-abi.h"
+
#define NUM_VL ((SVE_VQ_MAX - SVE_VQ_MIN) + 1)
-extern void do_syscall(int sve_vl);
+static int default_sme_vl;
+
+extern void do_syscall(int sve_vl, int sme_vl);
static void fill_random(void *buf, size_t size)
{
@@ -48,14 +52,15 @@ static struct syscall_cfg {
uint64_t gpr_in[NUM_GPR];
uint64_t gpr_out[NUM_GPR];
-static void setup_gpr(struct syscall_cfg *cfg, int sve_vl)
+static void setup_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
fill_random(gpr_in, sizeof(gpr_in));
gpr_in[8] = cfg->syscall_nr;
memset(gpr_out, 0, sizeof(gpr_out));
}
-static int check_gpr(struct syscall_cfg *cfg, int sve_vl)
+static int check_gpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl, uint64_t svcr)
{
int errors = 0;
int i;
@@ -79,13 +84,15 @@ static int check_gpr(struct syscall_cfg *cfg, int sve_vl)
uint64_t fpr_in[NUM_FPR * 2];
uint64_t fpr_out[NUM_FPR * 2];
-static void setup_fpr(struct syscall_cfg *cfg, int sve_vl)
+static void setup_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
fill_random(fpr_in, sizeof(fpr_in));
memset(fpr_out, 0, sizeof(fpr_out));
}
-static int check_fpr(struct syscall_cfg *cfg, int sve_vl)
+static int check_fpr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
int errors = 0;
int i;
@@ -109,13 +116,15 @@ static uint8_t z_zero[__SVE_ZREG_SIZE(SVE_VQ_MAX)];
uint8_t z_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
uint8_t z_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
-static void setup_z(struct syscall_cfg *cfg, int sve_vl)
+static void setup_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
fill_random(z_in, sizeof(z_in));
fill_random(z_out, sizeof(z_out));
}
-static int check_z(struct syscall_cfg *cfg, int sve_vl)
+static int check_z(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
size_t reg_size = sve_vl;
int errors = 0;
@@ -126,13 +135,17 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl)
/*
* After a syscall the low 128 bits of the Z registers should
- * be preserved and the rest be zeroed or preserved.
+ * be preserved and the rest be zeroed or preserved, except if
+ * we were in streaming mode in which case the low 128 bits may
+ * also be cleared by the transition out of streaming mode.
*/
for (i = 0; i < SVE_NUM_ZREGS; i++) {
void *in = &z_in[reg_size * i];
void *out = &z_out[reg_size * i];
- if (memcmp(in, out, SVE_VQ_BYTES) != 0) {
+ if ((memcmp(in, out, SVE_VQ_BYTES) != 0) &&
+ !((svcr & SVCR_SM_MASK) &&
+ memcmp(z_zero, out, SVE_VQ_BYTES) == 0)) {
ksft_print_msg("%s SVE VL %d Z%d low 128 bits changed\n",
cfg->name, sve_vl, i);
errors++;
@@ -145,13 +158,15 @@ static int check_z(struct syscall_cfg *cfg, int sve_vl)
uint8_t p_in[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
uint8_t p_out[SVE_NUM_PREGS * __SVE_PREG_SIZE(SVE_VQ_MAX)];
-static void setup_p(struct syscall_cfg *cfg, int sve_vl)
+static void setup_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
fill_random(p_in, sizeof(p_in));
fill_random(p_out, sizeof(p_out));
}
-static int check_p(struct syscall_cfg *cfg, int sve_vl)
+static int check_p(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */
@@ -175,9 +190,20 @@ static int check_p(struct syscall_cfg *cfg, int sve_vl)
uint8_t ffr_in[__SVE_PREG_SIZE(SVE_VQ_MAX)];
uint8_t ffr_out[__SVE_PREG_SIZE(SVE_VQ_MAX)];
-static void setup_ffr(struct syscall_cfg *cfg, int sve_vl)
+static void setup_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
/*
+ * If we are in streaming mode and do not have FA64 then FFR
+ * is unavailable.
+ */
+ if ((svcr & SVCR_SM_MASK) &&
+ !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)) {
+ memset(&ffr_in, 0, sizeof(ffr_in));
+ return;
+ }
+
+ /*
* It is only valid to set a contiguous set of bits starting
* at 0. For now since we're expecting this to be cleared by
* a syscall just set all bits.
@@ -186,7 +212,8 @@ static void setup_ffr(struct syscall_cfg *cfg, int sve_vl)
fill_random(ffr_out, sizeof(ffr_out));
}
-static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
+static int check_ffr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
size_t reg_size = sve_vq_from_vl(sve_vl) * 2; /* 1 bit per VL byte */
int errors = 0;
@@ -195,6 +222,10 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
if (!sve_vl)
return 0;
+ if ((svcr & SVCR_SM_MASK) &&
+ !(getauxval(AT_HWCAP2) & HWCAP2_SME_FA64))
+ return 0;
+
/* After a syscall the P registers should be preserved or zeroed */
for (i = 0; i < reg_size; i++)
if (ffr_out[i] && (ffr_in[i] != ffr_out[i]))
@@ -206,8 +237,65 @@ static int check_ffr(struct syscall_cfg *cfg, int sve_vl)
return errors;
}
-typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl);
-typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl);
+uint64_t svcr_in, svcr_out;
+
+static void setup_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ svcr_in = svcr;
+}
+
+static int check_svcr(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ int errors = 0;
+
+ if (svcr_out & SVCR_SM_MASK) {
+ ksft_print_msg("%s Still in SM, SVCR %llx\n",
+ cfg->name, svcr_out);
+ errors++;
+ }
+
+ if ((svcr_in & SVCR_ZA_MASK) != (svcr_out & SVCR_ZA_MASK)) {
+ ksft_print_msg("%s PSTATE.ZA changed, SVCR %llx != %llx\n",
+ cfg->name, svcr_in, svcr_out);
+ errors++;
+ }
+
+ return errors;
+}
+
+uint8_t za_in[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+uint8_t za_out[SVE_NUM_PREGS * __SVE_ZREG_SIZE(SVE_VQ_MAX)];
+
+static void setup_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ fill_random(za_in, sizeof(za_in));
+ memset(za_out, 0, sizeof(za_out));
+}
+
+static int check_za(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
+{
+ size_t reg_size = sme_vl * sme_vl;
+ int errors = 0;
+
+ if (!(svcr & SVCR_ZA_MASK))
+ return 0;
+
+ if (memcmp(za_in, za_out, reg_size) != 0) {
+ ksft_print_msg("SME VL %d ZA does not match\n", sme_vl);
+ errors++;
+ }
+
+ return errors;
+}
+
+typedef void (*setup_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr);
+typedef int (*check_fn)(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr);
/*
* Each set of registers has a setup function which is called before
@@ -225,20 +313,23 @@ static struct {
{ setup_z, check_z },
{ setup_p, check_p },
{ setup_ffr, check_ffr },
+ { setup_svcr, check_svcr },
+ { setup_za, check_za },
};
-static bool do_test(struct syscall_cfg *cfg, int sve_vl)
+static bool do_test(struct syscall_cfg *cfg, int sve_vl, int sme_vl,
+ uint64_t svcr)
{
int errors = 0;
int i;
for (i = 0; i < ARRAY_SIZE(regset); i++)
- regset[i].setup(cfg, sve_vl);
+ regset[i].setup(cfg, sve_vl, sme_vl, svcr);
- do_syscall(sve_vl);
+ do_syscall(sve_vl, sme_vl);
for (i = 0; i < ARRAY_SIZE(regset); i++)
- errors += regset[i].check(cfg, sve_vl);
+ errors += regset[i].check(cfg, sve_vl, sme_vl, svcr);
return errors == 0;
}
@@ -246,9 +337,10 @@ static bool do_test(struct syscall_cfg *cfg, int sve_vl)
static void test_one_syscall(struct syscall_cfg *cfg)
{
int sve_vq, sve_vl;
+ int sme_vq, sme_vl;
/* FPSIMD only case */
- ksft_test_result(do_test(cfg, 0),
+ ksft_test_result(do_test(cfg, 0, default_sme_vl, 0),
"%s FPSIMD\n", cfg->name);
if (!(getauxval(AT_HWCAP) & HWCAP_SVE))
@@ -265,8 +357,36 @@ static void test_one_syscall(struct syscall_cfg *cfg)
if (sve_vq != sve_vq_from_vl(sve_vl))
sve_vq = sve_vq_from_vl(sve_vl);
- ksft_test_result(do_test(cfg, sve_vl),
+ ksft_test_result(do_test(cfg, sve_vl, default_sme_vl, 0),
"%s SVE VL %d\n", cfg->name, sve_vl);
+
+ if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
+ continue;
+
+ for (sme_vq = SVE_VQ_MAX; sme_vq > 0; --sme_vq) {
+ sme_vl = prctl(PR_SME_SET_VL, sme_vq * 16);
+ if (sme_vl == -1)
+ ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+ strerror(errno), errno);
+
+ sme_vl &= PR_SME_VL_LEN_MASK;
+
+ if (sme_vq != sve_vq_from_vl(sme_vl))
+ sme_vq = sve_vq_from_vl(sme_vl);
+
+ ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+ SVCR_ZA_MASK | SVCR_SM_MASK),
+ "%s SVE VL %d/SME VL %d SM+ZA\n",
+ cfg->name, sve_vl, sme_vl);
+ ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+ SVCR_SM_MASK),
+ "%s SVE VL %d/SME VL %d SM\n",
+ cfg->name, sve_vl, sme_vl);
+ ksft_test_result(do_test(cfg, sve_vl, sme_vl,
+ SVCR_ZA_MASK),
+ "%s SVE VL %d/SME VL %d ZA\n",
+ cfg->name, sve_vl, sme_vl);
+ }
}
}
@@ -299,14 +419,54 @@ int sve_count_vls(void)
return vl_count;
}
+int sme_count_vls(void)
+{
+ unsigned int vq;
+ int vl_count = 0;
+ int vl;
+
+ if (!(getauxval(AT_HWCAP2) & HWCAP2_SME))
+ return 0;
+
+ /* Ensure we configure a SME VL, used to flag if SVCR is set */
+ default_sme_vl = 16;
+
+ /*
+ * Enumerate up to SVE_VQ_MAX vector lengths
+ */
+ for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+ vl = prctl(PR_SME_SET_VL, vq * 16);
+ if (vl == -1)
+ ksft_exit_fail_msg("PR_SME_SET_VL failed: %s (%d)\n",
+ strerror(errno), errno);
+
+ vl &= PR_SME_VL_LEN_MASK;
+
+ if (vq != sve_vq_from_vl(vl))
+ vq = sve_vq_from_vl(vl);
+
+ vl_count++;
+ }
+
+ return vl_count;
+}
+
int main(void)
{
int i;
+ int tests = 1; /* FPSIMD */
srandom(getpid());
ksft_print_header();
- ksft_set_plan(ARRAY_SIZE(syscalls) * (sve_count_vls() + 1));
+ tests += sve_count_vls();
+ tests += (sve_count_vls() * sme_count_vls()) * 3;
+ ksft_set_plan(ARRAY_SIZE(syscalls) * tests);
+
+ if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
+ ksft_print_msg("SME with FA64\n");
+ else if (getauxval(AT_HWCAP2) & HWCAP2_SME)
+ ksft_print_msg("SME without FA64\n");
for (i = 0; i < ARRAY_SIZE(syscalls); i++)
test_one_syscall(&syscalls[i]);
diff --git a/tools/testing/selftests/arm64/abi/syscall-abi.h b/tools/testing/selftests/arm64/abi/syscall-abi.h
new file mode 100644
index 000000000000..bda5a87ad381
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/syscall-abi.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+
+#ifndef SYSCALL_ABI_H
+#define SYSCALL_ABI_H
+
+#define SVCR_ZA_MASK 2
+#define SVCR_SM_MASK 1
+
+#define SVCR_ZA_SHIFT 1
+#define SVCR_SM_SHIFT 0
+
+#endif
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
new file mode 100644
index 000000000000..351a098b503a
--- /dev/null
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -0,0 +1,298 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define SYS_TPIDR2 "S3_3_C13_C0_5"
+
+#define EXPECTED_TESTS 5
+
+static void putstr(const char *str)
+{
+ write(1, str, strlen(str));
+}
+
+static void putnum(unsigned int num)
+{
+ char c;
+
+ if (num / 10)
+ putnum(num / 10);
+
+ c = '0' + (num % 10);
+ write(1, &c, 1);
+}
+
+static int tests_run;
+static int tests_passed;
+static int tests_failed;
+static int tests_skipped;
+
+static void set_tpidr2(uint64_t val)
+{
+ asm volatile (
+ "msr " SYS_TPIDR2 ", %0\n"
+ :
+ : "r"(val)
+ : "cc");
+}
+
+static uint64_t get_tpidr2(void)
+{
+ uint64_t val;
+
+ asm volatile (
+ "mrs %0, " SYS_TPIDR2 "\n"
+ : "=r"(val)
+ :
+ : "cc");
+
+ return val;
+}
+
+static void print_summary(void)
+{
+ if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
+ putstr("# UNEXPECTED TEST COUNT: ");
+
+ putstr("# Totals: pass:");
+ putnum(tests_passed);
+ putstr(" fail:");
+ putnum(tests_failed);
+ putstr(" xfail:0 xpass:0 skip:");
+ putnum(tests_skipped);
+ putstr(" error:0\n");
+}
+
+/* Processes should start with TPIDR2 == 0 */
+static int default_value(void)
+{
+ return get_tpidr2() == 0;
+}
+
+/* If we set TPIDR2 we should read that value */
+static int write_read(void)
+{
+ set_tpidr2(getpid());
+
+ return getpid() == get_tpidr2();
+}
+
+/* If we set a value we should read the same value after scheduling out */
+static int write_sleep_read(void)
+{
+ set_tpidr2(getpid());
+
+ msleep(100);
+
+ return getpid() == get_tpidr2();
+}
+
+/*
+ * If we fork the value in the parent should be unchanged and the
+ * child should start with the same value and be able to set its own
+ * value.
+ */
+static int write_fork_read(void)
+{
+ pid_t newpid, waiting, oldpid;
+ int status;
+
+ set_tpidr2(getpid());
+
+ oldpid = getpid();
+ newpid = fork();
+ if (newpid == 0) {
+ /* In child */
+ if (get_tpidr2() != oldpid) {
+ putstr("# TPIDR2 changed in child: ");
+ putnum(get_tpidr2());
+ putstr("\n");
+ exit(0);
+ }
+
+ set_tpidr2(getpid());
+ if (get_tpidr2() == getpid()) {
+ exit(1);
+ } else {
+ putstr("# Failed to set TPIDR2 in child\n");
+ exit(0);
+ }
+ }
+ if (newpid < 0) {
+ putstr("# fork() failed: -");
+ putnum(-newpid);
+ putstr("\n");
+ return 0;
+ }
+
+ for (;;) {
+ waiting = waitpid(newpid, &status, 0);
+
+ if (waiting < 0) {
+ if (errno == EINTR)
+ continue;
+ putstr("# waitpid() failed: ");
+ putnum(errno);
+ putstr("\n");
+ return 0;
+ }
+ if (waiting != newpid) {
+ putstr("# waitpid() returned wrong PID\n");
+ return 0;
+ }
+
+ if (!WIFEXITED(status)) {
+ putstr("# child did not exit\n");
+ return 0;
+ }
+
+ if (getpid() != get_tpidr2()) {
+ putstr("# TPIDR2 corrupted in parent\n");
+ return 0;
+ }
+
+ return WEXITSTATUS(status);
+ }
+}
+
+/*
+ * sys_clone() has a lot of per architecture variation so just define
+ * it here rather than adding it to nolibc, plus the raw API is a
+ * little more convenient for this test.
+ */
+static int sys_clone(unsigned long clone_flags, unsigned long newsp,
+ int *parent_tidptr, unsigned long tls,
+ int *child_tidptr)
+{
+ return my_syscall5(__NR_clone, clone_flags, newsp, parent_tidptr, tls,
+ child_tidptr);
+}
+
+/*
+ * If we clone with CLONE_SETTLS then the value in the parent should
+ * be unchanged and the child should start with zero and be able to
+ * set its own value.
+ */
+static int write_clone_read(void)
+{
+ int parent_tid, child_tid;
+ pid_t parent, waiting;
+ int ret, status;
+
+ parent = getpid();
+ set_tpidr2(parent);
+
+ ret = sys_clone(CLONE_SETTLS, 0, &parent_tid, 0, &child_tid);
+ if (ret == -1) {
+ putstr("# clone() failed\n");
+ putnum(errno);
+ putstr("\n");
+ return 0;
+ }
+
+ if (ret == 0) {
+ /* In child */
+ if (get_tpidr2() != 0) {
+ putstr("# TPIDR2 non-zero in child: ");
+ putnum(get_tpidr2());
+ putstr("\n");
+ exit(0);
+ }
+
+ if (gettid() == 0)
+ putstr("# Child TID==0\n");
+ set_tpidr2(gettid());
+ if (get_tpidr2() == gettid()) {
+ exit(1);
+ } else {
+ putstr("# Failed to set TPIDR2 in child\n");
+ exit(0);
+ }
+ }
+
+ for (;;) {
+ waiting = wait4(ret, &status, __WCLONE, NULL);
+
+ if (waiting < 0) {
+ if (errno == EINTR)
+ continue;
+ putstr("# wait4() failed: ");
+ putnum(errno);
+ putstr("\n");
+ return 0;
+ }
+ if (waiting != ret) {
+ putstr("# wait4() returned wrong PID ");
+ putnum(waiting);
+ putstr("\n");
+ return 0;
+ }
+
+ if (!WIFEXITED(status)) {
+ putstr("# child did not exit\n");
+ return 0;
+ }
+
+ if (parent != get_tpidr2()) {
+ putstr("# TPIDR2 corrupted in parent\n");
+ return 0;
+ }
+
+ return WEXITSTATUS(status);
+ }
+}
+
+#define run_test(name) \
+ if (name()) { \
+ tests_passed++; \
+ } else { \
+ tests_failed++; \
+ putstr("not "); \
+ } \
+ putstr("ok "); \
+ putnum(++tests_run); \
+ putstr(" " #name "\n");
+
+int main(int argc, char **argv)
+{
+ int ret, i;
+
+ putstr("TAP version 13\n");
+ putstr("1..");
+ putnum(EXPECTED_TESTS);
+ putstr("\n");
+
+ putstr("# PID: ");
+ putnum(getpid());
+ putstr("\n");
+
+ /*
+ * This test is run with nolibc which doesn't support hwcap and
+ * it's probably disproportionate to implement so instead check
+ * for the default vector length configuration in /proc.
+ */
+ ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
+ if (ret >= 0) {
+ run_test(default_value);
+ run_test(write_read);
+ run_test(write_sleep_read);
+ run_test(write_fork_read);
+ run_test(write_clone_read);
+
+ } else {
+ putstr("# SME support not present\n");
+
+ for (i = 0; i < EXPECTED_TESTS; i++) {
+ putstr("ok ");
+ putnum(i);
+ putstr(" skipped, TPIDR2 not supported\n");
+ }
+
+ tests_skipped += EXPECTED_TESTS;
+ }
+
+ print_summary();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/bti/Makefile b/tools/testing/selftests/arm64/bti/Makefile
index 73e013c082a6..ccdac414ad94 100644
--- a/tools/testing/selftests/arm64/bti/Makefile
+++ b/tools/testing/selftests/arm64/bti/Makefile
@@ -10,7 +10,7 @@ PROGS := $(patsubst %,gen/%,$(TEST_GEN_PROGS))
# cases for statically linked and dynamically lined binaries are
# slightly different.
-CFLAGS_NOBTI = -DBTI=0
+CFLAGS_NOBTI = -mbranch-protection=none -DBTI=0
CFLAGS_BTI = -mbranch-protection=standard -DBTI=1
CFLAGS_COMMON = -ffreestanding -Wall -Wextra $(CFLAGS)
@@ -39,7 +39,7 @@ BTI_OBJS = \
teststubs-bti.o \
trampoline-bti.o
gen/btitest: $(BTI_OBJS)
- $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^
+ $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^
NOBTI_OBJS = \
test-nobti.o \
@@ -50,7 +50,7 @@ NOBTI_OBJS = \
teststubs-nobti.o \
trampoline-nobti.o
gen/nobtitest: $(NOBTI_OBJS)
- $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -o $@ $^
+ $(CC) $(CFLAGS_BTI) $(CFLAGS_COMMON) -nostdlib -static -o $@ $^
# Including KSFT lib.mk here will also mangle the TEST_GEN_PROGS list
# to account for any OUTPUT target-dirs optionally provided by
diff --git a/tools/testing/selftests/arm64/fp/.gitignore b/tools/testing/selftests/arm64/fp/.gitignore
index c50d86331ed2..ea947af63882 100644
--- a/tools/testing/selftests/arm64/fp/.gitignore
+++ b/tools/testing/selftests/arm64/fp/.gitignore
@@ -1,8 +1,13 @@
fp-pidbench
fpsimd-test
+rdvl-sme
rdvl-sve
sve-probe-vls
sve-ptrace
sve-test
+ssve-test
vec-syscfg
vlset
+za-fork
+za-ptrace
+za-test
diff --git a/tools/testing/selftests/arm64/fp/Makefile b/tools/testing/selftests/arm64/fp/Makefile
index 95f0b877a060..a7c2286bf65b 100644
--- a/tools/testing/selftests/arm64/fp/Makefile
+++ b/tools/testing/selftests/arm64/fp/Makefile
@@ -1,24 +1,42 @@
# SPDX-License-Identifier: GPL-2.0
-CFLAGS += -I../../../../../usr/include/
-TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg
-TEST_PROGS_EXTENDED := fp-pidbench fpsimd-test fpsimd-stress \
- rdvl-sve \
- sve-test sve-stress \
+# A proper top_srcdir is needed by KSFT(lib.mk)
+top_srcdir = $(realpath ../../../../../)
+
+CFLAGS += -I$(top_srcdir)/usr/include/
+
+TEST_GEN_PROGS := sve-ptrace sve-probe-vls vec-syscfg za-fork za-ptrace
+TEST_GEN_PROGS_EXTENDED := fp-pidbench fpsimd-test \
+ rdvl-sme rdvl-sve \
+ sve-test \
+ ssve-test \
+ za-test \
vlset
+TEST_PROGS_EXTENDED := fpsimd-stress sve-stress ssve-stress za-stress
-all: $(TEST_GEN_PROGS) $(TEST_PROGS_EXTENDED)
+EXTRA_CLEAN += $(OUTPUT)/asm-utils.o $(OUTPUT)/rdvl.o $(OUTPUT)/za-fork-asm.o
-fp-pidbench: fp-pidbench.S asm-utils.o
+# Build with nolibc to avoid effects due to libc's clone() support
+$(OUTPUT)/fp-pidbench: fp-pidbench.S $(OUTPUT)/asm-utils.o
+ $(CC) -nostdlib $^ -o $@
+$(OUTPUT)/fpsimd-test: fpsimd-test.S $(OUTPUT)/asm-utils.o
$(CC) -nostdlib $^ -o $@
-fpsimd-test: fpsimd-test.o asm-utils.o
+$(OUTPUT)/rdvl-sve: rdvl-sve.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/rdvl-sme: rdvl-sme.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/sve-ptrace: sve-ptrace.c
+$(OUTPUT)/sve-probe-vls: sve-probe-vls.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/sve-test: sve-test.S $(OUTPUT)/asm-utils.o
$(CC) -nostdlib $^ -o $@
-rdvl-sve: rdvl-sve.o rdvl.o
-sve-ptrace: sve-ptrace.o
-sve-probe-vls: sve-probe-vls.o rdvl.o
-sve-test: sve-test.o asm-utils.o
+$(OUTPUT)/ssve-test: sve-test.S $(OUTPUT)/asm-utils.o
+ $(CC) -DSSVE -nostdlib $^ -o $@
+$(OUTPUT)/vec-syscfg: vec-syscfg.c $(OUTPUT)/rdvl.o
+$(OUTPUT)/vlset: vlset.c
+$(OUTPUT)/za-fork: za-fork.c $(OUTPUT)/za-fork-asm.o
+ $(CC) -fno-asynchronous-unwind-tables -fno-ident -s -Os -nostdlib \
+ -include ../../../../include/nolibc/nolibc.h \
+ -static -ffreestanding -Wall $^ -o $@
+$(OUTPUT)/za-ptrace: za-ptrace.c
+$(OUTPUT)/za-test: za-test.S $(OUTPUT)/asm-utils.o
$(CC) -nostdlib $^ -o $@
-vec-syscfg: vec-syscfg.o rdvl.o
-vlset: vlset.o
include ../../lib.mk
diff --git a/tools/testing/selftests/arm64/fp/rdvl-sme.c b/tools/testing/selftests/arm64/fp/rdvl-sme.c
new file mode 100644
index 000000000000..49b0b2e08bac
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/rdvl-sme.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <stdio.h>
+
+#include "rdvl.h"
+
+int main(void)
+{
+ int vl = rdvl_sme();
+
+ printf("%d\n", vl);
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/rdvl.S b/tools/testing/selftests/arm64/fp/rdvl.S
index c916c1c9defd..20dc29996dc6 100644
--- a/tools/testing/selftests/arm64/fp/rdvl.S
+++ b/tools/testing/selftests/arm64/fp/rdvl.S
@@ -1,6 +1,8 @@
// SPDX-License-Identifier: GPL-2.0-only
// Copyright (C) 2021 ARM Limited.
+#include "sme-inst.h"
+
.arch_extension sve
.globl rdvl_sve
@@ -8,3 +10,11 @@ rdvl_sve:
hint 34 // BTI C
rdvl x0, #1
ret
+
+.globl rdvl_sme
+rdvl_sme:
+ hint 34 // BTI C
+
+ rdsvl 0, 1
+
+ ret
diff --git a/tools/testing/selftests/arm64/fp/rdvl.h b/tools/testing/selftests/arm64/fp/rdvl.h
index 7c9d953fc9e7..5d323679fbc9 100644
--- a/tools/testing/selftests/arm64/fp/rdvl.h
+++ b/tools/testing/selftests/arm64/fp/rdvl.h
@@ -3,6 +3,7 @@
#ifndef RDVL_H
#define RDVL_H
+int rdvl_sme(void);
int rdvl_sve(void);
#endif
diff --git a/tools/testing/selftests/arm64/fp/sme-inst.h b/tools/testing/selftests/arm64/fp/sme-inst.h
new file mode 100644
index 000000000000..7191e53ca1c0
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/sme-inst.h
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021-2 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+
+#ifndef SME_INST_H
+#define SME_INST_H
+
+/*
+ * RDSVL X\nx, #\imm
+ */
+.macro rdsvl nx, imm
+ .inst 0x4bf5800 \
+ | (\imm << 5) \
+ | (\nx)
+.endm
+
+.macro smstop
+ msr S0_3_C4_C6_3, xzr
+.endm
+
+.macro smstart_za
+ msr S0_3_C4_C5_3, xzr
+.endm
+
+.macro smstart_sm
+ msr S0_3_C4_C3_3, xzr
+.endm
+
+/*
+ * LDR (vector to ZA array):
+ * LDR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _ldr_za nw, nxbase, offset=0
+ .inst 0xe1000000 \
+ | (((\nw) & 3) << 13) \
+ | ((\nxbase) << 5) \
+ | ((\offset) & 7)
+.endm
+
+/*
+ * STR (vector from ZA array):
+ * STR ZA[\nw, #\offset], [X\nxbase, #\offset, MUL VL]
+ */
+.macro _str_za nw, nxbase, offset=0
+ .inst 0xe1200000 \
+ | (((\nw) & 3) << 13) \
+ | ((\nxbase) << 5) \
+ | ((\offset) & 7)
+.endm
+
+#endif
diff --git a/tools/testing/selftests/arm64/fp/ssve-stress b/tools/testing/selftests/arm64/fp/ssve-stress
new file mode 100644
index 000000000000..e2bd2cc184ad
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/ssve-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+ trap - INT TERM CHLD
+ set +e
+
+ if [ -n "$pids" ]; then
+ kill $pids
+ wait $pids
+ pids=
+ fi
+
+ if [ -n "$logs" ]; then
+ cat $logs
+ rm $logs
+ logs=
+ fi
+}
+
+interrupt () {
+ cleanup
+ exit 0
+}
+
+child_died () {
+ cleanup
+ exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+ log=`mktemp`
+ logs=$logs\ $log
+ ./ssve-test >$log &
+ pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+ kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/sve-ptrace.c b/tools/testing/selftests/arm64/fp/sve-ptrace.c
index 4c418b2021e0..8c4847977583 100644
--- a/tools/testing/selftests/arm64/fp/sve-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/sve-ptrace.c
@@ -26,6 +26,10 @@
#define NT_ARM_SVE 0x405
#endif
+#ifndef NT_ARM_SSVE
+#define NT_ARM_SSVE 0x40b
+#endif
+
struct vec_type {
const char *name;
unsigned long hwcap_type;
@@ -42,11 +46,18 @@ static const struct vec_type vec_types[] = {
.regset = NT_ARM_SVE,
.prctl_set = PR_SVE_SET_VL,
},
+ {
+ .name = "Streaming SVE",
+ .hwcap_type = AT_HWCAP2,
+ .hwcap = HWCAP2_SME,
+ .regset = NT_ARM_SSVE,
+ .prctl_set = PR_SME_SET_VL,
+ },
};
-#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+#define VL_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 4)
#define FLAG_TESTS 2
-#define FPSIMD_TESTS 3
+#define FPSIMD_TESTS 2
#define EXPECTED_TESTS ((VL_TESTS + FLAG_TESTS + FPSIMD_TESTS) * ARRAY_SIZE(vec_types))
@@ -78,6 +89,15 @@ static int get_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
return ptrace(PTRACE_GETREGSET, pid, NT_PRFPREG, &iov);
}
+static int set_fpsimd(pid_t pid, struct user_fpsimd_state *fpsimd)
+{
+ struct iovec iov;
+
+ iov.iov_base = fpsimd;
+ iov.iov_len = sizeof(*fpsimd);
+ return ptrace(PTRACE_SETREGSET, pid, NT_PRFPREG, &iov);
+}
+
static struct user_sve_header *get_sve(pid_t pid, const struct vec_type *type,
void **buf, size_t *size)
{
@@ -240,28 +260,24 @@ static void check_u32(unsigned int vl, const char *reg,
/* Access the FPSIMD registers via the SVE regset */
static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
{
- void *svebuf = NULL;
- size_t svebufsz = 0;
+ void *svebuf;
struct user_sve_header *sve;
struct user_fpsimd_state *fpsimd, new_fpsimd;
unsigned int i, j;
unsigned char *p;
+ int ret;
- /* New process should start with FPSIMD registers only */
- sve = get_sve(child, type, &svebuf, &svebufsz);
- if (!sve) {
- ksft_test_result_fail("get_sve(%s): %s\n",
- type->name, strerror(errno));
-
+ svebuf = malloc(SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+ if (!svebuf) {
+ ksft_test_result_fail("Failed to allocate FPSIMD buffer\n");
return;
- } else {
- ksft_test_result_pass("get_sve(%s FPSIMD)\n", type->name);
}
- ksft_test_result((sve->flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD,
- "Got FPSIMD registers via %s\n", type->name);
- if ((sve->flags & SVE_PT_REGS_MASK) != SVE_PT_REGS_FPSIMD)
- goto out;
+ memset(svebuf, 0, SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD));
+ sve = svebuf;
+ sve->flags = SVE_PT_REGS_FPSIMD;
+ sve->size = SVE_PT_SIZE(0, SVE_PT_REGS_FPSIMD);
+ sve->vl = 16; /* We don't care what the VL is */
/* Try to set a known FPSIMD state via PT_REGS_SVE */
fpsimd = (struct user_fpsimd_state *)((char *)sve +
@@ -273,12 +289,11 @@ static void ptrace_sve_fpsimd(pid_t child, const struct vec_type *type)
p[j] = j;
}
- if (set_sve(child, type, sve)) {
- ksft_test_result_fail("set_sve(%s FPSIMD): %s\n",
- type->name, strerror(errno));
-
+ ret = set_sve(child, type, sve);
+ ksft_test_result(ret == 0, "%s FPSIMD set via SVE: %d\n",
+ type->name, ret);
+ if (ret)
goto out;
- }
/* Verify via the FPSIMD regset */
if (get_fpsimd(child, &new_fpsimd)) {
@@ -395,7 +410,7 @@ out:
free(write_buf);
}
-/* Validate attempting to set SVE data and read SVE data */
+/* Validate attempting to set SVE data and read it via the FPSIMD regset */
static void ptrace_set_sve_get_fpsimd_data(pid_t child,
const struct vec_type *type,
unsigned int vl)
@@ -478,6 +493,115 @@ out:
free(write_buf);
}
+/* Validate attempting to set FPSIMD data and read it via the SVE regset */
+static void ptrace_set_fpsimd_get_sve_data(pid_t child,
+ const struct vec_type *type,
+ unsigned int vl)
+{
+ void *read_buf = NULL;
+ unsigned char *p;
+ struct user_sve_header *read_sve;
+ unsigned int vq = sve_vq_from_vl(vl);
+ struct user_fpsimd_state write_fpsimd;
+ int ret, i, j;
+ size_t read_sve_size = 0;
+ size_t expected_size;
+ int errors = 0;
+
+ if (__BYTE_ORDER == __BIG_ENDIAN) {
+ ksft_test_result_skip("Big endian not supported\n");
+ return;
+ }
+
+ for (i = 0; i < 32; ++i) {
+ p = (unsigned char *)&write_fpsimd.vregs[i];
+
+ for (j = 0; j < sizeof(write_fpsimd.vregs[i]); ++j)
+ p[j] = j;
+ }
+
+ ret = set_fpsimd(child, &write_fpsimd);
+ if (ret != 0) {
+ ksft_test_result_fail("Failed to set FPSIMD state: %d\n)",
+ ret);
+ return;
+ }
+
+ if (!get_sve(child, type, (void **)&read_buf, &read_sve_size)) {
+ ksft_test_result_fail("Failed to read %s VL %u data\n",
+ type->name, vl);
+ return;
+ }
+ read_sve = read_buf;
+
+ if (read_sve->vl != vl) {
+ ksft_test_result_fail("Child VL != expected VL %d\n",
+ read_sve->vl, vl);
+ goto out;
+ }
+
+ /* The kernel may return either SVE or FPSIMD format */
+ switch (read_sve->flags & SVE_PT_REGS_MASK) {
+ case SVE_PT_REGS_FPSIMD:
+ expected_size = SVE_PT_FPSIMD_SIZE(vq, SVE_PT_REGS_FPSIMD);
+ if (read_sve_size < expected_size) {
+ ksft_test_result_fail("Read %d bytes, expected %d\n",
+ read_sve_size, expected_size);
+ goto out;
+ }
+
+ ret = memcmp(&write_fpsimd, read_buf + SVE_PT_FPSIMD_OFFSET,
+ sizeof(write_fpsimd));
+ if (ret != 0) {
+ ksft_print_msg("Read FPSIMD data mismatch\n");
+ errors++;
+ }
+ break;
+
+ case SVE_PT_REGS_SVE:
+ expected_size = SVE_PT_SVE_SIZE(vq, SVE_PT_REGS_SVE);
+ if (read_sve_size < expected_size) {
+ ksft_test_result_fail("Read %d bytes, expected %d\n",
+ read_sve_size, expected_size);
+ goto out;
+ }
+
+ for (i = 0; i < __SVE_NUM_ZREGS; i++) {
+ __uint128_t tmp = 0;
+
+ /*
+ * Z regs are stored endianness invariant, this won't
+ * work for big endian
+ */
+ memcpy(&tmp, read_buf + SVE_PT_SVE_ZREG_OFFSET(vq, i),
+ sizeof(tmp));
+
+ if (tmp != write_fpsimd.vregs[i]) {
+ ksft_print_msg("Mismatch in FPSIMD for %s VL %u Z%d/V%d\n",
+ type->name, vl, i, i);
+ errors++;
+ }
+ }
+
+ check_u32(vl, "FPSR", &write_fpsimd.fpsr,
+ read_buf + SVE_PT_SVE_FPSR_OFFSET(vq), &errors);
+ check_u32(vl, "FPCR", &write_fpsimd.fpcr,
+ read_buf + SVE_PT_SVE_FPCR_OFFSET(vq), &errors);
+ break;
+ default:
+ ksft_print_msg("Unexpected regs type %d\n",
+ read_sve->flags & SVE_PT_REGS_MASK);
+ errors++;
+ break;
+ }
+
+ ksft_test_result(errors == 0, "Set FPSIMD, read via SVE for %s VL %u\n",
+ type->name, vl);
+
+out:
+ free(read_buf);
+}
+
static int do_parent(pid_t child)
{
int ret = EXIT_FAILURE;
@@ -548,11 +672,9 @@ static int do_parent(pid_t child)
if (getauxval(vec_types[i].hwcap_type) & vec_types[i].hwcap) {
ptrace_sve_fpsimd(child, &vec_types[i]);
} else {
- ksft_test_result_skip("%s FPSIMD get via SVE\n",
- vec_types[i].name);
ksft_test_result_skip("%s FPSIMD set via SVE\n",
vec_types[i].name);
- ksft_test_result_skip("%s set read via FPSIMD\n",
+ ksft_test_result_skip("%s FPSIMD read\n",
vec_types[i].name);
}
@@ -585,11 +707,14 @@ static int do_parent(pid_t child)
if (vl_supported) {
ptrace_set_sve_get_sve_data(child, &vec_types[i], vl);
ptrace_set_sve_get_fpsimd_data(child, &vec_types[i], vl);
+ ptrace_set_fpsimd_get_sve_data(child, &vec_types[i], vl);
} else {
ksft_test_result_skip("%s set SVE get SVE for VL %d\n",
vec_types[i].name, vl);
ksft_test_result_skip("%s set SVE get FPSIMD for VL %d\n",
vec_types[i].name, vl);
+ ksft_test_result_skip("%s set FPSIMD get SVE for VL %d\n",
+ vec_types[i].name, vl);
}
}
}
diff --git a/tools/testing/selftests/arm64/fp/sve-test.S b/tools/testing/selftests/arm64/fp/sve-test.S
index f5b1b48ffff2..589264231a2d 100644
--- a/tools/testing/selftests/arm64/fp/sve-test.S
+++ b/tools/testing/selftests/arm64/fp/sve-test.S
@@ -13,6 +13,7 @@
#include <asm/unistd.h>
#include "assembler.h"
#include "asm-offsets.h"
+#include "sme-inst.h"
#define NZR 32
#define NPR 16
@@ -156,6 +157,7 @@ endfunction
// We fill the upper lanes of FFR with zeros.
// Beware: corrupts P0.
function setup_ffr
+#ifndef SSVE
mov x4, x30
and w0, w0, #0x3
@@ -178,6 +180,9 @@ function setup_ffr
wrffr p0.b
ret x4
+#else
+ ret
+#endif
endfunction
// Trivial memory compare: compare x2 bytes starting at address x0 with
@@ -260,6 +265,7 @@ endfunction
// Beware -- corrupts P0.
// Clobbers x0-x5.
function check_ffr
+#ifndef SSVE
mov x3, x30
ldr x4, =scratch
@@ -280,6 +286,9 @@ function check_ffr
mov x2, x5
mov x30, x3
b memcmp
+#else
+ ret
+#endif
endfunction
// Any SVE register modified here can cause corruption in the main
@@ -295,10 +304,12 @@ function irritator_handler
movi v0.8b, #1
movi v9.16b, #2
movi v31.8b, #3
+#ifndef SSVE
// And P0
rdffr p0.b
// And FFR
wrffr p15.b
+#endif
ret
endfunction
@@ -359,6 +370,11 @@ endfunction
.globl _start
function _start
_start:
+#ifdef SSVE
+ puts "Streaming mode "
+ smstart_sm
+#endif
+
// Sanity-check and report the vector length
rdvl x19, #8
@@ -407,6 +423,10 @@ _start:
orr w2, w2, #SA_NODEFER
bl setsignal
+#ifdef SSVE
+ smstart_sm // syscalls will have exited streaming mode
+#endif
+
mov x22, #0 // generation number, increments per iteration
.Ltest_loop:
rdvl x0, #8
diff --git a/tools/testing/selftests/arm64/fp/vec-syscfg.c b/tools/testing/selftests/arm64/fp/vec-syscfg.c
index c90658811a83..9bcfcdc34ee9 100644
--- a/tools/testing/selftests/arm64/fp/vec-syscfg.c
+++ b/tools/testing/selftests/arm64/fp/vec-syscfg.c
@@ -51,6 +51,16 @@ static struct vec_data vec_data[] = {
.prctl_set = PR_SVE_SET_VL,
.default_vl_file = "/proc/sys/abi/sve_default_vector_length",
},
+ {
+ .name = "SME",
+ .hwcap_type = AT_HWCAP2,
+ .hwcap = HWCAP2_SME,
+ .rdvl = rdvl_sme,
+ .rdvl_binary = "./rdvl-sme",
+ .prctl_get = PR_SME_GET_VL,
+ .prctl_set = PR_SME_SET_VL,
+ .default_vl_file = "/proc/sys/abi/sme_default_vector_length",
+ },
};
static int stdio_read_integer(FILE *f, const char *what, int *val)
diff --git a/tools/testing/selftests/arm64/fp/vlset.c b/tools/testing/selftests/arm64/fp/vlset.c
index 308d27a68226..76912a581a95 100644
--- a/tools/testing/selftests/arm64/fp/vlset.c
+++ b/tools/testing/selftests/arm64/fp/vlset.c
@@ -22,12 +22,15 @@ static int inherit = 0;
static int no_inherit = 0;
static int force = 0;
static unsigned long vl;
+static int set_ctl = PR_SVE_SET_VL;
+static int get_ctl = PR_SVE_GET_VL;
static const struct option options[] = {
{ "force", no_argument, NULL, 'f' },
{ "inherit", no_argument, NULL, 'i' },
{ "max", no_argument, NULL, 'M' },
{ "no-inherit", no_argument, &no_inherit, 1 },
+ { "sme", no_argument, NULL, 's' },
{ "help", no_argument, NULL, '?' },
{}
};
@@ -50,6 +53,9 @@ static int parse_options(int argc, char **argv)
case 'M': vl = SVE_VL_MAX; break;
case 'f': force = 1; break;
case 'i': inherit = 1; break;
+ case 's': set_ctl = PR_SME_SET_VL;
+ get_ctl = PR_SME_GET_VL;
+ break;
case 0: break;
default: goto error;
}
@@ -125,14 +131,14 @@ int main(int argc, char **argv)
if (inherit)
flags |= PR_SVE_VL_INHERIT;
- t = prctl(PR_SVE_SET_VL, vl | flags);
+ t = prctl(set_ctl, vl | flags);
if (t < 0) {
fprintf(stderr, "%s: PR_SVE_SET_VL: %s\n",
program_name, strerror(errno));
goto error;
}
- t = prctl(PR_SVE_GET_VL);
+ t = prctl(get_ctl);
if (t == -1) {
fprintf(stderr, "%s: PR_SVE_GET_VL: %s\n",
program_name, strerror(errno));
diff --git a/tools/testing/selftests/arm64/fp/za-fork-asm.S b/tools/testing/selftests/arm64/fp/za-fork-asm.S
new file mode 100644
index 000000000000..2fafadd491c3
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-fork-asm.S
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define MAGIC 42
+
+#define MAXVL 2048
+#define MAXVL_B (MAXVL / 8)
+
+.pushsection .text
+.data
+.align 4
+scratch:
+ .space MAXVL_B
+.popsection
+
+.globl fork_test
+fork_test:
+ smstart_za
+
+ // For simplicity just set one word in one vector, other tests
+ // cover general data corruption issues.
+ ldr x0, =scratch
+ mov x1, #MAGIC
+ str x1, [x0]
+ mov w12, wzr
+ _ldr_za 12, 0 // ZA.H[W12] loaded from [X0]
+
+ // Tail call into the C portion that does the fork & verify
+ b fork_test_c
+
+.globl verify_fork
+verify_fork:
+ // SVCR should have ZA=1, SM=0
+ mrs x0, S3_3_C4_C2_2
+ and x1, x0, #3
+ cmp x1, #2
+ beq 1f
+ mov x0, xzr
+ b 100f
+1:
+
+ // ZA should still have the value we loaded
+ ldr x0, =scratch
+ mov w12, wzr
+ _str_za 12, 0 // ZA.H[W12] stored to [X0]
+ ldr x1, [x0]
+ cmp x1, #MAGIC
+ beq 2f
+ mov x0, xzr
+ b 100f
+
+2:
+ // All tests passed
+ mov x0, #1
+100:
+ ret
+
diff --git a/tools/testing/selftests/arm64/fp/za-fork.c b/tools/testing/selftests/arm64/fp/za-fork.c
new file mode 100644
index 000000000000..ff475c649e96
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-fork.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2022 ARM Limited.
+ * Original author: Mark Brown <broonie@kernel.org>
+ */
+
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/sched.h>
+#include <linux/wait.h>
+
+#define EXPECTED_TESTS 1
+
+static void putstr(const char *str)
+{
+ write(1, str, strlen(str));
+}
+
+static void putnum(unsigned int num)
+{
+ char c;
+
+ if (num / 10)
+ putnum(num / 10);
+
+ c = '0' + (num % 10);
+ write(1, &c, 1);
+}
+
+static int tests_run;
+static int tests_passed;
+static int tests_failed;
+static int tests_skipped;
+
+static void print_summary(void)
+{
+ if (tests_passed + tests_failed + tests_skipped != EXPECTED_TESTS)
+ putstr("# UNEXPECTED TEST COUNT: ");
+
+ putstr("# Totals: pass:");
+ putnum(tests_passed);
+ putstr(" fail:");
+ putnum(tests_failed);
+ putstr(" xfail:0 xpass:0 skip:");
+ putnum(tests_skipped);
+ putstr(" error:0\n");
+}
+
+int fork_test(void);
+int verify_fork(void);
+
+/*
+ * If we fork the value in the parent should be unchanged and the
+ * child should start with the same value. This is called from the
+ * fork_test() asm function.
+ */
+int fork_test_c(void)
+{
+ pid_t newpid, waiting;
+ int child_status, parent_result;
+
+ newpid = fork();
+ if (newpid == 0) {
+ /* In child */
+ if (!verify_fork()) {
+ putstr("# ZA state invalid in child\n");
+ exit(0);
+ } else {
+ exit(1);
+ }
+ }
+ if (newpid < 0) {
+ putstr("# fork() failed: -");
+ putnum(-newpid);
+ putstr("\n");
+ return 0;
+ }
+
+ parent_result = verify_fork();
+ if (!parent_result)
+ putstr("# ZA state invalid in parent\n");
+
+ for (;;) {
+ waiting = waitpid(newpid, &child_status, 0);
+
+ if (waiting < 0) {
+ if (errno == EINTR)
+ continue;
+ putstr("# waitpid() failed: ");
+ putnum(errno);
+ putstr("\n");
+ return 0;
+ }
+ if (waiting != newpid) {
+ putstr("# waitpid() returned wrong PID\n");
+ return 0;
+ }
+
+ if (!WIFEXITED(child_status)) {
+ putstr("# child did not exit\n");
+ return 0;
+ }
+
+ return WEXITSTATUS(child_status) && parent_result;
+ }
+}
+
+#define run_test(name) \
+ if (name()) { \
+ tests_passed++; \
+ } else { \
+ tests_failed++; \
+ putstr("not "); \
+ } \
+ putstr("ok "); \
+ putnum(++tests_run); \
+ putstr(" " #name "\n");
+
+int main(int argc, char **argv)
+{
+ int ret, i;
+
+ putstr("TAP version 13\n");
+ putstr("1..");
+ putnum(EXPECTED_TESTS);
+ putstr("\n");
+
+ putstr("# PID: ");
+ putnum(getpid());
+ putstr("\n");
+
+ /*
+ * This test is run with nolibc which doesn't support hwcap and
+ * it's probably disproportionate to implement so instead check
+ * for the default vector length configuration in /proc.
+ */
+ ret = open("/proc/sys/abi/sme_default_vector_length", O_RDONLY, 0);
+ if (ret >= 0) {
+ run_test(fork_test);
+
+ } else {
+ putstr("# SME support not present\n");
+
+ for (i = 0; i < EXPECTED_TESTS; i++) {
+ putstr("ok ");
+ putnum(i);
+ putstr(" skipped\n");
+ }
+
+ tests_skipped += EXPECTED_TESTS;
+ }
+
+ print_summary();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/fp/za-ptrace.c b/tools/testing/selftests/arm64/fp/za-ptrace.c
new file mode 100644
index 000000000000..bf6158654056
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-ptrace.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 ARM Limited.
+ */
+#include <errno.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+#include <sys/ptrace.h>
+#include <sys/types.h>
+#include <sys/uio.h>
+#include <sys/wait.h>
+#include <asm/sigcontext.h>
+#include <asm/ptrace.h>
+
+#include "../../kselftest.h"
+
+/* <linux/elf.h> and <sys/auxv.h> don't like each other, so: */
+#ifndef NT_ARM_ZA
+#define NT_ARM_ZA 0x40c
+#endif
+
+#define EXPECTED_TESTS (((SVE_VQ_MAX - SVE_VQ_MIN) + 1) * 3)
+
+static void fill_buf(char *buf, size_t size)
+{
+ int i;
+
+ for (i = 0; i < size; i++)
+ buf[i] = random();
+}
+
+static int do_child(void)
+{
+ if (ptrace(PTRACE_TRACEME, -1, NULL, NULL))
+ ksft_exit_fail_msg("PTRACE_TRACEME", strerror(errno));
+
+ if (raise(SIGSTOP))
+ ksft_exit_fail_msg("raise(SIGSTOP)", strerror(errno));
+
+ return EXIT_SUCCESS;
+}
+
+static struct user_za_header *get_za(pid_t pid, void **buf, size_t *size)
+{
+ struct user_za_header *za;
+ void *p;
+ size_t sz = sizeof(*za);
+ struct iovec iov;
+
+ while (1) {
+ if (*size < sz) {
+ p = realloc(*buf, sz);
+ if (!p) {
+ errno = ENOMEM;
+ goto error;
+ }
+
+ *buf = p;
+ *size = sz;
+ }
+
+ iov.iov_base = *buf;
+ iov.iov_len = sz;
+ if (ptrace(PTRACE_GETREGSET, pid, NT_ARM_ZA, &iov))
+ goto error;
+
+ za = *buf;
+ if (za->size <= sz)
+ break;
+
+ sz = za->size;
+ }
+
+ return za;
+
+error:
+ return NULL;
+}
+
+static int set_za(pid_t pid, const struct user_za_header *za)
+{
+ struct iovec iov;
+
+ iov.iov_base = (void *)za;
+ iov.iov_len = za->size;
+ return ptrace(PTRACE_SETREGSET, pid, NT_ARM_ZA, &iov);
+}
+
+/* Validate attempting to set the specfied VL via ptrace */
+static void ptrace_set_get_vl(pid_t child, unsigned int vl, bool *supported)
+{
+ struct user_za_header za;
+ struct user_za_header *new_za = NULL;
+ size_t new_za_size = 0;
+ int ret, prctl_vl;
+
+ *supported = false;
+
+ /* Check if the VL is supported in this process */
+ prctl_vl = prctl(PR_SME_SET_VL, vl);
+ if (prctl_vl == -1)
+ ksft_exit_fail_msg("prctl(PR_SME_SET_VL) failed: %s (%d)\n",
+ strerror(errno), errno);
+
+ /* If the VL is not supported then a supported VL will be returned */
+ *supported = (prctl_vl == vl);
+
+ /* Set the VL by doing a set with no register payload */
+ memset(&za, 0, sizeof(za));
+ za.size = sizeof(za);
+ za.vl = vl;
+ ret = set_za(child, &za);
+ if (ret != 0) {
+ ksft_test_result_fail("Failed to set VL %u\n", vl);
+ return;
+ }
+
+ /*
+ * Read back the new register state and verify that we have the
+ * same VL that we got from prctl() on ourselves.
+ */
+ if (!get_za(child, (void **)&new_za, &new_za_size)) {
+ ksft_test_result_fail("Failed to read VL %u\n", vl);
+ return;
+ }
+
+ ksft_test_result(new_za->vl = prctl_vl, "Set VL %u\n", vl);
+
+ free(new_za);
+}
+
+/* Validate attempting to set no ZA data and read it back */
+static void ptrace_set_no_data(pid_t child, unsigned int vl)
+{
+ void *read_buf = NULL;
+ struct user_za_header write_za;
+ struct user_za_header *read_za;
+ size_t read_za_size = 0;
+ int ret;
+
+ /* Set up some data and write it out */
+ memset(&write_za, 0, sizeof(write_za));
+ write_za.size = ZA_PT_ZA_OFFSET;
+ write_za.vl = vl;
+
+ ret = set_za(child, &write_za);
+ if (ret != 0) {
+ ksft_test_result_fail("Failed to set VL %u no data\n", vl);
+ return;
+ }
+
+ /* Read the data back */
+ if (!get_za(child, (void **)&read_buf, &read_za_size)) {
+ ksft_test_result_fail("Failed to read VL %u no data\n", vl);
+ return;
+ }
+ read_za = read_buf;
+
+ /* We might read more data if there's extensions we don't know */
+ if (read_za->size < write_za.size) {
+ ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n",
+ vl, write_za.size, read_za->size);
+ goto out_read;
+ }
+
+ ksft_test_result(read_za->size == write_za.size,
+ "Disabled ZA for VL %u\n", vl);
+
+out_read:
+ free(read_buf);
+}
+
+/* Validate attempting to set data and read it back */
+static void ptrace_set_get_data(pid_t child, unsigned int vl)
+{
+ void *write_buf;
+ void *read_buf = NULL;
+ struct user_za_header *write_za;
+ struct user_za_header *read_za;
+ size_t read_za_size = 0;
+ unsigned int vq = sve_vq_from_vl(vl);
+ int ret;
+ size_t data_size;
+
+ data_size = ZA_PT_SIZE(vq);
+ write_buf = malloc(data_size);
+ if (!write_buf) {
+ ksft_test_result_fail("Error allocating %d byte buffer for VL %u\n",
+ data_size, vl);
+ return;
+ }
+ write_za = write_buf;
+
+ /* Set up some data and write it out */
+ memset(write_za, 0, data_size);
+ write_za->size = data_size;
+ write_za->vl = vl;
+
+ fill_buf(write_buf + ZA_PT_ZA_OFFSET, ZA_PT_ZA_SIZE(vq));
+
+ ret = set_za(child, write_za);
+ if (ret != 0) {
+ ksft_test_result_fail("Failed to set VL %u data\n", vl);
+ goto out;
+ }
+
+ /* Read the data back */
+ if (!get_za(child, (void **)&read_buf, &read_za_size)) {
+ ksft_test_result_fail("Failed to read VL %u data\n", vl);
+ goto out;
+ }
+ read_za = read_buf;
+
+ /* We might read more data if there's extensions we don't know */
+ if (read_za->size < write_za->size) {
+ ksft_test_result_fail("VL %u wrote %d bytes, only read %d\n",
+ vl, write_za->size, read_za->size);
+ goto out_read;
+ }
+
+ ksft_test_result(memcmp(write_buf + ZA_PT_ZA_OFFSET,
+ read_buf + ZA_PT_ZA_OFFSET,
+ ZA_PT_ZA_SIZE(vq)) == 0,
+ "Data match for VL %u\n", vl);
+
+out_read:
+ free(read_buf);
+out:
+ free(write_buf);
+}
+
+static int do_parent(pid_t child)
+{
+ int ret = EXIT_FAILURE;
+ pid_t pid;
+ int status;
+ siginfo_t si;
+ unsigned int vq, vl;
+ bool vl_supported;
+
+ /* Attach to the child */
+ while (1) {
+ int sig;
+
+ pid = wait(&status);
+ if (pid == -1) {
+ perror("wait");
+ goto error;
+ }
+
+ /*
+ * This should never happen but it's hard to flag in
+ * the framework.
+ */
+ if (pid != child)
+ continue;
+
+ if (WIFEXITED(status) || WIFSIGNALED(status))
+ ksft_exit_fail_msg("Child died unexpectedly\n");
+
+ if (!WIFSTOPPED(status))
+ goto error;
+
+ sig = WSTOPSIG(status);
+
+ if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &si)) {
+ if (errno == ESRCH)
+ goto disappeared;
+
+ if (errno == EINVAL) {
+ sig = 0; /* bust group-stop */
+ goto cont;
+ }
+
+ ksft_test_result_fail("PTRACE_GETSIGINFO: %s\n",
+ strerror(errno));
+ goto error;
+ }
+
+ if (sig == SIGSTOP && si.si_code == SI_TKILL &&
+ si.si_pid == pid)
+ break;
+
+ cont:
+ if (ptrace(PTRACE_CONT, pid, NULL, sig)) {
+ if (errno == ESRCH)
+ goto disappeared;
+
+ ksft_test_result_fail("PTRACE_CONT: %s\n",
+ strerror(errno));
+ goto error;
+ }
+ }
+
+ ksft_print_msg("Parent is %d, child is %d\n", getpid(), child);
+
+ /* Step through every possible VQ */
+ for (vq = SVE_VQ_MIN; vq <= SVE_VQ_MAX; vq++) {
+ vl = sve_vl_from_vq(vq);
+
+ /* First, try to set this vector length */
+ ptrace_set_get_vl(child, vl, &vl_supported);
+
+ /* If the VL is supported validate data set/get */
+ if (vl_supported) {
+ ptrace_set_no_data(child, vl);
+ ptrace_set_get_data(child, vl);
+ } else {
+ ksft_test_result_skip("Disabled ZA for VL %u\n", vl);
+ ksft_test_result_skip("Get and set data for VL %u\n",
+ vl);
+ }
+ }
+
+ ret = EXIT_SUCCESS;
+
+error:
+ kill(child, SIGKILL);
+
+disappeared:
+ return ret;
+}
+
+int main(void)
+{
+ int ret = EXIT_SUCCESS;
+ pid_t child;
+
+ srandom(getpid());
+
+ ksft_print_header();
+
+ if (!(getauxval(AT_HWCAP2) & HWCAP2_SME)) {
+ ksft_set_plan(1);
+ ksft_exit_skip("SME not available\n");
+ }
+
+ ksft_set_plan(EXPECTED_TESTS);
+
+ child = fork();
+ if (!child)
+ return do_child();
+
+ if (do_parent(child))
+ ret = EXIT_FAILURE;
+
+ ksft_print_cnts();
+
+ return ret;
+}
diff --git a/tools/testing/selftests/arm64/fp/za-stress b/tools/testing/selftests/arm64/fp/za-stress
new file mode 100644
index 000000000000..5ac386b55b95
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-stress
@@ -0,0 +1,59 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+# Copyright (C) 2015-2019 ARM Limited.
+# Original author: Dave Martin <Dave.Martin@arm.com>
+
+set -ue
+
+NR_CPUS=`nproc`
+
+pids=
+logs=
+
+cleanup () {
+ trap - INT TERM CHLD
+ set +e
+
+ if [ -n "$pids" ]; then
+ kill $pids
+ wait $pids
+ pids=
+ fi
+
+ if [ -n "$logs" ]; then
+ cat $logs
+ rm $logs
+ logs=
+ fi
+}
+
+interrupt () {
+ cleanup
+ exit 0
+}
+
+child_died () {
+ cleanup
+ exit 1
+}
+
+trap interrupt INT TERM EXIT
+
+for x in `seq 0 $((NR_CPUS * 4))`; do
+ log=`mktemp`
+ logs=$logs\ $log
+ ./za-test >$log &
+ pids=$pids\ $!
+done
+
+# Wait for all child processes to be created:
+sleep 10
+
+while :; do
+ kill -USR1 $pids
+done &
+pids=$pids\ $!
+
+wait
+
+exit 1
diff --git a/tools/testing/selftests/arm64/fp/za-test.S b/tools/testing/selftests/arm64/fp/za-test.S
new file mode 100644
index 000000000000..9ab6f9cd9623
--- /dev/null
+++ b/tools/testing/selftests/arm64/fp/za-test.S
@@ -0,0 +1,388 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2021 ARM Limited.
+// Original author: Mark Brown <broonie@kernel.org>
+//
+// Scalable Matrix Extension ZA context switch test
+// Repeatedly writes unique test patterns into each ZA tile
+// and reads them back to verify integrity.
+//
+// for x in `seq 1 NR_CPUS`; do sve-test & pids=$pids\ $! ; done
+// (leave it running for as long as you want...)
+// kill $pids
+
+#include <asm/unistd.h>
+#include "assembler.h"
+#include "asm-offsets.h"
+#include "sme-inst.h"
+
+.arch_extension sve
+
+#define MAXVL 2048
+#define MAXVL_B (MAXVL / 8)
+
+// Declare some storage space to shadow ZA register contents and a
+// scratch buffer for a vector.
+.pushsection .text
+.data
+.align 4
+zaref:
+ .space MAXVL_B * MAXVL_B
+scratch:
+ .space MAXVL_B
+.popsection
+
+// Trivial memory copy: copy x2 bytes, starting at address x1, to address x0.
+// Clobbers x0-x3
+function memcpy
+ cmp x2, #0
+ b.eq 1f
+0: ldrb w3, [x1], #1
+ strb w3, [x0], #1
+ subs x2, x2, #1
+ b.ne 0b
+1: ret
+endfunction
+
+// Generate a test pattern for storage in ZA
+// x0: pid
+// x1: row in ZA
+// x2: generation
+
+// These values are used to constuct a 32-bit pattern that is repeated in the
+// scratch buffer as many times as will fit:
+// bits 31:28 generation number (increments once per test_loop)
+// bits 27:16 pid
+// bits 15: 8 row number
+// bits 7: 0 32-bit lane index
+
+function pattern
+ mov w3, wzr
+ bfi w3, w0, #16, #12 // PID
+ bfi w3, w1, #8, #8 // Row
+ bfi w3, w2, #28, #4 // Generation
+
+ ldr x0, =scratch
+ mov w1, #MAXVL_B / 4
+
+0: str w3, [x0], #4
+ add w3, w3, #1 // Lane
+ subs w1, w1, #1
+ b.ne 0b
+
+ ret
+endfunction
+
+// Get the address of shadow data for ZA horizontal vector xn
+.macro _adrza xd, xn, nrtmp
+ ldr \xd, =zaref
+ rdsvl \nrtmp, 1
+ madd \xd, x\nrtmp, \xn, \xd
+.endm
+
+// Set up test pattern in a ZA horizontal vector
+// x0: pid
+// x1: row number
+// x2: generation
+function setup_za
+ mov x4, x30
+ mov x12, x1 // Use x12 for vector select
+
+ bl pattern // Get pattern in scratch buffer
+ _adrza x0, x12, 2 // Shadow buffer pointer to x0 and x5
+ mov x5, x0
+ ldr x1, =scratch
+ bl memcpy // length set up in x2 by _adrza
+
+ _ldr_za 12, 5 // load vector w12 from pointer x5
+
+ ret x4
+endfunction
+
+// Trivial memory compare: compare x2 bytes starting at address x0 with
+// bytes starting at address x1.
+// Returns only if all bytes match; otherwise, the program is aborted.
+// Clobbers x0-x5.
+function memcmp
+ cbz x2, 2f
+
+ stp x0, x1, [sp, #-0x20]!
+ str x2, [sp, #0x10]
+
+ mov x5, #0
+0: ldrb w3, [x0, x5]
+ ldrb w4, [x1, x5]
+ add x5, x5, #1
+ cmp w3, w4
+ b.ne 1f
+ subs x2, x2, #1
+ b.ne 0b
+
+1: ldr x2, [sp, #0x10]
+ ldp x0, x1, [sp], #0x20
+ b.ne barf
+
+2: ret
+endfunction
+
+// Verify that a ZA vector matches its shadow in memory, else abort
+// x0: row number
+// Clobbers x0-x7 and x12.
+function check_za
+ mov x3, x30
+
+ mov x12, x0
+ _adrza x5, x0, 6 // pointer to expected value in x5
+ mov x4, x0
+ ldr x7, =scratch // x7 is scratch
+
+ mov x0, x7 // Poison scratch
+ mov x1, x6
+ bl memfill_ae
+
+ _str_za 12, 7 // save vector w12 to pointer x7
+
+ mov x0, x5
+ mov x1, x7
+ mov x2, x6
+ mov x30, x3
+ b memcmp
+endfunction
+
+// Any SME register modified here can cause corruption in the main
+// thread -- but *only* the locations modified here.
+function irritator_handler
+ // Increment the irritation signal count (x23):
+ ldr x0, [x2, #ucontext_regs + 8 * 23]
+ add x0, x0, #1
+ str x0, [x2, #ucontext_regs + 8 * 23]
+
+ // Corrupt some random ZA data
+#if 0
+ adr x0, .text + (irritator_handler - .text) / 16 * 16
+ movi v0.8b, #1
+ movi v9.16b, #2
+ movi v31.8b, #3
+#endif
+
+ ret
+endfunction
+
+function terminate_handler
+ mov w21, w0
+ mov x20, x2
+
+ puts "Terminated by signal "
+ mov w0, w21
+ bl putdec
+ puts ", no error, iterations="
+ ldr x0, [x20, #ucontext_regs + 8 * 22]
+ bl putdec
+ puts ", signals="
+ ldr x0, [x20, #ucontext_regs + 8 * 23]
+ bl putdecn
+
+ mov x0, #0
+ mov x8, #__NR_exit
+ svc #0
+endfunction
+
+// w0: signal number
+// x1: sa_action
+// w2: sa_flags
+// Clobbers x0-x6,x8
+function setsignal
+ str x30, [sp, #-((sa_sz + 15) / 16 * 16 + 16)]!
+
+ mov w4, w0
+ mov x5, x1
+ mov w6, w2
+
+ add x0, sp, #16
+ mov x1, #sa_sz
+ bl memclr
+
+ mov w0, w4
+ add x1, sp, #16
+ str w6, [x1, #sa_flags]
+ str x5, [x1, #sa_handler]
+ mov x2, #0
+ mov x3, #sa_mask_sz
+ mov x8, #__NR_rt_sigaction
+ svc #0
+
+ cbz w0, 1f
+
+ puts "sigaction failure\n"
+ b .Labort
+
+1: ldr x30, [sp], #((sa_sz + 15) / 16 * 16 + 16)
+ ret
+endfunction
+
+// Main program entry point
+.globl _start
+function _start
+_start:
+ puts "Streaming mode "
+ smstart_za
+
+ // Sanity-check and report the vector length
+
+ rdsvl 19, 8
+ cmp x19, #128
+ b.lo 1f
+ cmp x19, #2048
+ b.hi 1f
+ tst x19, #(8 - 1)
+ b.eq 2f
+
+1: puts "bad vector length: "
+ mov x0, x19
+ bl putdecn
+ b .Labort
+
+2: puts "vector length:\t"
+ mov x0, x19
+ bl putdec
+ puts " bits\n"
+
+ // Obtain our PID, to ensure test pattern uniqueness between processes
+ mov x8, #__NR_getpid
+ svc #0
+ mov x20, x0
+
+ puts "PID:\t"
+ mov x0, x20
+ bl putdecn
+
+ mov x23, #0 // Irritation signal count
+
+ mov w0, #SIGINT
+ adr x1, terminate_handler
+ mov w2, #SA_SIGINFO
+ bl setsignal
+
+ mov w0, #SIGTERM
+ adr x1, terminate_handler
+ mov w2, #SA_SIGINFO
+ bl setsignal
+
+ mov w0, #SIGUSR1
+ adr x1, irritator_handler
+ mov w2, #SA_SIGINFO
+ orr w2, w2, #SA_NODEFER
+ bl setsignal
+
+ mov x22, #0 // generation number, increments per iteration
+.Ltest_loop:
+ rdsvl 0, 8
+ cmp x0, x19
+ b.ne vl_barf
+
+ rdsvl 21, 1 // Set up ZA & shadow with test pattern
+0: mov x0, x20
+ sub x1, x21, #1
+ mov x2, x22
+ bl setup_za
+ subs x21, x21, #1
+ b.ne 0b
+
+ and x8, x22, #127 // Every 128 interations...
+ cbz x8, 0f
+ mov x8, #__NR_getpid // (otherwise minimal syscall)
+ b 1f
+0:
+ mov x8, #__NR_sched_yield // ...encourage preemption
+1:
+ svc #0
+
+ mrs x0, S3_3_C4_C2_2 // SVCR should have ZA=1,SM=0
+ and x1, x0, #3
+ cmp x1, #2
+ b.ne svcr_barf
+
+ rdsvl 21, 1 // Verify that the data made it through
+ rdsvl 24, 1 // Verify that the data made it through
+0: sub x0, x24, x21
+ bl check_za
+ subs x21, x21, #1
+ bne 0b
+
+ add x22, x22, #1 // Everything still working
+ b .Ltest_loop
+
+.Labort:
+ mov x0, #0
+ mov x1, #SIGABRT
+ mov x8, #__NR_kill
+ svc #0
+endfunction
+
+function barf
+// fpsimd.c acitivty log dump hack
+// ldr w0, =0xdeadc0de
+// mov w8, #__NR_exit
+// svc #0
+// end hack
+ smstop
+ mov x10, x0 // expected data
+ mov x11, x1 // actual data
+ mov x12, x2 // data size
+
+ puts "Mismatch: PID="
+ mov x0, x20
+ bl putdec
+ puts ", iteration="
+ mov x0, x22
+ bl putdec
+ puts ", row="
+ mov x0, x21
+ bl putdecn
+ puts "\tExpected ["
+ mov x0, x10
+ mov x1, x12
+ bl dumphex
+ puts "]\n\tGot ["
+ mov x0, x11
+ mov x1, x12
+ bl dumphex
+ puts "]\n"
+
+ mov x8, #__NR_getpid
+ svc #0
+// fpsimd.c acitivty log dump hack
+// ldr w0, =0xdeadc0de
+// mov w8, #__NR_exit
+// svc #0
+// ^ end of hack
+ mov x1, #SIGABRT
+ mov x8, #__NR_kill
+ svc #0
+// mov x8, #__NR_exit
+// mov x1, #1
+// svc #0
+endfunction
+
+function vl_barf
+ mov x10, x0
+
+ puts "Bad active VL: "
+ mov x0, x10
+ bl putdecn
+
+ mov x8, #__NR_exit
+ mov x1, #1
+ svc #0
+endfunction
+
+function svcr_barf
+ mov x10, x0
+
+ puts "Bad SVCR: "
+ mov x0, x10
+ bl putdecn
+
+ mov x8, #__NR_exit
+ mov x1, #1
+ svc #0
+endfunction
diff --git a/tools/testing/selftests/arm64/mte/.gitignore b/tools/testing/selftests/arm64/mte/.gitignore
index d1fe4ddf1669..052d0f9f92b3 100644
--- a/tools/testing/selftests/arm64/mte/.gitignore
+++ b/tools/testing/selftests/arm64/mte/.gitignore
@@ -3,5 +3,6 @@ check_gcr_el1_cswitch
check_tags_inclusion
check_child_memory
check_mmap_options
+check_prctl
check_ksm_options
check_user_mem
diff --git a/tools/testing/selftests/arm64/mte/check_child_memory.c b/tools/testing/selftests/arm64/mte/check_child_memory.c
index 43bd94f853ba..7597fc632cad 100644
--- a/tools/testing/selftests/arm64/mte/check_child_memory.c
+++ b/tools/testing/selftests/arm64/mte/check_child_memory.c
@@ -85,9 +85,9 @@ static int check_child_memory_mapping(int mem_type, int mode, int mapping)
{
char *ptr;
int run, result;
- int item = sizeof(sizes)/sizeof(int);
+ int item = ARRAY_SIZE(sizes);
- item = sizeof(sizes)/sizeof(int);
+ item = ARRAY_SIZE(sizes);
mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
for (run = 0; run < item; run++) {
ptr = (char *)mte_allocate_memory_tag_range(sizes[run], mem_type, mapping,
@@ -107,7 +107,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping)
{
char *ptr, *map_ptr;
int run, fd, map_size, result = KSFT_PASS;
- int total = sizeof(sizes)/sizeof(int);
+ int total = ARRAY_SIZE(sizes);
mte_switch_mode(mode, MTE_ALLOW_NON_ZERO_TAG);
for (run = 0; run < total; run++) {
@@ -144,7 +144,7 @@ static int check_child_file_mapping(int mem_type, int mode, int mapping)
int main(int argc, char *argv[])
{
int err;
- int item = sizeof(sizes)/sizeof(int);
+ int item = ARRAY_SIZE(sizes);
page_size = getpagesize();
if (!page_size) {
diff --git a/tools/testing/selftests/arm64/mte/check_prctl.c b/tools/testing/selftests/arm64/mte/check_prctl.c
new file mode 100644
index 000000000000..f139a33a43ef
--- /dev/null
+++ b/tools/testing/selftests/arm64/mte/check_prctl.c
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2022 ARM Limited
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+#include <sys/auxv.h>
+#include <sys/prctl.h>
+
+#include <asm/hwcap.h>
+
+#include "kselftest.h"
+
+static int set_tagged_addr_ctrl(int val)
+{
+ int ret;
+
+ ret = prctl(PR_SET_TAGGED_ADDR_CTRL, val, 0, 0, 0);
+ if (ret < 0)
+ ksft_print_msg("PR_SET_TAGGED_ADDR_CTRL: failed %d %d (%s)\n",
+ ret, errno, strerror(errno));
+ return ret;
+}
+
+static int get_tagged_addr_ctrl(void)
+{
+ int ret;
+
+ ret = prctl(PR_GET_TAGGED_ADDR_CTRL, 0, 0, 0, 0);
+ if (ret < 0)
+ ksft_print_msg("PR_GET_TAGGED_ADDR_CTRL failed: %d %d (%s)\n",
+ ret, errno, strerror(errno));
+ return ret;
+}
+
+/*
+ * Read the current mode without having done any configuration, should
+ * run first.
+ */
+void check_basic_read(void)
+{
+ int ret;
+
+ ret = get_tagged_addr_ctrl();
+ if (ret < 0) {
+ ksft_test_result_fail("check_basic_read\n");
+ return;
+ }
+
+ if (ret & PR_MTE_TCF_SYNC)
+ ksft_print_msg("SYNC enabled\n");
+ if (ret & PR_MTE_TCF_ASYNC)
+ ksft_print_msg("ASYNC enabled\n");
+
+ /* Any configuration is valid */
+ ksft_test_result_pass("check_basic_read\n");
+}
+
+/*
+ * Attempt to set a specified combination of modes.
+ */
+void set_mode_test(const char *name, int hwcap2, int mask)
+{
+ int ret;
+
+ if ((getauxval(AT_HWCAP2) & hwcap2) != hwcap2) {
+ ksft_test_result_skip("%s\n", name);
+ return;
+ }
+
+ ret = set_tagged_addr_ctrl(mask);
+ if (ret < 0) {
+ ksft_test_result_fail("%s\n", name);
+ return;
+ }
+
+ ret = get_tagged_addr_ctrl();
+ if (ret < 0) {
+ ksft_test_result_fail("%s\n", name);
+ return;
+ }
+
+ if ((ret & PR_MTE_TCF_MASK) == mask) {
+ ksft_test_result_pass("%s\n", name);
+ } else {
+ ksft_print_msg("Got %x, expected %x\n",
+ (ret & PR_MTE_TCF_MASK), mask);
+ ksft_test_result_fail("%s\n", name);
+ }
+}
+
+struct mte_mode {
+ int mask;
+ int hwcap2;
+ const char *name;
+} mte_modes[] = {
+ { PR_MTE_TCF_NONE, 0, "NONE" },
+ { PR_MTE_TCF_SYNC, HWCAP2_MTE, "SYNC" },
+ { PR_MTE_TCF_ASYNC, HWCAP2_MTE, "ASYNC" },
+ { PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC, HWCAP2_MTE, "SYNC+ASYNC" },
+};
+
+int main(void)
+{
+ int i;
+
+ ksft_print_header();
+ ksft_set_plan(5);
+
+ check_basic_read();
+ for (i = 0; i < ARRAY_SIZE(mte_modes); i++)
+ set_mode_test(mte_modes[i].name, mte_modes[i].hwcap2,
+ mte_modes[i].mask);
+
+ ksft_print_cnts();
+
+ return 0;
+}
diff --git a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
index deaef1f61076..2b1425b92b69 100644
--- a/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
+++ b/tools/testing/selftests/arm64/mte/check_tags_inclusion.c
@@ -23,10 +23,13 @@ static int verify_mte_pointer_validity(char *ptr, int mode)
{
mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE);
/* Check the validity of the tagged pointer */
- memset((void *)ptr, '1', BUFFER_SIZE);
+ memset(ptr, '1', BUFFER_SIZE);
mte_wait_after_trig();
- if (cur_mte_cxt.fault_valid)
+ if (cur_mte_cxt.fault_valid) {
+ ksft_print_msg("Unexpected fault recorded for %p-%p in mode %x\n",
+ ptr, ptr + BUFFER_SIZE, mode);
return KSFT_FAIL;
+ }
/* Proceed further for nonzero tags */
if (!MT_FETCH_TAG((uintptr_t)ptr))
return KSFT_PASS;
@@ -34,27 +37,32 @@ static int verify_mte_pointer_validity(char *ptr, int mode)
/* Check the validity outside the range */
ptr[BUFFER_SIZE] = '2';
mte_wait_after_trig();
- if (!cur_mte_cxt.fault_valid)
+ if (!cur_mte_cxt.fault_valid) {
+ ksft_print_msg("No valid fault recorded for %p in mode %x\n",
+ ptr, mode);
return KSFT_FAIL;
- else
+ } else {
return KSFT_PASS;
+ }
}
static int check_single_included_tags(int mem_type, int mode)
{
char *ptr;
- int tag, run, result = KSFT_PASS;
+ int tag, run, ret, result = KSFT_PASS;
- ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
+ ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE,
mem_type, false) != KSFT_PASS)
return KSFT_FAIL;
for (tag = 0; (tag < MT_TAG_COUNT) && (result == KSFT_PASS); tag++) {
- mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag));
+ ret = mte_switch_mode(mode, MT_INCLUDE_VALID_TAG(tag));
+ if (ret != 0)
+ result = KSFT_FAIL;
/* Try to catch a excluded tag by a number of tries. */
for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
- ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
+ ptr = mte_insert_tags(ptr, BUFFER_SIZE);
/* Check tag value */
if (MT_FETCH_TAG((uintptr_t)ptr) == tag) {
ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n",
@@ -66,7 +74,7 @@ static int check_single_included_tags(int mem_type, int mode)
result = verify_mte_pointer_validity(ptr, mode);
}
}
- mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
+ mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
return result;
}
@@ -76,7 +84,7 @@ static int check_multiple_included_tags(int mem_type, int mode)
int tag, run, result = KSFT_PASS;
unsigned long excl_mask = 0;
- ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
+ ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE,
mem_type, false) != KSFT_PASS)
return KSFT_FAIL;
@@ -86,7 +94,7 @@ static int check_multiple_included_tags(int mem_type, int mode)
mte_switch_mode(mode, MT_INCLUDE_VALID_TAGS(excl_mask));
/* Try to catch a excluded tag by a number of tries. */
for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
- ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
+ ptr = mte_insert_tags(ptr, BUFFER_SIZE);
/* Check tag value */
if (MT_FETCH_TAG((uintptr_t)ptr) < tag) {
ksft_print_msg("FAIL: wrong tag = 0x%x with include mask=0x%x\n",
@@ -98,21 +106,23 @@ static int check_multiple_included_tags(int mem_type, int mode)
result = verify_mte_pointer_validity(ptr, mode);
}
}
- mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
+ mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
return result;
}
static int check_all_included_tags(int mem_type, int mode)
{
char *ptr;
- int run, result = KSFT_PASS;
+ int run, ret, result = KSFT_PASS;
- ptr = (char *)mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
+ ptr = mte_allocate_memory(BUFFER_SIZE + MT_GRANULE_SIZE, mem_type, 0, false);
if (check_allocated_memory(ptr, BUFFER_SIZE + MT_GRANULE_SIZE,
mem_type, false) != KSFT_PASS)
return KSFT_FAIL;
- mte_switch_mode(mode, MT_INCLUDE_TAG_MASK);
+ ret = mte_switch_mode(mode, MT_INCLUDE_TAG_MASK);
+ if (ret != 0)
+ return KSFT_FAIL;
/* Try to catch a excluded tag by a number of tries. */
for (run = 0; (run < RUNS) && (result == KSFT_PASS); run++) {
ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
@@ -122,20 +132,22 @@ static int check_all_included_tags(int mem_type, int mode)
*/
result = verify_mte_pointer_validity(ptr, mode);
}
- mte_free_memory_tag_range((void *)ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
+ mte_free_memory_tag_range(ptr, BUFFER_SIZE, mem_type, 0, MT_GRANULE_SIZE);
return result;
}
static int check_none_included_tags(int mem_type, int mode)
{
char *ptr;
- int run;
+ int run, ret;
- ptr = (char *)mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false);
+ ptr = mte_allocate_memory(BUFFER_SIZE, mem_type, 0, false);
if (check_allocated_memory(ptr, BUFFER_SIZE, mem_type, false) != KSFT_PASS)
return KSFT_FAIL;
- mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK);
+ ret = mte_switch_mode(mode, MT_EXCLUDE_TAG_MASK);
+ if (ret != 0)
+ return KSFT_FAIL;
/* Try to catch a excluded tag by a number of tries. */
for (run = 0; run < RUNS; run++) {
ptr = (char *)mte_insert_tags(ptr, BUFFER_SIZE);
@@ -147,12 +159,12 @@ static int check_none_included_tags(int mem_type, int mode)
}
mte_initialize_current_context(mode, (uintptr_t)ptr, BUFFER_SIZE);
/* Check the write validity of the untagged pointer */
- memset((void *)ptr, '1', BUFFER_SIZE);
+ memset(ptr, '1', BUFFER_SIZE);
mte_wait_after_trig();
if (cur_mte_cxt.fault_valid)
break;
}
- mte_free_memory((void *)ptr, BUFFER_SIZE, mem_type, false);
+ mte_free_memory(ptr, BUFFER_SIZE, mem_type, false);
if (cur_mte_cxt.fault_valid)
return KSFT_FAIL;
else
diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.c b/tools/testing/selftests/arm64/mte/mte_common_util.c
index 0328a1e08f65..00ffd34c66d3 100644
--- a/tools/testing/selftests/arm64/mte/mte_common_util.c
+++ b/tools/testing/selftests/arm64/mte/mte_common_util.c
@@ -37,6 +37,10 @@ void mte_default_handler(int signum, siginfo_t *si, void *uc)
if (si->si_code == SEGV_MTEAERR) {
if (cur_mte_cxt.trig_si_code == si->si_code)
cur_mte_cxt.fault_valid = true;
+ else
+ ksft_print_msg("Got unexpected SEGV_MTEAERR at pc=$lx, fault addr=%lx\n",
+ ((ucontext_t *)uc)->uc_mcontext.pc,
+ addr);
return;
}
/* Compare the context for precise error */
@@ -124,13 +128,16 @@ static void *__mte_allocate_memory_range(size_t size, int mem_type, int mapping,
int prot_flag, map_flag;
size_t entire_size = size + range_before + range_after;
- if (mem_type != USE_MALLOC && mem_type != USE_MMAP &&
- mem_type != USE_MPROTECT) {
+ switch (mem_type) {
+ case USE_MALLOC:
+ return malloc(entire_size) + range_before;
+ case USE_MMAP:
+ case USE_MPROTECT:
+ break;
+ default:
ksft_print_msg("FAIL: Invalid allocate request\n");
return NULL;
}
- if (mem_type == USE_MALLOC)
- return malloc(entire_size) + range_before;
prot_flag = PROT_READ | PROT_WRITE;
if (mem_type == USE_MMAP)
@@ -269,18 +276,33 @@ int mte_switch_mode(int mte_option, unsigned long incl_mask)
{
unsigned long en = 0;
- if (!(mte_option == MTE_SYNC_ERR || mte_option == MTE_ASYNC_ERR ||
- mte_option == MTE_NONE_ERR || incl_mask <= MTE_ALLOW_NON_ZERO_TAG)) {
- ksft_print_msg("FAIL: Invalid mte config option\n");
+ switch (mte_option) {
+ case MTE_NONE_ERR:
+ case MTE_SYNC_ERR:
+ case MTE_ASYNC_ERR:
+ break;
+ default:
+ ksft_print_msg("FAIL: Invalid MTE option %x\n", mte_option);
+ return -EINVAL;
+ }
+
+ if (incl_mask & ~MT_INCLUDE_TAG_MASK) {
+ ksft_print_msg("FAIL: Invalid incl_mask %lx\n", incl_mask);
return -EINVAL;
}
+
en = PR_TAGGED_ADDR_ENABLE;
- if (mte_option == MTE_SYNC_ERR)
+ switch (mte_option) {
+ case MTE_SYNC_ERR:
en |= PR_MTE_TCF_SYNC;
- else if (mte_option == MTE_ASYNC_ERR)
+ break;
+ case MTE_ASYNC_ERR:
en |= PR_MTE_TCF_ASYNC;
- else if (mte_option == MTE_NONE_ERR)
+ break;
+ case MTE_NONE_ERR:
en |= PR_MTE_TCF_NONE;
+ break;
+ }
en |= (incl_mask << PR_MTE_TAG_SHIFT);
/* Enable address tagging ABI, mte error reporting mode and tag inclusion mask. */
diff --git a/tools/testing/selftests/arm64/mte/mte_common_util.h b/tools/testing/selftests/arm64/mte/mte_common_util.h
index 195a7d1879e6..2d3e71724e55 100644
--- a/tools/testing/selftests/arm64/mte/mte_common_util.h
+++ b/tools/testing/selftests/arm64/mte/mte_common_util.h
@@ -75,10 +75,21 @@ unsigned int mte_get_pstate_tco(void);
/* Test framework static inline functions/macros */
static inline void evaluate_test(int err, const char *msg)
{
- if (err == KSFT_PASS)
+ switch (err) {
+ case KSFT_PASS:
ksft_test_result_pass(msg);
- else if (err == KSFT_FAIL)
+ break;
+ case KSFT_FAIL:
ksft_test_result_fail(msg);
+ break;
+ case KSFT_SKIP:
+ ksft_test_result_skip(msg);
+ break;
+ default:
+ ksft_test_result_error("Unknown return code %d from %s",
+ err, msg);
+ break;
+ }
}
static inline int check_allocated_memory(void *ptr, size_t size,
diff --git a/tools/testing/selftests/arm64/signal/.gitignore b/tools/testing/selftests/arm64/signal/.gitignore
index c1742755abb9..e8d2b57f73ec 100644
--- a/tools/testing/selftests/arm64/signal/.gitignore
+++ b/tools/testing/selftests/arm64/signal/.gitignore
@@ -1,5 +1,8 @@
# SPDX-License-Identifier: GPL-2.0-only
mangle_*
fake_sigreturn_*
+sme_*
+ssve_*
sve_*
+za_*
!*.[ch]
diff --git a/tools/testing/selftests/arm64/signal/test_signals.h b/tools/testing/selftests/arm64/signal/test_signals.h
index f909b70d9e98..c70fdec7d7c4 100644
--- a/tools/testing/selftests/arm64/signal/test_signals.h
+++ b/tools/testing/selftests/arm64/signal/test_signals.h
@@ -34,11 +34,15 @@
enum {
FSSBS_BIT,
FSVE_BIT,
+ FSME_BIT,
+ FSME_FA64_BIT,
FMAX_END
};
#define FEAT_SSBS (1UL << FSSBS_BIT)
#define FEAT_SVE (1UL << FSVE_BIT)
+#define FEAT_SME (1UL << FSME_BIT)
+#define FEAT_SME_FA64 (1UL << FSME_FA64_BIT)
/*
* A descriptor used to describe and configure a test case.
diff --git a/tools/testing/selftests/arm64/signal/test_signals_utils.c b/tools/testing/selftests/arm64/signal/test_signals_utils.c
index 5743897984b0..b588d10afd5b 100644
--- a/tools/testing/selftests/arm64/signal/test_signals_utils.c
+++ b/tools/testing/selftests/arm64/signal/test_signals_utils.c
@@ -27,6 +27,8 @@ static int sig_copyctx = SIGTRAP;
static char const *const feats_names[FMAX_END] = {
" SSBS ",
" SVE ",
+ " SME ",
+ " FA64 ",
};
#define MAX_FEATS_SZ 128
@@ -268,6 +270,10 @@ int test_init(struct tdescr *td)
td->feats_supported |= FEAT_SSBS;
if (getauxval(AT_HWCAP) & HWCAP_SVE)
td->feats_supported |= FEAT_SVE;
+ if (getauxval(AT_HWCAP2) & HWCAP2_SME)
+ td->feats_supported |= FEAT_SME;
+ if (getauxval(AT_HWCAP2) & HWCAP2_SME_FA64)
+ td->feats_supported |= FEAT_SME_FA64;
if (feats_ok(td)) {
if (td->feats_required & td->feats_supported)
fprintf(stderr,
diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
new file mode 100644
index 000000000000..7ed762b7202f
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Attempt to change the streaming SVE vector length in a signal
+ * handler, this is not supported and is expected to segfault.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+ int vq, vl;
+
+ /*
+ * Enumerate up to SVE_VQ_MAX vector lengths
+ */
+ for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+ vl = prctl(PR_SVE_SET_VL, vq * 16);
+ if (vl == -1)
+ return false;
+
+ vl &= PR_SME_VL_LEN_MASK;
+
+ /* Skip missing VLs */
+ vq = sve_vq_from_vl(vl);
+
+ vls[nvls++] = vl;
+ }
+
+ /* We need at least two VLs */
+ if (nvls < 2) {
+ fprintf(stderr, "Only %d VL supported\n", nvls);
+ return false;
+ }
+
+ return true;
+}
+
+static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
+ siginfo_t *si, ucontext_t *uc)
+{
+ size_t resv_sz, offset;
+ struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+ struct sve_context *sve;
+
+ /* Get a signal context with a SME ZA frame in it */
+ if (!get_current_context(td, &sf.uc))
+ return 1;
+
+ resv_sz = GET_SF_RESV_SIZE(sf);
+ head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+ if (!head) {
+ fprintf(stderr, "No SVE context\n");
+ return 1;
+ }
+
+ if (head->size != sizeof(struct sve_context)) {
+ fprintf(stderr, "Register data present, aborting\n");
+ return 1;
+ }
+
+ sve = (struct sve_context *)head;
+
+ /* No changes are supported; init left us at minimum VL so go to max */
+ fprintf(stderr, "Attempting to change VL from %d to %d\n",
+ sve->vl, vls[0]);
+ sve->vl = vls[0];
+
+ fake_sigreturn(&sf, sizeof(sf), 0);
+
+ return 1;
+}
+
+struct tdescr tde = {
+ .name = "FAKE_SIGRETURN_SSVE_CHANGE",
+ .descr = "Attempt to change Streaming SVE VL",
+ .feats_required = FEAT_SME,
+ .sig_ok = SIGSEGV,
+ .timeout = 3,
+ .init = sme_get_vls,
+ .run = fake_sigreturn_ssve_change_vl,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c
new file mode 100644
index 000000000000..f9d76ae32bba
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_no_sm.c
@@ -0,0 +1,38 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using a streaming mode instruction without enabling it
+ * generates a SIGILL.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+int sme_trap_no_sm_trigger(struct tdescr *td)
+{
+ /* SMSTART ZA ; ADDHA ZA0.S, P0/M, P0/M, Z0.S */
+ asm volatile(".inst 0xd503457f ; .inst 0xc0900000");
+
+ return 0;
+}
+
+int sme_trap_no_sm_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+ return 1;
+}
+
+struct tdescr tde = {
+ .name = "SME trap without SM",
+ .descr = "Check that we get a SIGILL if we use streaming mode without enabling it",
+ .timeout = 3,
+ .feats_required = FEAT_SME, /* We need a SMSTART ZA */
+ .sanity_disabled = true,
+ .trigger = sme_trap_no_sm_trigger,
+ .run = sme_trap_no_sm_run,
+ .sig_ok = SIGILL,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c
new file mode 100644
index 000000000000..e469ae5348e3
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_non_streaming.c
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that using an instruction not supported in streaming mode
+ * traps when in streaming mode.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+int sme_trap_non_streaming_trigger(struct tdescr *td)
+{
+ /*
+ * The framework will handle SIGILL so we need to exit SM to
+ * stop any other code triggering a further SIGILL down the
+ * line from using a streaming-illegal instruction.
+ */
+ asm volatile(".inst 0xd503437f; /* SMSTART ZA */ \
+ cnt v0.16b, v0.16b; \
+ .inst 0xd503447f /* SMSTOP ZA */");
+
+ return 0;
+}
+
+int sme_trap_non_streaming_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+ return 1;
+}
+
+struct tdescr tde = {
+ .name = "SME SM trap unsupported instruction",
+ .descr = "Check that we get a SIGILL if we use an unsupported instruction in streaming mode",
+ .feats_required = FEAT_SME,
+ .feats_incompatible = FEAT_SME_FA64,
+ .timeout = 3,
+ .sanity_disabled = true,
+ .trigger = sme_trap_non_streaming_trigger,
+ .run = sme_trap_non_streaming_run,
+ .sig_ok = SIGILL,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c
new file mode 100644
index 000000000000..3a7747af4715
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_trap_za.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that accessing ZA without enabling it generates a SIGILL.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+int sme_trap_za_trigger(struct tdescr *td)
+{
+ /* ZERO ZA */
+ asm volatile(".inst 0xc00800ff");
+
+ return 0;
+}
+
+int sme_trap_za_run(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+ return 1;
+}
+
+struct tdescr tde = {
+ .name = "SME ZA trap",
+ .descr = "Check that we get a SIGILL if we access ZA without enabling",
+ .timeout = 3,
+ .sanity_disabled = true,
+ .trigger = sme_trap_za_trigger,
+ .run = sme_trap_za_run,
+ .sig_ok = SIGILL,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/sme_vl.c b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
new file mode 100644
index 000000000000..13ff3b35cbaf
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/sme_vl.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Check that the SME vector length reported in signal contexts is the
+ * expected one.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+unsigned int vl;
+
+static bool get_sme_vl(struct tdescr *td)
+{
+ int ret = prctl(PR_SME_GET_VL);
+ if (ret == -1)
+ return false;
+
+ vl = ret;
+
+ return true;
+}
+
+static int sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+ size_t resv_sz, offset;
+ struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+ struct za_context *za;
+
+ /* Get a signal context which should have a ZA frame in it */
+ if (!get_current_context(td, &sf.uc))
+ return 1;
+
+ resv_sz = GET_SF_RESV_SIZE(sf);
+ head = get_header(head, ZA_MAGIC, resv_sz, &offset);
+ if (!head) {
+ fprintf(stderr, "No ZA context\n");
+ return 1;
+ }
+ za = (struct za_context *)head;
+
+ if (za->vl != vl) {
+ fprintf(stderr, "ZA sigframe VL %u, expected %u\n",
+ za->vl, vl);
+ return 1;
+ } else {
+ fprintf(stderr, "got expected VL %u\n", vl);
+ }
+
+ td->pass = 1;
+
+ return 0;
+}
+
+struct tdescr tde = {
+ .name = "SME VL",
+ .descr = "Check that we get the right SME VL reported",
+ .feats_required = FEAT_SME,
+ .timeout = 3,
+ .init = get_sme_vl,
+ .run = sme_vl,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
new file mode 100644
index 000000000000..9022a6cab4b3
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that the streaming SVE register context in signal frames is
+ * set up as expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+ int vq, vl;
+
+ /*
+ * Enumerate up to SVE_VQ_MAX vector lengths
+ */
+ for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+ vl = prctl(PR_SME_SET_VL, vq * 16);
+ if (vl == -1)
+ return false;
+
+ vl &= PR_SME_VL_LEN_MASK;
+
+ /* Skip missing VLs */
+ vq = sve_vq_from_vl(vl);
+
+ vls[nvls++] = vl;
+ }
+
+ /* We need at least one VL */
+ if (nvls < 1) {
+ fprintf(stderr, "Only %d VL supported\n", nvls);
+ return false;
+ }
+
+ return true;
+}
+
+static void setup_ssve_regs(void)
+{
+ /* smstart sm; real data is TODO */
+ asm volatile(".inst 0xd503437f" : : : );
+}
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+ unsigned int vl)
+{
+ size_t resv_sz, offset;
+ struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+ struct sve_context *ssve;
+ int ret;
+
+ fprintf(stderr, "Testing VL %d\n", vl);
+
+ ret = prctl(PR_SME_SET_VL, vl);
+ if (ret != vl) {
+ fprintf(stderr, "Failed to set VL, got %d\n", ret);
+ return 1;
+ }
+
+ /*
+ * Get a signal context which should have a SVE frame and registers
+ * in it.
+ */
+ setup_ssve_regs();
+ if (!get_current_context(td, &sf.uc))
+ return 1;
+
+ resv_sz = GET_SF_RESV_SIZE(sf);
+ head = get_header(head, SVE_MAGIC, resv_sz, &offset);
+ if (!head) {
+ fprintf(stderr, "No SVE context\n");
+ return 1;
+ }
+
+ ssve = (struct sve_context *)head;
+ if (ssve->vl != vl) {
+ fprintf(stderr, "Got VL %d, expected %d\n", ssve->vl, vl);
+ return 1;
+ }
+
+ /* The actual size validation is done in get_current_context() */
+ fprintf(stderr, "Got expected size %u and VL %d\n",
+ head->size, ssve->vl);
+
+ return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+ int i;
+
+ for (i = 0; i < nvls; i++) {
+ /*
+ * TODO: the signal test helpers can't currently cope
+ * with signal frames bigger than struct sigcontext,
+ * skip VLs that will trigger that.
+ */
+ if (vls[i] > 64) {
+ printf("Skipping VL %u due to stack size\n", vls[i]);
+ continue;
+ }
+
+ if (do_one_sme_vl(td, si, uc, vls[i]))
+ return 1;
+ }
+
+ td->pass = 1;
+
+ return 0;
+}
+
+struct tdescr tde = {
+ .name = "Streaming SVE registers",
+ .descr = "Check that we get the right Streaming SVE registers reported",
+ /*
+ * We shouldn't require FA64 but things like memset() used in the
+ * helpers might use unsupported instructions so for now disable
+ * the test unless we've got the full instruction set.
+ */
+ .feats_required = FEAT_SME | FEAT_SME_FA64,
+ .timeout = 3,
+ .init = sme_get_vls,
+ .run = sme_regs,
+};
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.c b/tools/testing/selftests/arm64/signal/testcases/testcases.c
index 8c2a57fc2f9c..84c36bee4d82 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.c
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.c
@@ -75,6 +75,31 @@ bool validate_sve_context(struct sve_context *sve, char **err)
return true;
}
+bool validate_za_context(struct za_context *za, char **err)
+{
+ /* Size will be rounded up to a multiple of 16 bytes */
+ size_t regs_size
+ = ((ZA_SIG_CONTEXT_SIZE(sve_vq_from_vl(za->vl)) + 15) / 16) * 16;
+
+ if (!za || !err)
+ return false;
+
+ /* Either a bare za_context or a za_context followed by regs data */
+ if ((za->head.size != sizeof(struct za_context)) &&
+ (za->head.size != regs_size)) {
+ *err = "bad size for ZA context";
+ return false;
+ }
+
+ if (!sve_vl_valid(za->vl)) {
+ *err = "SME VL in ZA context invalid";
+
+ return false;
+ }
+
+ return true;
+}
+
bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
{
bool terminated = false;
@@ -82,6 +107,7 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
int flags = 0;
struct extra_context *extra = NULL;
struct sve_context *sve = NULL;
+ struct za_context *za = NULL;
struct _aarch64_ctx *head =
(struct _aarch64_ctx *)uc->uc_mcontext.__reserved;
@@ -120,6 +146,13 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
sve = (struct sve_context *)head;
flags |= SVE_CTX;
break;
+ case ZA_MAGIC:
+ if (flags & ZA_CTX)
+ *err = "Multiple ZA_MAGIC";
+ /* Size is validated in validate_za_context() */
+ za = (struct za_context *)head;
+ flags |= ZA_CTX;
+ break;
case EXTRA_MAGIC:
if (flags & EXTRA_CTX)
*err = "Multiple EXTRA_MAGIC";
@@ -165,6 +198,9 @@ bool validate_reserved(ucontext_t *uc, size_t resv_sz, char **err)
if (flags & SVE_CTX)
if (!validate_sve_context(sve, err))
return false;
+ if (flags & ZA_CTX)
+ if (!validate_za_context(za, err))
+ return false;
head = GET_RESV_NEXT_HEAD(head);
}
diff --git a/tools/testing/selftests/arm64/signal/testcases/testcases.h b/tools/testing/selftests/arm64/signal/testcases/testcases.h
index ad884c135314..49f1d5de7b5b 100644
--- a/tools/testing/selftests/arm64/signal/testcases/testcases.h
+++ b/tools/testing/selftests/arm64/signal/testcases/testcases.h
@@ -16,7 +16,8 @@
#define FPSIMD_CTX (1 << 0)
#define SVE_CTX (1 << 1)
-#define EXTRA_CTX (1 << 2)
+#define ZA_CTX (1 << 2)
+#define EXTRA_CTX (1 << 3)
#define KSFT_BAD_MAGIC 0xdeadbeef
diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
new file mode 100644
index 000000000000..b94e4f99fcac
--- /dev/null
+++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021 ARM Limited
+ *
+ * Verify that the ZA register context in signal frames is set up as
+ * expected.
+ */
+
+#include <signal.h>
+#include <ucontext.h>
+#include <sys/prctl.h>
+
+#include "test_signals_utils.h"
+#include "testcases.h"
+
+struct fake_sigframe sf;
+static unsigned int vls[SVE_VQ_MAX];
+unsigned int nvls = 0;
+
+static bool sme_get_vls(struct tdescr *td)
+{
+ int vq, vl;
+
+ /*
+ * Enumerate up to SVE_VQ_MAX vector lengths
+ */
+ for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+ vl = prctl(PR_SVE_SET_VL, vq * 16);
+ if (vl == -1)
+ return false;
+
+ vl &= PR_SME_VL_LEN_MASK;
+
+ /* Skip missing VLs */
+ vq = sve_vq_from_vl(vl);
+
+ vls[nvls++] = vl;
+ }
+
+ /* We need at least one VL */
+ if (nvls < 1) {
+ fprintf(stderr, "Only %d VL supported\n", nvls);
+ return false;
+ }
+
+ return true;
+}
+
+static void setup_za_regs(void)
+{
+ /* smstart za; real data is TODO */
+ asm volatile(".inst 0xd503457f" : : : );
+}
+
+static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+ unsigned int vl)
+{
+ size_t resv_sz, offset;
+ struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+ struct za_context *za;
+
+ fprintf(stderr, "Testing VL %d\n", vl);
+
+ if (prctl(PR_SME_SET_VL, vl) != vl) {
+ fprintf(stderr, "Failed to set VL\n");
+ return 1;
+ }
+
+ /*
+ * Get a signal context which should have a SVE frame and registers
+ * in it.
+ */
+ setup_za_regs();
+ if (!get_current_context(td, &sf.uc))
+ return 1;
+
+ resv_sz = GET_SF_RESV_SIZE(sf);
+ head = get_header(head, ZA_MAGIC, resv_sz, &offset);
+ if (!head) {
+ fprintf(stderr, "No ZA context\n");
+ return 1;
+ }
+
+ za = (struct za_context *)head;
+ if (za->vl != vl) {
+ fprintf(stderr, "Got VL %d, expected %d\n", za->vl, vl);
+ return 1;
+ }
+
+ /* The actual size validation is done in get_current_context() */
+ fprintf(stderr, "Got expected size %u and VL %d\n",
+ head->size, za->vl);
+
+ return 0;
+}
+
+static int sme_regs(struct tdescr *td, siginfo_t *si, ucontext_t *uc)
+{
+ int i;
+
+ for (i = 0; i < nvls; i++) {
+ /*
+ * TODO: the signal test helpers can't currently cope
+ * with signal frames bigger than struct sigcontext,
+ * skip VLs that will trigger that.
+ */
+ if (vls[i] > 32) {
+ printf("Skipping VL %u due to stack size\n", vls[i]);
+ continue;
+ }
+
+ if (do_one_sme_vl(td, si, uc, vls[i]))
+ return 1;
+ }
+
+ td->pass = 1;
+
+ return 0;
+}
+
+struct tdescr tde = {
+ .name = "ZA register",
+ .descr = "Check that we get the right ZA registers reported",
+ .feats_required = FEAT_SME,
+ .timeout = 3,
+ .init = sme_get_vls,
+ .run = sme_regs,
+};
diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
index 5aa52cc31dc2..c11832657d2b 100644
--- a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
+++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
@@ -2,6 +2,7 @@
/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
#include <test_progs.h>
#include "dummy_st_ops.skel.h"
+#include "trace_dummy_st_ops.skel.h"
/* Need to keep consistent with definition in include/linux/bpf.h */
struct bpf_dummy_ops_state {
@@ -56,6 +57,7 @@ static void test_dummy_init_ptr_arg(void)
.ctx_in = args,
.ctx_size_in = sizeof(args),
);
+ struct trace_dummy_st_ops *trace_skel;
struct dummy_st_ops *skel;
int fd, err;
@@ -64,12 +66,33 @@ static void test_dummy_init_ptr_arg(void)
return;
fd = bpf_program__fd(skel->progs.test_1);
+
+ trace_skel = trace_dummy_st_ops__open();
+ if (!ASSERT_OK_PTR(trace_skel, "trace_dummy_st_ops__open"))
+ goto done;
+
+ err = bpf_program__set_attach_target(trace_skel->progs.fentry_test_1,
+ fd, "test_1");
+ if (!ASSERT_OK(err, "set_attach_target(fentry_test_1)"))
+ goto done;
+
+ err = trace_dummy_st_ops__load(trace_skel);
+ if (!ASSERT_OK(err, "load(trace_skel)"))
+ goto done;
+
+ err = trace_dummy_st_ops__attach(trace_skel);
+ if (!ASSERT_OK(err, "attach(trace_skel)"))
+ goto done;
+
err = bpf_prog_test_run_opts(fd, &attr);
ASSERT_OK(err, "test_run");
ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret");
ASSERT_EQ(attr.retval, exp_retval, "test_ret");
+ ASSERT_EQ(trace_skel->bss->val, exp_retval, "fentry_val");
+done:
dummy_st_ops__destroy(skel);
+ trace_dummy_st_ops__destroy(trace_skel);
}
static void test_dummy_multiple_args(void)
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index b64df94ec476..db388f593d0a 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -367,7 +367,7 @@ static inline int check_array_of_maps(void)
VERIFY(check_default(&array_of_maps->map, map));
inner_map = bpf_map_lookup_elem(array_of_maps, &key);
- VERIFY(inner_map != 0);
+ VERIFY(inner_map != NULL);
VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
return 1;
@@ -394,7 +394,7 @@ static inline int check_hash_of_maps(void)
VERIFY(check_default(&hash_of_maps->map, map));
inner_map = bpf_map_lookup_elem(hash_of_maps, &key);
- VERIFY(inner_map != 0);
+ VERIFY(inner_map != NULL);
VERIFY(inner_map->map.max_entries == INNER_MAX_ENTRIES);
return 1;
diff --git a/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c
new file mode 100644
index 000000000000..00a4be9d3074
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/trace_dummy_st_ops.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int val = 0;
+
+SEC("fentry/test_1")
+int BPF_PROG(fentry_test_1, __u64 *st_ops_ctx)
+{
+ __u64 state;
+
+ /* Read the traced st_ops arg1 which is a pointer */
+ bpf_probe_read_kernel(&state, sizeof(__u64), (void *)st_ops_ctx);
+ /* Read state->val */
+ bpf_probe_read_kernel(&val, sizeof(__u32), (void *)state);
+
+ return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
index b9e991d43155..e7775d3bbe08 100644
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
+++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c
@@ -18,8 +18,9 @@
#include "bpf_rlimit.h"
#include "cgroup_helpers.h"
-static int start_server(const struct sockaddr *addr, socklen_t len)
+static int start_server(const struct sockaddr *addr, socklen_t len, bool dual)
{
+ int mode = !dual;
int fd;
fd = socket(addr->sa_family, SOCK_STREAM, 0);
@@ -28,6 +29,14 @@ static int start_server(const struct sockaddr *addr, socklen_t len)
goto out;
}
+ if (addr->sa_family == AF_INET6) {
+ if (setsockopt(fd, IPPROTO_IPV6, IPV6_V6ONLY, (char *)&mode,
+ sizeof(mode)) == -1) {
+ log_err("Failed to set the dual-stack mode");
+ goto close_out;
+ }
+ }
+
if (bind(fd, addr, len) == -1) {
log_err("Failed to bind server socket");
goto close_out;
@@ -47,24 +56,17 @@ out:
return fd;
}
-static int connect_to_server(int server_fd)
+static int connect_to_server(const struct sockaddr *addr, socklen_t len)
{
- struct sockaddr_storage addr;
- socklen_t len = sizeof(addr);
int fd = -1;
- if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
- log_err("Failed to get server addr");
- goto out;
- }
-
- fd = socket(addr.ss_family, SOCK_STREAM, 0);
+ fd = socket(addr->sa_family, SOCK_STREAM, 0);
if (fd == -1) {
log_err("Failed to create client socket");
goto out;
}
- if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
+ if (connect(fd, (const struct sockaddr *)addr, len) == -1) {
log_err("Fail to connect to server");
goto close_out;
}
@@ -116,7 +118,8 @@ err:
return map_fd;
}
-static int run_test(int server_fd, int results_fd, bool xdp)
+static int run_test(int server_fd, int results_fd, bool xdp,
+ const struct sockaddr *addr, socklen_t len)
{
int client = -1, srv_client = -1;
int ret = 0;
@@ -142,7 +145,7 @@ static int run_test(int server_fd, int results_fd, bool xdp)
goto err;
}
- client = connect_to_server(server_fd);
+ client = connect_to_server(addr, len);
if (client == -1)
goto err;
@@ -199,12 +202,30 @@ out:
return ret;
}
+static bool get_port(int server_fd, in_port_t *port)
+{
+ struct sockaddr_in addr;
+ socklen_t len = sizeof(addr);
+
+ if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+ log_err("Failed to get server addr");
+ return false;
+ }
+
+ /* sin_port and sin6_port are located at the same offset. */
+ *port = addr.sin_port;
+ return true;
+}
+
int main(int argc, char **argv)
{
struct sockaddr_in addr4;
struct sockaddr_in6 addr6;
+ struct sockaddr_in addr4dual;
+ struct sockaddr_in6 addr6dual;
int server = -1;
int server_v6 = -1;
+ int server_dual = -1;
int results = -1;
int err = 0;
bool xdp;
@@ -224,25 +245,43 @@ int main(int argc, char **argv)
addr4.sin_family = AF_INET;
addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
addr4.sin_port = 0;
+ memcpy(&addr4dual, &addr4, sizeof(addr4dual));
memset(&addr6, 0, sizeof(addr6));
addr6.sin6_family = AF_INET6;
addr6.sin6_addr = in6addr_loopback;
addr6.sin6_port = 0;
- server = start_server((const struct sockaddr *)&addr4, sizeof(addr4));
- if (server == -1)
+ memset(&addr6dual, 0, sizeof(addr6dual));
+ addr6dual.sin6_family = AF_INET6;
+ addr6dual.sin6_addr = in6addr_any;
+ addr6dual.sin6_port = 0;
+
+ server = start_server((const struct sockaddr *)&addr4, sizeof(addr4),
+ false);
+ if (server == -1 || !get_port(server, &addr4.sin_port))
goto err;
server_v6 = start_server((const struct sockaddr *)&addr6,
- sizeof(addr6));
- if (server_v6 == -1)
+ sizeof(addr6), false);
+ if (server_v6 == -1 || !get_port(server_v6, &addr6.sin6_port))
+ goto err;
+
+ server_dual = start_server((const struct sockaddr *)&addr6dual,
+ sizeof(addr6dual), true);
+ if (server_dual == -1 || !get_port(server_dual, &addr4dual.sin_port))
+ goto err;
+
+ if (run_test(server, results, xdp,
+ (const struct sockaddr *)&addr4, sizeof(addr4)))
goto err;
- if (run_test(server, results, xdp))
+ if (run_test(server_v6, results, xdp,
+ (const struct sockaddr *)&addr6, sizeof(addr6)))
goto err;
- if (run_test(server_v6, results, xdp))
+ if (run_test(server_dual, results, xdp,
+ (const struct sockaddr *)&addr4dual, sizeof(addr4dual)))
goto err;
printf("ok\n");
@@ -252,6 +291,7 @@ err:
out:
close(server);
close(server_v6);
+ close(server_dual);
close(results);
return err;
}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
index 429f7ee735cf..fd23c80eba31 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/vxlan_flooding_ipv6.sh
@@ -159,6 +159,17 @@ flooding_remotes_add()
local lsb
local i
+ # Prevent unwanted packets from entering the bridge and interfering
+ # with the test.
+ tc qdisc add dev br0 clsact
+ tc filter add dev br0 egress protocol all pref 1 handle 1 \
+ matchall skip_hw action drop
+ tc qdisc add dev $h1 clsact
+ tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+ flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+ tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+ matchall skip_hw action drop
+
for i in $(eval echo {1..$num_remotes}); do
lsb=$((i + 1))
@@ -195,6 +206,12 @@ flooding_filters_del()
done
tc qdisc del dev $rp2 clsact
+
+ tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+ tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+ tc qdisc del dev $h1 clsact
+ tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+ tc qdisc del dev br0 clsact
}
flooding_check_packets()
diff --git a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
index fedcb7b35af9..af5ea50ed5c0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/vxlan_flooding.sh
@@ -172,6 +172,17 @@ flooding_filters_add()
local lsb
local i
+ # Prevent unwanted packets from entering the bridge and interfering
+ # with the test.
+ tc qdisc add dev br0 clsact
+ tc filter add dev br0 egress protocol all pref 1 handle 1 \
+ matchall skip_hw action drop
+ tc qdisc add dev $h1 clsact
+ tc filter add dev $h1 egress protocol all pref 1 handle 1 \
+ flower skip_hw dst_mac de:ad:be:ef:13:37 action pass
+ tc filter add dev $h1 egress protocol all pref 2 handle 2 \
+ matchall skip_hw action drop
+
tc qdisc add dev $rp2 clsact
for i in $(eval echo {1..$num_remotes}); do
@@ -194,6 +205,12 @@ flooding_filters_del()
done
tc qdisc del dev $rp2 clsact
+
+ tc filter del dev $h1 egress protocol all pref 2 handle 2 matchall
+ tc filter del dev $h1 egress protocol all pref 1 handle 1 flower
+ tc qdisc del dev $h1 clsact
+ tc filter del dev br0 egress protocol all pref 1 handle 1 matchall
+ tc qdisc del dev br0 clsact
}
flooding_check_packets()
diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index eaf8a04a7ca5..10e54bcca7a9 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -190,7 +190,7 @@ setup_prepare()
tc filter add dev $eth0 ingress chain $(IS2 0 0) pref 1 \
protocol ipv4 flower skip_sw ip_proto udp dst_port 5201 \
- action police rate 50mbit burst 64k \
+ action police rate 50mbit burst 64k conform-exceed drop/pipe \
action goto chain $(IS2 1 0)
}
diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h
index 11779405dc80..25f4d54067c0 100644
--- a/tools/testing/selftests/kselftest_harness.h
+++ b/tools/testing/selftests/kselftest_harness.h
@@ -64,6 +64,7 @@
#include <sys/types.h>
#include <sys/wait.h>
#include <unistd.h>
+#include <setjmp.h>
#include "kselftest.h"
@@ -183,7 +184,10 @@
struct __test_metadata *_metadata, \
struct __fixture_variant_metadata *variant) \
{ \
- test_name(_metadata); \
+ _metadata->setup_completed = true; \
+ if (setjmp(_metadata->env) == 0) \
+ test_name(_metadata); \
+ __test_check_assert(_metadata); \
} \
static struct __test_metadata _##test_name##_object = \
{ .name = #test_name, \
@@ -287,7 +291,9 @@
#define FIXTURE_TEARDOWN(fixture_name) \
void fixture_name##_teardown( \
struct __test_metadata __attribute__((unused)) *_metadata, \
- FIXTURE_DATA(fixture_name) __attribute__((unused)) *self)
+ FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \
+ const FIXTURE_VARIANT(fixture_name) \
+ __attribute__((unused)) *variant)
/**
* FIXTURE_VARIANT() - Optionally called once per fixture
@@ -302,9 +308,9 @@
* ...
* };
*
- * Defines type of constant parameters provided to FIXTURE_SETUP() and TEST_F()
- * as *variant*. Variants allow the same tests to be run with different
- * arguments.
+ * Defines type of constant parameters provided to FIXTURE_SETUP(), TEST_F() and
+ * FIXTURE_TEARDOWN as *variant*. Variants allow the same tests to be run with
+ * different arguments.
*/
#define FIXTURE_VARIANT(fixture_name) struct _fixture_variant_##fixture_name
@@ -356,10 +362,7 @@
* Defines a test that depends on a fixture (e.g., is part of a test case).
* Very similar to TEST() except that *self* is the setup instance of fixture's
* datatype exposed for use by the implementation.
- *
- * Warning: use of ASSERT_* here will skip TEARDOWN.
*/
-/* TODO(wad) register fixtures on dedicated test lists. */
#define TEST_F(fixture_name, test_name) \
__TEST_F_IMPL(fixture_name, test_name, -1, TEST_TIMEOUT_DEFAULT)
@@ -381,12 +384,17 @@
/* fixture data is alloced, setup, and torn down per call. */ \
FIXTURE_DATA(fixture_name) self; \
memset(&self, 0, sizeof(FIXTURE_DATA(fixture_name))); \
- fixture_name##_setup(_metadata, &self, variant->data); \
- /* Let setup failure terminate early. */ \
- if (!_metadata->passed) \
- return; \
- fixture_name##_##test_name(_metadata, &self, variant->data); \
- fixture_name##_teardown(_metadata, &self); \
+ if (setjmp(_metadata->env) == 0) { \
+ fixture_name##_setup(_metadata, &self, variant->data); \
+ /* Let setup failure terminate early. */ \
+ if (!_metadata->passed) \
+ return; \
+ _metadata->setup_completed = true; \
+ fixture_name##_##test_name(_metadata, &self, variant->data); \
+ } \
+ if (_metadata->setup_completed) \
+ fixture_name##_teardown(_metadata, &self, variant->data); \
+ __test_check_assert(_metadata); \
} \
static struct __test_metadata \
_##fixture_name##_##test_name##_object = { \
@@ -683,7 +691,7 @@
*/
#define OPTIONAL_HANDLER(_assert) \
for (; _metadata->trigger; _metadata->trigger = \
- __bail(_assert, _metadata->no_print, _metadata->step))
+ __bail(_assert, _metadata))
#define __INC_STEP(_metadata) \
/* Keep "step" below 255 (which is used for "SKIP" reporting). */ \
@@ -830,6 +838,9 @@ struct __test_metadata {
bool timed_out; /* did this test timeout instead of exiting? */
__u8 step;
bool no_print; /* manual trigger when TH_LOG_STREAM is not available */
+ bool aborted; /* stopped test due to failed ASSERT */
+ bool setup_completed; /* did setup finish? */
+ jmp_buf env; /* for exiting out of test early */
struct __test_results *results;
struct __test_metadata *prev, *next;
};
@@ -848,16 +859,26 @@ static inline void __register_test(struct __test_metadata *t)
__LIST_APPEND(t->fixture->tests, t);
}
-static inline int __bail(int for_realz, bool no_print, __u8 step)
+static inline int __bail(int for_realz, struct __test_metadata *t)
{
+ /* if this is ASSERT, return immediately. */
if (for_realz) {
- if (no_print)
- _exit(step);
- abort();
+ t->aborted = true;
+ longjmp(t->env, 1);
}
+ /* otherwise, end the for loop and continue. */
return 0;
}
+static inline void __test_check_assert(struct __test_metadata *t)
+{
+ if (t->aborted) {
+ if (t->no_print)
+ _exit(t->step);
+ abort();
+ }
+}
+
struct __test_metadata *__active_test;
static void __timeout_handler(int sig, siginfo_t *info, void *ucontext)
{
diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore
index d1e8f5237469..0b0e4402bba6 100644
--- a/tools/testing/selftests/kvm/.gitignore
+++ b/tools/testing/selftests/kvm/.gitignore
@@ -3,6 +3,7 @@
/aarch64/debug-exceptions
/aarch64/get-reg-list
/aarch64/psci_cpu_on_test
+/aarch64/vcpu_width_config
/aarch64/vgic_init
/aarch64/vgic_irq
/s390x/memop
@@ -33,6 +34,7 @@
/x86_64/state_test
/x86_64/svm_vmcall_test
/x86_64/svm_int_ctl_test
+/x86_64/tsc_scaling_sync
/x86_64/sync_regs_test
/x86_64/tsc_msrs_test
/x86_64/userspace_io_test
diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile
index 21c2dbd21a81..681b173aa87c 100644
--- a/tools/testing/selftests/kvm/Makefile
+++ b/tools/testing/selftests/kvm/Makefile
@@ -106,6 +106,7 @@ TEST_GEN_PROGS_aarch64 += aarch64/arch_timer
TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
+TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
TEST_GEN_PROGS_aarch64 += demand_paging_test
diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/aarch64/arch_timer.c
index b08d30bf71c5..3b940a101bc0 100644
--- a/tools/testing/selftests/kvm/aarch64/arch_timer.c
+++ b/tools/testing/selftests/kvm/aarch64/arch_timer.c
@@ -362,11 +362,12 @@ static void test_init_timer_irq(struct kvm_vm *vm)
pr_debug("ptimer_irq: %d; vtimer_irq: %d\n", ptimer_irq, vtimer_irq);
}
+static int gic_fd;
+
static struct kvm_vm *test_vm_create(void)
{
struct kvm_vm *vm;
unsigned int i;
- int ret;
int nr_vcpus = test_args.nr_vcpus;
vm = vm_create_default_with_vcpus(nr_vcpus, 0, 0, guest_code, NULL);
@@ -383,8 +384,8 @@ static struct kvm_vm *test_vm_create(void)
ucall_init(vm, NULL);
test_init_timer_irq(vm);
- ret = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
- if (ret < 0) {
+ gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+ if (gic_fd < 0) {
print_skip("Failed to create vgic-v3");
exit(KSFT_SKIP);
}
@@ -395,6 +396,12 @@ static struct kvm_vm *test_vm_create(void)
return vm;
}
+static void test_vm_cleanup(struct kvm_vm *vm)
+{
+ close(gic_fd);
+ kvm_vm_free(vm);
+}
+
static void test_print_help(char *name)
{
pr_info("Usage: %s [-h] [-n nr_vcpus] [-i iterations] [-p timer_period_ms]\n",
@@ -478,7 +485,7 @@ int main(int argc, char *argv[])
vm = test_vm_create();
test_run(vm);
- kvm_vm_free(vm);
+ test_vm_cleanup(vm);
return 0;
}
diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
index f12147c43464..0b571f3fe64c 100644
--- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c
+++ b/tools/testing/selftests/kvm/aarch64/get-reg-list.c
@@ -503,8 +503,13 @@ static void run_test(struct vcpu_config *c)
++missing_regs;
if (new_regs || missing_regs) {
+ n = 0;
+ for_each_reg_filtered(i)
+ ++n;
+
printf("%s: Number blessed registers: %5lld\n", config_name(c), blessed_n);
- printf("%s: Number registers: %5lld\n", config_name(c), reg_list->n);
+ printf("%s: Number registers: %5lld (includes %lld filtered registers)\n",
+ config_name(c), reg_list->n, reg_list->n - n);
}
if (new_regs) {
@@ -683,9 +688,10 @@ static __u64 base_regs[] = {
KVM_REG_ARM64 | KVM_REG_SIZE_U64 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(spsr[4]),
KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpsr),
KVM_REG_ARM64 | KVM_REG_SIZE_U32 | KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(fp_regs.fpcr),
- KVM_REG_ARM_FW_REG(0),
- KVM_REG_ARM_FW_REG(1),
- KVM_REG_ARM_FW_REG(2),
+ KVM_REG_ARM_FW_REG(0), /* KVM_REG_ARM_PSCI_VERSION */
+ KVM_REG_ARM_FW_REG(1), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1 */
+ KVM_REG_ARM_FW_REG(2), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2 */
+ KVM_REG_ARM_FW_REG(3), /* KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3 */
ARM64_SYS_REG(3, 3, 14, 3, 1), /* CNTV_CTL_EL0 */
ARM64_SYS_REG(3, 3, 14, 3, 2), /* CNTV_CVAL_EL0 */
ARM64_SYS_REG(3, 3, 14, 0, 2),
diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
new file mode 100644
index 000000000000..6e9402679229
--- /dev/null
+++ b/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vcpu_width_config - Test KVM_ARM_VCPU_INIT() with KVM_ARM_VCPU_EL1_32BIT.
+ *
+ * Copyright (c) 2022 Google LLC.
+ *
+ * This is a test that ensures that non-mixed-width vCPUs (all 64bit vCPUs
+ * or all 32bit vcPUs) can be configured and mixed-width vCPUs cannot be
+ * configured.
+ */
+
+#include "kvm_util.h"
+#include "processor.h"
+#include "test_util.h"
+
+
+/*
+ * Add a vCPU, run KVM_ARM_VCPU_INIT with @init1, and then
+ * add another vCPU, and run KVM_ARM_VCPU_INIT with @init2.
+ */
+static int add_init_2vcpus(struct kvm_vcpu_init *init1,
+ struct kvm_vcpu_init *init2)
+{
+ struct kvm_vm *vm;
+ int ret;
+
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+ vm_vcpu_add(vm, 0);
+ ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+ if (ret)
+ goto free_exit;
+
+ vm_vcpu_add(vm, 1);
+ ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+ kvm_vm_free(vm);
+ return ret;
+}
+
+/*
+ * Add two vCPUs, then run KVM_ARM_VCPU_INIT for one vCPU with @init1,
+ * and run KVM_ARM_VCPU_INIT for another vCPU with @init2.
+ */
+static int add_2vcpus_init_2vcpus(struct kvm_vcpu_init *init1,
+ struct kvm_vcpu_init *init2)
+{
+ struct kvm_vm *vm;
+ int ret;
+
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+
+ vm_vcpu_add(vm, 0);
+ vm_vcpu_add(vm, 1);
+
+ ret = _vcpu_ioctl(vm, 0, KVM_ARM_VCPU_INIT, init1);
+ if (ret)
+ goto free_exit;
+
+ ret = _vcpu_ioctl(vm, 1, KVM_ARM_VCPU_INIT, init2);
+
+free_exit:
+ kvm_vm_free(vm);
+ return ret;
+}
+
+/*
+ * Tests that two 64bit vCPUs can be configured, two 32bit vCPUs can be
+ * configured, and two mixed-width vCPUs cannot be configured.
+ * Each of those three cases, configure vCPUs in two different orders.
+ * The one is running KVM_CREATE_VCPU for 2 vCPUs, and then running
+ * KVM_ARM_VCPU_INIT for them.
+ * The other is running KVM_CREATE_VCPU and KVM_ARM_VCPU_INIT for a vCPU,
+ * and then run those commands for another vCPU.
+ */
+int main(void)
+{
+ struct kvm_vcpu_init init1, init2;
+ struct kvm_vm *vm;
+ int ret;
+
+ if (!kvm_check_cap(KVM_CAP_ARM_EL1_32BIT)) {
+ print_skip("KVM_CAP_ARM_EL1_32BIT is not supported");
+ exit(KSFT_SKIP);
+ }
+
+ /* Get the preferred target type and copy that to init2 for later use */
+ vm = vm_create(VM_MODE_DEFAULT, DEFAULT_GUEST_PHY_PAGES, O_RDWR);
+ vm_ioctl(vm, KVM_ARM_PREFERRED_TARGET, &init1);
+ kvm_vm_free(vm);
+ init2 = init1;
+
+ /* Test with 64bit vCPUs */
+ ret = add_init_2vcpus(&init1, &init1);
+ TEST_ASSERT(ret == 0,
+ "Configuring 64bit EL1 vCPUs failed unexpectedly");
+ ret = add_2vcpus_init_2vcpus(&init1, &init1);
+ TEST_ASSERT(ret == 0,
+ "Configuring 64bit EL1 vCPUs failed unexpectedly");
+
+ /* Test with 32bit vCPUs */
+ init1.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+ ret = add_init_2vcpus(&init1, &init1);
+ TEST_ASSERT(ret == 0,
+ "Configuring 32bit EL1 vCPUs failed unexpectedly");
+ ret = add_2vcpus_init_2vcpus(&init1, &init1);
+ TEST_ASSERT(ret == 0,
+ "Configuring 32bit EL1 vCPUs failed unexpectedly");
+
+ /* Test with mixed-width vCPUs */
+ init1.features[0] = 0;
+ init2.features[0] = (1 << KVM_ARM_VCPU_EL1_32BIT);
+ ret = add_init_2vcpus(&init1, &init2);
+ TEST_ASSERT(ret != 0,
+ "Configuring mixed-width vCPUs worked unexpectedly");
+ ret = add_2vcpus_init_2vcpus(&init1, &init2);
+ TEST_ASSERT(ret != 0,
+ "Configuring mixed-width vCPUs worked unexpectedly");
+
+ return 0;
+}
diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c
index c9d9e513ca04..7b47ae4f952e 100644
--- a/tools/testing/selftests/kvm/dirty_log_perf_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c
@@ -18,11 +18,40 @@
#include "test_util.h"
#include "perf_test_util.h"
#include "guest_modes.h"
+
#ifdef __aarch64__
#include "aarch64/vgic.h"
#define GICD_BASE_GPA 0x8000000ULL
#define GICR_BASE_GPA 0x80A0000ULL
+
+static int gic_fd;
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+ /*
+ * The test can still run even if hardware does not support GICv3, as it
+ * is only an optimization to reduce guest exits.
+ */
+ gic_fd = vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+ if (gic_fd > 0)
+ close(gic_fd);
+}
+
+#else /* __aarch64__ */
+
+static void arch_setup_vm(struct kvm_vm *vm, unsigned int nr_vcpus)
+{
+}
+
+static void arch_cleanup_vm(struct kvm_vm *vm)
+{
+}
+
#endif
/* How many host loops to run by default (one KVM_GET_DIRTY_LOG for each loop)*/
@@ -206,9 +235,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
vm_enable_cap(vm, &cap);
}
-#ifdef __aarch64__
- vgic_v3_setup(vm, nr_vcpus, 64, GICD_BASE_GPA, GICR_BASE_GPA);
-#endif
+ arch_setup_vm(vm, nr_vcpus);
/* Start the iterations */
iteration = 0;
@@ -302,6 +329,7 @@ static void run_test(enum vm_guest_mode mode, void *arg)
}
free_bitmaps(bitmaps, p->slots);
+ arch_cleanup_vm(vm);
perf_test_destroy_vm(vm);
}
diff --git a/tools/testing/selftests/kvm/include/riscv/processor.h b/tools/testing/selftests/kvm/include/riscv/processor.h
index dc284c6bdbc3..eca5c622efd2 100644
--- a/tools/testing/selftests/kvm/include/riscv/processor.h
+++ b/tools/testing/selftests/kvm/include/riscv/processor.h
@@ -101,7 +101,9 @@ static inline void set_reg(struct kvm_vm *vm, uint32_t vcpuid, uint64_t id,
#define PGTBL_PTE_WRITE_SHIFT 2
#define PGTBL_PTE_READ_MASK 0x0000000000000002ULL
#define PGTBL_PTE_READ_SHIFT 1
-#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_EXECUTE_MASK | \
+#define PGTBL_PTE_PERM_MASK (PGTBL_PTE_ACCESSED_MASK | \
+ PGTBL_PTE_DIRTY_MASK | \
+ PGTBL_PTE_EXECUTE_MASK | \
PGTBL_PTE_WRITE_MASK | \
PGTBL_PTE_READ_MASK)
#define PGTBL_PTE_VALID_MASK 0x0000000000000001ULL
diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h
index 37db341d4cc5..d0d51adec76e 100644
--- a/tools/testing/selftests/kvm/include/x86_64/processor.h
+++ b/tools/testing/selftests/kvm/include/x86_64/processor.h
@@ -60,6 +60,23 @@
/* CPUID.0x8000_0001.EDX */
#define CPUID_GBPAGES (1ul << 26)
+/* Page table bitfield declarations */
+#define PTE_PRESENT_MASK BIT_ULL(0)
+#define PTE_WRITABLE_MASK BIT_ULL(1)
+#define PTE_USER_MASK BIT_ULL(2)
+#define PTE_ACCESSED_MASK BIT_ULL(5)
+#define PTE_DIRTY_MASK BIT_ULL(6)
+#define PTE_LARGE_MASK BIT_ULL(7)
+#define PTE_GLOBAL_MASK BIT_ULL(8)
+#define PTE_NX_MASK BIT_ULL(63)
+
+#define PAGE_SHIFT 12
+#define PAGE_SIZE (1ULL << PAGE_SHIFT)
+#define PAGE_MASK (~(PAGE_SIZE-1))
+
+#define PHYSICAL_PAGE_MASK GENMASK_ULL(51, 12)
+#define PTE_GET_PFN(pte) (((pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+
/* General Registers in 64-Bit Mode */
struct gpr64_regs {
u64 rax;
diff --git a/tools/testing/selftests/kvm/kvm_page_table_test.c b/tools/testing/selftests/kvm/kvm_page_table_test.c
index ba1fdc3dcf4a..2c4a7563a4f8 100644
--- a/tools/testing/selftests/kvm/kvm_page_table_test.c
+++ b/tools/testing/selftests/kvm/kvm_page_table_test.c
@@ -278,7 +278,7 @@ static struct kvm_vm *pre_init_before_test(enum vm_guest_mode mode, void *arg)
else
guest_test_phys_mem = p->phys_offset;
#ifdef __s390x__
- alignment = max(0x100000, alignment);
+ alignment = max(0x100000UL, alignment);
#endif
guest_test_phys_mem = align_down(guest_test_phys_mem, alignment);
diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c
index d377f2603d98..3961487a4870 100644
--- a/tools/testing/selftests/kvm/lib/riscv/processor.c
+++ b/tools/testing/selftests/kvm/lib/riscv/processor.c
@@ -268,7 +268,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
core.regs.t3, core.regs.t4, core.regs.t5, core.regs.t6);
}
-static void guest_hang(void)
+static void __aligned(16) guest_hang(void)
{
while (1)
;
diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86_64/processor.c
index 9f000dfb5594..33ea5e9955d9 100644
--- a/tools/testing/selftests/kvm/lib/x86_64/processor.c
+++ b/tools/testing/selftests/kvm/lib/x86_64/processor.c
@@ -19,38 +19,6 @@
vm_vaddr_t exception_handlers;
-/* Virtual translation table structure declarations */
-struct pageUpperEntry {
- 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 pfn: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 pfn:40;
- uint64_t ignored_62_52:11;
- uint64_t execute_disable:1;
-};
-
void regs_dump(FILE *stream, struct kvm_regs *regs,
uint8_t indent)
{
@@ -195,23 +163,21 @@ static void *virt_get_pte(struct kvm_vm *vm, uint64_t pt_pfn, uint64_t vaddr,
return &page_table[index];
}
-static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
- uint64_t pt_pfn,
- uint64_t vaddr,
- uint64_t paddr,
- int level,
- enum x86_page_size page_size)
+static uint64_t *virt_create_upper_pte(struct kvm_vm *vm,
+ uint64_t pt_pfn,
+ uint64_t vaddr,
+ uint64_t paddr,
+ int level,
+ enum x86_page_size page_size)
{
- struct pageUpperEntry *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
-
- if (!pte->present) {
- pte->writable = true;
- pte->present = true;
- pte->page_size = (level == page_size);
- if (pte->page_size)
- pte->pfn = paddr >> vm->page_shift;
+ uint64_t *pte = virt_get_pte(vm, pt_pfn, vaddr, level);
+
+ if (!(*pte & PTE_PRESENT_MASK)) {
+ *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK;
+ if (level == page_size)
+ *pte |= PTE_LARGE_MASK | (paddr & PHYSICAL_PAGE_MASK);
else
- pte->pfn = vm_alloc_page_table(vm) >> vm->page_shift;
+ *pte |= vm_alloc_page_table(vm) & PHYSICAL_PAGE_MASK;
} else {
/*
* Entry already present. Assert that the caller doesn't want
@@ -221,7 +187,7 @@ static struct pageUpperEntry *virt_create_upper_pte(struct kvm_vm *vm,
TEST_ASSERT(level != page_size,
"Cannot create hugepage at level: %u, vaddr: 0x%lx\n",
page_size, vaddr);
- TEST_ASSERT(!pte->page_size,
+ TEST_ASSERT(!(*pte & PTE_LARGE_MASK),
"Cannot create page table at level: %u, vaddr: 0x%lx\n",
level, vaddr);
}
@@ -232,8 +198,8 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
enum x86_page_size page_size)
{
const uint64_t pg_size = 1ull << ((page_size * 9) + 12);
- struct pageUpperEntry *pml4e, *pdpe, *pde;
- struct pageTableEntry *pte;
+ uint64_t *pml4e, *pdpe, *pde;
+ uint64_t *pte;
TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K,
"Unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -257,24 +223,22 @@ void __virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
*/
pml4e = virt_create_upper_pte(vm, vm->pgd >> vm->page_shift,
vaddr, paddr, 3, page_size);
- if (pml4e->page_size)
+ if (*pml4e & PTE_LARGE_MASK)
return;
- pdpe = virt_create_upper_pte(vm, pml4e->pfn, vaddr, paddr, 2, page_size);
- if (pdpe->page_size)
+ pdpe = virt_create_upper_pte(vm, PTE_GET_PFN(*pml4e), vaddr, paddr, 2, page_size);
+ if (*pdpe & PTE_LARGE_MASK)
return;
- pde = virt_create_upper_pte(vm, pdpe->pfn, vaddr, paddr, 1, page_size);
- if (pde->page_size)
+ pde = virt_create_upper_pte(vm, PTE_GET_PFN(*pdpe), vaddr, paddr, 1, page_size);
+ if (*pde & PTE_LARGE_MASK)
return;
/* Fill in page table entry. */
- pte = virt_get_pte(vm, pde->pfn, vaddr, 0);
- TEST_ASSERT(!pte->present,
+ pte = virt_get_pte(vm, PTE_GET_PFN(*pde), vaddr, 0);
+ TEST_ASSERT(!(*pte & PTE_PRESENT_MASK),
"PTE already present for 4k page at vaddr: 0x%lx\n", vaddr);
- pte->pfn = paddr >> vm->page_shift;
- pte->writable = true;
- pte->present = 1;
+ *pte = PTE_PRESENT_MASK | PTE_WRITABLE_MASK | (paddr & PHYSICAL_PAGE_MASK);
}
void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
@@ -282,22 +246,22 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr)
__virt_pg_map(vm, vaddr, paddr, X86_PAGE_SIZE_4K);
}
-static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
+static uint64_t *_vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid,
uint64_t vaddr)
{
uint16_t index[4];
- struct pageUpperEntry *pml4e, *pdpe, *pde;
- struct pageTableEntry *pte;
+ uint64_t *pml4e, *pdpe, *pde;
+ uint64_t *pte;
struct kvm_cpuid_entry2 *entry;
struct kvm_sregs sregs;
int max_phy_addr;
- /* Set the bottom 52 bits. */
- uint64_t rsvd_mask = 0x000fffffffffffff;
+ uint64_t rsvd_mask = 0;
entry = kvm_get_supported_cpuid_index(0x80000008, 0);
max_phy_addr = entry->eax & 0x000000ff;
- /* Clear the bottom bits of the reserved mask. */
- rsvd_mask = (rsvd_mask >> max_phy_addr) << max_phy_addr;
+ /* Set the high bits in the reserved mask. */
+ if (max_phy_addr < 52)
+ rsvd_mask = GENMASK_ULL(51, max_phy_addr);
/*
* SDM vol 3, fig 4-11 "Formats of CR3 and Paging-Structure Entries
@@ -307,7 +271,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
*/
vcpu_sregs_get(vm, vcpuid, &sregs);
if ((sregs.efer & EFER_NX) == 0) {
- rsvd_mask |= (1ull << 63);
+ rsvd_mask |= PTE_NX_MASK;
}
TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
@@ -329,30 +293,29 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
index[3] = (vaddr >> 39) & 0x1ffu;
pml4e = addr_gpa2hva(vm, vm->pgd);
- TEST_ASSERT(pml4e[index[3]].present,
+ TEST_ASSERT(pml4e[index[3]] & PTE_PRESENT_MASK,
"Expected pml4e to be present for gva: 0x%08lx", vaddr);
- TEST_ASSERT((*(uint64_t*)(&pml4e[index[3]]) &
- (rsvd_mask | (1ull << 7))) == 0,
+ TEST_ASSERT((pml4e[index[3]] & (rsvd_mask | PTE_LARGE_MASK)) == 0,
"Unexpected reserved bits set.");
- pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
- TEST_ASSERT(pdpe[index[2]].present,
+ pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
+ TEST_ASSERT(pdpe[index[2]] & PTE_PRESENT_MASK,
"Expected pdpe to be present for gva: 0x%08lx", vaddr);
- TEST_ASSERT(pdpe[index[2]].page_size == 0,
+ TEST_ASSERT(!(pdpe[index[2]] & PTE_LARGE_MASK),
"Expected pdpe to map a pde not a 1-GByte page.");
- TEST_ASSERT((*(uint64_t*)(&pdpe[index[2]]) & rsvd_mask) == 0,
+ TEST_ASSERT((pdpe[index[2]] & rsvd_mask) == 0,
"Unexpected reserved bits set.");
- pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
- TEST_ASSERT(pde[index[1]].present,
+ pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
+ TEST_ASSERT(pde[index[1]] & PTE_PRESENT_MASK,
"Expected pde to be present for gva: 0x%08lx", vaddr);
- TEST_ASSERT(pde[index[1]].page_size == 0,
+ TEST_ASSERT(!(pde[index[1]] & PTE_LARGE_MASK),
"Expected pde to map a pte not a 2-MByte page.");
- TEST_ASSERT((*(uint64_t*)(&pde[index[1]]) & rsvd_mask) == 0,
+ TEST_ASSERT((pde[index[1]] & rsvd_mask) == 0,
"Unexpected reserved bits set.");
- pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
- TEST_ASSERT(pte[index[0]].present,
+ pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
+ TEST_ASSERT(pte[index[0]] & PTE_PRESENT_MASK,
"Expected pte to be present for gva: 0x%08lx", vaddr);
return &pte[index[0]];
@@ -360,7 +323,7 @@ static struct pageTableEntry *_vm_get_page_table_entry(struct kvm_vm *vm, int vc
uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
{
- struct pageTableEntry *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
+ uint64_t *pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
return *(uint64_t *)pte;
}
@@ -368,18 +331,17 @@ uint64_t vm_get_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr)
void vm_set_page_table_entry(struct kvm_vm *vm, int vcpuid, uint64_t vaddr,
uint64_t pte)
{
- struct pageTableEntry *new_pte = _vm_get_page_table_entry(vm, vcpuid,
- vaddr);
+ uint64_t *new_pte = _vm_get_page_table_entry(vm, vcpuid, vaddr);
*(uint64_t *)new_pte = pte;
}
void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
{
- struct pageUpperEntry *pml4e, *pml4e_start;
- struct pageUpperEntry *pdpe, *pdpe_start;
- struct pageUpperEntry *pde, *pde_start;
- struct pageTableEntry *pte, *pte_start;
+ uint64_t *pml4e, *pml4e_start;
+ uint64_t *pdpe, *pdpe_start;
+ uint64_t *pde, *pde_start;
+ uint64_t *pte, *pte_start;
if (!vm->pgd_created)
return;
@@ -389,58 +351,58 @@ void virt_dump(FILE *stream, struct kvm_vm *vm, uint8_t indent)
fprintf(stream, "%*s index hvaddr gpaddr "
"addr w exec dirty\n",
indent, "");
- pml4e_start = (struct pageUpperEntry *) addr_gpa2hva(vm, vm->pgd);
+ pml4e_start = (uint64_t *) addr_gpa2hva(vm, vm->pgd);
for (uint16_t n1 = 0; n1 <= 0x1ffu; n1++) {
pml4e = &pml4e_start[n1];
- if (!pml4e->present)
+ if (!(*pml4e & PTE_PRESENT_MASK))
continue;
- fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10lx %u "
+ fprintf(stream, "%*spml4e 0x%-3zx %p 0x%-12lx 0x%-10llx %u "
" %u\n",
indent, "",
pml4e - pml4e_start, pml4e,
- addr_hva2gpa(vm, pml4e), (uint64_t) pml4e->pfn,
- pml4e->writable, pml4e->execute_disable);
+ addr_hva2gpa(vm, pml4e), PTE_GET_PFN(*pml4e),
+ !!(*pml4e & PTE_WRITABLE_MASK), !!(*pml4e & PTE_NX_MASK));
- pdpe_start = addr_gpa2hva(vm, pml4e->pfn * vm->page_size);
+ pdpe_start = addr_gpa2hva(vm, *pml4e & PHYSICAL_PAGE_MASK);
for (uint16_t n2 = 0; n2 <= 0x1ffu; n2++) {
pdpe = &pdpe_start[n2];
- if (!pdpe->present)
+ if (!(*pdpe & PTE_PRESENT_MASK))
continue;
- fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10lx "
+ fprintf(stream, "%*spdpe 0x%-3zx %p 0x%-12lx 0x%-10llx "
"%u %u\n",
indent, "",
pdpe - pdpe_start, pdpe,
addr_hva2gpa(vm, pdpe),
- (uint64_t) pdpe->pfn, pdpe->writable,
- pdpe->execute_disable);
+ PTE_GET_PFN(*pdpe), !!(*pdpe & PTE_WRITABLE_MASK),
+ !!(*pdpe & PTE_NX_MASK));
- pde_start = addr_gpa2hva(vm, pdpe->pfn * vm->page_size);
+ pde_start = addr_gpa2hva(vm, *pdpe & PHYSICAL_PAGE_MASK);
for (uint16_t n3 = 0; n3 <= 0x1ffu; n3++) {
pde = &pde_start[n3];
- if (!pde->present)
+ if (!(*pde & PTE_PRESENT_MASK))
continue;
fprintf(stream, "%*spde 0x%-3zx %p "
- "0x%-12lx 0x%-10lx %u %u\n",
+ "0x%-12lx 0x%-10llx %u %u\n",
indent, "", pde - pde_start, pde,
addr_hva2gpa(vm, pde),
- (uint64_t) pde->pfn, pde->writable,
- pde->execute_disable);
+ PTE_GET_PFN(*pde), !!(*pde & PTE_WRITABLE_MASK),
+ !!(*pde & PTE_NX_MASK));
- pte_start = addr_gpa2hva(vm, pde->pfn * vm->page_size);
+ pte_start = addr_gpa2hva(vm, *pde & PHYSICAL_PAGE_MASK);
for (uint16_t n4 = 0; n4 <= 0x1ffu; n4++) {
pte = &pte_start[n4];
- if (!pte->present)
+ if (!(*pte & PTE_PRESENT_MASK))
continue;
fprintf(stream, "%*spte 0x%-3zx %p "
- "0x%-12lx 0x%-10lx %u %u "
+ "0x%-12lx 0x%-10llx %u %u "
" %u 0x%-10lx\n",
indent, "",
pte - pte_start, pte,
addr_hva2gpa(vm, pte),
- (uint64_t) pte->pfn,
- pte->writable,
- pte->execute_disable,
- pte->dirty,
+ PTE_GET_PFN(*pte),
+ !!(*pte & PTE_WRITABLE_MASK),
+ !!(*pte & PTE_NX_MASK),
+ !!(*pte & PTE_DIRTY_MASK),
((uint64_t) n1 << 27)
| ((uint64_t) n2 << 18)
| ((uint64_t) n3 << 9)
@@ -558,8 +520,8 @@ static void kvm_seg_set_kernel_data_64bit(struct kvm_vm *vm, uint16_t selector,
vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
{
uint16_t index[4];
- struct pageUpperEntry *pml4e, *pdpe, *pde;
- struct pageTableEntry *pte;
+ uint64_t *pml4e, *pdpe, *pde;
+ uint64_t *pte;
TEST_ASSERT(vm->mode == VM_MODE_PXXV48_4K, "Attempt to use "
"unknown or unsupported guest mode, mode: 0x%x", vm->mode);
@@ -572,22 +534,22 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva)
if (!vm->pgd_created)
goto unmapped_gva;
pml4e = addr_gpa2hva(vm, vm->pgd);
- if (!pml4e[index[3]].present)
+ if (!(pml4e[index[3]] & PTE_PRESENT_MASK))
goto unmapped_gva;
- pdpe = addr_gpa2hva(vm, pml4e[index[3]].pfn * vm->page_size);
- if (!pdpe[index[2]].present)
+ pdpe = addr_gpa2hva(vm, PTE_GET_PFN(pml4e[index[3]]) * vm->page_size);
+ if (!(pdpe[index[2]] & PTE_PRESENT_MASK))
goto unmapped_gva;
- pde = addr_gpa2hva(vm, pdpe[index[2]].pfn * vm->page_size);
- if (!pde[index[1]].present)
+ pde = addr_gpa2hva(vm, PTE_GET_PFN(pdpe[index[2]]) * vm->page_size);
+ if (!(pde[index[1]] & PTE_PRESENT_MASK))
goto unmapped_gva;
- pte = addr_gpa2hva(vm, pde[index[1]].pfn * vm->page_size);
- if (!pte[index[0]].present)
+ pte = addr_gpa2hva(vm, PTE_GET_PFN(pde[index[1]]) * vm->page_size);
+ if (!(pte[index[0]] & PTE_PRESENT_MASK))
goto unmapped_gva;
- return (pte[index[0]].pfn * vm->page_size) + (gva & 0xfffu);
+ return (PTE_GET_PFN(pte[index[0]]) * vm->page_size) + (gva & ~PAGE_MASK);
unmapped_gva:
TEST_FAIL("No mapping for vm virtual address, gva: 0x%lx", gva);
diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86_64/amx_test.c
index 52a3ef6629e8..76f65c22796f 100644
--- a/tools/testing/selftests/kvm/x86_64/amx_test.c
+++ b/tools/testing/selftests/kvm/x86_64/amx_test.c
@@ -29,7 +29,6 @@
#define X86_FEATURE_XSAVE (1 << 26)
#define X86_FEATURE_OSXSAVE (1 << 27)
-#define PAGE_SIZE (1 << 12)
#define NUM_TILES 8
#define TILE_SIZE 1024
#define XSAVE_SIZE ((NUM_TILES * TILE_SIZE) + PAGE_SIZE)
diff --git a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
index f070ff0224fa..aeb3850f81bd 100644
--- a/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
+++ b/tools/testing/selftests/kvm/x86_64/emulator_error_test.c
@@ -12,7 +12,6 @@
#include "vmx.h"
#define VCPU_ID 1
-#define PAGE_SIZE 4096
#define MAXPHYADDR 36
#define MEM_REGION_GVA 0x0000123456789000
diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
index 0d06ffa95d9d..93d77574b255 100644
--- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c
@@ -208,7 +208,7 @@ static bool sanity_check_pmu(struct kvm_vm *vm)
return success;
}
-static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents)
+static struct kvm_pmu_event_filter *alloc_pmu_event_filter(uint32_t nevents)
{
struct kvm_pmu_event_filter *f;
int size = sizeof(*f) + nevents * sizeof(f->events[0]);
@@ -220,19 +220,29 @@ static struct kvm_pmu_event_filter *make_pmu_event_filter(uint32_t nevents)
return f;
}
-static struct kvm_pmu_event_filter *event_filter(uint32_t action)
+
+static struct kvm_pmu_event_filter *
+create_pmu_event_filter(const uint64_t event_list[],
+ int nevents, uint32_t action)
{
struct kvm_pmu_event_filter *f;
int i;
- f = make_pmu_event_filter(ARRAY_SIZE(event_list));
+ f = alloc_pmu_event_filter(nevents);
f->action = action;
- for (i = 0; i < ARRAY_SIZE(event_list); i++)
+ for (i = 0; i < nevents; i++)
f->events[i] = event_list[i];
return f;
}
+static struct kvm_pmu_event_filter *event_filter(uint32_t action)
+{
+ return create_pmu_event_filter(event_list,
+ ARRAY_SIZE(event_list),
+ action);
+}
+
/*
* Remove the first occurrence of 'event' (if any) from the filter's
* event list.
@@ -271,6 +281,22 @@ static uint64_t test_with_filter(struct kvm_vm *vm,
return run_vm_to_sync(vm);
}
+static void test_amd_deny_list(struct kvm_vm *vm)
+{
+ uint64_t event = EVENT(0x1C2, 0);
+ struct kvm_pmu_event_filter *f;
+ uint64_t count;
+
+ f = create_pmu_event_filter(&event, 1, KVM_PMU_EVENT_DENY);
+ count = test_with_filter(vm, f);
+
+ free(f);
+ if (count != NUM_BRANCHES)
+ pr_info("%s: Branch instructions retired = %lu (expected %u)\n",
+ __func__, count, NUM_BRANCHES);
+ TEST_ASSERT(count, "Allowed PMU event is not counting");
+}
+
static void test_member_deny_list(struct kvm_vm *vm)
{
struct kvm_pmu_event_filter *f = event_filter(KVM_PMU_EVENT_DENY);
@@ -453,6 +479,9 @@ int main(int argc, char *argv[])
exit(KSFT_SKIP);
}
+ if (use_amd_pmu())
+ test_amd_deny_list(vm);
+
test_without_filter(vm);
test_member_deny_list(vm);
test_member_allow_list(vm);
diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86_64/smm_test.c
index a626d40fdb48..b4e0c860769e 100644
--- a/tools/testing/selftests/kvm/x86_64/smm_test.c
+++ b/tools/testing/selftests/kvm/x86_64/smm_test.c
@@ -21,8 +21,6 @@
#define VCPU_ID 1
-#define PAGE_SIZE 4096
-
#define SMRAM_SIZE 65536
#define SMRAM_MEMSLOT ((1 << 16) | 1)
#define SMRAM_PAGES (SMRAM_SIZE / PAGE_SIZE)
diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
index e683d0ac3e45..19b35c607dc6 100644
--- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
+++ b/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c
@@ -32,7 +32,6 @@
#define MSR_IA32_TSC_ADJUST 0x3b
#endif
-#define PAGE_SIZE 4096
#define VCPU_ID 5
#define TSC_ADJUST_VALUE (1ll << 32)
diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
index 865e17146815..bcd370827859 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
@@ -23,7 +23,6 @@
#define SHINFO_REGION_GVA 0xc0000000ULL
#define SHINFO_REGION_GPA 0xc0000000ULL
#define SHINFO_REGION_SLOT 10
-#define PAGE_SIZE 4096
#define DUMMY_REGION_GPA (SHINFO_REGION_GPA + (2 * PAGE_SIZE))
#define DUMMY_REGION_SLOT 11
diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
index adc94452b57c..b30fe9de1d4f 100644
--- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
+++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
@@ -15,7 +15,6 @@
#define HCALL_REGION_GPA 0xc0000000ULL
#define HCALL_REGION_SLOT 10
-#define PAGE_SIZE 4096
static struct kvm_vm *vm;
diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c
index ca40abe9daa8..da9290817866 100644
--- a/tools/testing/selftests/landlock/base_test.c
+++ b/tools/testing/selftests/landlock/base_test.c
@@ -18,10 +18,11 @@
#include "common.h"
#ifndef O_PATH
-#define O_PATH 010000000
+#define O_PATH 010000000
#endif
-TEST(inconsistent_attr) {
+TEST(inconsistent_attr)
+{
const long page_size = sysconf(_SC_PAGESIZE);
char *const buf = malloc(page_size + 1);
struct landlock_ruleset_attr *const ruleset_attr = (void *)buf;
@@ -34,20 +35,26 @@ TEST(inconsistent_attr) {
ASSERT_EQ(EINVAL, errno);
ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 1, 0));
ASSERT_EQ(EINVAL, errno);
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 7, 0));
+ ASSERT_EQ(EINVAL, errno);
ASSERT_EQ(-1, landlock_create_ruleset(NULL, 1, 0));
/* The size if less than sizeof(struct landlock_attr_enforce). */
ASSERT_EQ(EFAULT, errno);
- ASSERT_EQ(-1, landlock_create_ruleset(NULL,
- sizeof(struct landlock_ruleset_attr), 0));
+ ASSERT_EQ(-1, landlock_create_ruleset(
+ NULL, sizeof(struct landlock_ruleset_attr), 0));
ASSERT_EQ(EFAULT, errno);
ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size + 1, 0));
ASSERT_EQ(E2BIG, errno);
- ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr,
- sizeof(struct landlock_ruleset_attr), 0));
+ /* Checks minimal valid attribute size. */
+ ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, 8, 0));
+ ASSERT_EQ(ENOMSG, errno);
+ ASSERT_EQ(-1, landlock_create_ruleset(
+ ruleset_attr,
+ sizeof(struct landlock_ruleset_attr), 0));
ASSERT_EQ(ENOMSG, errno);
ASSERT_EQ(-1, landlock_create_ruleset(ruleset_attr, page_size, 0));
ASSERT_EQ(ENOMSG, errno);
@@ -63,38 +70,44 @@ TEST(inconsistent_attr) {
free(buf);
}
-TEST(abi_version) {
+TEST(abi_version)
+{
const struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
};
- ASSERT_EQ(1, landlock_create_ruleset(NULL, 0,
- LANDLOCK_CREATE_RULESET_VERSION));
+ ASSERT_EQ(2, landlock_create_ruleset(NULL, 0,
+ LANDLOCK_CREATE_RULESET_VERSION));
ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0,
- LANDLOCK_CREATE_RULESET_VERSION));
+ LANDLOCK_CREATE_RULESET_VERSION));
ASSERT_EQ(EINVAL, errno);
ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr),
- LANDLOCK_CREATE_RULESET_VERSION));
+ LANDLOCK_CREATE_RULESET_VERSION));
ASSERT_EQ(EINVAL, errno);
- ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr),
- LANDLOCK_CREATE_RULESET_VERSION));
+ ASSERT_EQ(-1,
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr),
+ LANDLOCK_CREATE_RULESET_VERSION));
ASSERT_EQ(EINVAL, errno);
ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0,
- LANDLOCK_CREATE_RULESET_VERSION | 1 << 31));
+ LANDLOCK_CREATE_RULESET_VERSION |
+ 1 << 31));
ASSERT_EQ(EINVAL, errno);
}
-TEST(inval_create_ruleset_flags) {
+/* Tests ordering of syscall argument checks. */
+TEST(create_ruleset_checks_ordering)
+{
const int last_flag = LANDLOCK_CREATE_RULESET_VERSION;
const int invalid_flag = last_flag << 1;
+ int ruleset_fd;
const struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE,
};
+ /* Checks priority for invalid flags. */
ASSERT_EQ(-1, landlock_create_ruleset(NULL, 0, invalid_flag));
ASSERT_EQ(EINVAL, errno);
@@ -102,44 +115,121 @@ TEST(inval_create_ruleset_flags) {
ASSERT_EQ(EINVAL, errno);
ASSERT_EQ(-1, landlock_create_ruleset(NULL, sizeof(ruleset_attr),
- invalid_flag));
+ invalid_flag));
+ ASSERT_EQ(EINVAL, errno);
+
+ ASSERT_EQ(-1,
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr),
+ invalid_flag));
ASSERT_EQ(EINVAL, errno);
- ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), invalid_flag));
+ /* Checks too big ruleset_attr size. */
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, -1, 0));
+ ASSERT_EQ(E2BIG, errno);
+
+ /* Checks too small ruleset_attr size. */
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, 0));
+ ASSERT_EQ(EINVAL, errno);
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 1, 0));
ASSERT_EQ(EINVAL, errno);
+
+ /* Checks valid call. */
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
}
-TEST(empty_path_beneath_attr) {
+/* Tests ordering of syscall argument checks. */
+TEST(add_rule_checks_ordering)
+{
const struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE,
};
- const int ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ struct landlock_path_beneath_attr path_beneath_attr = {
+ .allowed_access = LANDLOCK_ACCESS_FS_EXECUTE,
+ .parent_fd = -1,
+ };
+ const int ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
- /* Similar to struct landlock_path_beneath_attr.parent_fd = 0 */
+ /* Checks invalid flags. */
+ ASSERT_EQ(-1, landlock_add_rule(-1, 0, NULL, 1));
+ ASSERT_EQ(EINVAL, errno);
+
+ /* Checks invalid ruleset FD. */
+ ASSERT_EQ(-1, landlock_add_rule(-1, 0, NULL, 0));
+ ASSERT_EQ(EBADF, errno);
+
+ /* Checks invalid rule type. */
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, 0, NULL, 0));
+ ASSERT_EQ(EINVAL, errno);
+
+ /* Checks invalid rule attr. */
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- NULL, 0));
+ NULL, 0));
ASSERT_EQ(EFAULT, errno);
+
+ /* Checks invalid path_beneath.parent_fd. */
+ ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath_attr, 0));
+ ASSERT_EQ(EBADF, errno);
+
+ /* Checks valid call. */
+ path_beneath_attr.parent_fd =
+ open("/tmp", O_PATH | O_NOFOLLOW | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath_attr.parent_fd);
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath_attr, 0));
+ ASSERT_EQ(0, close(path_beneath_attr.parent_fd));
ASSERT_EQ(0, close(ruleset_fd));
}
-TEST(inval_fd_enforce) {
+/* Tests ordering of syscall argument and permission checks. */
+TEST(restrict_self_checks_ordering)
+{
+ const struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = LANDLOCK_ACCESS_FS_EXECUTE,
+ };
+ struct landlock_path_beneath_attr path_beneath_attr = {
+ .allowed_access = LANDLOCK_ACCESS_FS_EXECUTE,
+ .parent_fd = -1,
+ };
+ const int ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+
+ ASSERT_LE(0, ruleset_fd);
+ path_beneath_attr.parent_fd =
+ open("/tmp", O_PATH | O_NOFOLLOW | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath_attr.parent_fd);
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath_attr, 0));
+ ASSERT_EQ(0, close(path_beneath_attr.parent_fd));
+
+ /* Checks unprivileged enforcement without no_new_privs. */
+ drop_caps(_metadata);
+ ASSERT_EQ(-1, landlock_restrict_self(-1, -1));
+ ASSERT_EQ(EPERM, errno);
+ ASSERT_EQ(-1, landlock_restrict_self(-1, 0));
+ ASSERT_EQ(EPERM, errno);
+ ASSERT_EQ(-1, landlock_restrict_self(ruleset_fd, 0));
+ ASSERT_EQ(EPERM, errno);
+
ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ /* Checks invalid flags. */
+ ASSERT_EQ(-1, landlock_restrict_self(-1, -1));
+ ASSERT_EQ(EINVAL, errno);
+
+ /* Checks invalid ruleset FD. */
ASSERT_EQ(-1, landlock_restrict_self(-1, 0));
ASSERT_EQ(EBADF, errno);
-}
-
-TEST(unpriv_enforce_without_no_new_privs) {
- int err;
- drop_caps(_metadata);
- err = landlock_restrict_self(-1, 0);
- ASSERT_EQ(EPERM, errno);
- ASSERT_EQ(err, -1);
+ /* Checks valid call. */
+ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
+ ASSERT_EQ(0, close(ruleset_fd));
}
TEST(ruleset_fd_io)
@@ -151,8 +241,8 @@ TEST(ruleset_fd_io)
char buf;
drop_caps(_metadata);
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
ASSERT_EQ(-1, write(ruleset_fd, ".", 1));
@@ -197,14 +287,15 @@ TEST(ruleset_fd_transfer)
drop_caps(_metadata);
/* Creates a test ruleset with a simple rule. */
- ruleset_fd_tx = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ ruleset_fd_tx =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd_tx);
- path_beneath_attr.parent_fd = open("/tmp", O_PATH | O_NOFOLLOW |
- O_DIRECTORY | O_CLOEXEC);
+ path_beneath_attr.parent_fd =
+ open("/tmp", O_PATH | O_NOFOLLOW | O_DIRECTORY | O_CLOEXEC);
ASSERT_LE(0, path_beneath_attr.parent_fd);
- ASSERT_EQ(0, landlock_add_rule(ruleset_fd_tx, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath_attr, 0));
+ ASSERT_EQ(0,
+ landlock_add_rule(ruleset_fd_tx, LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath_attr, 0));
ASSERT_EQ(0, close(path_beneath_attr.parent_fd));
cmsg = CMSG_FIRSTHDR(&msg);
@@ -215,7 +306,8 @@ TEST(ruleset_fd_transfer)
memcpy(CMSG_DATA(cmsg), &ruleset_fd_tx, sizeof(ruleset_fd_tx));
/* Sends the ruleset FD over a socketpair and then close it. */
- ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0, socket_fds));
+ ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_STREAM | SOCK_CLOEXEC, 0,
+ socket_fds));
ASSERT_EQ(sizeof(data_tx), sendmsg(socket_fds[0], &msg, 0));
ASSERT_EQ(0, close(socket_fds[0]));
ASSERT_EQ(0, close(ruleset_fd_tx));
@@ -226,7 +318,8 @@ TEST(ruleset_fd_transfer)
int ruleset_fd_rx;
*(char *)msg.msg_iov->iov_base = '\0';
- ASSERT_EQ(sizeof(data_tx), recvmsg(socket_fds[1], &msg, MSG_CMSG_CLOEXEC));
+ ASSERT_EQ(sizeof(data_tx),
+ recvmsg(socket_fds[1], &msg, MSG_CMSG_CLOEXEC));
ASSERT_EQ('.', *(char *)msg.msg_iov->iov_base);
ASSERT_EQ(0, close(socket_fds[1]));
cmsg = CMSG_FIRSTHDR(&msg);
diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index 183b7e8e1b95..7ba18eb23783 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -25,6 +25,7 @@
* this to be possible, we must not call abort() but instead exit smoothly
* (hence the step print).
*/
+/* clang-format off */
#define TEST_F_FORK(fixture_name, test_name) \
static void fixture_name##_##test_name##_child( \
struct __test_metadata *_metadata, \
@@ -71,11 +72,12 @@
FIXTURE_DATA(fixture_name) __attribute__((unused)) *self, \
const FIXTURE_VARIANT(fixture_name) \
__attribute__((unused)) *variant)
+/* clang-format on */
#ifndef landlock_create_ruleset
-static inline int landlock_create_ruleset(
- const struct landlock_ruleset_attr *const attr,
- const size_t size, const __u32 flags)
+static inline int
+landlock_create_ruleset(const struct landlock_ruleset_attr *const attr,
+ const size_t size, const __u32 flags)
{
return syscall(__NR_landlock_create_ruleset, attr, size, flags);
}
@@ -83,17 +85,18 @@ static inline int landlock_create_ruleset(
#ifndef landlock_add_rule
static inline int landlock_add_rule(const int ruleset_fd,
- const enum landlock_rule_type rule_type,
- const void *const rule_attr, const __u32 flags)
+ const enum landlock_rule_type rule_type,
+ const void *const rule_attr,
+ const __u32 flags)
{
- return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type,
- rule_attr, flags);
+ return syscall(__NR_landlock_add_rule, ruleset_fd, rule_type, rule_attr,
+ flags);
}
#endif
#ifndef landlock_restrict_self
static inline int landlock_restrict_self(const int ruleset_fd,
- const __u32 flags)
+ const __u32 flags)
{
return syscall(__NR_landlock_restrict_self, ruleset_fd, flags);
}
@@ -111,69 +114,76 @@ static void _init_caps(struct __test_metadata *const _metadata, bool drop_all)
};
cap_p = cap_get_proc();
- EXPECT_NE(NULL, cap_p) {
+ EXPECT_NE(NULL, cap_p)
+ {
TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
}
- EXPECT_NE(-1, cap_clear(cap_p)) {
+ EXPECT_NE(-1, cap_clear(cap_p))
+ {
TH_LOG("Failed to cap_clear: %s", strerror(errno));
}
if (!drop_all) {
EXPECT_NE(-1, cap_set_flag(cap_p, CAP_PERMITTED,
- ARRAY_SIZE(caps), caps, CAP_SET)) {
+ ARRAY_SIZE(caps), caps, CAP_SET))
+ {
TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
}
}
- EXPECT_NE(-1, cap_set_proc(cap_p)) {
+ EXPECT_NE(-1, cap_set_proc(cap_p))
+ {
TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
}
- EXPECT_NE(-1, cap_free(cap_p)) {
+ EXPECT_NE(-1, cap_free(cap_p))
+ {
TH_LOG("Failed to cap_free: %s", strerror(errno));
}
}
/* We cannot put such helpers in a library because of kselftest_harness.h . */
-__attribute__((__unused__))
-static void disable_caps(struct __test_metadata *const _metadata)
+__attribute__((__unused__)) static void
+disable_caps(struct __test_metadata *const _metadata)
{
_init_caps(_metadata, false);
}
-__attribute__((__unused__))
-static void drop_caps(struct __test_metadata *const _metadata)
+__attribute__((__unused__)) static void
+drop_caps(struct __test_metadata *const _metadata)
{
_init_caps(_metadata, true);
}
static void _effective_cap(struct __test_metadata *const _metadata,
- const cap_value_t caps, const cap_flag_value_t value)
+ const cap_value_t caps, const cap_flag_value_t value)
{
cap_t cap_p;
cap_p = cap_get_proc();
- EXPECT_NE(NULL, cap_p) {
+ EXPECT_NE(NULL, cap_p)
+ {
TH_LOG("Failed to cap_get_proc: %s", strerror(errno));
}
- EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value)) {
+ EXPECT_NE(-1, cap_set_flag(cap_p, CAP_EFFECTIVE, 1, &caps, value))
+ {
TH_LOG("Failed to cap_set_flag: %s", strerror(errno));
}
- EXPECT_NE(-1, cap_set_proc(cap_p)) {
+ EXPECT_NE(-1, cap_set_proc(cap_p))
+ {
TH_LOG("Failed to cap_set_proc: %s", strerror(errno));
}
- EXPECT_NE(-1, cap_free(cap_p)) {
+ EXPECT_NE(-1, cap_free(cap_p))
+ {
TH_LOG("Failed to cap_free: %s", strerror(errno));
}
}
-__attribute__((__unused__))
-static void set_cap(struct __test_metadata *const _metadata,
- const cap_value_t caps)
+__attribute__((__unused__)) static void
+set_cap(struct __test_metadata *const _metadata, const cap_value_t caps)
{
_effective_cap(_metadata, caps, CAP_SET);
}
-__attribute__((__unused__))
-static void clear_cap(struct __test_metadata *const _metadata,
- const cap_value_t caps)
+__attribute__((__unused__)) static void
+clear_cap(struct __test_metadata *const _metadata, const cap_value_t caps)
{
_effective_cap(_metadata, caps, CAP_CLEAR);
}
diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c
index 10c9a1e4ebd9..21a2ce8fa739 100644
--- a/tools/testing/selftests/landlock/fs_test.c
+++ b/tools/testing/selftests/landlock/fs_test.c
@@ -22,8 +22,21 @@
#include "common.h"
-#define TMP_DIR "tmp"
-#define BINARY_PATH "./true"
+#ifndef renameat2
+int renameat2(int olddirfd, const char *oldpath, int newdirfd,
+ const char *newpath, unsigned int flags)
+{
+ return syscall(__NR_renameat2, olddirfd, oldpath, newdirfd, newpath,
+ flags);
+}
+#endif
+
+#ifndef RENAME_EXCHANGE
+#define RENAME_EXCHANGE (1 << 1)
+#endif
+
+#define TMP_DIR "tmp"
+#define BINARY_PATH "./true"
/* Paths (sibling number and depth) */
static const char dir_s1d1[] = TMP_DIR "/s1d1";
@@ -75,7 +88,7 @@ static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3";
*/
static void mkdir_parents(struct __test_metadata *const _metadata,
- const char *const path)
+ const char *const path)
{
char *walker;
const char *parent;
@@ -90,9 +103,10 @@ static void mkdir_parents(struct __test_metadata *const _metadata,
continue;
walker[i] = '\0';
err = mkdir(parent, 0700);
- ASSERT_FALSE(err && errno != EEXIST) {
- TH_LOG("Failed to create directory \"%s\": %s",
- parent, strerror(errno));
+ ASSERT_FALSE(err && errno != EEXIST)
+ {
+ TH_LOG("Failed to create directory \"%s\": %s", parent,
+ strerror(errno));
}
walker[i] = '/';
}
@@ -100,22 +114,24 @@ static void mkdir_parents(struct __test_metadata *const _metadata,
}
static void create_directory(struct __test_metadata *const _metadata,
- const char *const path)
+ const char *const path)
{
mkdir_parents(_metadata, path);
- ASSERT_EQ(0, mkdir(path, 0700)) {
+ ASSERT_EQ(0, mkdir(path, 0700))
+ {
TH_LOG("Failed to create directory \"%s\": %s", path,
- strerror(errno));
+ strerror(errno));
}
}
static void create_file(struct __test_metadata *const _metadata,
- const char *const path)
+ const char *const path)
{
mkdir_parents(_metadata, path);
- ASSERT_EQ(0, mknod(path, S_IFREG | 0700, 0)) {
+ ASSERT_EQ(0, mknod(path, S_IFREG | 0700, 0))
+ {
TH_LOG("Failed to create file \"%s\": %s", path,
- strerror(errno));
+ strerror(errno));
}
}
@@ -130,7 +146,7 @@ static int remove_path(const char *const path)
goto out;
}
if (unlink(path) && rmdir(path)) {
- if (errno != ENOENT)
+ if (errno != ENOENT && errno != ENOTDIR)
err = errno;
goto out;
}
@@ -221,8 +237,9 @@ static void remove_layout1(struct __test_metadata *const _metadata)
EXPECT_EQ(0, remove_path(dir_s3d2));
}
-FIXTURE(layout1) {
-};
+/* clang-format off */
+FIXTURE(layout1) {};
+/* clang-format on */
FIXTURE_SETUP(layout1)
{
@@ -242,7 +259,8 @@ FIXTURE_TEARDOWN(layout1)
* This helper enables to use the ASSERT_* macros and print the line number
* pointing to the test caller.
*/
-static int test_open_rel(const int dirfd, const char *const path, const int flags)
+static int test_open_rel(const int dirfd, const char *const path,
+ const int flags)
{
int fd;
@@ -291,23 +309,23 @@ TEST_F_FORK(layout1, inval)
{
struct landlock_path_beneath_attr path_beneath = {
.allowed_access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
.parent_fd = -1,
};
struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
};
int ruleset_fd;
- path_beneath.parent_fd = open(dir_s1d2, O_PATH | O_DIRECTORY |
- O_CLOEXEC);
+ path_beneath.parent_fd =
+ open(dir_s1d2, O_PATH | O_DIRECTORY | O_CLOEXEC);
ASSERT_LE(0, path_beneath.parent_fd);
ruleset_fd = open(dir_s1d1, O_PATH | O_DIRECTORY | O_CLOEXEC);
ASSERT_LE(0, ruleset_fd);
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
/* Returns EBADF because ruleset_fd is not a landlock-ruleset FD. */
ASSERT_EQ(EBADF, errno);
ASSERT_EQ(0, close(ruleset_fd));
@@ -315,55 +333,55 @@ TEST_F_FORK(layout1, inval)
ruleset_fd = open(dir_s1d1, O_DIRECTORY | O_CLOEXEC);
ASSERT_LE(0, ruleset_fd);
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
/* Returns EBADFD because ruleset_fd is not a valid ruleset. */
ASSERT_EQ(EBADFD, errno);
ASSERT_EQ(0, close(ruleset_fd));
/* Gets a real ruleset. */
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(0, close(path_beneath.parent_fd));
/* Tests without O_PATH. */
path_beneath.parent_fd = open(dir_s1d2, O_DIRECTORY | O_CLOEXEC);
ASSERT_LE(0, path_beneath.parent_fd);
ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(0, close(path_beneath.parent_fd));
/* Tests with a ruleset FD. */
path_beneath.parent_fd = ruleset_fd;
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(EBADFD, errno);
/* Checks unhandled allowed_access. */
- path_beneath.parent_fd = open(dir_s1d2, O_PATH | O_DIRECTORY |
- O_CLOEXEC);
+ path_beneath.parent_fd =
+ open(dir_s1d2, O_PATH | O_DIRECTORY | O_CLOEXEC);
ASSERT_LE(0, path_beneath.parent_fd);
/* Test with legitimate values. */
path_beneath.allowed_access |= LANDLOCK_ACCESS_FS_EXECUTE;
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(EINVAL, errno);
path_beneath.allowed_access &= ~LANDLOCK_ACCESS_FS_EXECUTE;
/* Test with unknown (64-bits) value. */
path_beneath.allowed_access |= (1ULL << 60);
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(EINVAL, errno);
path_beneath.allowed_access &= ~(1ULL << 60);
/* Test with no access. */
path_beneath.allowed_access = 0;
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(ENOMSG, errno);
path_beneath.allowed_access &= ~(1ULL << 60);
@@ -376,12 +394,14 @@ TEST_F_FORK(layout1, inval)
ASSERT_EQ(0, close(ruleset_fd));
}
+/* clang-format off */
+
#define ACCESS_FILE ( \
LANDLOCK_ACCESS_FS_EXECUTE | \
LANDLOCK_ACCESS_FS_WRITE_FILE | \
LANDLOCK_ACCESS_FS_READ_FILE)
-#define ACCESS_LAST LANDLOCK_ACCESS_FS_MAKE_SYM
+#define ACCESS_LAST LANDLOCK_ACCESS_FS_REFER
#define ACCESS_ALL ( \
ACCESS_FILE | \
@@ -394,55 +414,90 @@ TEST_F_FORK(layout1, inval)
LANDLOCK_ACCESS_FS_MAKE_SOCK | \
LANDLOCK_ACCESS_FS_MAKE_FIFO | \
LANDLOCK_ACCESS_FS_MAKE_BLOCK | \
+ LANDLOCK_ACCESS_FS_MAKE_SYM | \
ACCESS_LAST)
-TEST_F_FORK(layout1, file_access_rights)
+/* clang-format on */
+
+TEST_F_FORK(layout1, file_and_dir_access_rights)
{
__u64 access;
int err;
- struct landlock_path_beneath_attr path_beneath = {};
+ struct landlock_path_beneath_attr path_beneath_file = {},
+ path_beneath_dir = {};
struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = ACCESS_ALL,
};
- const int ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ const int ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
/* Tests access rights for files. */
- path_beneath.parent_fd = open(file1_s1d2, O_PATH | O_CLOEXEC);
- ASSERT_LE(0, path_beneath.parent_fd);
+ path_beneath_file.parent_fd = open(file1_s1d2, O_PATH | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath_file.parent_fd);
+
+ /* Tests access rights for directories. */
+ path_beneath_dir.parent_fd =
+ open(dir_s1d2, O_PATH | O_DIRECTORY | O_CLOEXEC);
+ ASSERT_LE(0, path_beneath_dir.parent_fd);
+
for (access = 1; access <= ACCESS_LAST; access <<= 1) {
- path_beneath.allowed_access = access;
+ path_beneath_dir.allowed_access = access;
+ ASSERT_EQ(0, landlock_add_rule(ruleset_fd,
+ LANDLOCK_RULE_PATH_BENEATH,
+ &path_beneath_dir, 0));
+
+ path_beneath_file.allowed_access = access;
err = landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0);
- if ((access | ACCESS_FILE) == ACCESS_FILE) {
+ &path_beneath_file, 0);
+ if (access & ACCESS_FILE) {
ASSERT_EQ(0, err);
} else {
ASSERT_EQ(-1, err);
ASSERT_EQ(EINVAL, errno);
}
}
- ASSERT_EQ(0, close(path_beneath.parent_fd));
+ ASSERT_EQ(0, close(path_beneath_file.parent_fd));
+ ASSERT_EQ(0, close(path_beneath_dir.parent_fd));
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, unknown_access_rights)
+{
+ __u64 access_mask;
+
+ for (access_mask = 1ULL << 63; access_mask != ACCESS_LAST;
+ access_mask >>= 1) {
+ struct landlock_ruleset_attr ruleset_attr = {
+ .handled_access_fs = access_mask,
+ };
+
+ ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr,
+ sizeof(ruleset_attr), 0));
+ ASSERT_EQ(EINVAL, errno);
+ }
}
static void add_path_beneath(struct __test_metadata *const _metadata,
- const int ruleset_fd, const __u64 allowed_access,
- const char *const path)
+ const int ruleset_fd, const __u64 allowed_access,
+ const char *const path)
{
struct landlock_path_beneath_attr path_beneath = {
.allowed_access = allowed_access,
};
path_beneath.parent_fd = open(path, O_PATH | O_CLOEXEC);
- ASSERT_LE(0, path_beneath.parent_fd) {
+ ASSERT_LE(0, path_beneath.parent_fd)
+ {
TH_LOG("Failed to open directory \"%s\": %s", path,
- strerror(errno));
+ strerror(errno));
}
ASSERT_EQ(0, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0)) {
+ &path_beneath, 0))
+ {
TH_LOG("Failed to update the ruleset with \"%s\": %s", path,
- strerror(errno));
+ strerror(errno));
}
ASSERT_EQ(0, close(path_beneath.parent_fd));
}
@@ -452,6 +507,8 @@ struct rule {
__u64 access;
};
+/* clang-format off */
+
#define ACCESS_RO ( \
LANDLOCK_ACCESS_FS_READ_FILE | \
LANDLOCK_ACCESS_FS_READ_DIR)
@@ -460,39 +517,46 @@ struct rule {
ACCESS_RO | \
LANDLOCK_ACCESS_FS_WRITE_FILE)
+/* clang-format on */
+
static int create_ruleset(struct __test_metadata *const _metadata,
- const __u64 handled_access_fs, const struct rule rules[])
+ const __u64 handled_access_fs,
+ const struct rule rules[])
{
int ruleset_fd, i;
struct landlock_ruleset_attr ruleset_attr = {
.handled_access_fs = handled_access_fs,
};
- ASSERT_NE(NULL, rules) {
+ ASSERT_NE(NULL, rules)
+ {
TH_LOG("No rule list");
}
- ASSERT_NE(NULL, rules[0].path) {
+ ASSERT_NE(NULL, rules[0].path)
+ {
TH_LOG("Empty rule list");
}
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
- ASSERT_LE(0, ruleset_fd) {
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ ASSERT_LE(0, ruleset_fd)
+ {
TH_LOG("Failed to create a ruleset: %s", strerror(errno));
}
for (i = 0; rules[i].path; i++) {
add_path_beneath(_metadata, ruleset_fd, rules[i].access,
- rules[i].path);
+ rules[i].path);
}
return ruleset_fd;
}
static void enforce_ruleset(struct __test_metadata *const _metadata,
- const int ruleset_fd)
+ const int ruleset_fd)
{
ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
- ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0)) {
+ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0))
+ {
TH_LOG("Failed to enforce ruleset: %s", strerror(errno));
}
}
@@ -503,13 +567,14 @@ TEST_F_FORK(layout1, proc_nsfs)
{
.path = "/dev/null",
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
struct landlock_path_beneath_attr path_beneath;
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access |
- LANDLOCK_ACCESS_FS_READ_DIR, rules);
+ const int ruleset_fd = create_ruleset(
+ _metadata, rules[0].access | LANDLOCK_ACCESS_FS_READ_DIR,
+ rules);
ASSERT_LE(0, ruleset_fd);
ASSERT_EQ(0, test_open("/proc/self/ns/mnt", O_RDONLY));
@@ -536,22 +601,23 @@ TEST_F_FORK(layout1, proc_nsfs)
* references to a ruleset.
*/
path_beneath.allowed_access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
path_beneath.parent_fd = open("/proc/self/ns/mnt", O_PATH | O_CLOEXEC);
ASSERT_LE(0, path_beneath.parent_fd);
ASSERT_EQ(-1, landlock_add_rule(ruleset_fd, LANDLOCK_RULE_PATH_BENEATH,
- &path_beneath, 0));
+ &path_beneath, 0));
ASSERT_EQ(EBADFD, errno);
ASSERT_EQ(0, close(path_beneath.parent_fd));
}
-TEST_F_FORK(layout1, unpriv) {
+TEST_F_FORK(layout1, unpriv)
+{
const struct rule rules[] = {
{
.path = dir_s1d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
int ruleset_fd;
@@ -577,9 +643,9 @@ TEST_F_FORK(layout1, effective_access)
{
.path = file1_s2d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
char buf;
@@ -589,17 +655,23 @@ TEST_F_FORK(layout1, effective_access)
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
- /* Tests on a directory. */
+ /* Tests on a directory (with or without O_PATH). */
ASSERT_EQ(EACCES, test_open("/", O_RDONLY));
+ ASSERT_EQ(0, test_open("/", O_RDONLY | O_PATH));
ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY | O_PATH));
ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY | O_PATH));
+
ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY));
ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY));
ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
- /* Tests on a file. */
+ /* Tests on a file (with or without O_PATH). */
ASSERT_EQ(EACCES, test_open(dir_s2d2, O_RDONLY));
+ ASSERT_EQ(0, test_open(dir_s2d2, O_RDONLY | O_PATH));
+
ASSERT_EQ(0, test_open(file1_s2d2, O_RDONLY));
/* Checks effective read and write actions. */
@@ -626,7 +698,7 @@ TEST_F_FORK(layout1, unhandled_access)
.path = dir_s1d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
/* Here, we only handle read accesses, not write accesses. */
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RO, rules);
@@ -653,14 +725,14 @@ TEST_F_FORK(layout1, ruleset_overlap)
{
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
{
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_READ_DIR,
+ LANDLOCK_ACCESS_FS_READ_DIR,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -687,6 +759,113 @@ TEST_F_FORK(layout1, ruleset_overlap)
ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY | O_DIRECTORY));
}
+TEST_F_FORK(layout1, layer_rule_unions)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE,
+ },
+ /* dir_s1d3 should allow READ_FILE and WRITE_FILE (O_RDWR). */
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {},
+ };
+ const struct rule layer2[] = {
+ /* Doesn't change anything from layer1. */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {},
+ };
+ const struct rule layer3[] = {
+ /* Only allows write (but not read) to dir_s1d3. */
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_WRITE_FILE,
+ },
+ {},
+ };
+ int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks s1d1 hierarchy with layer1. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d2 hierarchy with layer1. */
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d3 hierarchy with layer1. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY));
+ /* dir_s1d3 should allow READ_FILE and WRITE_FILE (O_RDWR). */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Doesn't change anything from layer1. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer2);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks s1d1 hierarchy with layer2. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d2 hierarchy with layer2. */
+ ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d3 hierarchy with layer2. */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY));
+ /* dir_s1d3 should allow READ_FILE and WRITE_FILE (O_RDWR). */
+ ASSERT_EQ(0, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Only allows write (but not read) to dir_s1d3. */
+ ruleset_fd = create_ruleset(_metadata, ACCESS_RW, layer3);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks s1d1 hierarchy with layer3. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d2 hierarchy with layer3. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_WRONLY));
+ ASSERT_EQ(EACCES, test_open(file1_s1d2, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+
+ /* Checks s1d3 hierarchy with layer3. */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_RDONLY));
+ ASSERT_EQ(0, test_open(file1_s1d3, O_WRONLY));
+ /* dir_s1d3 should now deny READ_FILE and WRITE_FILE (O_RDWR). */
+ ASSERT_EQ(EACCES, test_open(file1_s1d3, O_RDWR));
+ ASSERT_EQ(EACCES, test_open(dir_s1d1, O_RDONLY | O_DIRECTORY));
+}
+
TEST_F_FORK(layout1, non_overlapping_accesses)
{
const struct rule layer1[] = {
@@ -694,22 +873,22 @@ TEST_F_FORK(layout1, non_overlapping_accesses)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_MAKE_REG,
},
- {}
+ {},
};
const struct rule layer2[] = {
{
.path = dir_s1d3,
.access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
},
- {}
+ {},
};
int ruleset_fd;
ASSERT_EQ(0, unlink(file1_s1d1));
ASSERT_EQ(0, unlink(file1_s1d2));
- ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG,
- layer1);
+ ruleset_fd =
+ create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_REG, layer1);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -720,7 +899,7 @@ TEST_F_FORK(layout1, non_overlapping_accesses)
ASSERT_EQ(0, unlink(file1_s1d2));
ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_REMOVE_FILE,
- layer2);
+ layer2);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -758,7 +937,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
.path = file1_s1d3,
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
/* First rule with write restrictions. */
const struct rule layer2_read_write[] = {
@@ -766,14 +945,14 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
{
.path = dir_s1d3,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
/* ...but also denies read access via its grandparent directory. */
{
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
const struct rule layer3_read[] = {
/* Allows read access via its great-grandparent directory. */
@@ -781,7 +960,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
.path = dir_s1d1,
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
const struct rule layer4_read_write[] = {
/*
@@ -792,7 +971,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
const struct rule layer5_read[] = {
/*
@@ -803,7 +982,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
const struct rule layer6_execute[] = {
/*
@@ -814,7 +993,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
.path = dir_s2d1,
.access = LANDLOCK_ACCESS_FS_EXECUTE,
},
- {}
+ {},
};
const struct rule layer7_read_write[] = {
/*
@@ -825,12 +1004,12 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
int ruleset_fd;
ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
- layer1_read);
+ layer1_read);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -840,8 +1019,10 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY));
- ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE, layer2_read_write);
+ ruleset_fd = create_ruleset(_metadata,
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ layer2_read_write);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -852,7 +1033,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY));
ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
- layer3_read);
+ layer3_read);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -863,8 +1044,10 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
ASSERT_EQ(0, test_open(file2_s1d3, O_WRONLY));
/* This time, denies write access for the file hierarchy. */
- ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE, layer4_read_write);
+ ruleset_fd = create_ruleset(_metadata,
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ layer4_read_write);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -879,7 +1062,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY));
ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE,
- layer5_read);
+ layer5_read);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -891,7 +1074,7 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_EXECUTE,
- layer6_execute);
+ layer6_execute);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -902,8 +1085,10 @@ TEST_F_FORK(layout1, interleaved_masked_accesses)
ASSERT_EQ(EACCES, test_open(file2_s1d3, O_WRONLY));
ASSERT_EQ(EACCES, test_open(file2_s1d3, O_RDONLY));
- ruleset_fd = create_ruleset(_metadata, LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE, layer7_read_write);
+ ruleset_fd = create_ruleset(_metadata,
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
+ layer7_read_write);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -921,9 +1106,9 @@ TEST_F_FORK(layout1, inherit_subset)
{
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_READ_DIR,
+ LANDLOCK_ACCESS_FS_READ_DIR,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -949,7 +1134,7 @@ TEST_F_FORK(layout1, inherit_subset)
* ANDed with the previous ones.
*/
add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_WRITE_FILE,
- dir_s1d2);
+ dir_s1d2);
/*
* According to ruleset_fd, dir_s1d2 should now have the
* LANDLOCK_ACCESS_FS_READ_FILE and LANDLOCK_ACCESS_FS_WRITE_FILE
@@ -1004,7 +1189,7 @@ TEST_F_FORK(layout1, inherit_subset)
* that there was no rule tied to it before.
*/
add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_WRITE_FILE,
- dir_s1d3);
+ dir_s1d3);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -1039,7 +1224,7 @@ TEST_F_FORK(layout1, inherit_superset)
.path = dir_s1d3,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1054,8 +1239,10 @@ TEST_F_FORK(layout1, inherit_superset)
ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY));
/* Now dir_s1d2, parent of dir_s1d3, gets a new rule tied to it. */
- add_path_beneath(_metadata, ruleset_fd, LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_READ_DIR, dir_s1d2);
+ add_path_beneath(_metadata, ruleset_fd,
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_READ_DIR,
+ dir_s1d2);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
@@ -1075,12 +1262,12 @@ TEST_F_FORK(layout1, max_layers)
.path = dir_s1d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
ASSERT_LE(0, ruleset_fd);
- for (i = 0; i < 64; i++)
+ for (i = 0; i < 16; i++)
enforce_ruleset(_metadata, ruleset_fd);
for (i = 0; i < 2; i++) {
@@ -1097,15 +1284,15 @@ TEST_F_FORK(layout1, empty_or_same_ruleset)
int ruleset_fd;
/* Tests empty handled_access_fs. */
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(-1, ruleset_fd);
ASSERT_EQ(ENOMSG, errno);
/* Enforces policy which deny read access to all files. */
ruleset_attr.handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE;
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
@@ -1113,8 +1300,8 @@ TEST_F_FORK(layout1, empty_or_same_ruleset)
/* Nests a policy which deny read access to all directories. */
ruleset_attr.handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR;
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(EACCES, test_open(file1_s1d1, O_RDONLY));
@@ -1137,7 +1324,7 @@ TEST_F_FORK(layout1, rule_on_mountpoint)
.path = dir_s3d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1166,7 +1353,7 @@ TEST_F_FORK(layout1, rule_over_mountpoint)
.path = dir_s3d1,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1194,7 +1381,7 @@ TEST_F_FORK(layout1, rule_over_root_allow_then_deny)
.path = "/",
.access = ACCESS_RO,
},
- {}
+ {},
};
int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1224,7 +1411,7 @@ TEST_F_FORK(layout1, rule_over_root_deny)
.path = "/",
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1244,12 +1431,13 @@ TEST_F_FORK(layout1, rule_inside_mount_ns)
.path = "s3d3",
.access = ACCESS_RO,
},
- {}
+ {},
};
int ruleset_fd;
set_cap(_metadata, CAP_SYS_ADMIN);
- ASSERT_EQ(0, syscall(SYS_pivot_root, dir_s3d2, dir_s3d3)) {
+ ASSERT_EQ(0, syscall(__NR_pivot_root, dir_s3d2, dir_s3d3))
+ {
TH_LOG("Failed to pivot root: %s", strerror(errno));
};
ASSERT_EQ(0, chdir("/"));
@@ -1271,7 +1459,7 @@ TEST_F_FORK(layout1, mount_and_pivot)
.path = dir_s3d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1282,7 +1470,7 @@ TEST_F_FORK(layout1, mount_and_pivot)
set_cap(_metadata, CAP_SYS_ADMIN);
ASSERT_EQ(-1, mount(NULL, dir_s3d2, NULL, MS_RDONLY, NULL));
ASSERT_EQ(EPERM, errno);
- ASSERT_EQ(-1, syscall(SYS_pivot_root, dir_s3d2, dir_s3d3));
+ ASSERT_EQ(-1, syscall(__NR_pivot_root, dir_s3d2, dir_s3d3));
ASSERT_EQ(EPERM, errno);
clear_cap(_metadata, CAP_SYS_ADMIN);
}
@@ -1294,28 +1482,29 @@ TEST_F_FORK(layout1, move_mount)
.path = dir_s3d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
ASSERT_LE(0, ruleset_fd);
set_cap(_metadata, CAP_SYS_ADMIN);
- ASSERT_EQ(0, syscall(SYS_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD,
- dir_s1d2, 0)) {
+ ASSERT_EQ(0, syscall(__NR_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD,
+ dir_s1d2, 0))
+ {
TH_LOG("Failed to move mount: %s", strerror(errno));
}
- ASSERT_EQ(0, syscall(SYS_move_mount, AT_FDCWD, dir_s1d2, AT_FDCWD,
- dir_s3d2, 0));
+ ASSERT_EQ(0, syscall(__NR_move_mount, AT_FDCWD, dir_s1d2, AT_FDCWD,
+ dir_s3d2, 0));
clear_cap(_metadata, CAP_SYS_ADMIN);
enforce_ruleset(_metadata, ruleset_fd);
ASSERT_EQ(0, close(ruleset_fd));
set_cap(_metadata, CAP_SYS_ADMIN);
- ASSERT_EQ(-1, syscall(SYS_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD,
- dir_s1d2, 0));
+ ASSERT_EQ(-1, syscall(__NR_move_mount, AT_FDCWD, dir_s3d2, AT_FDCWD,
+ dir_s1d2, 0));
ASSERT_EQ(EPERM, errno);
clear_cap(_metadata, CAP_SYS_ADMIN);
}
@@ -1335,7 +1524,7 @@ TEST_F_FORK(layout1, release_inodes)
.path = dir_s3d3,
.access = ACCESS_RO,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, ACCESS_RW, rules);
@@ -1362,7 +1551,7 @@ enum relative_access {
};
static void test_relative_path(struct __test_metadata *const _metadata,
- const enum relative_access rel)
+ const enum relative_access rel)
{
/*
* Common layer to check that chroot doesn't ignore it (i.e. a chroot
@@ -1373,7 +1562,7 @@ static void test_relative_path(struct __test_metadata *const _metadata,
.path = TMP_DIR,
.access = ACCESS_RO,
},
- {}
+ {},
};
const struct rule layer2_subs[] = {
{
@@ -1384,7 +1573,7 @@ static void test_relative_path(struct __test_metadata *const _metadata,
.path = dir_s2d2,
.access = ACCESS_RO,
},
- {}
+ {},
};
int dirfd, ruleset_fd;
@@ -1425,14 +1614,16 @@ static void test_relative_path(struct __test_metadata *const _metadata,
break;
case REL_CHROOT_ONLY:
/* Do chroot into dir_s1d2 (relative to dir_s2d2). */
- ASSERT_EQ(0, chroot("../../s1d1/s1d2")) {
+ ASSERT_EQ(0, chroot("../../s1d1/s1d2"))
+ {
TH_LOG("Failed to chroot: %s", strerror(errno));
}
dirfd = AT_FDCWD;
break;
case REL_CHROOT_CHDIR:
/* Do chroot into dir_s1d2. */
- ASSERT_EQ(0, chroot(".")) {
+ ASSERT_EQ(0, chroot("."))
+ {
TH_LOG("Failed to chroot: %s", strerror(errno));
}
dirfd = AT_FDCWD;
@@ -1440,7 +1631,7 @@ static void test_relative_path(struct __test_metadata *const _metadata,
}
ASSERT_EQ((rel == REL_CHROOT_CHDIR) ? 0 : EACCES,
- test_open_rel(dirfd, "..", O_RDONLY));
+ test_open_rel(dirfd, "..", O_RDONLY));
ASSERT_EQ(0, test_open_rel(dirfd, ".", O_RDONLY));
if (rel == REL_CHROOT_ONLY) {
@@ -1462,11 +1653,13 @@ static void test_relative_path(struct __test_metadata *const _metadata,
if (rel != REL_CHROOT_CHDIR) {
ASSERT_EQ(EACCES, test_open_rel(dirfd, "../../s1d1", O_RDONLY));
ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2", O_RDONLY));
- ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2/s1d3", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "../../s1d1/s1d2/s1d3",
+ O_RDONLY));
ASSERT_EQ(EACCES, test_open_rel(dirfd, "../../s2d1", O_RDONLY));
ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2", O_RDONLY));
- ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2/s2d3", O_RDONLY));
+ ASSERT_EQ(0, test_open_rel(dirfd, "../../s2d1/s2d2/s2d3",
+ O_RDONLY));
}
if (rel == REL_OPEN)
@@ -1495,40 +1688,42 @@ TEST_F_FORK(layout1, relative_chroot_chdir)
}
static void copy_binary(struct __test_metadata *const _metadata,
- const char *const dst_path)
+ const char *const dst_path)
{
int dst_fd, src_fd;
struct stat statbuf;
dst_fd = open(dst_path, O_WRONLY | O_TRUNC | O_CLOEXEC);
- ASSERT_LE(0, dst_fd) {
- TH_LOG("Failed to open \"%s\": %s", dst_path,
- strerror(errno));
+ ASSERT_LE(0, dst_fd)
+ {
+ TH_LOG("Failed to open \"%s\": %s", dst_path, strerror(errno));
}
src_fd = open(BINARY_PATH, O_RDONLY | O_CLOEXEC);
- ASSERT_LE(0, src_fd) {
+ ASSERT_LE(0, src_fd)
+ {
TH_LOG("Failed to open \"" BINARY_PATH "\": %s",
- strerror(errno));
+ strerror(errno));
}
ASSERT_EQ(0, fstat(src_fd, &statbuf));
- ASSERT_EQ(statbuf.st_size, sendfile(dst_fd, src_fd, 0,
- statbuf.st_size));
+ ASSERT_EQ(statbuf.st_size,
+ sendfile(dst_fd, src_fd, 0, statbuf.st_size));
ASSERT_EQ(0, close(src_fd));
ASSERT_EQ(0, close(dst_fd));
}
-static void test_execute(struct __test_metadata *const _metadata,
- const int err, const char *const path)
+static void test_execute(struct __test_metadata *const _metadata, const int err,
+ const char *const path)
{
int status;
- char *const argv[] = {(char *)path, NULL};
+ char *const argv[] = { (char *)path, NULL };
const pid_t child = fork();
ASSERT_LE(0, child);
if (child == 0) {
- ASSERT_EQ(err ? -1 : 0, execve(path, argv, NULL)) {
+ ASSERT_EQ(err ? -1 : 0, execve(path, argv, NULL))
+ {
TH_LOG("Failed to execute \"%s\": %s", path,
- strerror(errno));
+ strerror(errno));
};
ASSERT_EQ(err, errno);
_exit(_metadata->passed ? 2 : 1);
@@ -1536,9 +1731,10 @@ static void test_execute(struct __test_metadata *const _metadata,
}
ASSERT_EQ(child, waitpid(child, &status, 0));
ASSERT_EQ(1, WIFEXITED(status));
- ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status)) {
+ ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status))
+ {
TH_LOG("Unexpected return code for \"%s\": %s", path,
- strerror(errno));
+ strerror(errno));
};
}
@@ -1549,10 +1745,10 @@ TEST_F_FORK(layout1, execute)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_EXECUTE,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
copy_binary(_metadata, file1_s1d1);
@@ -1577,15 +1773,21 @@ TEST_F_FORK(layout1, execute)
TEST_F_FORK(layout1, link)
{
- const struct rule rules[] = {
+ const struct rule layer1[] = {
{
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_MAKE_REG,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const struct rule layer2[] = {
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {},
+ };
+ int ruleset_fd = create_ruleset(_metadata, layer1[0].access, layer1);
ASSERT_LE(0, ruleset_fd);
@@ -1598,14 +1800,30 @@ TEST_F_FORK(layout1, link)
ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1));
ASSERT_EQ(EACCES, errno);
+
/* Denies linking because of reparenting. */
ASSERT_EQ(-1, link(file1_s2d1, file1_s1d2));
ASSERT_EQ(EXDEV, errno);
ASSERT_EQ(-1, link(file2_s1d2, file1_s1d3));
ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, link(file2_s1d3, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
ASSERT_EQ(0, link(file2_s1d2, file1_s1d2));
ASSERT_EQ(0, link(file2_s1d3, file1_s1d3));
+
+ /* Prepares for next unlinks. */
+ ASSERT_EQ(0, unlink(file2_s1d2));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+
+ ruleset_fd = create_ruleset(_metadata, layer2[0].access, layer2);
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks that linkind doesn't require the ability to delete a file. */
+ ASSERT_EQ(0, link(file1_s1d2, file2_s1d2));
+ ASSERT_EQ(0, link(file1_s1d3, file2_s1d3));
}
TEST_F_FORK(layout1, rename_file)
@@ -1619,14 +1837,13 @@ TEST_F_FORK(layout1, rename_file)
.path = dir_s2d2,
.access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
- ASSERT_EQ(0, unlink(file1_s1d1));
ASSERT_EQ(0, unlink(file1_s1d2));
enforce_ruleset(_metadata, ruleset_fd);
@@ -1662,9 +1879,15 @@ TEST_F_FORK(layout1, rename_file)
ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d2, AT_FDCWD, file1_s2d1,
RENAME_EXCHANGE));
ASSERT_EQ(EACCES, errno);
+ /* Checks that file1_s2d1 cannot be removed (instead of ENOTDIR). */
+ ASSERT_EQ(-1, rename(dir_s2d2, file1_s2d1));
+ ASSERT_EQ(EACCES, errno);
ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, dir_s2d2,
RENAME_EXCHANGE));
ASSERT_EQ(EACCES, errno);
+ /* Checks that file1_s1d1 cannot be removed (instead of EISDIR). */
+ ASSERT_EQ(-1, rename(file1_s1d1, dir_s1d2));
+ ASSERT_EQ(EACCES, errno);
/* Renames files with different parents. */
ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d2));
@@ -1675,14 +1898,14 @@ TEST_F_FORK(layout1, rename_file)
/* Exchanges and renames files with same parent. */
ASSERT_EQ(0, renameat2(AT_FDCWD, file2_s2d3, AT_FDCWD, file1_s2d3,
- RENAME_EXCHANGE));
+ RENAME_EXCHANGE));
ASSERT_EQ(0, rename(file2_s2d3, file1_s2d3));
/* Exchanges files and directories with same parent, twice. */
ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s2d3,
- RENAME_EXCHANGE));
+ RENAME_EXCHANGE));
ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s2d3,
- RENAME_EXCHANGE));
+ RENAME_EXCHANGE));
}
TEST_F_FORK(layout1, rename_dir)
@@ -1696,10 +1919,10 @@ TEST_F_FORK(layout1, rename_dir)
.path = dir_s2d1,
.access = LANDLOCK_ACCESS_FS_REMOVE_DIR,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
@@ -1727,22 +1950,743 @@ TEST_F_FORK(layout1, rename_dir)
ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d1, AT_FDCWD, dir_s2d1,
RENAME_EXCHANGE));
ASSERT_EQ(EACCES, errno);
+ /* Checks that dir_s1d2 cannot be removed (instead of ENOTDIR). */
+ ASSERT_EQ(-1, rename(dir_s1d2, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s1d2,
RENAME_EXCHANGE));
ASSERT_EQ(EACCES, errno);
+ /* Checks that dir_s1d2 cannot be removed (instead of EISDIR). */
+ ASSERT_EQ(-1, rename(file1_s1d1, dir_s1d2));
+ ASSERT_EQ(EACCES, errno);
/*
* Exchanges and renames directory to the same parent, which allows
* directory removal.
*/
ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, file1_s1d2,
- RENAME_EXCHANGE));
+ RENAME_EXCHANGE));
ASSERT_EQ(0, unlink(dir_s1d3));
ASSERT_EQ(0, mkdir(dir_s1d3, 0700));
ASSERT_EQ(0, rename(file1_s1d2, dir_s1d3));
ASSERT_EQ(0, rmdir(dir_s1d3));
}
+TEST_F_FORK(layout1, reparent_refer)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {},
+ };
+ int ruleset_fd =
+ create_ruleset(_metadata, LANDLOCK_ACCESS_FS_REFER, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d1));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d2));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(dir_s1d2, dir_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ ASSERT_EQ(-1, rename(dir_s1d3, dir_s2d1));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(dir_s1d3, dir_s2d2));
+ ASSERT_EQ(EXDEV, errno);
+ /*
+ * Moving should only be allowed when the source and the destination
+ * parent directory have REFER.
+ */
+ ASSERT_EQ(-1, rename(dir_s1d3, dir_s2d3));
+ ASSERT_EQ(ENOTEMPTY, errno);
+ ASSERT_EQ(0, unlink(file1_s2d3));
+ ASSERT_EQ(0, unlink(file2_s2d3));
+ ASSERT_EQ(0, rename(dir_s1d3, dir_s2d3));
+}
+
+TEST_F_FORK(layout1, reparent_link)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = dir_s2d3,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {},
+ };
+ const int ruleset_fd = create_ruleset(
+ _metadata,
+ LANDLOCK_ACCESS_FS_MAKE_REG | LANDLOCK_ACCESS_FS_REFER, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+
+ /* Denies linking because of missing MAKE_REG. */
+ ASSERT_EQ(-1, link(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ /* Denies linking because of missing source and destination REFER. */
+ ASSERT_EQ(-1, link(file1_s2d1, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+ /* Denies linking because of missing source REFER. */
+ ASSERT_EQ(-1, link(file1_s2d1, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Denies linking because of missing MAKE_REG. */
+ ASSERT_EQ(-1, link(file1_s2d2, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ /* Denies linking because of missing destination REFER. */
+ ASSERT_EQ(-1, link(file1_s2d2, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Allows linking because of REFER and MAKE_REG. */
+ ASSERT_EQ(0, link(file1_s2d2, file1_s1d3));
+ ASSERT_EQ(0, unlink(file1_s2d2));
+ /* Reverse linking denied because of missing MAKE_REG. */
+ ASSERT_EQ(-1, link(file1_s1d3, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, unlink(file1_s2d3));
+ /* Checks reverse linking. */
+ ASSERT_EQ(0, link(file1_s1d3, file1_s2d3));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+
+ /*
+ * This is OK for a file link, but it should not be allowed for a
+ * directory rename (because of the superset of access rights.
+ */
+ ASSERT_EQ(0, link(file1_s2d3, file1_s1d3));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+
+ ASSERT_EQ(-1, link(file2_s1d2, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, link(file2_s1d3, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ ASSERT_EQ(0, link(file2_s1d2, file1_s1d2));
+ ASSERT_EQ(0, link(file2_s1d3, file1_s1d3));
+}
+
+TEST_F_FORK(layout1, reparent_rename)
+{
+ /* Same rules as for reparent_link. */
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = dir_s2d3,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {},
+ };
+ const int ruleset_fd = create_ruleset(
+ _metadata,
+ LANDLOCK_ACCESS_FS_MAKE_REG | LANDLOCK_ACCESS_FS_REFER, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+
+ /* Denies renaming because of missing MAKE_REG. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file2_s1d1, AT_FDCWD, file1_s1d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, file2_s1d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, unlink(file1_s1d1));
+ ASSERT_EQ(-1, rename(file2_s1d1, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ /* Even denies same file exchange. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file2_s1d1, AT_FDCWD, file2_s1d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Denies renaming because of missing source and destination REFER. */
+ ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+ /*
+ * Denies renaming because of missing MAKE_REG, source and destination
+ * REFER.
+ */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, file2_s1d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file2_s1d1, AT_FDCWD, file1_s2d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Denies renaming because of missing source REFER. */
+ ASSERT_EQ(-1, rename(file1_s2d1, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+ /* Denies renaming because of missing MAKE_REG. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d1, AT_FDCWD, file2_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Denies renaming because of missing MAKE_REG. */
+ ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ /* Denies renaming because of missing destination REFER*/
+ ASSERT_EQ(-1, rename(file1_s2d2, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Denies exchange because of one missing MAKE_REG. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, file2_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ /* Allows renaming because of REFER and MAKE_REG. */
+ ASSERT_EQ(0, rename(file1_s2d2, file1_s1d3));
+
+ /* Reverse renaming denied because of missing MAKE_REG. */
+ ASSERT_EQ(-1, rename(file1_s1d3, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(0, unlink(file1_s2d3));
+ ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3));
+
+ /* Tests reverse renaming. */
+ ASSERT_EQ(0, rename(file1_s2d3, file1_s1d3));
+ ASSERT_EQ(0, renameat2(AT_FDCWD, file2_s2d3, AT_FDCWD, file1_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3));
+
+ /*
+ * This is OK for a file rename, but it should not be allowed for a
+ * directory rename (because of the superset of access rights).
+ */
+ ASSERT_EQ(0, rename(file1_s2d3, file1_s1d3));
+ ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3));
+
+ /*
+ * Tests superset restrictions applied to directories. Not only the
+ * dir_s2d3's parent (dir_s2d2) should be taken into account but also
+ * access rights tied to dir_s2d3. dir_s2d2 is missing one access right
+ * compared to dir_s1d3/file1_s1d3 (MAKE_REG) but it is provided
+ * directly by the moved dir_s2d3.
+ */
+ ASSERT_EQ(0, rename(dir_s2d3, file1_s1d3));
+ ASSERT_EQ(0, rename(file1_s1d3, dir_s2d3));
+ /*
+ * The first rename is allowed but not the exchange because dir_s1d3's
+ * parent (dir_s1d2) doesn't have REFER.
+ */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, file1_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(file1_s2d3, dir_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ ASSERT_EQ(-1, rename(file2_s1d2, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(file2_s1d3, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Renaming in the same directory is always allowed. */
+ ASSERT_EQ(0, rename(file2_s1d2, file1_s1d2));
+ ASSERT_EQ(0, rename(file2_s1d3, file1_s1d3));
+
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ /* Denies because of missing source MAKE_REG and destination REFER. */
+ ASSERT_EQ(-1, rename(dir_s2d3, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ /* Denies because of missing source MAKE_REG and REFER. */
+ ASSERT_EQ(-1, rename(dir_s2d2, file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+}
+
+static void
+reparent_exdev_layers_enforce1(struct __test_metadata *const _metadata)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ /* Interesting for the layer2 tests. */
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = dir_s2d3,
+ .access = LANDLOCK_ACCESS_FS_MAKE_REG,
+ },
+ {},
+ };
+ const int ruleset_fd = create_ruleset(
+ _metadata,
+ LANDLOCK_ACCESS_FS_MAKE_REG | LANDLOCK_ACCESS_FS_REFER, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+static void
+reparent_exdev_layers_enforce2(struct __test_metadata *const _metadata)
+{
+ const struct rule layer2[] = {
+ {
+ .path = dir_s2d3,
+ .access = LANDLOCK_ACCESS_FS_MAKE_DIR,
+ },
+ {},
+ };
+ /*
+ * Same checks as before but with a second layer and a new MAKE_DIR
+ * rule (and no explicit handling of REFER).
+ */
+ const int ruleset_fd =
+ create_ruleset(_metadata, LANDLOCK_ACCESS_FS_MAKE_DIR, layer2);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+}
+
+TEST_F_FORK(layout1, reparent_exdev_layers_rename1)
+{
+ ASSERT_EQ(0, unlink(file1_s2d2));
+ ASSERT_EQ(0, unlink(file1_s2d3));
+
+ reparent_exdev_layers_enforce1(_metadata);
+
+ /*
+ * Moving the dir_s1d3 directory below dir_s2d2 is allowed by Landlock
+ * because it doesn't inherit new access rights.
+ */
+ ASSERT_EQ(0, rename(dir_s1d3, file1_s2d2));
+ ASSERT_EQ(0, rename(file1_s2d2, dir_s1d3));
+
+ /*
+ * Moving the dir_s1d3 directory below dir_s2d3 is allowed, even if it
+ * gets a new inherited access rights (MAKE_REG), because MAKE_REG is
+ * already allowed for dir_s1d3.
+ */
+ ASSERT_EQ(0, rename(dir_s1d3, file1_s2d3));
+ ASSERT_EQ(0, rename(file1_s2d3, dir_s1d3));
+
+ /*
+ * However, moving the file1_s1d3 file below dir_s2d3 is allowed
+ * because it cannot inherit MAKE_REG right (which is dedicated to
+ * directories).
+ */
+ ASSERT_EQ(0, rename(file1_s1d3, file1_s2d3));
+
+ reparent_exdev_layers_enforce2(_metadata);
+
+ /*
+ * Moving the dir_s1d3 directory below dir_s2d2 is now denied because
+ * MAKE_DIR is not tied to dir_s2d2.
+ */
+ ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+
+ /*
+ * Moving the dir_s1d3 directory below dir_s2d3 is forbidden because it
+ * would grants MAKE_REG and MAKE_DIR rights to it.
+ */
+ ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ /*
+ * However, moving the file2_s1d3 file below dir_s2d3 is allowed
+ * because it cannot inherit MAKE_REG nor MAKE_DIR rights (which are
+ * dedicated to directories).
+ */
+ ASSERT_EQ(0, rename(file2_s1d3, file1_s2d3));
+}
+
+TEST_F_FORK(layout1, reparent_exdev_layers_rename2)
+{
+ reparent_exdev_layers_enforce1(_metadata);
+
+ /* Checks EACCES predominance over EXDEV. */
+ ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(file1_s1d2, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+ /* Modify layout! */
+ ASSERT_EQ(0, rename(file1_s1d2, file1_s2d3));
+
+ /* Without REFER source. */
+ ASSERT_EQ(-1, rename(dir_s1d1, file1_s2d2));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, rename(dir_s1d2, file1_s2d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ reparent_exdev_layers_enforce2(_metadata);
+
+ /* Checks EACCES predominance over EXDEV. */
+ ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ /* Checks with actual file2_s1d2. */
+ ASSERT_EQ(-1, rename(file2_s1d2, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(file1_s1d1, file1_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+ /* Modify layout! */
+ ASSERT_EQ(0, rename(file2_s1d2, file1_s2d3));
+
+ /* Without REFER source, EACCES wins over EXDEV. */
+ ASSERT_EQ(-1, rename(dir_s1d1, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(dir_s1d2, file1_s2d2));
+ ASSERT_EQ(EACCES, errno);
+}
+
+TEST_F_FORK(layout1, reparent_exdev_layers_exchange1)
+{
+ const char *const dir_file1_s1d2 = file1_s1d2, *const dir_file2_s2d3 =
+ file2_s2d3;
+
+ ASSERT_EQ(0, unlink(file1_s1d2));
+ ASSERT_EQ(0, mkdir(file1_s1d2, 0700));
+ ASSERT_EQ(0, unlink(file2_s2d3));
+ ASSERT_EQ(0, mkdir(file2_s2d3, 0700));
+
+ reparent_exdev_layers_enforce1(_metadata);
+
+ /* Error predominance with file exchange: returns EXDEV and EACCES. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, file1_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, file1_s1d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /*
+ * Checks with directories which creation could be allowed, but denied
+ * because of access rights that would be inherited.
+ */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD,
+ dir_file2_s2d3, RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD,
+ dir_file1_s1d2, RENAME_EXCHANGE));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Checks with same access rights. */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+
+ /* Checks with different (child-only) access rights. */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_file1_s1d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+
+ /*
+ * Checks that exchange between file and directory are consistent.
+ *
+ * Moving a file (file1_s2d2) to a directory which only grants more
+ * directory-related access rights is allowed, and at the same time
+ * moving a directory (dir_file2_s2d3) to another directory which
+ * grants less access rights is allowed too.
+ *
+ * See layout1.reparent_exdev_layers_exchange3 for inverted arguments.
+ */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3,
+ RENAME_EXCHANGE));
+ /*
+ * However, moving back the directory is denied because it would get
+ * more access rights than the current state and because file creation
+ * is forbidden (in dir_s2d2).
+ */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ reparent_exdev_layers_enforce2(_metadata);
+
+ /* Error predominance with file exchange: returns EXDEV and EACCES. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, file1_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d3, AT_FDCWD, file1_s1d1,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Checks with directories which creation is now denied. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD,
+ dir_file2_s2d3, RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD,
+ dir_file1_s1d2, RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Checks with different (child-only) access rights. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s1d3, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+ /* Denied because of MAKE_DIR. */
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Checks with different (child-only) access rights. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_s2d3, AT_FDCWD, dir_file1_s1d2,
+ RENAME_EXCHANGE));
+ /* Denied because of MAKE_DIR. */
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file1_s1d2, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* See layout1.reparent_exdev_layers_exchange2 for complement. */
+}
+
+TEST_F_FORK(layout1, reparent_exdev_layers_exchange2)
+{
+ const char *const dir_file2_s2d3 = file2_s2d3;
+
+ ASSERT_EQ(0, unlink(file2_s2d3));
+ ASSERT_EQ(0, mkdir(file2_s2d3, 0700));
+
+ reparent_exdev_layers_enforce1(_metadata);
+ reparent_exdev_layers_enforce2(_metadata);
+
+ /* Checks that exchange between file and directory are consistent. */
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+}
+
+TEST_F_FORK(layout1, reparent_exdev_layers_exchange3)
+{
+ const char *const dir_file2_s2d3 = file2_s2d3;
+
+ ASSERT_EQ(0, unlink(file2_s2d3));
+ ASSERT_EQ(0, mkdir(file2_s2d3, 0700));
+
+ reparent_exdev_layers_enforce1(_metadata);
+
+ /*
+ * Checks that exchange between file and directory are consistent,
+ * including with inverted arguments (see
+ * layout1.reparent_exdev_layers_exchange1).
+ */
+ ASSERT_EQ(0, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_file2_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, dir_file2_s2d3, AT_FDCWD, file1_s2d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+}
+
+TEST_F_FORK(layout1, reparent_remove)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d1,
+ .access = LANDLOCK_ACCESS_FS_REFER |
+ LANDLOCK_ACCESS_FS_REMOVE_DIR,
+ },
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {
+ .path = dir_s2d1,
+ .access = LANDLOCK_ACCESS_FS_REFER |
+ LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ },
+ {},
+ };
+ const int ruleset_fd = create_ruleset(
+ _metadata,
+ LANDLOCK_ACCESS_FS_REFER | LANDLOCK_ACCESS_FS_REMOVE_DIR |
+ LANDLOCK_ACCESS_FS_REMOVE_FILE,
+ layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Access denied because of wrong/swapped remove file/dir. */
+ ASSERT_EQ(-1, rename(file1_s1d1, dir_s2d2));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, rename(dir_s2d2, file1_s1d1));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s2d2,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s1d1, AT_FDCWD, dir_s2d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+
+ /* Access allowed thanks to the matching rights. */
+ ASSERT_EQ(-1, rename(file1_s2d1, dir_s1d2));
+ ASSERT_EQ(EISDIR, errno);
+ ASSERT_EQ(-1, rename(dir_s1d2, file1_s2d1));
+ ASSERT_EQ(ENOTDIR, errno);
+ ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d1));
+ ASSERT_EQ(ENOTDIR, errno);
+ ASSERT_EQ(0, unlink(file1_s2d1));
+ ASSERT_EQ(0, unlink(file1_s1d3));
+ ASSERT_EQ(0, unlink(file2_s1d3));
+ ASSERT_EQ(0, rename(dir_s1d3, file1_s2d1));
+
+ /* Effectively removes a file and a directory by exchanging them. */
+ ASSERT_EQ(0, mkdir(dir_s1d3, 0700));
+ ASSERT_EQ(0, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(-1, renameat2(AT_FDCWD, file1_s2d2, AT_FDCWD, dir_s1d3,
+ RENAME_EXCHANGE));
+ ASSERT_EQ(EACCES, errno);
+}
+
+TEST_F_FORK(layout1, reparent_dom_superset)
+{
+ const struct rule layer1[] = {
+ {
+ .path = dir_s1d2,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = file1_s1d2,
+ .access = LANDLOCK_ACCESS_FS_EXECUTE,
+ },
+ {
+ .path = dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_MAKE_SOCK |
+ LANDLOCK_ACCESS_FS_EXECUTE,
+ },
+ {
+ .path = dir_s2d2,
+ .access = LANDLOCK_ACCESS_FS_REFER |
+ LANDLOCK_ACCESS_FS_EXECUTE |
+ LANDLOCK_ACCESS_FS_MAKE_SOCK,
+ },
+ {
+ .path = dir_s2d3,
+ .access = LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_MAKE_FIFO,
+ },
+ {},
+ };
+ int ruleset_fd = create_ruleset(_metadata,
+ LANDLOCK_ACCESS_FS_REFER |
+ LANDLOCK_ACCESS_FS_EXECUTE |
+ LANDLOCK_ACCESS_FS_MAKE_SOCK |
+ LANDLOCK_ACCESS_FS_READ_FILE |
+ LANDLOCK_ACCESS_FS_MAKE_FIFO,
+ layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ ASSERT_EQ(-1, rename(file1_s1d2, file1_s2d1));
+ ASSERT_EQ(EXDEV, errno);
+ /*
+ * Moving file1_s1d2 beneath dir_s2d3 would grant it the READ_FILE
+ * access right.
+ */
+ ASSERT_EQ(-1, rename(file1_s1d2, file1_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+ /*
+ * Moving file1_s1d2 should be allowed even if dir_s2d2 grants a
+ * superset of access rights compared to dir_s1d2, because file1_s1d2
+ * already has these access rights anyway.
+ */
+ ASSERT_EQ(0, rename(file1_s1d2, file1_s2d2));
+ ASSERT_EQ(0, rename(file1_s2d2, file1_s1d2));
+
+ ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d1));
+ ASSERT_EQ(EXDEV, errno);
+ /*
+ * Moving dir_s1d3 beneath dir_s2d3 would grant it the MAKE_FIFO access
+ * right.
+ */
+ ASSERT_EQ(-1, rename(dir_s1d3, file1_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+ /*
+ * Moving dir_s1d3 should be allowed even if dir_s2d2 grants a superset
+ * of access rights compared to dir_s1d2, because dir_s1d3 already has
+ * these access rights anyway.
+ */
+ ASSERT_EQ(0, rename(dir_s1d3, file1_s2d2));
+ ASSERT_EQ(0, rename(file1_s2d2, dir_s1d3));
+
+ /*
+ * Moving file1_s2d3 beneath dir_s1d2 is allowed, but moving it back
+ * will be denied because the new inherited access rights from dir_s1d2
+ * will be less than the destination (original) dir_s2d3. This is a
+ * sinkhole scenario where we cannot move back files or directories.
+ */
+ ASSERT_EQ(0, rename(file1_s2d3, file2_s1d2));
+ ASSERT_EQ(-1, rename(file2_s1d2, file1_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+ ASSERT_EQ(0, unlink(file2_s1d2));
+ ASSERT_EQ(0, unlink(file2_s2d3));
+ /*
+ * Checks similar directory one-way move: dir_s2d3 loses EXECUTE and
+ * MAKE_SOCK which were inherited from dir_s1d3.
+ */
+ ASSERT_EQ(0, rename(dir_s2d3, file2_s1d2));
+ ASSERT_EQ(-1, rename(file2_s1d2, dir_s2d3));
+ ASSERT_EQ(EXDEV, errno);
+}
+
TEST_F_FORK(layout1, remove_dir)
{
const struct rule rules[] = {
@@ -1750,10 +2694,10 @@ TEST_F_FORK(layout1, remove_dir)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_REMOVE_DIR,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
@@ -1787,10 +2731,10 @@ TEST_F_FORK(layout1, remove_file)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_REMOVE_FILE,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
@@ -1805,14 +2749,15 @@ TEST_F_FORK(layout1, remove_file)
}
static void test_make_file(struct __test_metadata *const _metadata,
- const __u64 access, const mode_t mode, const dev_t dev)
+ const __u64 access, const mode_t mode,
+ const dev_t dev)
{
const struct rule rules[] = {
{
.path = dir_s1d2,
.access = access,
},
- {}
+ {},
};
const int ruleset_fd = create_ruleset(_metadata, access, rules);
@@ -1820,9 +2765,10 @@ static void test_make_file(struct __test_metadata *const _metadata,
ASSERT_EQ(0, unlink(file1_s1d1));
ASSERT_EQ(0, unlink(file2_s1d1));
- ASSERT_EQ(0, mknod(file2_s1d1, mode | 0400, dev)) {
- TH_LOG("Failed to make file \"%s\": %s",
- file2_s1d1, strerror(errno));
+ ASSERT_EQ(0, mknod(file2_s1d1, mode | 0400, dev))
+ {
+ TH_LOG("Failed to make file \"%s\": %s", file2_s1d1,
+ strerror(errno));
};
ASSERT_EQ(0, unlink(file1_s1d2));
@@ -1841,9 +2787,10 @@ static void test_make_file(struct __test_metadata *const _metadata,
ASSERT_EQ(-1, rename(file2_s1d1, file1_s1d1));
ASSERT_EQ(EACCES, errno);
- ASSERT_EQ(0, mknod(file1_s1d2, mode | 0400, dev)) {
- TH_LOG("Failed to make file \"%s\": %s",
- file1_s1d2, strerror(errno));
+ ASSERT_EQ(0, mknod(file1_s1d2, mode | 0400, dev))
+ {
+ TH_LOG("Failed to make file \"%s\": %s", file1_s1d2,
+ strerror(errno));
};
ASSERT_EQ(0, link(file1_s1d2, file2_s1d2));
ASSERT_EQ(0, unlink(file2_s1d2));
@@ -1860,7 +2807,7 @@ TEST_F_FORK(layout1, make_char)
/* Creates a /dev/null device. */
set_cap(_metadata, CAP_MKNOD);
test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_CHAR, S_IFCHR,
- makedev(1, 3));
+ makedev(1, 3));
}
TEST_F_FORK(layout1, make_block)
@@ -1868,7 +2815,7 @@ TEST_F_FORK(layout1, make_block)
/* Creates a /dev/loop0 device. */
set_cap(_metadata, CAP_MKNOD);
test_make_file(_metadata, LANDLOCK_ACCESS_FS_MAKE_BLOCK, S_IFBLK,
- makedev(7, 0));
+ makedev(7, 0));
}
TEST_F_FORK(layout1, make_reg_1)
@@ -1898,10 +2845,10 @@ TEST_F_FORK(layout1, make_sym)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_MAKE_SYM,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
@@ -1943,10 +2890,10 @@ TEST_F_FORK(layout1, make_dir)
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_MAKE_DIR,
},
- {}
+ {},
};
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
@@ -1965,12 +2912,12 @@ TEST_F_FORK(layout1, make_dir)
}
static int open_proc_fd(struct __test_metadata *const _metadata, const int fd,
- const int open_flags)
+ const int open_flags)
{
static const char path_template[] = "/proc/self/fd/%d";
char procfd_path[sizeof(path_template) + 10];
- const int procfd_path_size = snprintf(procfd_path, sizeof(procfd_path),
- path_template, fd);
+ const int procfd_path_size =
+ snprintf(procfd_path, sizeof(procfd_path), path_template, fd);
ASSERT_LT(procfd_path_size, sizeof(procfd_path));
return open(procfd_path, open_flags);
@@ -1983,12 +2930,13 @@ TEST_F_FORK(layout1, proc_unlinked_file)
.path = file1_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
int reg_fd, proc_fd;
- const int ruleset_fd = create_ruleset(_metadata,
- LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE, rules);
+ const int ruleset_fd = create_ruleset(
+ _metadata,
+ LANDLOCK_ACCESS_FS_READ_FILE | LANDLOCK_ACCESS_FS_WRITE_FILE,
+ rules);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
@@ -2005,9 +2953,10 @@ TEST_F_FORK(layout1, proc_unlinked_file)
ASSERT_EQ(0, close(proc_fd));
proc_fd = open_proc_fd(_metadata, reg_fd, O_RDWR | O_CLOEXEC);
- ASSERT_EQ(-1, proc_fd) {
- TH_LOG("Successfully opened /proc/self/fd/%d: %s",
- reg_fd, strerror(errno));
+ ASSERT_EQ(-1, proc_fd)
+ {
+ TH_LOG("Successfully opened /proc/self/fd/%d: %s", reg_fd,
+ strerror(errno));
}
ASSERT_EQ(EACCES, errno);
@@ -2023,13 +2972,13 @@ TEST_F_FORK(layout1, proc_pipe)
{
.path = dir_s1d2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
/* Limits read and write access to files tied to the filesystem. */
- const int ruleset_fd = create_ruleset(_metadata, rules[0].access,
- rules);
+ const int ruleset_fd =
+ create_ruleset(_metadata, rules[0].access, rules);
ASSERT_LE(0, ruleset_fd);
enforce_ruleset(_metadata, ruleset_fd);
@@ -2041,7 +2990,8 @@ TEST_F_FORK(layout1, proc_pipe)
/* Checks access to pipes through FD. */
ASSERT_EQ(0, pipe2(pipe_fds, O_CLOEXEC));
- ASSERT_EQ(1, write(pipe_fds[1], ".", 1)) {
+ ASSERT_EQ(1, write(pipe_fds[1], ".", 1))
+ {
TH_LOG("Failed to write in pipe: %s", strerror(errno));
}
ASSERT_EQ(1, read(pipe_fds[0], &buf, 1));
@@ -2050,9 +3000,10 @@ TEST_F_FORK(layout1, proc_pipe)
/* Checks write access to pipe through /proc/self/fd . */
proc_fd = open_proc_fd(_metadata, pipe_fds[1], O_WRONLY | O_CLOEXEC);
ASSERT_LE(0, proc_fd);
- ASSERT_EQ(1, write(proc_fd, ".", 1)) {
+ ASSERT_EQ(1, write(proc_fd, ".", 1))
+ {
TH_LOG("Failed to write through /proc/self/fd/%d: %s",
- pipe_fds[1], strerror(errno));
+ pipe_fds[1], strerror(errno));
}
ASSERT_EQ(0, close(proc_fd));
@@ -2060,9 +3011,10 @@ TEST_F_FORK(layout1, proc_pipe)
proc_fd = open_proc_fd(_metadata, pipe_fds[0], O_RDONLY | O_CLOEXEC);
ASSERT_LE(0, proc_fd);
buf = '\0';
- ASSERT_EQ(1, read(proc_fd, &buf, 1)) {
+ ASSERT_EQ(1, read(proc_fd, &buf, 1))
+ {
TH_LOG("Failed to read through /proc/self/fd/%d: %s",
- pipe_fds[1], strerror(errno));
+ pipe_fds[1], strerror(errno));
}
ASSERT_EQ(0, close(proc_fd));
@@ -2070,8 +3022,9 @@ TEST_F_FORK(layout1, proc_pipe)
ASSERT_EQ(0, close(pipe_fds[1]));
}
-FIXTURE(layout1_bind) {
-};
+/* clang-format off */
+FIXTURE(layout1_bind) {};
+/* clang-format on */
FIXTURE_SETUP(layout1_bind)
{
@@ -2161,7 +3114,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file)
.path = dir_s2d1,
.access = ACCESS_RW,
},
- {}
+ {},
};
/*
* Sets access rights on the same bind-mounted directories. The result
@@ -2177,7 +3130,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file)
.path = dir_s2d2,
.access = ACCESS_RW,
},
- {}
+ {},
};
/* Only allow read-access to the s1d3 hierarchies. */
const struct rule layer3_source[] = {
@@ -2185,7 +3138,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file)
.path = dir_s1d3,
.access = LANDLOCK_ACCESS_FS_READ_FILE,
},
- {}
+ {},
};
/* Removes all access rights. */
const struct rule layer4_destination[] = {
@@ -2193,7 +3146,7 @@ TEST_F_FORK(layout1_bind, same_content_same_file)
.path = bind_file1_s1d3,
.access = LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
int ruleset_fd;
@@ -2282,8 +3235,46 @@ TEST_F_FORK(layout1_bind, same_content_same_file)
ASSERT_EQ(EACCES, test_open(bind_file1_s1d3, O_WRONLY));
}
-#define LOWER_BASE TMP_DIR "/lower"
-#define LOWER_DATA LOWER_BASE "/data"
+TEST_F_FORK(layout1_bind, reparent_cross_mount)
+{
+ const struct rule layer1[] = {
+ {
+ /* dir_s2d1 is beneath the dir_s2d2 mount point. */
+ .path = dir_s2d1,
+ .access = LANDLOCK_ACCESS_FS_REFER,
+ },
+ {
+ .path = bind_dir_s1d3,
+ .access = LANDLOCK_ACCESS_FS_EXECUTE,
+ },
+ {},
+ };
+ int ruleset_fd = create_ruleset(
+ _metadata,
+ LANDLOCK_ACCESS_FS_REFER | LANDLOCK_ACCESS_FS_EXECUTE, layer1);
+
+ ASSERT_LE(0, ruleset_fd);
+ enforce_ruleset(_metadata, ruleset_fd);
+ ASSERT_EQ(0, close(ruleset_fd));
+
+ /* Checks basic denied move. */
+ ASSERT_EQ(-1, rename(file1_s1d1, file1_s1d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Checks real cross-mount move (Landlock is not involved). */
+ ASSERT_EQ(-1, rename(file1_s2d1, file1_s2d2));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Checks move that will give more accesses. */
+ ASSERT_EQ(-1, rename(file1_s2d2, bind_file1_s1d3));
+ ASSERT_EQ(EXDEV, errno);
+
+ /* Checks legitimate downgrade move. */
+ ASSERT_EQ(0, rename(bind_file1_s1d3, file1_s2d2));
+}
+
+#define LOWER_BASE TMP_DIR "/lower"
+#define LOWER_DATA LOWER_BASE "/data"
static const char lower_fl1[] = LOWER_DATA "/fl1";
static const char lower_dl1[] = LOWER_DATA "/dl1";
static const char lower_dl1_fl2[] = LOWER_DATA "/dl1/fl2";
@@ -2295,23 +3286,23 @@ static const char lower_do1_fl3[] = LOWER_DATA "/do1/fl3";
static const char (*lower_base_files[])[] = {
&lower_fl1,
&lower_fo1,
- NULL
+ NULL,
};
static const char (*lower_base_directories[])[] = {
&lower_dl1,
&lower_do1,
- NULL
+ NULL,
};
static const char (*lower_sub_files[])[] = {
&lower_dl1_fl2,
&lower_do1_fo2,
&lower_do1_fl3,
- NULL
+ NULL,
};
-#define UPPER_BASE TMP_DIR "/upper"
-#define UPPER_DATA UPPER_BASE "/data"
-#define UPPER_WORK UPPER_BASE "/work"
+#define UPPER_BASE TMP_DIR "/upper"
+#define UPPER_DATA UPPER_BASE "/data"
+#define UPPER_WORK UPPER_BASE "/work"
static const char upper_fu1[] = UPPER_DATA "/fu1";
static const char upper_du1[] = UPPER_DATA "/du1";
static const char upper_du1_fu2[] = UPPER_DATA "/du1/fu2";
@@ -2323,22 +3314,22 @@ static const char upper_do1_fu3[] = UPPER_DATA "/do1/fu3";
static const char (*upper_base_files[])[] = {
&upper_fu1,
&upper_fo1,
- NULL
+ NULL,
};
static const char (*upper_base_directories[])[] = {
&upper_du1,
&upper_do1,
- NULL
+ NULL,
};
static const char (*upper_sub_files[])[] = {
&upper_du1_fu2,
&upper_do1_fo2,
&upper_do1_fu3,
- NULL
+ NULL,
};
-#define MERGE_BASE TMP_DIR "/merge"
-#define MERGE_DATA MERGE_BASE "/data"
+#define MERGE_BASE TMP_DIR "/merge"
+#define MERGE_DATA MERGE_BASE "/data"
static const char merge_fl1[] = MERGE_DATA "/fl1";
static const char merge_dl1[] = MERGE_DATA "/dl1";
static const char merge_dl1_fl2[] = MERGE_DATA "/dl1/fl2";
@@ -2355,21 +3346,17 @@ static const char (*merge_base_files[])[] = {
&merge_fl1,
&merge_fu1,
&merge_fo1,
- NULL
+ NULL,
};
static const char (*merge_base_directories[])[] = {
&merge_dl1,
&merge_du1,
&merge_do1,
- NULL
+ NULL,
};
static const char (*merge_sub_files[])[] = {
- &merge_dl1_fl2,
- &merge_du1_fu2,
- &merge_do1_fo2,
- &merge_do1_fl3,
- &merge_do1_fu3,
- NULL
+ &merge_dl1_fl2, &merge_du1_fu2, &merge_do1_fo2,
+ &merge_do1_fl3, &merge_do1_fu3, NULL,
};
/*
@@ -2411,8 +3398,9 @@ static const char (*merge_sub_files[])[] = {
* └── work
*/
-FIXTURE(layout2_overlay) {
-};
+/* clang-format off */
+FIXTURE(layout2_overlay) {};
+/* clang-format on */
FIXTURE_SETUP(layout2_overlay)
{
@@ -2444,9 +3432,8 @@ FIXTURE_SETUP(layout2_overlay)
set_cap(_metadata, CAP_SYS_ADMIN);
set_cap(_metadata, CAP_DAC_OVERRIDE);
ASSERT_EQ(0, mount("overlay", MERGE_DATA, "overlay", 0,
- "lowerdir=" LOWER_DATA
- ",upperdir=" UPPER_DATA
- ",workdir=" UPPER_WORK));
+ "lowerdir=" LOWER_DATA ",upperdir=" UPPER_DATA
+ ",workdir=" UPPER_WORK));
clear_cap(_metadata, CAP_DAC_OVERRIDE);
clear_cap(_metadata, CAP_SYS_ADMIN);
}
@@ -2513,9 +3500,9 @@ TEST_F_FORK(layout2_overlay, no_restriction)
ASSERT_EQ(0, test_open(merge_do1_fu3, O_RDONLY));
}
-#define for_each_path(path_list, path_entry, i) \
- for (i = 0, path_entry = *path_list[i]; path_list[i]; \
- path_entry = *path_list[++i])
+#define for_each_path(path_list, path_entry, i) \
+ for (i = 0, path_entry = *path_list[i]; path_list[i]; \
+ path_entry = *path_list[++i])
TEST_F_FORK(layout2_overlay, same_content_different_file)
{
@@ -2533,7 +3520,7 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
.path = MERGE_BASE,
.access = ACCESS_RW,
},
- {}
+ {},
};
const struct rule layer2_data[] = {
{
@@ -2548,7 +3535,7 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
.path = MERGE_DATA,
.access = ACCESS_RW,
},
- {}
+ {},
};
/* Sets access right on directories inside both layers. */
const struct rule layer3_subdirs[] = {
@@ -2580,7 +3567,7 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
.path = merge_do1,
.access = ACCESS_RW,
},
- {}
+ {},
};
/* Tighten access rights to the files. */
const struct rule layer4_files[] = {
@@ -2611,37 +3598,37 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
{
.path = merge_dl1_fl2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
{
.path = merge_du1_fu2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
{
.path = merge_do1_fo2,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
{
.path = merge_do1_fl3,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
{
.path = merge_do1_fu3,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
const struct rule layer5_merge_only[] = {
{
.path = MERGE_DATA,
.access = LANDLOCK_ACCESS_FS_READ_FILE |
- LANDLOCK_ACCESS_FS_WRITE_FILE,
+ LANDLOCK_ACCESS_FS_WRITE_FILE,
},
- {}
+ {},
};
int ruleset_fd;
size_t i;
@@ -2659,7 +3646,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
}
for_each_path(lower_base_directories, path_entry, i) {
- ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ ASSERT_EQ(EACCES,
+ test_open(path_entry, O_RDONLY | O_DIRECTORY));
}
for_each_path(lower_sub_files, path_entry, i) {
ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
@@ -2671,7 +3659,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
ASSERT_EQ(EACCES, test_open(path_entry, O_WRONLY));
}
for_each_path(upper_base_directories, path_entry, i) {
- ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ ASSERT_EQ(EACCES,
+ test_open(path_entry, O_RDONLY | O_DIRECTORY));
}
for_each_path(upper_sub_files, path_entry, i) {
ASSERT_EQ(0, test_open(path_entry, O_RDONLY));
@@ -2756,7 +3745,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR));
}
for_each_path(merge_base_directories, path_entry, i) {
- ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ ASSERT_EQ(EACCES,
+ test_open(path_entry, O_RDONLY | O_DIRECTORY));
}
for_each_path(merge_sub_files, path_entry, i) {
ASSERT_EQ(0, test_open(path_entry, O_RDWR));
@@ -2781,7 +3771,8 @@ TEST_F_FORK(layout2_overlay, same_content_different_file)
ASSERT_EQ(EACCES, test_open(path_entry, O_RDWR));
}
for_each_path(merge_base_directories, path_entry, i) {
- ASSERT_EQ(EACCES, test_open(path_entry, O_RDONLY | O_DIRECTORY));
+ ASSERT_EQ(EACCES,
+ test_open(path_entry, O_RDONLY | O_DIRECTORY));
}
for_each_path(merge_sub_files, path_entry, i) {
ASSERT_EQ(0, test_open(path_entry, O_RDWR));
diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c
index 15fbef9cc849..c28ef98ff3ac 100644
--- a/tools/testing/selftests/landlock/ptrace_test.c
+++ b/tools/testing/selftests/landlock/ptrace_test.c
@@ -26,9 +26,10 @@ static void create_domain(struct __test_metadata *const _metadata)
.handled_access_fs = LANDLOCK_ACCESS_FS_MAKE_BLOCK,
};
- ruleset_fd = landlock_create_ruleset(&ruleset_attr,
- sizeof(ruleset_attr), 0);
- EXPECT_LE(0, ruleset_fd) {
+ ruleset_fd =
+ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
+ EXPECT_LE(0, ruleset_fd)
+ {
TH_LOG("Failed to create a ruleset: %s", strerror(errno));
}
EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
@@ -43,7 +44,7 @@ static int test_ptrace_read(const pid_t pid)
int procenv_path_size, fd;
procenv_path_size = snprintf(procenv_path, sizeof(procenv_path),
- path_template, pid);
+ path_template, pid);
if (procenv_path_size >= sizeof(procenv_path))
return E2BIG;
@@ -59,9 +60,12 @@ static int test_ptrace_read(const pid_t pid)
return 0;
}
-FIXTURE(hierarchy) { };
+/* clang-format off */
+FIXTURE(hierarchy) {};
+/* clang-format on */
-FIXTURE_VARIANT(hierarchy) {
+FIXTURE_VARIANT(hierarchy)
+{
const bool domain_both;
const bool domain_parent;
const bool domain_child;
@@ -83,7 +87,9 @@ FIXTURE_VARIANT(hierarchy) {
* \ P2 -> P1 : allow
* 'P2
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) {
+ /* clang-format on */
.domain_both = false,
.domain_parent = false,
.domain_child = false,
@@ -98,7 +104,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_without_domain) {
* | P2 |
* '------'
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) {
+ /* clang-format on */
.domain_both = false,
.domain_parent = false,
.domain_child = true,
@@ -112,7 +120,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_with_one_domain) {
* '
* P2
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) {
+ /* clang-format on */
.domain_both = false,
.domain_parent = true,
.domain_child = false,
@@ -127,7 +137,9 @@ FIXTURE_VARIANT_ADD(hierarchy, deny_with_parent_domain) {
* | P2 |
* '------'
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) {
+ /* clang-format on */
.domain_both = false,
.domain_parent = true,
.domain_child = true,
@@ -142,7 +154,9 @@ FIXTURE_VARIANT_ADD(hierarchy, deny_with_sibling_domain) {
* | P2 |
* '-------------'
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) {
+ /* clang-format on */
.domain_both = true,
.domain_parent = false,
.domain_child = false,
@@ -158,7 +172,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_sibling_domain) {
* | '------' |
* '-----------------'
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) {
+ /* clang-format on */
.domain_both = true,
.domain_parent = false,
.domain_child = true,
@@ -174,7 +190,9 @@ FIXTURE_VARIANT_ADD(hierarchy, allow_with_nested_domain) {
* | P2 |
* '-----------------'
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) {
+ /* clang-format on */
.domain_both = true,
.domain_parent = true,
.domain_child = false,
@@ -192,17 +210,21 @@ FIXTURE_VARIANT_ADD(hierarchy, deny_with_nested_and_parent_domain) {
* | '------' |
* '-----------------'
*/
+/* clang-format off */
FIXTURE_VARIANT_ADD(hierarchy, deny_with_forked_domain) {
+ /* clang-format on */
.domain_both = true,
.domain_parent = true,
.domain_child = true,
};
FIXTURE_SETUP(hierarchy)
-{ }
+{
+}
FIXTURE_TEARDOWN(hierarchy)
-{ }
+{
+}
/* Test PTRACE_TRACEME and PTRACE_ATTACH for parent and child. */
TEST_F(hierarchy, trace)
@@ -330,7 +352,7 @@ TEST_F(hierarchy, trace)
ASSERT_EQ(1, write(pipe_parent[1], ".", 1));
ASSERT_EQ(child, waitpid(child, &status, 0));
if (WIFSIGNALED(status) || !WIFEXITED(status) ||
- WEXITSTATUS(status) != EXIT_SUCCESS)
+ WEXITSTATUS(status) != EXIT_SUCCESS)
_metadata->passed = 0;
}
diff --git a/tools/testing/selftests/mqueue/mq_perf_tests.c b/tools/testing/selftests/mqueue/mq_perf_tests.c
index b019e0b8221c..84fda3b49073 100644
--- a/tools/testing/selftests/mqueue/mq_perf_tests.c
+++ b/tools/testing/selftests/mqueue/mq_perf_tests.c
@@ -180,6 +180,9 @@ void shutdown(int exit_val, char *err_cause, int line_no)
if (in_shutdown++)
return;
+ /* Free the cpu_set allocated using CPU_ALLOC in main function */
+ CPU_FREE(cpu_set);
+
for (i = 0; i < num_cpus_to_pin; i++)
if (cpu_threads[i]) {
pthread_kill(cpu_threads[i], SIGUSR1);
@@ -551,6 +554,12 @@ int main(int argc, char *argv[])
perror("sysconf(_SC_NPROCESSORS_ONLN)");
exit(1);
}
+
+ if (getuid() != 0)
+ ksft_exit_skip("Not running as root, but almost all tests "
+ "require root in order to modify\nsystem settings. "
+ "Exiting.\n");
+
cpus_online = min(MAX_CPUS, sysconf(_SC_NPROCESSORS_ONLN));
cpu_set = CPU_ALLOC(cpus_online);
if (cpu_set == NULL) {
@@ -589,7 +598,7 @@ int main(int argc, char *argv[])
cpu_set)) {
fprintf(stderr, "Any given CPU may "
"only be given once.\n");
- exit(1);
+ goto err_code;
} else
CPU_SET_S(cpus_to_pin[cpu],
cpu_set_size, cpu_set);
@@ -607,7 +616,7 @@ int main(int argc, char *argv[])
queue_path = malloc(strlen(option) + 2);
if (!queue_path) {
perror("malloc()");
- exit(1);
+ goto err_code;
}
queue_path[0] = '/';
queue_path[1] = 0;
@@ -622,17 +631,12 @@ int main(int argc, char *argv[])
fprintf(stderr, "Must pass at least one CPU to continuous "
"mode.\n");
poptPrintUsage(popt_context, stderr, 0);
- exit(1);
+ goto err_code;
} else if (!continuous_mode) {
num_cpus_to_pin = 1;
cpus_to_pin[0] = cpus_online - 1;
}
- if (getuid() != 0)
- ksft_exit_skip("Not running as root, but almost all tests "
- "require root in order to modify\nsystem settings. "
- "Exiting.\n");
-
max_msgs = fopen(MAX_MSGS, "r+");
max_msgsize = fopen(MAX_MSGSIZE, "r+");
if (!max_msgs)
@@ -740,4 +744,9 @@ int main(int argc, char *argv[])
sleep(1);
}
shutdown(0, "", 0);
+
+err_code:
+ CPU_FREE(cpu_set);
+ exit(1);
+
}
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 3fe2515aa616..e1f998defd10 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -25,12 +25,13 @@ TEST_PROGS += bareudp.sh
TEST_PROGS += amt.sh
TEST_PROGS += unicast_extensions.sh
TEST_PROGS += udpgro_fwd.sh
+TEST_PROGS += udpgro_frglist.sh
TEST_PROGS += veth.sh
TEST_PROGS += ioam6.sh
TEST_PROGS += gro.sh
TEST_PROGS += gre_gso.sh
TEST_PROGS += cmsg_so_mark.sh
-TEST_PROGS += cmsg_time.sh
+TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
@@ -54,12 +55,15 @@ TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
TEST_GEN_FILES += toeplitz
TEST_GEN_FILES += cmsg_sender
+TEST_PROGS += test_vxlan_vnifiltering.sh
TEST_FILES := settings
KSFT_KHDR_INSTALL := 1
include ../lib.mk
+include bpf/Makefile
+
$(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
$(OUTPUT)/tcp_mmap: LDLIBS += -lpthread
$(OUTPUT)/tcp_inq: LDLIBS += -lpthread
diff --git a/tools/testing/selftests/net/bpf/Makefile b/tools/testing/selftests/net/bpf/Makefile
new file mode 100644
index 000000000000..f91bf14bbee7
--- /dev/null
+++ b/tools/testing/selftests/net/bpf/Makefile
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+CLANG ?= clang
+CCINCLUDE += -I../../bpf
+CCINCLUDE += -I../../../../../usr/include/
+
+TEST_CUSTOM_PROGS = $(OUTPUT)/bpf/nat6to4.o
+all: $(TEST_CUSTOM_PROGS)
+
+$(OUTPUT)/%.o: %.c
+ $(CLANG) -O2 -target bpf -c $< $(CCINCLUDE) -o $@
+
+clean:
+ rm -f $(TEST_CUSTOM_PROGS)
diff --git a/tools/testing/selftests/net/bpf/nat6to4.c b/tools/testing/selftests/net/bpf/nat6to4.c
new file mode 100644
index 000000000000..ac54c36b25fc
--- /dev/null
+++ b/tools/testing/selftests/net/bpf/nat6to4.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * This code is taken from the Android Open Source Project and the author
+ * (Maciej Żenczykowski) has gave permission to relicense it under the
+ * GPLv2. Therefore this program is free software;
+ * You can redistribute it and/or modify it under the terms of the GNU
+ * General Public License version 2 as published by the Free Software
+ * Foundation
+
+ * The original headers, including the original license headers, are
+ * included below for completeness.
+ *
+ * Copyright (C) 2019 The Android Open Source Project
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+#include <linux/bpf.h>
+#include <linux/if.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/pkt_cls.h>
+#include <linux/swab.h>
+#include <stdbool.h>
+#include <stdint.h>
+
+
+#include <linux/udp.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define IP_DF 0x4000 // Flag: "Don't Fragment"
+
+SEC("schedcls/ingress6/nat_6")
+int sched_cls_ingress6_nat_6_prog(struct __sk_buff *skb)
+{
+ const int l2_header_size = sizeof(struct ethhdr);
+ void *data = (void *)(long)skb->data;
+ const void *data_end = (void *)(long)skb->data_end;
+ const struct ethhdr * const eth = data; // used iff is_ethernet
+ const struct ipv6hdr * const ip6 = (void *)(eth + 1);
+
+ // Require ethernet dst mac address to be our unicast address.
+ if (skb->pkt_type != PACKET_HOST)
+ return TC_ACT_OK;
+
+ // Must be meta-ethernet IPv6 frame
+ if (skb->protocol != bpf_htons(ETH_P_IPV6))
+ return TC_ACT_OK;
+
+ // Must have (ethernet and) ipv6 header
+ if (data + l2_header_size + sizeof(*ip6) > data_end)
+ return TC_ACT_OK;
+
+ // Ethertype - if present - must be IPv6
+ if (eth->h_proto != bpf_htons(ETH_P_IPV6))
+ return TC_ACT_OK;
+
+ // IP version must be 6
+ if (ip6->version != 6)
+ return TC_ACT_OK;
+ // Maximum IPv6 payload length that can be translated to IPv4
+ if (bpf_ntohs(ip6->payload_len) > 0xFFFF - sizeof(struct iphdr))
+ return TC_ACT_OK;
+ switch (ip6->nexthdr) {
+ case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6
+ case IPPROTO_UDP: // address means there is no need to update their checksums.
+ case IPPROTO_GRE: // We do not need to bother looking at GRE/ESP headers,
+ case IPPROTO_ESP: // since there is never a checksum to update.
+ break;
+ default: // do not know how to handle anything else
+ return TC_ACT_OK;
+ }
+
+ struct ethhdr eth2; // used iff is_ethernet
+
+ eth2 = *eth; // Copy over the ethernet header (src/dst mac)
+ eth2.h_proto = bpf_htons(ETH_P_IP); // But replace the ethertype
+
+ struct iphdr ip = {
+ .version = 4, // u4
+ .ihl = sizeof(struct iphdr) / sizeof(__u32), // u4
+ .tos = (ip6->priority << 4) + (ip6->flow_lbl[0] >> 4), // u8
+ .tot_len = bpf_htons(bpf_ntohs(ip6->payload_len) + sizeof(struct iphdr)), // u16
+ .id = 0, // u16
+ .frag_off = bpf_htons(IP_DF), // u16
+ .ttl = ip6->hop_limit, // u8
+ .protocol = ip6->nexthdr, // u8
+ .check = 0, // u16
+ .saddr = 0x0201a8c0, // u32
+ .daddr = 0x0101a8c0, // u32
+ };
+
+ // Calculate the IPv4 one's complement checksum of the IPv4 header.
+ __wsum sum4 = 0;
+
+ for (int i = 0; i < sizeof(ip) / sizeof(__u16); ++i)
+ sum4 += ((__u16 *)&ip)[i];
+
+ // Note that sum4 is guaranteed to be non-zero by virtue of ip.version == 4
+ sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE
+ sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16
+ ip.check = (__u16)~sum4; // sum4 cannot be zero, so this is never 0xFFFF
+
+ // Calculate the *negative* IPv6 16-bit one's complement checksum of the IPv6 header.
+ __wsum sum6 = 0;
+ // We'll end up with a non-zero sum due to ip6->version == 6 (which has '0' bits)
+ for (int i = 0; i < sizeof(*ip6) / sizeof(__u16); ++i)
+ sum6 += ~((__u16 *)ip6)[i]; // note the bitwise negation
+
+ // Note that there is no L4 checksum update: we are relying on the checksum neutrality
+ // of the ipv6 address chosen by netd's ClatdController.
+
+ // Packet mutations begin - point of no return, but if this first modification fails
+ // the packet is probably still pristine, so let clatd handle it.
+ if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IP), 0))
+ return TC_ACT_OK;
+ bpf_csum_update(skb, sum6);
+
+ data = (void *)(long)skb->data;
+ data_end = (void *)(long)skb->data_end;
+ if (data + l2_header_size + sizeof(struct iphdr) > data_end)
+ return TC_ACT_SHOT;
+
+ struct ethhdr *new_eth = data;
+
+ // Copy over the updated ethernet header
+ *new_eth = eth2;
+
+ // Copy over the new ipv4 header.
+ *(struct iphdr *)(new_eth + 1) = ip;
+ return bpf_redirect(skb->ifindex, BPF_F_INGRESS);
+}
+
+SEC("schedcls/egress4/snat4")
+int sched_cls_egress4_snat4_prog(struct __sk_buff *skb)
+{
+ const int l2_header_size = sizeof(struct ethhdr);
+ void *data = (void *)(long)skb->data;
+ const void *data_end = (void *)(long)skb->data_end;
+ const struct ethhdr *const eth = data; // used iff is_ethernet
+ const struct iphdr *const ip4 = (void *)(eth + 1);
+
+ // Must be meta-ethernet IPv4 frame
+ if (skb->protocol != bpf_htons(ETH_P_IP))
+ return TC_ACT_OK;
+
+ // Must have ipv4 header
+ if (data + l2_header_size + sizeof(struct ipv6hdr) > data_end)
+ return TC_ACT_OK;
+
+ // Ethertype - if present - must be IPv4
+ if (eth->h_proto != bpf_htons(ETH_P_IP))
+ return TC_ACT_OK;
+
+ // IP version must be 4
+ if (ip4->version != 4)
+ return TC_ACT_OK;
+
+ // We cannot handle IP options, just standard 20 byte == 5 dword minimal IPv4 header
+ if (ip4->ihl != 5)
+ return TC_ACT_OK;
+
+ // Maximum IPv6 payload length that can be translated to IPv4
+ if (bpf_htons(ip4->tot_len) > 0xFFFF - sizeof(struct ipv6hdr))
+ return TC_ACT_OK;
+
+ // Calculate the IPv4 one's complement checksum of the IPv4 header.
+ __wsum sum4 = 0;
+
+ for (int i = 0; i < sizeof(*ip4) / sizeof(__u16); ++i)
+ sum4 += ((__u16 *)ip4)[i];
+
+ // Note that sum4 is guaranteed to be non-zero by virtue of ip4->version == 4
+ sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse u32 into range 1 .. 0x1FFFE
+ sum4 = (sum4 & 0xFFFF) + (sum4 >> 16); // collapse any potential carry into u16
+ // for a correct checksum we should get *a* zero, but sum4 must be positive, ie 0xFFFF
+ if (sum4 != 0xFFFF)
+ return TC_ACT_OK;
+
+ // Minimum IPv4 total length is the size of the header
+ if (bpf_ntohs(ip4->tot_len) < sizeof(*ip4))
+ return TC_ACT_OK;
+
+ // We are incapable of dealing with IPv4 fragments
+ if (ip4->frag_off & ~bpf_htons(IP_DF))
+ return TC_ACT_OK;
+
+ switch (ip4->protocol) {
+ case IPPROTO_TCP: // For TCP & UDP the checksum neutrality of the chosen IPv6
+ case IPPROTO_GRE: // address means there is no need to update their checksums.
+ case IPPROTO_ESP: // We do not need to bother looking at GRE/ESP headers,
+ break; // since there is never a checksum to update.
+
+ case IPPROTO_UDP: // See above comment, but must also have UDP header...
+ if (data + sizeof(*ip4) + sizeof(struct udphdr) > data_end)
+ return TC_ACT_OK;
+ const struct udphdr *uh = (const struct udphdr *)(ip4 + 1);
+ // If IPv4/UDP checksum is 0 then fallback to clatd so it can calculate the
+ // checksum. Otherwise the network or more likely the NAT64 gateway might
+ // drop the packet because in most cases IPv6/UDP packets with a zero checksum
+ // are invalid. See RFC 6935. TODO: calculate checksum via bpf_csum_diff()
+ if (!uh->check)
+ return TC_ACT_OK;
+ break;
+
+ default: // do not know how to handle anything else
+ return TC_ACT_OK;
+ }
+ struct ethhdr eth2; // used iff is_ethernet
+
+ eth2 = *eth; // Copy over the ethernet header (src/dst mac)
+ eth2.h_proto = bpf_htons(ETH_P_IPV6); // But replace the ethertype
+
+ struct ipv6hdr ip6 = {
+ .version = 6, // __u8:4
+ .priority = ip4->tos >> 4, // __u8:4
+ .flow_lbl = {(ip4->tos & 0xF) << 4, 0, 0}, // __u8[3]
+ .payload_len = bpf_htons(bpf_ntohs(ip4->tot_len) - 20), // __be16
+ .nexthdr = ip4->protocol, // __u8
+ .hop_limit = ip4->ttl, // __u8
+ };
+ ip6.saddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8);
+ ip6.saddr.in6_u.u6_addr32[1] = 0;
+ ip6.saddr.in6_u.u6_addr32[2] = 0;
+ ip6.saddr.in6_u.u6_addr32[3] = bpf_htonl(1);
+ ip6.daddr.in6_u.u6_addr32[0] = bpf_htonl(0x20010db8);
+ ip6.daddr.in6_u.u6_addr32[1] = 0;
+ ip6.daddr.in6_u.u6_addr32[2] = 0;
+ ip6.daddr.in6_u.u6_addr32[3] = bpf_htonl(2);
+
+ // Calculate the IPv6 16-bit one's complement checksum of the IPv6 header.
+ __wsum sum6 = 0;
+ // We'll end up with a non-zero sum due to ip6.version == 6
+ for (int i = 0; i < sizeof(ip6) / sizeof(__u16); ++i)
+ sum6 += ((__u16 *)&ip6)[i];
+
+ // Packet mutations begin - point of no return, but if this first modification fails
+ // the packet is probably still pristine, so let clatd handle it.
+ if (bpf_skb_change_proto(skb, bpf_htons(ETH_P_IPV6), 0))
+ return TC_ACT_OK;
+
+ // This takes care of updating the skb->csum field for a CHECKSUM_COMPLETE packet.
+ // In such a case, skb->csum is a 16-bit one's complement sum of the entire payload,
+ // thus we need to subtract out the ipv4 header's sum, and add in the ipv6 header's sum.
+ // However, we've already verified the ipv4 checksum is correct and thus 0.
+ // Thus we only need to add the ipv6 header's sum.
+ //
+ // bpf_csum_update() always succeeds if the skb is CHECKSUM_COMPLETE and returns an error
+ // (-ENOTSUPP) if it isn't. So we just ignore the return code (see above for more details).
+ bpf_csum_update(skb, sum6);
+
+ // bpf_skb_change_proto() invalidates all pointers - reload them.
+ data = (void *)(long)skb->data;
+ data_end = (void *)(long)skb->data_end;
+
+ // I cannot think of any valid way for this error condition to trigger, however I do
+ // believe the explicit check is required to keep the in kernel ebpf verifier happy.
+ if (data + l2_header_size + sizeof(ip6) > data_end)
+ return TC_ACT_SHOT;
+
+ struct ethhdr *new_eth = data;
+
+ // Copy over the updated ethernet header
+ *new_eth = eth2;
+ // Copy over the new ipv4 header.
+ *(struct ipv6hdr *)(new_eth + 1) = ip6;
+ return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = ("GPL");
diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 47c4d4b4a44a..54701c8b0cd7 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -810,10 +810,16 @@ ipv4_ping()
setup
set_sysctl net.ipv4.raw_l3mdev_accept=1 2>/dev/null
ipv4_ping_novrf
+ setup
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
+ ipv4_ping_novrf
log_subsection "With VRF"
setup "yes"
ipv4_ping_vrf
+ setup "yes"
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
+ ipv4_ping_vrf
}
################################################################################
@@ -2348,10 +2354,16 @@ ipv6_ping()
log_subsection "No VRF"
setup
ipv6_ping_novrf
+ setup
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
+ ipv6_ping_novrf
log_subsection "With VRF"
setup "yes"
ipv6_ping_vrf
+ setup "yes"
+ set_sysctl net.ipv4.ping_group_range='0 2147483647' 2>/dev/null
+ ipv6_ping_vrf
}
################################################################################
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index d444ee6aa3cb..b3bf5319bb0e 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -1208,6 +1208,20 @@ ipv4_fcnal()
set +e
check_nexthop "dev veth1" ""
log_test $? 0 "Nexthops removed on admin down"
+
+ # nexthop route delete warning: route add with nhid and delete
+ # using device
+ run_cmd "$IP li set dev veth1 up"
+ run_cmd "$IP nexthop add id 12 via 172.16.1.3 dev veth1"
+ out1=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l`
+ run_cmd "$IP route add 172.16.101.1/32 nhid 12"
+ run_cmd "$IP route delete 172.16.101.1/32 dev veth1"
+ out2=`dmesg | grep "WARNING:.*fib_nh_match.*" | wc -l`
+ [ $out1 -eq $out2 ]
+ rc=$?
+ log_test $rc 0 "Delete nexthop route warning"
+ run_cmd "$IP route delete 172.16.101.1/32 nhid 12"
+ run_cmd "$IP nexthop del id 12"
}
ipv4_grp_fcnal()
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index 8fa97ae9af9e..e811090f7748 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -2,15 +2,31 @@
TEST_PROGS = bridge_igmp.sh \
bridge_locked_port.sh \
+ bridge_mld.sh \
bridge_port_isolation.sh \
bridge_sticky_fdb.sh \
bridge_vlan_aware.sh \
+ bridge_vlan_mcast.sh \
bridge_vlan_unaware.sh \
+ custom_multipath_hash.sh \
+ dual_vxlan_bridge.sh \
+ ethtool_extended_state.sh \
ethtool.sh \
+ gre_custom_multipath_hash.sh \
gre_inner_v4_multipath.sh \
gre_inner_v6_multipath.sh \
+ gre_multipath_nh_res.sh \
+ gre_multipath_nh.sh \
gre_multipath.sh \
+ hw_stats_l3.sh \
ip6_forward_instats_vrf.sh \
+ ip6gre_custom_multipath_hash.sh \
+ ip6gre_flat_key.sh \
+ ip6gre_flat_keys.sh \
+ ip6gre_flat.sh \
+ ip6gre_hier_key.sh \
+ ip6gre_hier_keys.sh \
+ ip6gre_hier.sh \
ip6gre_inner_v4_multipath.sh \
ip6gre_inner_v6_multipath.sh \
ipip_flat_gre_key.sh \
@@ -34,36 +50,53 @@ TEST_PROGS = bridge_igmp.sh \
mirror_gre_vlan_bridge_1q.sh \
mirror_gre_vlan.sh \
mirror_vlan.sh \
+ pedit_dsfield.sh \
+ pedit_ip.sh \
+ pedit_l4port.sh \
+ q_in_vni_ipv6.sh \
+ q_in_vni.sh \
router_bridge.sh \
router_bridge_vlan.sh \
router_broadcast.sh \
+ router_mpath_nh_res.sh \
router_mpath_nh.sh \
router_multicast.sh \
router_multipath.sh \
+ router_nh.sh \
router.sh \
router_vid_1.sh \
sch_ets.sh \
+ sch_red.sh \
sch_tbf_ets.sh \
sch_tbf_prio.sh \
sch_tbf_root.sh \
+ skbedit_priority.sh \
tc_actions.sh \
tc_chains.sh \
tc_flower_router.sh \
tc_flower.sh \
tc_mpls_l2vpn.sh \
+ tc_police.sh \
tc_shblocks.sh \
tc_vlan_modify.sh \
+ vxlan_asymmetric_ipv6.sh \
vxlan_asymmetric.sh \
+ vxlan_bridge_1d_ipv6.sh \
+ vxlan_bridge_1d_port_8472_ipv6.sh \
vxlan_bridge_1d_port_8472.sh \
vxlan_bridge_1d.sh \
+ vxlan_bridge_1q_ipv6.sh \
+ vxlan_bridge_1q_port_8472_ipv6.sh \
vxlan_bridge_1q_port_8472.sh \
vxlan_bridge_1q.sh \
+ vxlan_symmetric_ipv6.sh \
vxlan_symmetric.sh
TEST_PROGS_EXTENDED := devlink_lib.sh \
ethtool_lib.sh \
fib_offload_lib.sh \
forwarding.config.sample \
+ ip6gre_lib.sh \
ipip_lib.sh \
lib.sh \
mirror_gre_lib.sh \
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
index a3402cd8d5b6..9ff22f28032d 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
@@ -61,9 +61,12 @@ setup_prepare()
vrf_prepare
mirror_gre_topo_create
+ # Avoid changing br1's PVID while it is operational as a L3 interface.
+ ip link set dev br1 down
ip link set dev $swp3 master br1
bridge vlan add dev br1 vid 555 pvid untagged self
+ ip link set dev br1 up
ip address add dev br1 192.0.2.129/28
ip address add dev br1 2001:db8:2::1/64
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 7314257d248a..48ef112f42c2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -1444,6 +1444,33 @@ chk_prio_nr()
[ "${dump_stats}" = 1 ] && dump_stats
}
+chk_subflow_nr()
+{
+ local need_title="$1"
+ local msg="$2"
+ local subflow_nr=$3
+ local cnt1
+ local cnt2
+
+ if [ -n "${need_title}" ]; then
+ printf "%03u %-36s %s" "${TEST_COUNT}" "${TEST_NAME}" "${msg}"
+ else
+ printf "%-${nr_blank}s %s" " " "${msg}"
+ fi
+
+ cnt1=$(ss -N $ns1 -tOni | grep -c token)
+ cnt2=$(ss -N $ns2 -tOni | grep -c token)
+ if [ "$cnt1" != "$subflow_nr" -o "$cnt2" != "$subflow_nr" ]; then
+ echo "[fail] got $cnt1:$cnt2 subflows expected $subflow_nr"
+ fail_test
+ dump_stats=1
+ else
+ echo "[ ok ]"
+ fi
+
+ [ "${dump_stats}" = 1 ] && ( ss -N $ns1 -tOni ; ss -N $ns1 -tOni | grep token; ip -n $ns1 mptcp endpoint )
+}
+
chk_link_usage()
{
local ns=$1
@@ -2556,7 +2583,7 @@ fastclose_tests()
fi
}
-implicit_tests()
+endpoint_tests()
{
# userspace pm type prevents add_addr
if reset "implicit EP"; then
@@ -2578,6 +2605,23 @@ implicit_tests()
$ns2 10.0.2.2 id 1 flags signal
wait
fi
+
+ if reset "delete and re-add"; then
+ pm_nl_set_limits $ns1 1 1
+ pm_nl_set_limits $ns2 1 1
+ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
+ run_tests $ns1 $ns2 10.0.1.1 4 0 0 slow &
+
+ wait_mpj $ns2
+ pm_nl_del_endpoint $ns2 2 10.0.2.2
+ sleep 0.5
+ chk_subflow_nr needtitle "after delete" 1
+
+ pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
+ wait_mpj $ns2
+ chk_subflow_nr "" "after re-add" 2
+ wait
+ fi
}
# [$1: error message]
@@ -2624,7 +2668,7 @@ all_tests_sorted=(
d@deny_join_id0_tests
m@fullmesh_tests
z@fastclose_tests
- I@implicit_tests
+ I@endpoint_tests
)
all_tests_args=""
diff --git a/tools/testing/selftests/net/so_txtime.c b/tools/testing/selftests/net/so_txtime.c
index 59067f64b775..2672ac0b6d1f 100644
--- a/tools/testing/selftests/net/so_txtime.c
+++ b/tools/testing/selftests/net/so_txtime.c
@@ -421,7 +421,7 @@ static void usage(const char *progname)
"Options:\n"
" -4 only IPv4\n"
" -6 only IPv6\n"
- " -c <clock> monotonic (default) or tai\n"
+ " -c <clock> monotonic or tai (default)\n"
" -D <addr> destination IP address (server)\n"
" -S <addr> source IP address (client)\n"
" -r run rx mode\n"
@@ -475,7 +475,7 @@ static void parse_opts(int argc, char **argv)
cfg_rx = true;
break;
case 't':
- cfg_start_time_ns = strtol(optarg, NULL, 0);
+ cfg_start_time_ns = strtoll(optarg, NULL, 0);
break;
case 'm':
cfg_mark = strtol(optarg, NULL, 0);
diff --git a/tools/testing/selftests/net/udpgro_frglist.sh b/tools/testing/selftests/net/udpgro_frglist.sh
new file mode 100755
index 000000000000..807b74c8fd80
--- /dev/null
+++ b/tools/testing/selftests/net/udpgro_frglist.sh
@@ -0,0 +1,101 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a series of udpgro benchmarks
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+cleanup() {
+ local -r jobs="$(jobs -p)"
+ local -r ns="$(ip netns list|grep $PEER_NS)"
+
+ [ -n "${jobs}" ] && kill -INT ${jobs} 2>/dev/null
+ [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+}
+trap cleanup EXIT
+
+run_one() {
+ # use 'rx' as separator between sender args and receiver args
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local rx_args=${all#*rx}
+
+
+
+ ip netns add "${PEER_NS}"
+ ip -netns "${PEER_NS}" link set lo up
+ ip link add type veth
+ ip link set dev veth0 up
+ ip addr add dev veth0 192.168.1.2/24
+ ip addr add dev veth0 2001:db8::2/64 nodad
+
+ ip link set dev veth1 netns "${PEER_NS}"
+ ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+ ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+ ip -netns "${PEER_NS}" link set dev veth1 up
+ ip netns exec "${PEER_NS}" ethtool -K veth1 rx-gro-list on
+
+
+ ip -n "${PEER_NS}" link set veth1 xdp object ../bpf/xdp_dummy.o section xdp_dummy
+ tc -n "${PEER_NS}" qdisc add dev veth1 clsact
+ tc -n "${PEER_NS}" filter add dev veth1 ingress prio 4 protocol ipv6 bpf object-file ../bpf/nat6to4.o section schedcls/ingress6/nat_6 direct-action
+ tc -n "${PEER_NS}" filter add dev veth1 egress prio 4 protocol ip bpf object-file ../bpf/nat6to4.o section schedcls/egress4/snat4 direct-action
+ echo ${rx_args}
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx ${rx_args} -r &
+
+ # Hack: let bg programs complete the startup
+ sleep 0.1
+ ./udpgso_bench_tx ${tx_args}
+}
+
+run_in_netns() {
+ local -r args=$@
+ echo ${args}
+ ./in_netns.sh $0 __subprocess ${args}
+}
+
+run_udp() {
+ local -r args=$@
+
+ echo "udp gso - over veth touching data"
+ run_in_netns ${args} -u -S 0 rx -4 -v
+
+ echo "udp gso and gro - over veth touching data"
+ run_in_netns ${args} -S 0 rx -4 -G
+}
+
+run_tcp() {
+ local -r args=$@
+
+ echo "tcp - over veth touching data"
+ run_in_netns ${args} -t rx -4 -t
+}
+
+run_all() {
+ local -r core_args="-l 4"
+ local -r ipv4_args="${core_args} -4 -D 192.168.1.1"
+ local -r ipv6_args="${core_args} -6 -D 2001:db8::1"
+
+ echo "ipv6"
+ run_tcp "${ipv6_args}"
+ run_udp "${ipv6_args}"
+}
+
+if [ ! -f ../bpf/xdp_dummy.o ]; then
+ echo "Missing xdp_dummy helper. Build bpf selftest first"
+ exit -1
+fi
+
+if [ ! -f bpf/nat6to4.o ]; then
+ echo "Missing nat6to4 helper. Build bpfnat6to4.o selftest first"
+ exit -1
+fi
+
+if [[ $# -eq 0 ]]; then
+ run_all
+elif [[ $1 == "__subprocess" ]]; then
+ shift
+ run_one $@
+else
+ run_in_netns $@
+fi
diff --git a/tools/testing/selftests/pid_namespace/Makefile b/tools/testing/selftests/pid_namespace/Makefile
index dcaefa224ca0..edafaca1aeb3 100644
--- a/tools/testing/selftests/pid_namespace/Makefile
+++ b/tools/testing/selftests/pid_namespace/Makefile
@@ -1,8 +1,8 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -g -I../../../../usr/include/
-TEST_GEN_PROGS := regression_enomem
+TEST_GEN_PROGS = regression_enomem
-include ../lib.mk
+LOCAL_HDRS += $(selfdir)/pidfd/pidfd.h
-$(OUTPUT)/regression_enomem: regression_enomem.c ../pidfd/pidfd.h
+include ../lib.mk
diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c
index 17999e082aa7..070c1c876df1 100644
--- a/tools/testing/selftests/pidfd/pidfd_wait.c
+++ b/tools/testing/selftests/pidfd/pidfd_wait.c
@@ -95,7 +95,6 @@ TEST(wait_states)
.flags = CLONE_PIDFD | CLONE_PARENT_SETTID,
.exit_signal = SIGCHLD,
};
- int ret;
pid_t pid;
siginfo_t info = {
.si_signo = 0,
diff --git a/tools/testing/selftests/proc/proc-pid-vm.c b/tools/testing/selftests/proc/proc-pid-vm.c
index 18a3bde8bc96..28604c9f805c 100644
--- a/tools/testing/selftests/proc/proc-pid-vm.c
+++ b/tools/testing/selftests/proc/proc-pid-vm.c
@@ -46,6 +46,8 @@
#include <sys/time.h>
#include <sys/resource.h>
+#include "../kselftest.h"
+
static inline long sys_execveat(int dirfd, const char *pathname, char **argv, char **envp, int flags)
{
return syscall(SYS_execveat, dirfd, pathname, argv, envp, flags);
@@ -368,7 +370,7 @@ int main(void)
};
int i;
- for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) {
+ for (i = 0; i < ARRAY_SIZE(S); i++) {
assert(memmem(buf, rv, S[i], strlen(S[i])));
}
@@ -417,7 +419,7 @@ int main(void)
};
int i;
- for (i = 0; i < sizeof(S)/sizeof(S[0]); i++) {
+ for (i = 0; i < ARRAY_SIZE(S); i++) {
assert(memmem(buf, rv, S[i], strlen(S[i])));
}
}
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index c35ba24f994c..66d0414d8e4b 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -301,7 +301,7 @@ specify_qemu_cpus () {
echo $2 -smp $3
;;
qemu-system-ppc64)
- nt="`lscpu | grep '^NUMA node0' | sed -e 's/^[^,]*,\([0-9]*\),.*$/\1/'`"
+ nt="`lscpu | sed -n 's/^Thread(s) per core:\s*//p'`"
echo $2 -smp cores=`expr \( $3 + $nt - 1 \) / $nt`,threads=$nt
;;
esac
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
index 5f682fc892dd..88983cba7956 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh
@@ -36,7 +36,7 @@ do
then
egrep "error:|warning:|^ld: .*undefined reference to" < $i > $i.diags
files="$files $i.diags $i"
- elif ! test -f ${scenariobasedir}/vmlinux
+ elif ! test -f ${scenariobasedir}/vmlinux && ! test -f "${rundir}/re-run"
then
echo No ${scenariobasedir}/vmlinux file > $i.diags
files="$files $i.diags $i"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index 0a5419982ab3..0789c5606d2a 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -33,7 +33,12 @@ do
TORTURE_SUITE="`cat $i/../torture_suite`"
configfile=`echo $i | sed -e 's,^.*/,,'`
rm -f $i/console.log.*.diags
- kvm-recheck-${TORTURE_SUITE}.sh $i
+ case "${TORTURE_SUITE}" in
+ X*)
+ ;;
+ *)
+ kvm-recheck-${TORTURE_SUITE}.sh $i
+ esac
if test -f "$i/qemu-retval" && test "`cat $i/qemu-retval`" -ne 0 && test "`cat $i/qemu-retval`" -ne 137
then
echo QEMU error, output:
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
index 8c4c1e4792d0..0ff59bd8b640 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-remote.sh
@@ -138,14 +138,14 @@ chmod +x $T/bin/kvm-remote-*.sh
# Check first to avoid the need for cleanup for system-name typos
for i in $systems
do
- ncpus="`ssh $i getconf _NPROCESSORS_ONLN 2> /dev/null`"
- echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log"
+ ncpus="`ssh -o BatchMode=yes $i getconf _NPROCESSORS_ONLN 2> /dev/null`"
ret=$?
if test "$ret" -ne 0
then
echo System $i unreachable, giving up. | tee -a "$oldrun/remote-log"
exit 4
fi
+ echo $i: $ncpus CPUs " " `date` | tee -a "$oldrun/remote-log"
done
# Download and expand the tarball on all systems.
@@ -153,14 +153,14 @@ echo Build-products tarball: `du -h $T/binres.tgz` | tee -a "$oldrun/remote-log"
for i in $systems
do
echo Downloading tarball to $i `date` | tee -a "$oldrun/remote-log"
- cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
+ cat $T/binres.tgz | ssh -o BatchMode=yes $i "cd /tmp; tar -xzf -"
ret=$?
tries=0
while test "$ret" -ne 0
do
echo Unable to download $T/binres.tgz to system $i, waiting and then retrying. $tries prior retries. | tee -a "$oldrun/remote-log"
sleep 60
- cat $T/binres.tgz | ssh $i "cd /tmp; tar -xzf -"
+ cat $T/binres.tgz | ssh -o BatchMode=yes $i "cd /tmp; tar -xzf -"
ret=$?
if test "$ret" -ne 0
then
@@ -185,7 +185,7 @@ checkremotefile () {
while :
do
- ssh $1 "test -f \"$2\""
+ ssh -o BatchMode=yes $1 "test -f \"$2\""
ret=$?
if test "$ret" -eq 255
then
@@ -228,7 +228,7 @@ startbatches () {
then
continue # System still running last test, skip.
fi
- ssh "$i" "cd \"$resdir/$ds\"; touch remote.run; PATH=\"$T/bin:$PATH\" nohup kvm-remote-$curbatch.sh > kvm-remote-$curbatch.sh.out 2>&1 &" 1>&2
+ ssh -o BatchMode=yes "$i" "cd \"$resdir/$ds\"; touch remote.run; PATH=\"$T/bin:$PATH\" nohup kvm-remote-$curbatch.sh > kvm-remote-$curbatch.sh.out 2>&1 &" 1>&2
ret=$?
if test "$ret" -ne 0
then
@@ -267,7 +267,7 @@ do
sleep 30
done
echo " ---" Collecting results from $i `date` | tee -a "$oldrun/remote-log"
- ( cd "$oldrun"; ssh $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - )
+ ( cd "$oldrun"; ssh -o BatchMode=yes $i "cd $rundir; tar -czf - kvm-remote-*.sh.out */console.log */kvm-test-1-run*.sh.out */qemu[_-]pid */qemu-retval */qemu-affinity; rm -rf $T > /dev/null 2>&1" | tar -xzf - )
done
( kvm-end-run-stats.sh "$oldrun" "$starttime"; echo $? > $T/exitcode ) | tee -a "$oldrun/remote-log"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 55b2c1533282..263e16aeca0e 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -44,6 +44,7 @@ TORTURE_KCONFIG_KASAN_ARG=""
TORTURE_KCONFIG_KCSAN_ARG=""
TORTURE_KMAKE_ARG=""
TORTURE_QEMU_MEM=512
+torture_qemu_mem_default=1
TORTURE_REMOTE=
TORTURE_SHUTDOWN_GRACE=180
TORTURE_SUITE=rcu
@@ -86,7 +87,7 @@ usage () {
echo " --remote"
echo " --results absolute-pathname"
echo " --shutdown-grace seconds"
- echo " --torture lock|rcu|rcuscale|refscale|scf"
+ echo " --torture lock|rcu|rcuscale|refscale|scf|X*"
echo " --trust-make"
exit 1
}
@@ -180,6 +181,10 @@ do
;;
--kasan)
TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG
+ if test -n "$torture_qemu_mem_default"
+ then
+ TORTURE_QEMU_MEM=2G
+ fi
;;
--kconfig|--kconfigs)
checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$'
@@ -202,6 +207,7 @@ do
--memory)
checkarg --memory "(memory size)" $# "$2" '^[0-9]\+[MG]\?$' error
TORTURE_QEMU_MEM=$2
+ torture_qemu_mem_default=
shift
;;
--no-initrd)
@@ -231,7 +237,7 @@ do
shift
;;
--torture)
- checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\)$' '^--'
+ checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuscale\|refscale\|scf\|X.*\)$' '^--'
TORTURE_SUITE=$2
TORTURE_MOD="`echo $TORTURE_SUITE | sed -e 's/^\(lock\|rcu\|scf\)$/\1torture/'`"
shift
diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh
index bfe09e2829c8..d477618e7261 100755
--- a/tools/testing/selftests/rcutorture/bin/torture.sh
+++ b/tools/testing/selftests/rcutorture/bin/torture.sh
@@ -54,6 +54,7 @@ do_kvfree=yes
do_kasan=yes
do_kcsan=no
do_clocksourcewd=yes
+do_rt=yes
# doyesno - Helper function for yes/no arguments
function doyesno () {
@@ -82,6 +83,7 @@ usage () {
echo " --do-rcuscale / --do-no-rcuscale"
echo " --do-rcutorture / --do-no-rcutorture"
echo " --do-refscale / --do-no-refscale"
+ echo " --do-rt / --do-no-rt"
echo " --do-scftorture / --do-no-scftorture"
echo " --duration [ <minutes> | <hours>h | <days>d ]"
echo " --kcsan-kmake-arg kernel-make-arguments"
@@ -118,6 +120,7 @@ do
do_scftorture=yes
do_rcuscale=yes
do_refscale=yes
+ do_rt=yes
do_kvfree=yes
do_kasan=yes
do_kcsan=yes
@@ -148,6 +151,7 @@ do
do_scftorture=no
do_rcuscale=no
do_refscale=no
+ do_rt=no
do_kvfree=no
do_kasan=no
do_kcsan=no
@@ -162,6 +166,9 @@ do
--do-refscale|--do-no-refscale)
do_refscale=`doyesno "$1" --do-refscale`
;;
+ --do-rt|--do-no-rt)
+ do_rt=`doyesno "$1" --do-rt`
+ ;;
--do-scftorture|--do-no-scftorture)
do_scftorture=`doyesno "$1" --do-scftorture`
;;
@@ -322,6 +329,7 @@ then
echo " --- make clean" > "$amcdir/Make.out" 2>&1
make -j$MAKE_ALLOTED_CPUS clean >> "$amcdir/Make.out" 2>&1
echo " --- make allmodconfig" >> "$amcdir/Make.out" 2>&1
+ cp .config $amcdir
make -j$MAKE_ALLOTED_CPUS allmodconfig >> "$amcdir/Make.out" 2>&1
echo " --- make " >> "$amcdir/Make.out" 2>&1
make -j$MAKE_ALLOTED_CPUS >> "$amcdir/Make.out" 2>&1
@@ -350,8 +358,19 @@ fi
if test "$do_scftorture" = "yes"
then
- torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot"
- torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make
+ torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot csdlock_debug=1"
+ torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make
+fi
+
+if test "$do_rt" = "yes"
+then
+ # With all post-boot grace periods forced to normal.
+ torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 rcupdate.rcu_normal=1"
+ torture_set "rcurttorture" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make
+
+ # With all post-boot grace periods forced to expedited.
+ torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000 rcupdate.rcu_expedited=1"
+ torture_set "rcurttorture-exp" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "TREE03" --trust-make
fi
if test "$do_refscale" = yes
@@ -363,7 +382,7 @@ fi
for prim in $primlist
do
torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot"
- torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make
+ torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make
done
if test "$do_rcuscale" = yes
@@ -375,13 +394,13 @@ fi
for prim in $primlist
do
torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot"
- torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make
+ torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_TASKS_TRACE_RCU=y CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make
done
if test "$do_kvfree" = "yes"
then
torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot"
- torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 1G --trust-make
+ torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --memory 2G --trust-make
fi
if test "$do_clocksourcewd" = "yes"
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01 b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
index 7093422050f6..6fd6acb94518 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/RUDE01
@@ -8,3 +8,5 @@ CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
#CHECK#CONFIG_PROVE_RCU=y
CONFIG_RCU_EXPERT=y
+CONFIG_FORCE_TASKS_RUDE_RCU=y
+#CHECK#CONFIG_TASKS_RUDE_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
index 2da8b49589a0..07f5e0a70ae7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
+++ b/tools/testing/selftests/rcutorture/configs/rcu/SRCU-N
@@ -6,3 +6,5 @@ CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
#CHECK#CONFIG_RCU_EXPERT=n
+CONFIG_KPROBES=n
+CONFIG_FTRACE=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
index 3ca112444ce7..d84801b9a7ae 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01
@@ -7,4 +7,5 @@ CONFIG_PREEMPT=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_TASKS_RCU=y
CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
index ad2be91e5ee7..2f9fcffff5ae 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02
@@ -2,3 +2,7 @@ CONFIG_SMP=n
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
+#CHECK#CONFIG_TASKS_RCU=y
+CONFIG_FORCE_TASKS_RCU=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
index cd2a188eeb6d..b9b6d67cbc5f 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot
@@ -1 +1,2 @@
rcutorture.torture_type=tasks
+rcutorture.stat_interval=60
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
index dc02083803ce..dea26c568678 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -7,3 +7,5 @@ CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=n
CONFIG_NO_HZ_FULL=y
#CHECK#CONFIG_RCU_EXPERT=n
+CONFIG_TASKS_RCU=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
index e4d74e5fc1d0..85b407467454 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE01
@@ -4,8 +4,11 @@ CONFIG_HOTPLUG_CPU=y
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_PROVE_LOCKING=n
#CHECK#CONFIG_PROVE_RCU=n
+CONFIG_FORCE_TASKS_TRACE_RCU=y
+#CHECK#CONFIG_TASKS_TRACE_RCU=y
CONFIG_TASKS_TRACE_RCU_READ_MB=y
CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02 b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
index 77541eeb4e9f..093ea6e8e65c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TRACE02
@@ -7,5 +7,7 @@ CONFIG_PREEMPT=y
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
#CHECK#CONFIG_PROVE_RCU=y
+CONFIG_FORCE_TASKS_TRACE_RCU=y
+#CHECK#CONFIG_TASKS_TRACE_RCU=y
CONFIG_TASKS_TRACE_RCU_READ_MB=n
CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 22ad0261728d..ae395981b5e5 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -1,8 +1,9 @@
CONFIG_SMP=y
CONFIG_NR_CPUS=8
-CONFIG_PREEMPT_NONE=y
-CONFIG_PREEMPT_VOLUNTARY=n
+CONFIG_PREEMPT_NONE=n
+CONFIG_PREEMPT_VOLUNTARY=y
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TREE_RCU=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 2789b47e4ecd..d30922d8c883 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -3,6 +3,7 @@ CONFIG_NR_CPUS=16
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TREE_RCU=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE09 b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
index 8523a7515cbf..fc45645bb5f4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE09
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE09
@@ -13,3 +13,5 @@ CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
#CHECK#CONFIG_RCU_EXPERT=n
+CONFIG_KPROBES=n
+CONFIG_FTRACE=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE10 b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
index 4a00539bfdd7..a323d8948b7c 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE10
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE10
@@ -3,6 +3,7 @@ CONFIG_NR_CPUS=56
CONFIG_PREEMPT_NONE=y
CONFIG_PREEMPT_VOLUNTARY=n
CONFIG_PREEMPT=n
+CONFIG_PREEMPT_DYNAMIC=n
#CHECK#CONFIG_TREE_RCU=y
CONFIG_HZ_PERIODIC=n
CONFIG_NO_HZ_IDLE=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index effa415f9b92..e2bc99c785e7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -9,7 +9,7 @@
# rcutorture_param_n_barrier_cbs bootparam-string
#
-# Adds n_barrier_cbs rcutorture module parameter to kernels having it.
+# Adds n_barrier_cbs rcutorture module parameter if not already specified.
rcutorture_param_n_barrier_cbs () {
if echo $1 | grep -q "rcutorture\.n_barrier_cbs"
then
@@ -30,13 +30,25 @@ rcutorture_param_onoff () {
fi
}
+# rcutorture_param_stat_interval bootparam-string
+#
+# Adds stat_interval rcutorture module parameter if not already specified.
+rcutorture_param_stat_interval () {
+ if echo $1 | grep -q "rcutorture\.stat_interval"
+ then
+ :
+ else
+ echo rcutorture.stat_interval=15
+ fi
+}
+
# per_version_boot_params bootparam-string config-file seconds
#
# Adds per-version torture-module parameters to kernels supporting them.
per_version_boot_params () {
echo $1 `rcutorture_param_onoff "$1" "$2"` \
`rcutorture_param_n_barrier_cbs "$1"` \
- rcutorture.stat_interval=15 \
+ `rcutorture_param_stat_interval "$1"` \
rcutorture.shutdown_secs=$3 \
rcutorture.test_no_idle_hz=1 \
rcutorture.verbose=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon
index 90942bb5bebc..6a00157bee5b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/CFcommon
@@ -1,5 +1,6 @@
CONFIG_RCU_SCALE_TEST=y
CONFIG_PRINTK_TIME=y
-CONFIG_TASKS_RCU_GENERIC=y
-CONFIG_TASKS_RCU=y
-CONFIG_TASKS_TRACE_RCU=y
+CONFIG_FORCE_TASKS_RCU=y
+#CHECK#CONFIG_TASKS_RCU=y
+CONFIG_FORCE_TASKS_TRACE_RCU=y
+#CHECK#CONFIG_TASKS_TRACE_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
index f110d9ffbe4c..b10706fd03a4 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
+++ b/tools/testing/selftests/rcutorture/configs/rcuscale/TREE
@@ -16,3 +16,5 @@ CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
CONFIG_RCU_TRACE=y
+CONFIG_KPROBES=n
+CONFIG_FTRACE=n
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon
index a98b58b54bb1..fbea3b13baba 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/CFcommon
+++ b/tools/testing/selftests/rcutorture/configs/refscale/CFcommon
@@ -1,2 +1,6 @@
CONFIG_RCU_REF_SCALE_TEST=y
CONFIG_PRINTK_TIME=y
+CONFIG_FORCE_TASKS_RCU=y
+#CHECK#CONFIG_TASKS_RCU=y
+CONFIG_FORCE_TASKS_TRACE_RCU=y
+#CHECK#CONFIG_TASKS_TRACE_RCU=y
diff --git a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
index 7f06838a91e6..ef2b501a6971 100644
--- a/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/refscale/NOPREEMPT
@@ -15,3 +15,5 @@ CONFIG_PROVE_LOCKING=n
CONFIG_RCU_BOOST=n
CONFIG_DEBUG_OBJECTS_RCU_HEAD=n
CONFIG_RCU_EXPERT=y
+CONFIG_KPROBES=n
+CONFIG_FTRACE=n
diff --git a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
index b8429d6c6ebc..3a59346b3de7 100644
--- a/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/scf/NOPREEMPT
@@ -7,3 +7,5 @@ CONFIG_NO_HZ_IDLE=n
CONFIG_NO_HZ_FULL=y
CONFIG_DEBUG_LOCK_ALLOC=n
CONFIG_PROVE_LOCKING=n
+CONFIG_KPROBES=n
+CONFIG_FTRACE=n
diff --git a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT
index ae4992b141b0..cb37e08037d6 100644
--- a/tools/testing/selftests/rcutorture/configs/scf/PREEMPT
+++ b/tools/testing/selftests/rcutorture/configs/scf/PREEMPT
@@ -7,3 +7,4 @@ CONFIG_NO_HZ_IDLE=y
CONFIG_NO_HZ_FULL=n
CONFIG_DEBUG_LOCK_ALLOC=y
CONFIG_PROVE_LOCKING=y
+CONFIG_RCU_EXPERT=y
diff --git a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh
index d3d9e35d3d55..2d949e58f5a5 100644
--- a/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/scf/ver_functions.sh
@@ -25,6 +25,5 @@ per_version_boot_params () {
echo $1 `scftorture_param_onoff "$1" "$2"` \
scftorture.stat_interval=15 \
scftorture.shutdown_secs=$3 \
- scftorture.verbose=1 \
- scf
+ scftorture.verbose=1
}
diff --git a/tools/testing/selftests/seccomp/Makefile b/tools/testing/selftests/seccomp/Makefile
index 585f7a0c10cb..f017c382c036 100644
--- a/tools/testing/selftests/seccomp/Makefile
+++ b/tools/testing/selftests/seccomp/Makefile
@@ -1,6 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
CFLAGS += -Wl,-no-as-needed -Wall -isystem ../../../../usr/include/
LDFLAGS += -lpthread
+LDLIBS += -lcap
TEST_GEN_PROGS := seccomp_bpf seccomp_benchmark
include ../lib.mk
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 9d126d7fabdb..136df5b76319 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -46,6 +46,7 @@
#include <sys/ioctl.h>
#include <linux/kcmp.h>
#include <sys/resource.h>
+#include <sys/capability.h>
#include <unistd.h>
#include <sys/syscall.h>
@@ -59,6 +60,8 @@
#define SKIP(s, ...) XFAIL(s, ##__VA_ARGS__)
#endif
+#define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
+
#ifndef PR_SET_PTRACER
# define PR_SET_PTRACER 0x59616d61
#endif
@@ -268,6 +271,10 @@ struct seccomp_notif_addfd_big {
#define SECCOMP_FILTER_FLAG_TSYNC_ESRCH (1UL << 4)
#endif
+#ifndef SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV
+#define SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV (1UL << 5)
+#endif
+
#ifndef seccomp
int seccomp(unsigned int op, unsigned int flags, void *args)
{
@@ -955,7 +962,7 @@ TEST(ERRNO_valid)
ASSERT_EQ(0, ret);
EXPECT_EQ(parent, syscall(__NR_getppid));
- EXPECT_EQ(-1, read(0, NULL, 0));
+ EXPECT_EQ(-1, read(-1, NULL, 0));
EXPECT_EQ(E2BIG, errno);
}
@@ -974,7 +981,7 @@ TEST(ERRNO_zero)
EXPECT_EQ(parent, syscall(__NR_getppid));
/* "errno" of 0 is ok. */
- EXPECT_EQ(0, read(0, NULL, 0));
+ EXPECT_EQ(0, read(-1, NULL, 0));
}
/*
@@ -995,7 +1002,7 @@ TEST(ERRNO_capped)
ASSERT_EQ(0, ret);
EXPECT_EQ(parent, syscall(__NR_getppid));
- EXPECT_EQ(-1, read(0, NULL, 0));
+ EXPECT_EQ(-1, read(-1, NULL, 0));
EXPECT_EQ(4095, errno);
}
@@ -1026,7 +1033,7 @@ TEST(ERRNO_order)
ASSERT_EQ(0, ret);
EXPECT_EQ(parent, syscall(__NR_getppid));
- EXPECT_EQ(-1, read(0, NULL, 0));
+ EXPECT_EQ(-1, read(-1, NULL, 0));
EXPECT_EQ(12, errno);
}
@@ -2623,7 +2630,7 @@ void *tsync_sibling(void *data)
ret = prctl(PR_GET_NO_NEW_PRIVS, 0, 0, 0, 0);
if (!ret)
return (void *)SIBLING_EXIT_NEWPRIVS;
- read(0, NULL, 0);
+ read(-1, NULL, 0);
return (void *)SIBLING_EXIT_UNKILLED;
}
@@ -3742,7 +3749,10 @@ TEST(user_notification_fault_recv)
struct seccomp_notif req = {};
struct seccomp_notif_resp resp = {};
- ASSERT_EQ(unshare(CLONE_NEWUSER), 0);
+ ASSERT_EQ(unshare(CLONE_NEWUSER), 0) {
+ if (errno == EINVAL)
+ SKIP(return, "kernel missing CLONE_NEWUSER support");
+ }
listener = user_notif_syscall(__NR_getppid,
SECCOMP_FILTER_FLAG_NEW_LISTENER);
@@ -4231,6 +4241,421 @@ TEST(user_notification_addfd_rlimit)
close(memfd);
}
+/* Make sure PTRACE_O_SUSPEND_SECCOMP requires CAP_SYS_ADMIN. */
+FIXTURE(O_SUSPEND_SECCOMP) {
+ pid_t pid;
+};
+
+FIXTURE_SETUP(O_SUSPEND_SECCOMP)
+{
+ ERRNO_FILTER(block_read, E2BIG);
+ cap_value_t cap_list[] = { CAP_SYS_ADMIN };
+ cap_t caps;
+
+ self->pid = 0;
+
+ /* make sure we don't have CAP_SYS_ADMIN */
+ caps = cap_get_proc();
+ ASSERT_NE(NULL, caps);
+ ASSERT_EQ(0, cap_set_flag(caps, CAP_EFFECTIVE, 1, cap_list, CAP_CLEAR));
+ ASSERT_EQ(0, cap_set_proc(caps));
+ cap_free(caps);
+
+ ASSERT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
+ ASSERT_EQ(0, prctl(PR_SET_SECCOMP, SECCOMP_MODE_FILTER, &prog_block_read));
+
+ self->pid = fork();
+ ASSERT_GE(self->pid, 0);
+
+ if (self->pid == 0) {
+ while (1)
+ pause();
+ _exit(127);
+ }
+}
+
+FIXTURE_TEARDOWN(O_SUSPEND_SECCOMP)
+{
+ if (self->pid)
+ kill(self->pid, SIGKILL);
+}
+
+TEST_F(O_SUSPEND_SECCOMP, setoptions)
+{
+ int wstatus;
+
+ ASSERT_EQ(0, ptrace(PTRACE_ATTACH, self->pid, NULL, 0));
+ ASSERT_EQ(self->pid, wait(&wstatus));
+ ASSERT_EQ(-1, ptrace(PTRACE_SETOPTIONS, self->pid, NULL, PTRACE_O_SUSPEND_SECCOMP));
+ if (errno == EINVAL)
+ SKIP(return, "Kernel does not support PTRACE_O_SUSPEND_SECCOMP (missing CONFIG_CHECKPOINT_RESTORE?)");
+ ASSERT_EQ(EPERM, errno);
+}
+
+TEST_F(O_SUSPEND_SECCOMP, seize)
+{
+ int ret;
+
+ ret = ptrace(PTRACE_SEIZE, self->pid, NULL, PTRACE_O_SUSPEND_SECCOMP);
+ ASSERT_EQ(-1, ret);
+ if (errno == EINVAL)
+ SKIP(return, "Kernel does not support PTRACE_O_SUSPEND_SECCOMP (missing CONFIG_CHECKPOINT_RESTORE?)");
+ ASSERT_EQ(EPERM, errno);
+}
+
+/*
+ * get_nth - Get the nth, space separated entry in a file.
+ *
+ * Returns the length of the read field.
+ * Throws error if field is zero-lengthed.
+ */
+static ssize_t get_nth(struct __test_metadata *_metadata, const char *path,
+ const unsigned int position, char **entry)
+{
+ char *line = NULL;
+ unsigned int i;
+ ssize_t nread;
+ size_t len = 0;
+ FILE *f;
+
+ f = fopen(path, "r");
+ ASSERT_NE(f, NULL) {
+ TH_LOG("Could not open %s: %s", path, strerror(errno));
+ }
+
+ for (i = 0; i < position; i++) {
+ nread = getdelim(&line, &len, ' ', f);
+ ASSERT_GE(nread, 0) {
+ TH_LOG("Failed to read %d entry in file %s", i, path);
+ }
+ }
+ fclose(f);
+
+ ASSERT_GT(nread, 0) {
+ TH_LOG("Entry in file %s had zero length", path);
+ }
+
+ *entry = line;
+ return nread - 1;
+}
+
+/* For a given PID, get the task state (D, R, etc...) */
+static char get_proc_stat(struct __test_metadata *_metadata, pid_t pid)
+{
+ char proc_path[100] = {0};
+ char status;
+ char *line;
+
+ snprintf(proc_path, sizeof(proc_path), "/proc/%d/stat", pid);
+ ASSERT_EQ(get_nth(_metadata, proc_path, 3, &line), 1);
+
+ status = *line;
+ free(line);
+
+ return status;
+}
+
+TEST(user_notification_fifo)
+{
+ struct seccomp_notif_resp resp = {};
+ struct seccomp_notif req = {};
+ int i, status, listener;
+ pid_t pid, pids[3];
+ __u64 baseid;
+ long ret;
+ /* 100 ms */
+ struct timespec delay = { .tv_nsec = 100000000 };
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret) {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ /* Setup a listener */
+ listener = user_notif_syscall(__NR_getppid,
+ SECCOMP_FILTER_FLAG_NEW_LISTENER);
+ ASSERT_GE(listener, 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ ret = syscall(__NR_getppid);
+ exit(ret != USER_NOTIF_MAGIC);
+ }
+
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+ baseid = req.id + 1;
+
+ resp.id = req.id;
+ resp.error = 0;
+ resp.val = USER_NOTIF_MAGIC;
+
+ /* check that we make sure flags == 0 */
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+
+ /* Start children, and generate notifications */
+ for (i = 0; i < ARRAY_SIZE(pids); i++) {
+ pid = fork();
+ if (pid == 0) {
+ ret = syscall(__NR_getppid);
+ exit(ret != USER_NOTIF_MAGIC);
+ }
+ pids[i] = pid;
+ }
+
+ /* This spins until all of the children are sleeping */
+restart_wait:
+ for (i = 0; i < ARRAY_SIZE(pids); i++) {
+ if (get_proc_stat(_metadata, pids[i]) != 'S') {
+ nanosleep(&delay, NULL);
+ goto restart_wait;
+ }
+ }
+
+ /* Read the notifications in order (and respond) */
+ for (i = 0; i < ARRAY_SIZE(pids); i++) {
+ memset(&req, 0, sizeof(req));
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+ EXPECT_EQ(req.id, baseid + i);
+ resp.id = req.id;
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+ }
+
+ /* Make sure notifications were received */
+ for (i = 0; i < ARRAY_SIZE(pids); i++) {
+ EXPECT_EQ(waitpid(pids[i], &status, 0), pids[i]);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+ }
+}
+
+/* get_proc_syscall - Get the syscall in progress for a given pid
+ *
+ * Returns the current syscall number for a given process
+ * Returns -1 if not in syscall (running or blocked)
+ */
+static long get_proc_syscall(struct __test_metadata *_metadata, int pid)
+{
+ char proc_path[100] = {0};
+ long ret = -1;
+ ssize_t nread;
+ char *line;
+
+ snprintf(proc_path, sizeof(proc_path), "/proc/%d/syscall", pid);
+ nread = get_nth(_metadata, proc_path, 1, &line);
+ ASSERT_GT(nread, 0);
+
+ if (!strncmp("running", line, MIN(7, nread)))
+ ret = strtol(line, NULL, 16);
+
+ free(line);
+ return ret;
+}
+
+/* Ensure non-fatal signals prior to receive are unmodified */
+TEST(user_notification_wait_killable_pre_notification)
+{
+ struct sigaction new_action = {
+ .sa_handler = signal_handler,
+ };
+ int listener, status, sk_pair[2];
+ pid_t pid;
+ long ret;
+ char c;
+ /* 100 ms */
+ struct timespec delay = { .tv_nsec = 100000000 };
+
+ ASSERT_EQ(sigemptyset(&new_action.sa_mask), 0);
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret)
+ {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0);
+
+ listener = user_notif_syscall(
+ __NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER |
+ SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV);
+ ASSERT_GE(listener, 0);
+
+ /*
+ * Check that we can kill the process with SIGUSR1 prior to receiving
+ * the notification. SIGUSR1 is wired up to a custom signal handler,
+ * and make sure it gets called.
+ */
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(sk_pair[0]);
+ handled = sk_pair[1];
+
+ /* Setup the non-fatal sigaction without SA_RESTART */
+ if (sigaction(SIGUSR1, &new_action, NULL)) {
+ perror("sigaction");
+ exit(1);
+ }
+
+ ret = syscall(__NR_getppid);
+ /* Make sure we got a return from a signal interruption */
+ exit(ret != -1 || errno != EINTR);
+ }
+
+ /*
+ * Make sure we've gotten to the seccomp user notification wait
+ * from getppid prior to sending any signals
+ */
+ while (get_proc_syscall(_metadata, pid) != __NR_getppid &&
+ get_proc_stat(_metadata, pid) != 'S')
+ nanosleep(&delay, NULL);
+
+ /* Send non-fatal kill signal */
+ EXPECT_EQ(kill(pid, SIGUSR1), 0);
+
+ /* wait for process to exit (exit checks for EINTR) */
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+
+ EXPECT_EQ(read(sk_pair[0], &c, 1), 1);
+}
+
+/* Ensure non-fatal signals after receive are blocked */
+TEST(user_notification_wait_killable)
+{
+ struct sigaction new_action = {
+ .sa_handler = signal_handler,
+ };
+ struct seccomp_notif_resp resp = {};
+ struct seccomp_notif req = {};
+ int listener, status, sk_pair[2];
+ pid_t pid;
+ long ret;
+ char c;
+ /* 100 ms */
+ struct timespec delay = { .tv_nsec = 100000000 };
+
+ ASSERT_EQ(sigemptyset(&new_action.sa_mask), 0);
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret)
+ {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ ASSERT_EQ(socketpair(PF_LOCAL, SOCK_SEQPACKET, 0, sk_pair), 0);
+
+ listener = user_notif_syscall(
+ __NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER |
+ SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV);
+ ASSERT_GE(listener, 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ close(sk_pair[0]);
+ handled = sk_pair[1];
+
+ /* Setup the sigaction without SA_RESTART */
+ if (sigaction(SIGUSR1, &new_action, NULL)) {
+ perror("sigaction");
+ exit(1);
+ }
+
+ /* Make sure that the syscall is completed (no EINTR) */
+ ret = syscall(__NR_getppid);
+ exit(ret != USER_NOTIF_MAGIC);
+ }
+
+ /*
+ * Get the notification, to make move the notifying process into a
+ * non-preemptible (TASK_KILLABLE) state.
+ */
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+ /* Send non-fatal kill signal */
+ EXPECT_EQ(kill(pid, SIGUSR1), 0);
+
+ /*
+ * Make sure the task enters moves to TASK_KILLABLE by waiting for
+ * D (Disk Sleep) state after receiving non-fatal signal.
+ */
+ while (get_proc_stat(_metadata, pid) != 'D')
+ nanosleep(&delay, NULL);
+
+ resp.id = req.id;
+ resp.val = USER_NOTIF_MAGIC;
+ /* Make sure the notification is found and able to be replied to */
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_SEND, &resp), 0);
+
+ /*
+ * Make sure that the signal handler does get called once we're back in
+ * userspace.
+ */
+ EXPECT_EQ(read(sk_pair[0], &c, 1), 1);
+ /* wait for process to exit (exit checks for USER_NOTIF_MAGIC) */
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFEXITED(status));
+ EXPECT_EQ(0, WEXITSTATUS(status));
+}
+
+/* Ensure fatal signals after receive are not blocked */
+TEST(user_notification_wait_killable_fatal)
+{
+ struct seccomp_notif req = {};
+ int listener, status;
+ pid_t pid;
+ long ret;
+ /* 100 ms */
+ struct timespec delay = { .tv_nsec = 100000000 };
+
+ ret = prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0);
+ ASSERT_EQ(0, ret)
+ {
+ TH_LOG("Kernel does not support PR_SET_NO_NEW_PRIVS!");
+ }
+
+ listener = user_notif_syscall(
+ __NR_getppid, SECCOMP_FILTER_FLAG_NEW_LISTENER |
+ SECCOMP_FILTER_FLAG_WAIT_KILLABLE_RECV);
+ ASSERT_GE(listener, 0);
+
+ pid = fork();
+ ASSERT_GE(pid, 0);
+
+ if (pid == 0) {
+ /* This should never complete as it should get a SIGTERM */
+ syscall(__NR_getppid);
+ exit(1);
+ }
+
+ while (get_proc_stat(_metadata, pid) != 'S')
+ nanosleep(&delay, NULL);
+
+ /*
+ * Get the notification, to make move the notifying process into a
+ * non-preemptible (TASK_KILLABLE) state.
+ */
+ EXPECT_EQ(ioctl(listener, SECCOMP_IOCTL_NOTIF_RECV, &req), 0);
+ /* Kill the process with a fatal signal */
+ EXPECT_EQ(kill(pid, SIGTERM), 0);
+
+ /*
+ * Wait for the process to exit, and make sure the process terminated
+ * due to the SIGTERM signal.
+ */
+ EXPECT_EQ(waitpid(pid, &status, 0), pid);
+ EXPECT_EQ(true, WIFSIGNALED(status));
+ EXPECT_EQ(SIGTERM, WTERMSIG(status));
+}
+
/*
* TODO:
* - expand NNP testing
diff --git a/tools/testing/selftests/vDSO/vdso_test_correctness.c b/tools/testing/selftests/vDSO/vdso_test_correctness.c
index c4aea794725a..e691a3cf1491 100644
--- a/tools/testing/selftests/vDSO/vdso_test_correctness.c
+++ b/tools/testing/selftests/vDSO/vdso_test_correctness.c
@@ -20,6 +20,7 @@
#include <limits.h>
#include "vdso_config.h"
+#include "../kselftest.h"
static const char **name;
@@ -306,10 +307,8 @@ static void test_clock_gettime(void)
return;
}
- for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
- clock++) {
+ for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++)
test_one_clock_gettime(clock, clocknames[clock]);
- }
/* Also test some invalid clock ids */
test_one_clock_gettime(-1, "invalid");
@@ -370,10 +369,8 @@ static void test_clock_gettime64(void)
return;
}
- for (int clock = 0; clock < sizeof(clocknames) / sizeof(clocknames[0]);
- clock++) {
+ for (int clock = 0; clock < ARRAY_SIZE(clocknames); clock++)
test_one_clock_gettime64(clock, clocknames[clock]);
- }
/* Also test some invalid clock ids */
test_one_clock_gettime64(-1, "invalid");
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 04a49e876a46..5b1ecd00695b 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -57,9 +57,9 @@ CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_32bit_prog
CAN_BUILD_X86_64 := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_64bit_program.c)
CAN_BUILD_WITH_NOPIE := $(shell ./../x86/check_cc.sh "$(CC)" ../x86/trivial_program.c -no-pie)
-TARGETS := protection_keys
-BINARIES_32 := $(TARGETS:%=%_32)
-BINARIES_64 := $(TARGETS:%=%_64)
+VMTARGETS := protection_keys
+BINARIES_32 := $(VMTARGETS:%=%_32)
+BINARIES_64 := $(VMTARGETS:%=%_64)
ifeq ($(CAN_BUILD_WITH_NOPIE),1)
CFLAGS += -no-pie
@@ -112,7 +112,7 @@ $(BINARIES_32): CFLAGS += -m32 -mxsave
$(BINARIES_32): LDLIBS += -lrt -ldl -lm
$(BINARIES_32): $(OUTPUT)/%_32: %.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
-$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-32,$(t))))
+$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-32,$(t))))
endif
ifeq ($(CAN_BUILD_X86_64),1)
@@ -120,7 +120,7 @@ $(BINARIES_64): CFLAGS += -m64 -mxsave
$(BINARIES_64): LDLIBS += -lrt -ldl
$(BINARIES_64): $(OUTPUT)/%_64: %.c
$(CC) $(CFLAGS) $(EXTRA_CFLAGS) $(notdir $^) $(LDLIBS) -o $@
-$(foreach t,$(TARGETS),$(eval $(call gen-target-rule-64,$(t))))
+$(foreach t,$(VMTARGETS),$(eval $(call gen-target-rule-64,$(t))))
endif
# x86_64 users should be encouraged to install 32-bit libraries
diff --git a/tools/testing/selftests/vm/mremap_test.c b/tools/testing/selftests/vm/mremap_test.c
index 7c0b0617b9f8..db0270127aeb 100644
--- a/tools/testing/selftests/vm/mremap_test.c
+++ b/tools/testing/selftests/vm/mremap_test.c
@@ -6,9 +6,11 @@
#include <errno.h>
#include <stdlib.h>
+#include <stdio.h>
#include <string.h>
#include <sys/mman.h>
#include <time.h>
+#include <stdbool.h>
#include "../kselftest.h"
@@ -64,6 +66,59 @@ enum {
}
/*
+ * Returns false if the requested remap region overlaps with an
+ * existing mapping (e.g text, stack) else returns true.
+ */
+static bool is_remap_region_valid(void *addr, unsigned long long size)
+{
+ void *remap_addr = NULL;
+ bool ret = true;
+
+ /* Use MAP_FIXED_NOREPLACE flag to ensure region is not mapped */
+ remap_addr = mmap(addr, size, PROT_READ | PROT_WRITE,
+ MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
+ -1, 0);
+
+ if (remap_addr == MAP_FAILED) {
+ if (errno == EEXIST)
+ ret = false;
+ } else {
+ munmap(remap_addr, size);
+ }
+
+ return ret;
+}
+
+/* Returns mmap_min_addr sysctl tunable from procfs */
+static unsigned long long get_mmap_min_addr(void)
+{
+ FILE *fp;
+ int n_matched;
+ static unsigned long long addr;
+
+ if (addr)
+ return addr;
+
+ fp = fopen("/proc/sys/vm/mmap_min_addr", "r");
+ if (fp == NULL) {
+ ksft_print_msg("Failed to open /proc/sys/vm/mmap_min_addr: %s\n",
+ strerror(errno));
+ exit(KSFT_SKIP);
+ }
+
+ n_matched = fscanf(fp, "%llu", &addr);
+ if (n_matched != 1) {
+ ksft_print_msg("Failed to read /proc/sys/vm/mmap_min_addr: %s\n",
+ strerror(errno));
+ fclose(fp);
+ exit(KSFT_SKIP);
+ }
+
+ fclose(fp);
+ return addr;
+}
+
+/*
* Returns the start address of the mapping on success, else returns
* NULL on failure.
*/
@@ -71,11 +126,18 @@ static void *get_source_mapping(struct config c)
{
unsigned long long addr = 0ULL;
void *src_addr = NULL;
+ unsigned long long mmap_min_addr;
+
+ mmap_min_addr = get_mmap_min_addr();
+
retry:
addr += c.src_alignment;
+ if (addr < mmap_min_addr)
+ goto retry;
+
src_addr = mmap((void *) addr, c.region_size, PROT_READ | PROT_WRITE,
- MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
- -1, 0);
+ MAP_FIXED_NOREPLACE | MAP_ANONYMOUS | MAP_SHARED,
+ -1, 0);
if (src_addr == MAP_FAILED) {
if (errno == EPERM || errno == EEXIST)
goto retry;
@@ -90,8 +152,10 @@ retry:
* alignment in the tests.
*/
if (((unsigned long long) src_addr & (c.src_alignment - 1)) ||
- !((unsigned long long) src_addr & c.src_alignment))
+ !((unsigned long long) src_addr & c.src_alignment)) {
+ munmap(src_addr, c.region_size);
goto retry;
+ }
if (!src_addr)
goto error;
@@ -140,9 +204,20 @@ static long long remap_region(struct config c, unsigned int threshold_mb,
if (!((unsigned long long) addr & c.dest_alignment))
addr = (void *) ((unsigned long long) addr | c.dest_alignment);
+ /* Don't destroy existing mappings unless expected to overlap */
+ while (!is_remap_region_valid(addr, c.region_size) && !c.overlapping) {
+ /* Check for unsigned overflow */
+ if (addr + c.dest_alignment < addr) {
+ ksft_print_msg("Couldn't find a valid region to remap to\n");
+ ret = -1;
+ goto out;
+ }
+ addr += c.dest_alignment;
+ }
+
clock_gettime(CLOCK_MONOTONIC, &t_start);
dest_addr = mremap(src_addr, c.region_size, c.region_size,
- MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr);
+ MREMAP_MAYMOVE|MREMAP_FIXED, (char *) addr);
clock_gettime(CLOCK_MONOTONIC, &t_end);
if (dest_addr == MAP_FAILED) {
@@ -193,7 +268,7 @@ static void run_mremap_test_case(struct test test_case, int *failures,
if (remap_time < 0) {
if (test_case.expect_failure)
- ksft_test_result_pass("%s\n\tExpected mremap failure\n",
+ ksft_test_result_xfail("%s\n\tExpected mremap failure\n",
test_case.name);
else {
ksft_test_result_fail("%s\n", test_case.name);
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 3b265f140c25..352ba00cf26b 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -291,11 +291,16 @@ echo "-------------------"
echo "running mremap_test"
echo "-------------------"
./mremap_test
-if [ $? -ne 0 ]; then
+ret_val=$?
+
+if [ $ret_val -eq 0 ]; then
+ echo "[PASS]"
+elif [ $ret_val -eq $ksft_skip ]; then
+ echo "[SKIP]"
+ exitcode=$ksft_skip
+else
echo "[FAIL]"
exitcode=1
-else
- echo "[PASS]"
fi
echo "-----------------"
diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh
index 8a9461aa0878..69c7796c7ca9 100755
--- a/tools/testing/selftests/wireguard/netns.sh
+++ b/tools/testing/selftests/wireguard/netns.sh
@@ -22,10 +22,12 @@
# interfaces in $ns1 and $ns2. See https://www.wireguard.com/netns/ for further
# details on how this is accomplished.
set -e
+shopt -s extglob
exec 3>&1
export LANG=C
export WG_HIDE_KEYS=never
+NPROC=( /sys/devices/system/cpu/cpu+([0-9]) ); NPROC=${#NPROC[@]}
netns0="wg-test-$$-0"
netns1="wg-test-$$-1"
netns2="wg-test-$$-2"
@@ -143,17 +145,15 @@ tests() {
n1 iperf3 -Z -t 3 -b 0 -u -c fd00::2
# TCP over IPv4, in parallel
- for max in 4 5 50; do
- local pids=( )
- for ((i=0; i < max; ++i)) do
- n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 &
- pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i ))
- done
- for ((i=0; i < max; ++i)) do
- n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 &
- done
- wait "${pids[@]}"
+ local pids=( ) i
+ for ((i=0; i < NPROC; ++i)) do
+ n2 iperf3 -p $(( 5200 + i )) -s -1 -B 192.168.241.2 &
+ pids+=( $! ); waitiperf $netns2 $! $(( 5200 + i ))
done
+ for ((i=0; i < NPROC; ++i)) do
+ n1 iperf3 -Z -t 3 -p $(( 5200 + i )) -c 192.168.241.2 &
+ done
+ wait "${pids[@]}"
}
[[ $(ip1 link show dev wg0) =~ mtu\ ([0-9]+) ]] && orig_mtu="${BASH_REMATCH[1]}"
@@ -280,7 +280,19 @@ read _ _ tx_bytes_before < <(n0 wg show wg1 transfer)
! n0 ping -W 1 -c 10 -f 192.168.241.2 || false
sleep 1
read _ _ tx_bytes_after < <(n0 wg show wg1 transfer)
-(( tx_bytes_after - tx_bytes_before < 70000 ))
+if ! (( tx_bytes_after - tx_bytes_before < 70000 )); then
+ errstart=$'\x1b[37m\x1b[41m\x1b[1m'
+ errend=$'\x1b[0m'
+ echo "${errstart} ${errend}"
+ echo "${errstart} E R R O R ${errend}"
+ echo "${errstart} ${errend}"
+ echo "${errstart} This architecture does not do the right thing ${errend}"
+ echo "${errstart} with cross-namespace routing loops. This test ${errend}"
+ echo "${errstart} has thus technically failed but, as this issue ${errend}"
+ echo "${errstart} is as yet unsolved, these tests will continue ${errend}"
+ echo "${errstart} onward. :( ${errend}"
+ echo "${errstart} ${errend}"
+fi
ip0 link del wg1
ip1 link del wg0
diff --git a/tools/testing/selftests/wireguard/qemu/.gitignore b/tools/testing/selftests/wireguard/qemu/.gitignore
index bfa15e6feb2f..42ab9d72b37b 100644
--- a/tools/testing/selftests/wireguard/qemu/.gitignore
+++ b/tools/testing/selftests/wireguard/qemu/.gitignore
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0-only
build/
distfiles/
+ccache/
diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile
index 4bdd6c1a19d3..bca07b93eeb0 100644
--- a/tools/testing/selftests/wireguard/qemu/Makefile
+++ b/tools/testing/selftests/wireguard/qemu/Makefile
@@ -4,26 +4,24 @@
PWD := $(shell pwd)
-CHOST := $(shell gcc -dumpmachine)
-HOST_ARCH := $(firstword $(subst -, ,$(CHOST)))
-ifneq (,$(ARCH))
-CBUILD := $(subst -gcc,,$(lastword $(subst /, ,$(firstword $(wildcard $(foreach bindir,$(subst :, ,$(PATH)),$(bindir)/$(ARCH)-*-gcc))))))
-ifeq (,$(CBUILD))
-$(error The toolchain for $(ARCH) is not installed)
-endif
-else
-CBUILD := $(CHOST)
-ARCH := $(firstword $(subst -, ,$(CBUILD)))
-endif
-
# Set these from the environment to override
KERNEL_PATH ?= $(PWD)/../../../../..
BUILD_PATH ?= $(PWD)/build/$(ARCH)
DISTFILES_PATH ?= $(PWD)/distfiles
NR_CPUS ?= 4
+ARCH ?=
+CBUILD := $(shell gcc -dumpmachine)
+HOST_ARCH := $(firstword $(subst -, ,$(CBUILD)))
+ifeq ($(ARCH),)
+ARCH := $(HOST_ARCH)
+endif
MIRROR := https://download.wireguard.com/qemu-test/distfiles/
+KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
+rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
+WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*)
+
default: qemu
# variable name, tarball project name, version, tarball extension, default URI base
@@ -36,42 +34,33 @@ $(call file_download,$$($(1)_NAME)$(4),$(5),$(6))
endef
define file_download =
-$(DISTFILES_PATH)/$(1):
+$(DISTFILES_PATH)/$(1): | $(4)
mkdir -p $(DISTFILES_PATH)
- flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
+ flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if ([ -n "$(4)" ] && sed -n "s#^\([a-f0-9]\{64\}\) \($(1)\)\$$$$#\1 $(DISTFILES_PATH)/\2.tmp#p" "$(4)" || echo "$(3) $$@.tmp") | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi'
endef
-$(eval $(call tar_download,MUSL,musl,1.2.0,.tar.gz,https://musl.libc.org/releases/,c6de7b191139142d3f9a7b5b702c9cae1b5ee6e7f57e582da9328629408fd4e8))
-$(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c))
-$(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d))
-$(eval $(call tar_download,IPROUTE2,iproute2,5.6.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,1b5b0e25ce6e23da7526ea1da044e814ad85ba761b10dd29c2b027c056b04692))
-$(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c))
-$(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa))
+$(eval $(call tar_download,IPERF,iperf,3.11,.tar.gz,https://downloads.es.net/pub/iperf/,de8cb409fad61a0574f4cb07eb19ce1159707403ac2dc01b5d175e91240b7e5f))
+$(eval $(call tar_download,BASH,bash,5.1.16,.tar.gz,https://ftp.gnu.org/gnu/bash/,5bac17218d3911834520dad13cd1f85ab944e1c09ae1aba55906be1f8192f558))
+$(eval $(call tar_download,IPROUTE2,iproute2,5.17.0,.tar.gz,https://www.kernel.org/pub/linux/utils/net/iproute2/,bda331d5c4606138892f23a565d78fca18919b4d508a0b7ca8391c2da2db68b9))
+$(eval $(call tar_download,IPTABLES,iptables,1.8.7,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,c109c96bb04998cd44156622d36f8e04b140701ec60531a10668cfdff5e8d8f0))
+$(eval $(call tar_download,NMAP,nmap,7.92,.tgz,https://nmap.org/dist/,064183ea642dc4c12b1ab3b5358ce1cef7d2e7e11ffa2849f16d339f5b717117))
$(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a))
-$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64))
-
-KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug)
-rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d))
-WIREGUARD_SOURCES := $(call rwildcard,$(KERNEL_PATH)/drivers/net/wireguard/,*)
-
-export CFLAGS ?= -O3 -pipe
-export LDFLAGS ?=
-export CPPFLAGS := -I$(BUILD_PATH)/include
+$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20210914,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,97ff31489217bb265b7ae850d3d0f335ab07d2652ba1feec88b734bc96bd05ac))
+export CFLAGS := -O3 -pipe
ifeq ($(HOST_ARCH),$(ARCH))
-CROSS_COMPILE_FLAG := --host=$(CHOST)
CFLAGS += -march=native
-STRIP := strip
-else
-$(info Cross compilation: building for $(CBUILD) using $(CHOST))
-CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
-export CROSS_COMPILE=$(CBUILD)-
-STRIP := $(CBUILD)-strip
endif
+export LDFLAGS :=
+export CPPFLAGS :=
+
+QEMU_VPORT_RESULT :=
ifeq ($(ARCH),aarch64)
+CHOST := aarch64-linux-musl
QEMU_ARCH := aarch64
KERNEL_ARCH := arm64
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
+QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
@@ -79,9 +68,11 @@ QEMU_MACHINE := -cpu cortex-a53 -machine virt
CFLAGS += -march=armv8-a -mtune=cortex-a53
endif
else ifeq ($(ARCH),aarch64_be)
+CHOST := aarch64_be-linux-musl
QEMU_ARCH := aarch64
KERNEL_ARCH := arm64
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm64/boot/Image
+QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
@@ -89,9 +80,11 @@ QEMU_MACHINE := -cpu cortex-a53 -machine virt
CFLAGS += -march=armv8-a -mtune=cortex-a53
endif
else ifeq ($(ARCH),arm)
+CHOST := arm-linux-musleabi
QEMU_ARCH := arm
KERNEL_ARCH := arm
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
+QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
@@ -99,9 +92,11 @@ QEMU_MACHINE := -cpu cortex-a15 -machine virt
CFLAGS += -march=armv7-a -mtune=cortex-a15 -mabi=aapcs-linux
endif
else ifeq ($(ARCH),armeb)
+CHOST := armeb-linux-musleabi
QEMU_ARCH := arm
KERNEL_ARCH := arm
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/arm/boot/zImage
+QEMU_VPORT_RESULT := virtio-serial-device
ifeq ($(HOST_ARCH),$(ARCH))
QEMU_MACHINE := -cpu host -machine virt,gic_version=host,accel=kvm
else
@@ -110,6 +105,7 @@ CFLAGS += -march=armv7-a -mabi=aapcs-linux # We don't pass -mtune=cortex-a15 due
LDFLAGS += -Wl,--be8
endif
else ifeq ($(ARCH),x86_64)
+CHOST := x86_64-linux-musl
QEMU_ARCH := x86_64
KERNEL_ARCH := x86_64
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
@@ -120,6 +116,7 @@ QEMU_MACHINE := -cpu Skylake-Server -machine q35
CFLAGS += -march=skylake-avx512
endif
else ifeq ($(ARCH),i686)
+CHOST := i686-linux-musl
QEMU_ARCH := i386
KERNEL_ARCH := x86
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/x86/boot/bzImage
@@ -130,6 +127,7 @@ QEMU_MACHINE := -cpu coreduo -machine q35
CFLAGS += -march=prescott
endif
else ifeq ($(ARCH),mips64)
+CHOST := mips64-linux-musl
QEMU_ARCH := mips64
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
@@ -141,6 +139,7 @@ QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1
CFLAGS += -march=mips64r2 -EB
endif
else ifeq ($(ARCH),mips64el)
+CHOST := mips64el-linux-musl
QEMU_ARCH := mips64el
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
@@ -152,6 +151,7 @@ QEMU_MACHINE := -cpu MIPS64R2-generic -machine malta -smp 1
CFLAGS += -march=mips64r2 -EL
endif
else ifeq ($(ARCH),mips)
+CHOST := mips-linux-musl
QEMU_ARCH := mips
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
@@ -163,6 +163,7 @@ QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1
CFLAGS += -march=mips32r2 -EB
endif
else ifeq ($(ARCH),mipsel)
+CHOST := mipsel-linux-musl
QEMU_ARCH := mipsel
KERNEL_ARCH := mips
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
@@ -173,7 +174,18 @@ else
QEMU_MACHINE := -cpu 24Kf -machine malta -smp 1
CFLAGS += -march=mips32r2 -EL
endif
+else ifeq ($(ARCH),powerpc64)
+CHOST := powerpc64-linux-musl
+QEMU_ARCH := ppc64
+KERNEL_ARCH := powerpc
+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
+ifeq ($(HOST_ARCH),$(ARCH))
+QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
+else
+QEMU_MACHINE := -machine pseries
+endif
else ifeq ($(ARCH),powerpc64le)
+CHOST := powerpc64le-linux-musl
QEMU_ARCH := ppc64
KERNEL_ARCH := powerpc
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
@@ -182,8 +194,8 @@ QEMU_MACHINE := -cpu host,accel=kvm -machine pseries
else
QEMU_MACHINE := -machine pseries
endif
-CFLAGS += -mcpu=powerpc64le -mlong-double-64
else ifeq ($(ARCH),powerpc)
+CHOST := powerpc-linux-musl
QEMU_ARCH := ppc
KERNEL_ARCH := powerpc
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/powerpc/boot/uImage
@@ -192,26 +204,79 @@ QEMU_MACHINE := -cpu host,accel=kvm -machine ppce500
else
QEMU_MACHINE := -machine ppce500
endif
-CFLAGS += -mcpu=powerpc -mlong-double-64 -msecure-plt
else ifeq ($(ARCH),m68k)
+CHOST := m68k-linux-musl
QEMU_ARCH := m68k
KERNEL_ARCH := m68k
KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/vmlinux
KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/m68k.config)
ifeq ($(HOST_ARCH),$(ARCH))
-QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
+QEMU_MACHINE := -cpu host,accel=kvm -machine q800 -append $(KERNEL_CMDLINE)
else
QEMU_MACHINE := -machine q800 -smp 1 -append $(KERNEL_CMDLINE)
endif
+else ifeq ($(ARCH),riscv64)
+CHOST := riscv64-linux-musl
+QEMU_ARCH := riscv64
+KERNEL_ARCH := riscv
+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/riscv/boot/Image
+QEMU_VPORT_RESULT := virtio-serial-device
+ifeq ($(HOST_ARCH),$(ARCH))
+QEMU_MACHINE := -cpu host,accel=kvm -machine virt
+else
+QEMU_MACHINE := -cpu rv64 -machine virt
+endif
+else ifeq ($(ARCH),riscv32)
+CHOST := riscv32-linux-musl
+QEMU_ARCH := riscv32
+KERNEL_ARCH := riscv
+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/riscv/boot/Image
+QEMU_VPORT_RESULT := virtio-serial-device
+ifeq ($(HOST_ARCH),$(ARCH))
+QEMU_MACHINE := -cpu host,accel=kvm -machine virt
+else
+QEMU_MACHINE := -cpu rv32 -machine virt
+endif
+else ifeq ($(ARCH),s390x)
+CHOST := s390x-linux-musl
+QEMU_ARCH := s390x
+KERNEL_ARCH := s390
+KERNEL_BZIMAGE := $(KERNEL_BUILD_PATH)/arch/s390/boot/bzImage
+KERNEL_CMDLINE := $(shell sed -n 's/CONFIG_CMDLINE=\(.*\)/\1/p' arch/s390x.config)
+QEMU_VPORT_RESULT := virtio-serial-ccw
+ifeq ($(HOST_ARCH),$(ARCH))
+QEMU_MACHINE := -cpu host,accel=kvm -machine s390-ccw-virtio -append $(KERNEL_CMDLINE)
+else
+QEMU_MACHINE := -machine s390-ccw-virtio -append $(KERNEL_CMDLINE)
+endif
else
-$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64le, powerpc, m68k)
+$(error I only build: x86_64, i686, arm, armeb, aarch64, aarch64_be, mips, mipsel, mips64, mips64el, powerpc64, powerpc64le, powerpc, m68k, riscv64, riscv32, s390x)
+endif
+
+TOOLCHAIN_FILENAME := $(CHOST)-cross.tgz
+TOOLCHAIN_TAR := $(DISTFILES_PATH)/$(TOOLCHAIN_FILENAME)
+TOOLCHAIN_PATH := $(BUILD_PATH)/$(CHOST)-cross
+TOOLCHAIN_DIR := https://download.wireguard.com/qemu-test/toolchains/20211123/
+$(eval $(call file_download,toolchain-sha256sums-20211123,$(TOOLCHAIN_DIR)SHA256SUMS#,83da033fd8c798df476c21d9612da2dfb896ec62fbed4ceec5eefc0e56b3f0c8))
+$(eval $(call file_download,$(TOOLCHAIN_FILENAME),$(TOOLCHAIN_DIR),,$(DISTFILES_PATH)/toolchain-sha256sums-20211123))
+
+STRIP := $(CHOST)-strip
+CROSS_COMPILE_FLAG := --build=$(CBUILD) --host=$(CHOST)
+$(info Building for $(CHOST) using $(CBUILD))
+export CROSS_COMPILE := $(CHOST)-
+export PATH := $(TOOLCHAIN_PATH)/bin:$(PATH)
+export CC := $(CHOST)-gcc
+CCACHE_PATH := $(shell which ccache 2>/dev/null)
+ifneq ($(CCACHE_PATH),)
+export KBUILD_BUILD_TIMESTAMP := Fri Jun 5 15:58:00 CEST 2015
+export PATH := $(TOOLCHAIN_PATH)/bin/ccache:$(PATH)
+export CCACHE_SLOPPINESS := file_macro,time_macros
+export CCACHE_DIR ?= $(PWD)/ccache
endif
-REAL_CC := $(CBUILD)-gcc
-MUSL_CC := $(BUILD_PATH)/musl-gcc
-export CC := $(MUSL_CC)
-USERSPACE_DEPS := $(MUSL_CC) $(BUILD_PATH)/include/.installed $(BUILD_PATH)/include/linux/.installed
+USERSPACE_DEPS := $(TOOLCHAIN_PATH)/.installed $(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed
+comma := ,
build: $(KERNEL_BZIMAGE)
qemu: $(KERNEL_BZIMAGE)
rm -f $(BUILD_PATH)/result
@@ -222,13 +287,14 @@ qemu: $(KERNEL_BZIMAGE)
$(QEMU_MACHINE) \
-m $$(grep -q CONFIG_DEBUG_KMEMLEAK=y $(KERNEL_BUILD_PATH)/.config && echo 1G || echo 256M) \
-serial stdio \
- -serial file:$(BUILD_PATH)/result \
+ -chardev file,path=$(BUILD_PATH)/result,id=result \
+ $(if $(QEMU_VPORT_RESULT),-device $(QEMU_VPORT_RESULT) -device virtserialport$(comma)chardev=result,-serial chardev:result) \
-no-reboot \
-monitor none \
-kernel $<
grep -Fq success $(BUILD_PATH)/result
-$(BUILD_PATH)/init-cpio-spec.txt:
+$(BUILD_PATH)/init-cpio-spec.txt: $(TOOLCHAIN_PATH)/.installed $(BUILD_PATH)/init
mkdir -p $(BUILD_PATH)
echo "file /init $(BUILD_PATH)/init 755 0 0" > $@
echo "file /init.sh $(PWD)/../netns.sh 755 0 0" >> $@
@@ -246,10 +312,10 @@ $(BUILD_PATH)/init-cpio-spec.txt:
echo "slink /bin/iptables xtables-legacy-multi 777 0 0" >> $@
echo "slink /bin/ping6 ping 777 0 0" >> $@
echo "dir /lib 755 0 0" >> $@
- echo "file /lib/libc.so $(MUSL_PATH)/lib/libc.so 755 0 0" >> $@
- echo "slink /lib/ld-linux.so.1 libc.so 777 0 0" >> $@
+ echo "file /lib/libc.so $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so 755 0 0" >> $@
+ echo "slink $$($(CHOST)-readelf -p .interp '$(BUILD_PATH)/init'| grep -o '/lib/.*') libc.so 777 0 0" >> $@
-$(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config
+$(KERNEL_BUILD_PATH)/.config: $(TOOLCHAIN_PATH)/.installed kernel.config arch/$(ARCH).config
mkdir -p $(KERNEL_BUILD_PATH)
cp kernel.config $(KERNEL_BUILD_PATH)/minimal.config
printf 'CONFIG_NR_CPUS=$(NR_CPUS)\nCONFIG_INITRAMFS_SOURCE="$(BUILD_PATH)/init-cpio-spec.txt"\n' >> $(KERNEL_BUILD_PATH)/minimal.config
@@ -258,29 +324,24 @@ $(KERNEL_BUILD_PATH)/.config: kernel.config arch/$(ARCH).config
cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config $(KERNEL_BUILD_PATH)/minimal.config
$(if $(findstring yes,$(DEBUG_KERNEL)),cp debug.config $(KERNEL_BUILD_PATH) && cd $(KERNEL_BUILD_PATH) && ARCH=$(KERNEL_ARCH) $(KERNEL_PATH)/scripts/kconfig/merge_config.sh -n $(KERNEL_BUILD_PATH)/.config debug.config,)
-$(KERNEL_BZIMAGE): $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(MUSL_PATH)/lib/libc.so $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
+$(KERNEL_BZIMAGE): $(TOOLCHAIN_PATH)/.installed $(KERNEL_BUILD_PATH)/.config $(BUILD_PATH)/init-cpio-spec.txt $(IPERF_PATH)/src/iperf3 $(IPUTILS_PATH)/ping $(BASH_PATH)/bash $(IPROUTE2_PATH)/misc/ss $(IPROUTE2_PATH)/ip/ip $(IPTABLES_PATH)/iptables/xtables-legacy-multi $(NMAP_PATH)/ncat/ncat $(WIREGUARD_TOOLS_PATH)/src/wg $(BUILD_PATH)/init ../netns.sh $(WIREGUARD_SOURCES)
$(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE)
-$(BUILD_PATH)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config
- $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
+$(TOOLCHAIN_PATH)/$(CHOST)/include/linux/.installed: | $(KERNEL_BUILD_PATH)/.config $(TOOLCHAIN_PATH)/.installed
+ rm -rf $(TOOLCHAIN_PATH)/$(CHOST)/include/linux
+ $(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) INSTALL_HDR_PATH=$(TOOLCHAIN_PATH)/$(CHOST) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) headers_install
touch $@
-$(MUSL_PATH)/lib/libc.so: $(MUSL_TAR)
+$(TOOLCHAIN_PATH)/.installed: $(TOOLCHAIN_TAR)
mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- cd $(MUSL_PATH) && CC=$(REAL_CC) ./configure --prefix=/ --disable-static --build=$(CBUILD)
- $(MAKE) -C $(MUSL_PATH)
- $(STRIP) -s $@
-
-$(BUILD_PATH)/include/.installed: $(MUSL_PATH)/lib/libc.so
- $(MAKE) -C $(MUSL_PATH) DESTDIR=$(BUILD_PATH) install-headers
+ $(STRIP) -s $(TOOLCHAIN_PATH)/$(CHOST)/lib/libc.so
+ifneq ($(CCACHE_PATH),)
+ mkdir -p $(TOOLCHAIN_PATH)/bin/ccache
+ ln -s $(CCACHE_PATH) $(TOOLCHAIN_PATH)/bin/ccache/$(CC)
+endif
touch $@
-$(MUSL_CC): $(MUSL_PATH)/lib/libc.so
- sh $(MUSL_PATH)/tools/musl-gcc.specs.sh $(BUILD_PATH)/include $(MUSL_PATH)/lib /lib/ld-linux.so.1 > $(BUILD_PATH)/musl-gcc.specs
- printf '#!/bin/sh\nexec "$(REAL_CC)" --specs="$(BUILD_PATH)/musl-gcc.specs" "$$@"\n' > $(BUILD_PATH)/musl-gcc
- chmod +x $(BUILD_PATH)/musl-gcc
-
$(IPERF_PATH)/.installed: $(IPERF_TAR)
mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
@@ -289,6 +350,7 @@ $(IPERF_PATH)/.installed: $(IPERF_TAR)
touch $@
$(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS)
+ cd $(IPERF_PATH) && autoreconf -fi
cd $(IPERF_PATH) && CFLAGS="$(CFLAGS) -D_GNU_SOURCE" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --with-openssl=no
$(MAKE) -C $(IPERF_PATH)
$(STRIP) -s $@
@@ -304,7 +366,7 @@ $(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE
$(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS)
mkdir -p $(BUILD_PATH)
- $(MUSL_CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $<
+ $(CC) -o $@ $(CFLAGS) $(LDFLAGS) -std=gnu11 $<
$(STRIP) -s $@
$(IPUTILS_PATH)/.installed: $(IPUTILS_TAR)
@@ -323,15 +385,15 @@ $(BASH_PATH)/.installed: $(BASH_TAR)
touch $@
$(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS)
- cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-multibyte --disable-progcomp --disable-readline --disable-mem-scramble
+ cd $(BASH_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --without-bash-malloc --disable-debugger --disable-help-builtin --disable-history --disable-progcomp --disable-readline --disable-mem-scramble
$(MAKE) -C $(BASH_PATH)
$(STRIP) -s $@
$(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR)
mkdir -p $(BUILD_PATH)
flock -s $<.lock tar -C $(BUILD_PATH) -xf $<
- printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk
- printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
+ printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_HANDLE_AT\n' > $(IPROUTE2_PATH)/config.mk
+ printf 'libutil.a.done:\n\tflock -x $$@.lock $$(MAKE) -C lib\n\ttouch $$@\nip/ip: libutil.a.done\n\t$$(MAKE) -C ip ip\nmisc/ss: libutil.a.done\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile
touch $@
$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS)
@@ -370,8 +432,13 @@ clean:
distclean: clean
rm -rf $(DISTFILES_PATH)
+cacheclean: clean
+ifneq ($(CCACHE_DIR),)
+ rm -rf $(CCACHE_DIR)
+endif
+
menuconfig: $(KERNEL_BUILD_PATH)/.config
$(MAKE) -C $(KERNEL_PATH) O=$(KERNEL_BUILD_PATH) ARCH=$(KERNEL_ARCH) CROSS_COMPILE=$(CROSS_COMPILE) menuconfig
-.PHONY: qemu build clean distclean menuconfig
+.PHONY: qemu build clean distclean cacheclean menuconfig
.DELETE_ON_ERROR:
diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config
index 3d063bb247bb..09016880ce03 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/aarch64.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64.config
@@ -1,5 +1,8 @@
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
+CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1"
CONFIG_FRAME_WARN=1280
diff --git a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
index dbdc7e406a7b..19ff66e4c602 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/aarch64_be.config
@@ -1,6 +1,9 @@
CONFIG_CPU_BIG_ENDIAN=y
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
+CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1"
CONFIG_FRAME_WARN=1280
diff --git a/tools/testing/selftests/wireguard/qemu/arch/arm.config b/tools/testing/selftests/wireguard/qemu/arch/arm.config
index 148f49905418..fc7959bef9c2 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/arm.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/arm.config
@@ -4,6 +4,9 @@ CONFIG_ARCH_VIRT=y
CONFIG_THUMB2_KERNEL=n
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
+CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/armeb.config b/tools/testing/selftests/wireguard/qemu/arch/armeb.config
index bd76b07d00a2..f3066be81c19 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/armeb.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/armeb.config
@@ -4,7 +4,10 @@ CONFIG_ARCH_VIRT=y
CONFIG_THUMB2_KERNEL=n
CONFIG_SERIAL_AMBA_PL011=y
CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyAMA0 wg.success=ttyAMA1"
+CONFIG_CMDLINE="console=ttyAMA0 wg.success=vport0p1 panic_on_warn=1"
CONFIG_CPU_BIG_ENDIAN=y
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/i686.config b/tools/testing/selftests/wireguard/qemu/arch/i686.config
index a85025d7206e..6d90892a85a2 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/i686.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/i686.config
@@ -1,5 +1,6 @@
+CONFIG_ACPI=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/m68k.config b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
index 62a15bdb877e..82c925e49beb 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/m68k.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/m68k.config
@@ -5,5 +5,5 @@ CONFIG_MAC=y
CONFIG_SERIAL_PMACZILOG=y
CONFIG_SERIAL_PMACZILOG_TTYS=y
CONFIG_SERIAL_PMACZILOG_CONSOLE=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips.config b/tools/testing/selftests/wireguard/qemu/arch/mips.config
index df71d6b95546..d7ec63c17b30 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/mips.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/mips.config
@@ -7,5 +7,5 @@ CONFIG_POWER_RESET_SYSCON=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64.config b/tools/testing/selftests/wireguard/qemu/arch/mips64.config
index 90c783f725c4..0994947e3392 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/mips64.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/mips64.config
@@ -10,5 +10,5 @@ CONFIG_POWER_RESET_SYSCON=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1280
diff --git a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config
index 435b0b43e00c..591184342f47 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/mips64el.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/mips64el.config
@@ -11,5 +11,5 @@ CONFIG_POWER_RESET_SYSCON=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1280
diff --git a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config
index 62bb50c4a85f..18a498293737 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/mipsel.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/mipsel.config
@@ -8,5 +8,5 @@ CONFIG_POWER_RESET_SYSCON=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config
index 57957093b71b..5e04882e8e35 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/powerpc.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc.config
@@ -6,5 +6,5 @@ CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_MATH_EMULATION=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1024
diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config
new file mode 100644
index 000000000000..737194b7619e
--- /dev/null
+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64.config
@@ -0,0 +1,13 @@
+CONFIG_PPC64=y
+CONFIG_PPC_PSERIES=y
+CONFIG_ALTIVEC=y
+CONFIG_VSX=y
+CONFIG_PPC_OF_BOOT_TRAMPOLINE=y
+CONFIG_PPC_RADIX_MMU=y
+CONFIG_HVC_CONSOLE=y
+CONFIG_CPU_BIG_ENDIAN=y
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1"
+CONFIG_SECTION_MISMATCH_WARN_ONLY=y
+CONFIG_FRAME_WARN=1280
+CONFIG_THREAD_SHIFT=14
diff --git a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
index f52f1e2bc7f6..8148b9d1220a 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/powerpc64le.config
@@ -7,7 +7,7 @@ CONFIG_PPC_RADIX_MMU=y
CONFIG_HVC_CONSOLE=y
CONFIG_CPU_LITTLE_ENDIAN=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=hvc0 wg.success=hvc1"
+CONFIG_CMDLINE="console=hvc0 wg.success=hvc1 panic_on_warn=1"
CONFIG_SECTION_MISMATCH_WARN_ONLY=y
CONFIG_FRAME_WARN=1280
CONFIG_THREAD_SHIFT=14
diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv32.config b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config
new file mode 100644
index 000000000000..0bd0e72d95d4
--- /dev/null
+++ b/tools/testing/selftests/wireguard/qemu/arch/riscv32.config
@@ -0,0 +1,12 @@
+CONFIG_ARCH_RV32I=y
+CONFIG_MMU=y
+CONFIG_FPU=y
+CONFIG_SOC_VIRT=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1 panic_on_warn=1"
+CONFIG_CMDLINE_FORCE=y
diff --git a/tools/testing/selftests/wireguard/qemu/arch/riscv64.config b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config
new file mode 100644
index 000000000000..dc266f3b1915
--- /dev/null
+++ b/tools/testing/selftests/wireguard/qemu/arch/riscv64.config
@@ -0,0 +1,12 @@
+CONFIG_ARCH_RV64I=y
+CONFIG_MMU=y
+CONFIG_FPU=y
+CONFIG_SOC_VIRT=y
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_OF_PLATFORM=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_MMIO=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_CMDLINE="console=ttyS0 wg.success=vport0p1 panic_on_warn=1"
+CONFIG_CMDLINE_FORCE=y
diff --git a/tools/testing/selftests/wireguard/qemu/arch/s390x.config b/tools/testing/selftests/wireguard/qemu/arch/s390x.config
new file mode 100644
index 000000000000..a7b44dca0b0a
--- /dev/null
+++ b/tools/testing/selftests/wireguard/qemu/arch/s390x.config
@@ -0,0 +1,6 @@
+CONFIG_SCLP_VT220_TTY=y
+CONFIG_SCLP_VT220_CONSOLE=y
+CONFIG_VIRTIO_MENU=y
+CONFIG_VIRTIO_CONSOLE=y
+CONFIG_S390_GUEST=y
+CONFIG_CMDLINE="console=ttysclp0 wg.success=vport0p1 panic_on_warn=1"
diff --git a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
index 00a1ef4869d5..efa00693e08b 100644
--- a/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
+++ b/tools/testing/selftests/wireguard/qemu/arch/x86_64.config
@@ -1,5 +1,6 @@
+CONFIG_ACPI=y
CONFIG_SERIAL_8250=y
CONFIG_SERIAL_8250_CONSOLE=y
CONFIG_CMDLINE_BOOL=y
-CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1"
+CONFIG_CMDLINE="console=ttyS0 wg.success=ttyS1 panic_on_warn=1"
CONFIG_FRAME_WARN=1280
diff --git a/tools/testing/selftests/wireguard/qemu/init.c b/tools/testing/selftests/wireguard/qemu/init.c
index 0b45055d9de0..2a0f48fac925 100644
--- a/tools/testing/selftests/wireguard/qemu/init.c
+++ b/tools/testing/selftests/wireguard/qemu/init.c
@@ -110,12 +110,6 @@ static void enable_logging(void)
panic("write(exception-trace)");
close(fd);
}
- fd = open("/proc/sys/kernel/panic_on_warn", O_WRONLY);
- if (fd >= 0) {
- if (write(fd, "1\n", 2) != 2)
- panic("write(panic_on_warn)");
- close(fd);
- }
}
static void kmod_selftests(void)
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 53df7d3893d3..0388c4d60af0 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -92,6 +92,10 @@ warn_32bit_failure:
echo "If you are using a Fedora-like distribution, try:"; \
echo ""; \
echo " yum install glibc-devel.*i686"; \
+ echo ""; \
+ echo "If you are using a SUSE-like distribution, try:"; \
+ echo ""; \
+ echo " zypper install gcc-32bit glibc-devel-static-32bit"; \
exit 0;
endif
diff --git a/tools/thermal/lib/Build b/tools/thermal/lib/Build
new file mode 100644
index 000000000000..06f22760a272
--- /dev/null
+++ b/tools/thermal/lib/Build
@@ -0,0 +1,3 @@
+libthermal_tools-y += mainloop.o
+libthermal_tools-y += log.o
+libthermal_tools-y += uptimeofday.o
diff --git a/tools/thermal/lib/Makefile b/tools/thermal/lib/Makefile
new file mode 100644
index 000000000000..82db451935c5
--- /dev/null
+++ b/tools/thermal/lib/Makefile
@@ -0,0 +1,158 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+# Most of this file is copied from tools/lib/perf/Makefile
+
+LIBTHERMAL_TOOLS_VERSION = 0
+LIBTHERMAL_TOOLS_PATCHLEVEL = 0
+LIBTHERMAL_TOOLS_EXTRAVERSION = 1
+
+MAKEFLAGS += --no-print-directory
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+# $(info Determined 'srctree' to be $(srctree))
+endif
+
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+include $(srctree)/tools/scripts/Makefile.include
+include $(srctree)/tools/scripts/Makefile.arch
+
+ifeq ($(LP64), 1)
+ libdir_relative = lib64
+else
+ libdir_relative = lib
+endif
+
+prefix ?=
+libdir = $(prefix)/$(libdir_relative)
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
+
+ifeq ("$(origin V)", "command line")
+ VERBOSE = $(V)
+endif
+ifndef VERBOSE
+ VERBOSE = 0
+endif
+
+ifeq ($(VERBOSE),1)
+ Q =
+else
+ Q = @
+endif
+
+# Set compile option CFLAGS
+ifdef EXTRA_CFLAGS
+ CFLAGS := $(EXTRA_CFLAGS)
+else
+ CFLAGS := -g -Wall
+endif
+
+INCLUDES = \
+-I/usr/include/libnl3 \
+-I$(srctree)/tools/lib/thermal/include \
+-I$(srctree)/tools/lib/ \
+-I$(srctree)/tools/include \
+-I$(srctree)/tools/arch/$(SRCARCH)/include/ \
+-I$(srctree)/tools/arch/$(SRCARCH)/include/uapi \
+-I$(srctree)/tools/include/uapi
+
+# Append required CFLAGS
+override CFLAGS += $(EXTRA_WARNINGS)
+override CFLAGS += -Werror -Wall
+override CFLAGS += -fPIC
+override CFLAGS += $(INCLUDES)
+override CFGLAS += -Wl,-L.
+override CFGLAS += -Wl,-lthermal
+
+all:
+
+export srctree OUTPUT CC LD CFLAGS V
+export DESTDIR DESTDIR_SQ
+
+include $(srctree)/tools/build/Makefile.include
+
+PATCHLEVEL = $(LIBTHERMAL_TOOLS_PATCHLEVEL)
+EXTRAVERSION = $(LIBTHERMAL_TOOLS_EXTRAVERSION)
+VERSION = $(LIBTHERMAL_TOOLS_VERSION).$(LIBTHERMAL_TOOLS_PATCHLEVEL).$(LIBTHERMAL_TOOLS_EXTRAVERSION)
+
+LIBTHERMAL_TOOLS_SO := $(OUTPUT)libthermal_tools.so.$(VERSION)
+LIBTHERMAL_TOOLS_A := $(OUTPUT)libthermal_tools.a
+LIBTHERMAL_TOOLS_IN := $(OUTPUT)libthermal_tools-in.o
+LIBTHERMAL_TOOLS_PC := $(OUTPUT)libthermal_tools.pc
+
+LIBTHERMAL_TOOLS_ALL := $(LIBTHERMAL_TOOLS_A) $(OUTPUT)libthermal_tools.so*
+
+$(LIBTHERMAL_TOOLS_IN): FORCE
+ $(Q)$(MAKE) $(build)=libthermal_tools
+
+$(LIBTHERMAL_TOOLS_A): $(LIBTHERMAL_TOOLS_IN)
+ $(QUIET_AR)$(RM) $@ && $(AR) rcs $@ $(LIBTHERMAL_TOOLS_IN)
+
+$(LIBTHERMAL_TOOLS_SO): $(LIBTHERMAL_TOOLS_IN)
+ $(QUIET_LINK)$(CC) --shared -Wl,-soname,libthermal_tools.so $^ -o $@
+ @ln -sf $(@F) $(OUTPUT)libthermal_tools.so
+ @ln -sf $(@F) $(OUTPUT)libthermal_tools.so.$(LIBTHERMAL_TOOLS_VERSION)
+
+
+libs: $(LIBTHERMAL_TOOLS_A) $(LIBTHERMAL_TOOLS_SO) $(LIBTHERMAL_TOOLS_PC)
+
+all: fixdep
+ $(Q)$(MAKE) libs
+
+clean:
+ $(call QUIET_CLEAN, libthermal_tools) $(RM) $(LIBTHERMAL_TOOLS_A) \
+ *.o *~ *.a *.so *.so.$(VERSION) *.so.$(LIBTHERMAL_TOOLS_VERSION) .*.d .*.cmd LIBTHERMAL_TOOLS-CFLAGS $(LIBTHERMAL_TOOLS_PC)
+
+$(LIBTHERMAL_TOOLS_PC):
+ $(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+ -e "s|@LIBDIR@|$(libdir_SQ)|" \
+ -e "s|@VERSION@|$(VERSION)|" \
+ < libthermal_tools.pc.template > $@
+
+define do_install_mkdir
+ if [ ! -d '$(DESTDIR_SQ)$1' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1'; \
+ fi
+endef
+
+define do_install
+ if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
+ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
+ fi; \
+ $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: libs
+ $(call QUIET_INSTALL, $(LIBTHERMAL_TOOLS_ALL)) \
+ $(call do_install_mkdir,$(libdir_SQ)); \
+ cp -fpR $(LIBTHERMAL_TOOLS_ALL) $(DESTDIR)$(libdir_SQ)
+
+install_headers:
+ $(call QUIET_INSTALL, headers) \
+ $(call do_install,include/thermal.h,$(prefix)/include/thermal,644); \
+
+install_pkgconfig: $(LIBTHERMAL_TOOLS_PC)
+ $(call QUIET_INSTALL, $(LIBTHERMAL_TOOLS_PC)) \
+ $(call do_install,$(LIBTHERMAL_TOOLS_PC),$(libdir_SQ)/pkgconfig,644)
+
+install_doc:
+ $(Q)$(MAKE) -C Documentation install-man install-html install-examples
+
+#install: install_lib install_headers install_pkgconfig install_doc
+install: install_lib install_headers install_pkgconfig
+
+FORCE:
+
+.PHONY: all install clean FORCE
diff --git a/tools/thermal/lib/libthermal_tools.pc.template b/tools/thermal/lib/libthermal_tools.pc.template
new file mode 100644
index 000000000000..6f3769731b59
--- /dev/null
+++ b/tools/thermal/lib/libthermal_tools.pc.template
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=${prefix}/include
+
+Name: libthermal
+Description: thermal library
+Requires: libnl-3.0 libnl-genl-3.0
+Version: @VERSION@
+Libs: -L${libdir} -lnl-genl-3 -lnl-3
+Cflags: -I${includedir} -I{include}/libnl3
diff --git a/tools/thermal/lib/log.c b/tools/thermal/lib/log.c
new file mode 100644
index 000000000000..597d6e7f7858
--- /dev/null
+++ b/tools/thermal/lib/log.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <stdarg.h>
+#include <stdio.h>
+#include <string.h>
+#include <syslog.h>
+#include "log.h"
+
+static const char *__ident = "unknown";
+static int __options;
+
+static const char * const loglvl[] = {
+ [LOG_DEBUG] = "DEBUG",
+ [LOG_INFO] = "INFO",
+ [LOG_NOTICE] = "NOTICE",
+ [LOG_WARNING] = "WARN",
+ [LOG_ERR] = "ERROR",
+ [LOG_CRIT] = "CRITICAL",
+ [LOG_ALERT] = "ALERT",
+ [LOG_EMERG] = "EMERG",
+};
+
+int log_str2level(const char *lvl)
+{
+ int i;
+
+ for (i = 0; i < sizeof(loglvl) / sizeof(loglvl[LOG_DEBUG]); i++)
+ if (!strcmp(lvl, loglvl[i]))
+ return i;
+
+ return LOG_DEBUG;
+}
+
+extern void logit(int level, const char *format, ...)
+{
+ va_list args;
+
+ va_start(args, format);
+
+ if (__options & TO_SYSLOG)
+ vsyslog(level, format, args);
+
+ if (__options & TO_STDERR)
+ vfprintf(stderr, format, args);
+
+ if (__options & TO_STDOUT)
+ vfprintf(stdout, format, args);
+
+ va_end(args);
+}
+
+int log_init(int level, const char *ident, int options)
+{
+ if (!options)
+ return -1;
+
+ if (level > LOG_DEBUG)
+ return -1;
+
+ if (!ident)
+ return -1;
+
+ __ident = ident;
+ __options = options;
+
+ if (options & TO_SYSLOG) {
+ openlog(__ident, options | LOG_NDELAY, LOG_USER);
+ setlogmask(LOG_UPTO(level));
+ }
+
+ return 0;
+}
+
+void log_exit(void)
+{
+ closelog();
+}
diff --git a/tools/thermal/lib/log.h b/tools/thermal/lib/log.h
new file mode 100644
index 000000000000..be8ab5144938
--- /dev/null
+++ b/tools/thermal/lib/log.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: LGPL-2.1+ */
+/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */
+#ifndef __THERMAL_TOOLS_LOG_H
+#define __THERMAL_TOOLS_LOG_H
+
+#include <syslog.h>
+
+#ifndef __maybe_unused
+#define __maybe_unused __attribute__((__unused__))
+#endif
+
+#define TO_SYSLOG 0x1
+#define TO_STDOUT 0x2
+#define TO_STDERR 0x4
+
+extern void logit(int level, const char *format, ...);
+
+#define DEBUG(fmt, ...) logit(LOG_DEBUG, "%s:%d: " fmt, __func__, __LINE__, ##__VA_ARGS__)
+#define INFO(fmt, ...) logit(LOG_INFO, fmt, ##__VA_ARGS__)
+#define NOTICE(fmt, ...) logit(LOG_NOTICE, fmt, ##__VA_ARGS__)
+#define WARN(fmt, ...) logit(LOG_WARNING, fmt, ##__VA_ARGS__)
+#define ERROR(fmt, ...) logit(LOG_ERR, fmt, ##__VA_ARGS__)
+#define CRITICAL(fmt, ...) logit(LOG_CRIT, fmt, ##__VA_ARGS__)
+#define ALERT(fmt, ...) logit(LOG_ALERT, fmt, ##__VA_ARGS__)
+#define EMERG(fmt, ...) logit(LOG_EMERG, fmt, ##__VA_ARGS__)
+
+int log_init(int level, const char *ident, int options);
+int log_str2level(const char *lvl);
+void log_exit(void);
+
+#endif
diff --git a/tools/thermal/lib/mainloop.c b/tools/thermal/lib/mainloop.c
new file mode 100644
index 000000000000..94cbbcbd1c14
--- /dev/null
+++ b/tools/thermal/lib/mainloop.c
@@ -0,0 +1,120 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <stdlib.h>
+#include <errno.h>
+#include <unistd.h>
+#include <signal.h>
+#include <sys/epoll.h>
+#include "mainloop.h"
+#include "log.h"
+
+static int epfd = -1;
+static unsigned short nrhandler;
+static sig_atomic_t exit_mainloop;
+
+struct mainloop_data {
+ mainloop_callback_t cb;
+ void *data;
+ int fd;
+};
+
+static struct mainloop_data **mds;
+
+#define MAX_EVENTS 10
+
+int mainloop(unsigned int timeout)
+{
+ int i, nfds;
+ struct epoll_event events[MAX_EVENTS];
+ struct mainloop_data *md;
+
+ if (epfd < 0)
+ return -1;
+
+ for (;;) {
+
+ nfds = epoll_wait(epfd, events, MAX_EVENTS, timeout);
+
+ if (exit_mainloop || !nfds)
+ return 0;
+
+ if (nfds < 0) {
+ if (errno == EINTR)
+ continue;
+ return -1;
+ }
+
+ for (i = 0; i < nfds; i++) {
+ md = events[i].data.ptr;
+
+ if (md->cb(md->fd, md->data) > 0)
+ return 0;
+ }
+ }
+}
+
+int mainloop_add(int fd, mainloop_callback_t cb, void *data)
+{
+ struct epoll_event ev = {
+ .events = EPOLLIN,
+ };
+
+ struct mainloop_data *md;
+
+ if (fd >= nrhandler) {
+ mds = realloc(mds, sizeof(*mds) * (fd + 1));
+ if (!mds)
+ return -1;
+ nrhandler = fd + 1;
+ }
+
+ md = malloc(sizeof(*md));
+ if (!md)
+ return -1;
+
+ md->data = data;
+ md->cb = cb;
+ md->fd = fd;
+
+ mds[fd] = md;
+ ev.data.ptr = md;
+
+ if (epoll_ctl(epfd, EPOLL_CTL_ADD, fd, &ev) < 0) {
+ free(md);
+ return -1;
+ }
+
+ return 0;
+}
+
+int mainloop_del(int fd)
+{
+ if (fd >= nrhandler)
+ return -1;
+
+ if (epoll_ctl(epfd, EPOLL_CTL_DEL, fd, NULL) < 0)
+ return -1;
+
+ free(mds[fd]);
+
+ return 0;
+}
+
+int mainloop_init(void)
+{
+ epfd = epoll_create(2);
+ if (epfd < 0)
+ return -1;
+
+ return 0;
+}
+
+void mainloop_exit(void)
+{
+ exit_mainloop = 1;
+}
+
+void mainloop_fini(void)
+{
+ close(epfd);
+}
diff --git a/tools/thermal/lib/mainloop.h b/tools/thermal/lib/mainloop.h
new file mode 100644
index 000000000000..89b61e89d905
--- /dev/null
+++ b/tools/thermal/lib/mainloop.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: LGPL-2.1+ */
+/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */
+#ifndef __THERMAL_TOOLS_MAINLOOP_H
+#define __THERMAL_TOOLS_MAINLOOP_H
+
+typedef int (*mainloop_callback_t)(int fd, void *data);
+
+extern int mainloop(unsigned int timeout);
+extern int mainloop_add(int fd, mainloop_callback_t cb, void *data);
+extern int mainloop_del(int fd);
+extern void mainloop_exit(void);
+extern int mainloop_init(void);
+extern void mainloop_fini(void);
+
+#endif
diff --git a/tools/thermal/lib/thermal-tools.h b/tools/thermal/lib/thermal-tools.h
new file mode 100644
index 000000000000..f43939a468a3
--- /dev/null
+++ b/tools/thermal/lib/thermal-tools.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: LGPL-2.1+ */
+/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */
+#ifndef __THERMAL_TOOLS
+#define __THERMAL_TOOLS
+
+#include "log.h"
+#include "mainloop.h"
+#include "uptimeofday.h"
+
+#endif
diff --git a/tools/thermal/lib/uptimeofday.c b/tools/thermal/lib/uptimeofday.c
new file mode 100644
index 000000000000..dacb02956a68
--- /dev/null
+++ b/tools/thermal/lib/uptimeofday.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: LGPL-2.1+
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#include <stdio.h>
+#include <sys/time.h>
+#include <linux/sysinfo.h>
+#include "thermal-tools.h"
+
+static unsigned long __offset;
+static struct timeval __tv;
+
+int uptimeofday_init(void)
+{
+ struct sysinfo info;
+
+ if (sysinfo(&info))
+ return -1;
+
+ gettimeofday(&__tv, NULL);
+
+ __offset = __tv.tv_sec - info.uptime;
+
+ return 0;
+}
+
+unsigned long getuptimeofday_ms(void)
+{
+ gettimeofday(&__tv, NULL);
+
+ return ((__tv.tv_sec - __offset) * 1000) + (__tv.tv_usec / 1000);
+}
+
+struct timespec msec_to_timespec(int msec)
+{
+ struct timespec tv = {
+ .tv_sec = (msec / 1000),
+ .tv_nsec = (msec % 1000) * 1000000,
+ };
+
+ return tv;
+}
diff --git a/tools/thermal/lib/uptimeofday.h b/tools/thermal/lib/uptimeofday.h
new file mode 100644
index 000000000000..c0da5de41325
--- /dev/null
+++ b/tools/thermal/lib/uptimeofday.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: LGPL-2.1+ */
+/* Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org> */
+#ifndef __THERMAL_TOOLS_UPTIMEOFDAY_H
+#define __THERMAL_TOOLS_UPTIMEOFDAY_H
+#include <sys/sysinfo.h>
+#include <sys/time.h>
+
+int uptimeofday_init(void);
+unsigned long getuptimeofday_ms(void);
+struct timespec msec_to_timespec(int msec);
+
+#endif
diff --git a/tools/thermal/thermal-engine/Build b/tools/thermal/thermal-engine/Build
new file mode 100644
index 000000000000..20c3c478b88d
--- /dev/null
+++ b/tools/thermal/thermal-engine/Build
@@ -0,0 +1 @@
+thermal-engine-y += thermal-engine.o
diff --git a/tools/thermal/thermal-engine/Makefile b/tools/thermal/thermal-engine/Makefile
new file mode 100644
index 000000000000..6bd05ff89485
--- /dev/null
+++ b/tools/thermal/thermal-engine/Makefile
@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for thermal tools
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+# $(info Determined 'srctree' to be $(srctree))
+endif
+
+CFLAGS = -Wall -Wextra
+CFLAGS += -I$(srctree)/tools/thermal/lib
+CFLAGS += -I$(srctree)/tools/lib/thermal/include
+
+LDFLAGS = -L$(srctree)/tools/thermal/lib
+LDFLAGS += -L$(srctree)/tools/lib/thermal
+LDFLAGS += -lthermal_tools
+LDFLAGS += -lthermal
+LDFLAGS += -lconfig
+LDFLAGS += -lnl-genl-3 -lnl-3
+
+VERSION = 0.0.1
+
+all: thermal-engine
+%: %.c
+ $(CC) $(CFLAGS) -D VERSION=\"$(VERSION)\" -o $@ $^ $(LDFLAGS)
+clean:
+ $(RM) thermal-engine
diff --git a/tools/thermal/thermal-engine/thermal-engine.c b/tools/thermal/thermal-engine/thermal-engine.c
new file mode 100644
index 000000000000..9b1476a2680f
--- /dev/null
+++ b/tools/thermal/thermal-engine/thermal-engine.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Thermal monitoring tool based on the thermal netlink events.
+ *
+ * Copyright (C) 2022 Linaro Ltd.
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@kernel.org>
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <libgen.h>
+#include <limits.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <signal.h>
+#include <unistd.h>
+
+#include <syslog.h>
+
+#include <sys/epoll.h>
+#include <sys/stat.h>
+#include <sys/types.h>
+
+#include <thermal.h>
+#include "thermal-tools.h"
+
+struct options {
+ int loglevel;
+ int logopt;
+ int interactive;
+ int daemonize;
+};
+
+struct thermal_data {
+ struct thermal_zone *tz;
+ struct thermal_handler *th;
+};
+
+static int show_trip(struct thermal_trip *tt, __maybe_unused void *arg)
+{
+ INFO("trip id=%d, type=%d, temp=%d, hyst=%d\n",
+ tt->id, tt->type, tt->temp, tt->hyst);
+
+ return 0;
+}
+
+static int show_temp(struct thermal_zone *tz, __maybe_unused void *arg)
+{
+ thermal_cmd_get_temp(arg, tz);
+
+ INFO("temperature: %d\n", tz->temp);
+
+ return 0;
+}
+
+static int show_governor(struct thermal_zone *tz, __maybe_unused void *arg)
+{
+ thermal_cmd_get_governor(arg, tz);
+
+ INFO("governor: '%s'\n", tz->governor);
+
+ return 0;
+}
+
+static int show_tz(struct thermal_zone *tz, __maybe_unused void *arg)
+{
+ INFO("thermal zone '%s', id=%d\n", tz->name, tz->id);
+
+ for_each_thermal_trip(tz->trip, show_trip, NULL);
+
+ show_temp(tz, arg);
+
+ show_governor(tz, arg);
+
+ return 0;
+}
+
+static int tz_create(const char *name, int tz_id, __maybe_unused void *arg)
+{
+ INFO("Thermal zone '%s'/%d created\n", name, tz_id);
+
+ return 0;
+}
+
+static int tz_delete(int tz_id, __maybe_unused void *arg)
+{
+ INFO("Thermal zone %d deleted\n", tz_id);
+
+ return 0;
+}
+
+static int tz_disable(int tz_id, void *arg)
+{
+ struct thermal_data *td = arg;
+ struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+ INFO("Thermal zone %d ('%s') disabled\n", tz_id, tz->name);
+
+ return 0;
+}
+
+static int tz_enable(int tz_id, void *arg)
+{
+ struct thermal_data *td = arg;
+ struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+ INFO("Thermal zone %d ('%s') enabled\n", tz_id, tz->name);
+
+ return 0;
+}
+
+static int trip_high(int tz_id, int trip_id, int temp, void *arg)
+{
+ struct thermal_data *td = arg;
+ struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+ INFO("Thermal zone %d ('%s'): trip point %d crossed way up with %d °C\n",
+ tz_id, tz->name, trip_id, temp);
+
+ return 0;
+}
+
+static int trip_low(int tz_id, int trip_id, int temp, void *arg)
+{
+ struct thermal_data *td = arg;
+ struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+ INFO("Thermal zone %d ('%s'): trip point %d crossed way down with %d °C\n",
+ tz_id, tz->name, trip_id, temp);
+
+ return 0;
+}
+
+static int trip_add(int tz_id, int trip_id, int type, int temp, int hyst, __maybe_unused void *arg)
+{
+ INFO("Trip point added %d: id=%d, type=%d, temp=%d, hyst=%d\n",
+ tz_id, trip_id, type, temp, hyst);
+
+ return 0;
+}
+
+static int trip_delete(int tz_id, int trip_id, __maybe_unused void *arg)
+{
+ INFO("Trip point deleted %d: id=%d\n", tz_id, trip_id);
+
+ return 0;
+}
+
+static int trip_change(int tz_id, int trip_id, int type, int temp,
+ int hyst, __maybe_unused void *arg)
+{
+ struct thermal_data *td = arg;
+ struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+ INFO("Trip point changed %d: id=%d, type=%d, temp=%d, hyst=%d\n",
+ tz_id, trip_id, type, temp, hyst);
+
+ tz->trip[trip_id].type = type;
+ tz->trip[trip_id].temp = temp;
+ tz->trip[trip_id].hyst = hyst;
+
+ return 0;
+}
+
+static int cdev_add(const char *name, int cdev_id, int max_state, __maybe_unused void *arg)
+{
+ INFO("Cooling device '%s'/%d (max state=%d) added\n", name, cdev_id, max_state);
+
+ return 0;
+}
+
+static int cdev_delete(int cdev_id, __maybe_unused void *arg)
+{
+ INFO("Cooling device %d deleted", cdev_id);
+
+ return 0;
+}
+
+static int cdev_update(int cdev_id, int cur_state, __maybe_unused void *arg)
+{
+ INFO("cdev:%d state:%d\n", cdev_id, cur_state);
+
+ return 0;
+}
+
+static int gov_change(int tz_id, const char *name, __maybe_unused void *arg)
+{
+ struct thermal_data *td = arg;
+ struct thermal_zone *tz = thermal_zone_find_by_id(td->tz, tz_id);
+
+ INFO("%s: governor changed %s -> %s\n", tz->name, tz->governor, name);
+
+ strcpy(tz->governor, name);
+
+ return 0;
+}
+
+static struct thermal_ops ops = {
+ .events.tz_create = tz_create,
+ .events.tz_delete = tz_delete,
+ .events.tz_disable = tz_disable,
+ .events.tz_enable = tz_enable,
+ .events.trip_high = trip_high,
+ .events.trip_low = trip_low,
+ .events.trip_add = trip_add,
+ .events.trip_delete = trip_delete,
+ .events.trip_change = trip_change,
+ .events.cdev_add = cdev_add,
+ .events.cdev_delete = cdev_delete,
+ .events.cdev_update = cdev_update,
+ .events.gov_change = gov_change
+};
+
+static int thermal_event(__maybe_unused int fd, __maybe_unused void *arg)
+{
+ struct thermal_data *td = arg;
+
+ return thermal_events_handle(td->th, td);
+}
+
+static void usage(const char *cmd)
+{
+ printf("%s : A thermal monitoring engine based on notifications\n", cmd);
+ printf("Usage: %s [options]\n", cmd);
+ printf("\t-h, --help\t\tthis help\n");
+ printf("\t-d, --daemonize\n");
+ printf("\t-l <level>, --loglevel <level>\tlog level: ");
+ printf("DEBUG, INFO, NOTICE, WARN, ERROR\n");
+ printf("\t-s, --syslog\t\toutput to syslog\n");
+ printf("\n");
+ exit(0);
+}
+
+static int options_init(int argc, char *argv[], struct options *options)
+{
+ int opt;
+
+ struct option long_options[] = {
+ { "help", no_argument, NULL, 'h' },
+ { "daemonize", no_argument, NULL, 'd' },
+ { "syslog", no_argument, NULL, 's' },
+ { "loglevel", required_argument, NULL, 'l' },
+ { 0, 0, 0, 0 }
+ };
+
+ while (1) {
+
+ int optindex = 0;
+
+ opt = getopt_long(argc, argv, "l:dhs", long_options, &optindex);
+ if (opt == -1)
+ break;
+
+ switch (opt) {
+ case 'l':
+ options->loglevel = log_str2level(optarg);
+ break;
+ case 'd':
+ options->daemonize = 1;
+ break;
+ case 's':
+ options->logopt = TO_SYSLOG;
+ break;
+ case 'h':
+ usage(basename(argv[0]));
+ break;
+ default: /* '?' */
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+enum {
+ THERMAL_ENGINE_SUCCESS = 0,
+ THERMAL_ENGINE_OPTION_ERROR,
+ THERMAL_ENGINE_DAEMON_ERROR,
+ THERMAL_ENGINE_LOG_ERROR,
+ THERMAL_ENGINE_THERMAL_ERROR,
+ THERMAL_ENGINE_MAINLOOP_ERROR,
+};
+
+int main(int argc, char *argv[])
+{
+ struct thermal_data td;
+ struct options options = {
+ .loglevel = LOG_INFO,
+ .logopt = TO_STDOUT,
+ };
+
+ if (options_init(argc, argv, &options)) {
+ ERROR("Usage: %s --help\n", argv[0]);
+ return THERMAL_ENGINE_OPTION_ERROR;
+ }
+
+ if (options.daemonize && daemon(0, 0)) {
+ ERROR("Failed to daemonize: %p\n");
+ return THERMAL_ENGINE_DAEMON_ERROR;
+ }
+
+ if (log_init(options.loglevel, basename(argv[0]), options.logopt)) {
+ ERROR("Failed to initialize logging facility\n");
+ return THERMAL_ENGINE_LOG_ERROR;
+ }
+
+ td.th = thermal_init(&ops);
+ if (!td.th) {
+ ERROR("Failed to initialize the thermal library\n");
+ return THERMAL_ENGINE_THERMAL_ERROR;
+ }
+
+ td.tz = thermal_zone_discover(td.th);
+ if (!td.tz) {
+ ERROR("No thermal zone available\n");
+ return THERMAL_ENGINE_THERMAL_ERROR;
+ }
+
+ for_each_thermal_zone(td.tz, show_tz, td.th);
+
+ if (mainloop_init()) {
+ ERROR("Failed to initialize the mainloop\n");
+ return THERMAL_ENGINE_MAINLOOP_ERROR;
+ }
+
+ if (mainloop_add(thermal_events_fd(td.th), thermal_event, &td)) {
+ ERROR("Failed to setup the mainloop\n");
+ return THERMAL_ENGINE_MAINLOOP_ERROR;
+ }
+
+ INFO("Waiting for thermal events ...\n");
+
+ if (mainloop(-1)) {
+ ERROR("Mainloop failed\n");
+ return THERMAL_ENGINE_MAINLOOP_ERROR;
+ }
+
+ return THERMAL_ENGINE_SUCCESS;
+}
diff --git a/tools/thermal/thermometer/Build b/tools/thermal/thermometer/Build
new file mode 100644
index 000000000000..1b96c159c3c8
--- /dev/null
+++ b/tools/thermal/thermometer/Build
@@ -0,0 +1 @@
+thermometer-y += thermometer.o
diff --git a/tools/thermal/thermometer/Makefile b/tools/thermal/thermometer/Makefile
new file mode 100644
index 000000000000..d8f8bc82fe3b
--- /dev/null
+++ b/tools/thermal/thermometer/Makefile
@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+# Makefile for cgroup tools
+
+ifeq ($(srctree),)
+srctree := $(patsubst %/,%,$(dir $(CURDIR)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+srctree := $(patsubst %/,%,$(dir $(srctree)))
+# $(info Determined 'srctree' to be $(srctree))
+endif
+
+CFLAGS = -Wall -Wextra
+CFLAGS += -I$(srctree)/tools/thermal/lib
+
+LDFLAGS = -L$(srctree)/tools/thermal/lib
+LDFLAGS += -lthermal_tools
+LDFLAGS += -lconfig
+
+VERSION = 0.0.1
+TARGET=thermometer
+
+all: $(TARGET)
+%: %.c
+ $(CC) $(CFLAGS) -D VERSION=\"$(VERSION)\" -o $@ $^ $(LDFLAGS)
+
+clean:
+ $(RM) $(TARGET)
diff --git a/tools/thermal/thermometer/thermometer.8 b/tools/thermal/thermometer/thermometer.8
new file mode 100644
index 000000000000..d090fbca4cba
--- /dev/null
+++ b/tools/thermal/thermometer/thermometer.8
@@ -0,0 +1,92 @@
+.TH THERMOMETER 8
+# SPDX-License-Identifier: GPL-2.0
+.SH NAME
+\fBthermometer\fP - A thermal profiling tool
+
+.SH SYNOPSIS
+.ft B
+.B thermometer
+.RB [ options ]
+.RB [ command ]
+.br
+.SH DESCRIPTION
+\fBthermometer \fP captures the thermal zones temperature at a
+specified sampling period. It is optimized to reduce as much as
+possible the overhead while doing the temperature acquisition in order
+to prevent disrupting the running application we may want to profile.
+
+This low overhead also allows a high rate sampling for the temperature
+which could be necessary to spot overshots and undershots.
+
+If no configuration file is specified, then all the thermal zones will
+be monitored at 4Hz, so every 250ms. A configuration file specifies
+the thermal zone names and the desired sampling period. A thermal zone
+name can be a regular expression to specify a group of thermal zone.
+
+The sampling of the different thermal zones will be written into
+separate files with the thermal zone name. It is possible to specify a
+postfix to identify them for example for a specific scenario. The
+output directory can be specified in addition.
+
+Without any parameters, \fBthermometer \fP captures all the thermal
+zone temperatures every 250ms and write to the current directory the
+captured files postfixed with the current date.
+
+If a running \fBduration\fP is specified or a \fBcommand\fP, the
+capture ends at the end of the duration if the command did not
+finished before. The \fBduration\fP can be specified alone as well as
+the \fBcommand\fP. If none is specified, the capture will continue
+indefinitively until interrupted by \fBSIGINT\fP or \fBSIGQUIT\fP.
+.PP
+
+.SS Options
+.PP
+The \fB-h, --help\fP option shows a short usage help
+.PP
+The \fB-o <dir>, --output <dir>\fP option defines the output directory to put the
+sampling files
+.PP
+The \fB-c <config>, --config <config>\fP option specifies the configuration file to use
+.PP
+The \fB-d <seconds>, --duration <seconds>\fP option specifies the duration of the capture
+.PP
+The \fB-l <loglevel>, --loglevel <loglevel>\fP option sets the loglevel [DEBUG,INFO,NOTICE,WARN,ERROR]
+.PP
+The \fB-p <string>, --postfix <string>\fP option appends \fBstring\fP at the end of the capture filenames
+.PP
+The \fB-s, --syslog\fP option sets the output to syslog, default is \fBstdout\fP
+.PP
+The \fB-w, --overwrite\fP overwrites the output files if they exist
+.PP
+
+.PP
+
+.SS "Exit status:"
+.TP
+0
+if OK,
+.TP
+1
+Error with the options specified as parameters
+.TP
+2
+Error when configuring the logging facility
+.TP
+3
+Error when configuring the time
+.TP
+4
+Error in the initialization routine
+.TP
+5
+Error during the runtime
+
+.SH Capture file format
+
+Every file contains two columns. The first one is the uptime timestamp
+in order to find a point in time since the system started up if there
+is any thermal event. The second one is the temperature in milli
+degree. The first line contains the label of each column.
+
+.SH AUTHOR
+Daniel Lezcano <daniel.lezcano@kernel.org>
diff --git a/tools/thermal/thermometer/thermometer.c b/tools/thermal/thermometer/thermometer.c
new file mode 100644
index 000000000000..1a87a0a77f9f
--- /dev/null
+++ b/tools/thermal/thermometer/thermometer.c
@@ -0,0 +1,572 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2022, Linaro Ltd - Daniel Lezcano <daniel.lezcano@linaro.org>
+#define _GNU_SOURCE
+#include <dirent.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <regex.h>
+#include <signal.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <sys/signalfd.h>
+#include <sys/timerfd.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <time.h>
+#include <unistd.h>
+#include <linux/thermal.h>
+
+#include <libconfig.h>
+#include "thermal-tools.h"
+
+#define CLASS_THERMAL "/sys/class/thermal"
+
+enum {
+ THERMOMETER_SUCCESS = 0,
+ THERMOMETER_OPTION_ERROR,
+ THERMOMETER_LOG_ERROR,
+ THERMOMETER_CONFIG_ERROR,
+ THERMOMETER_TIME_ERROR,
+ THERMOMETER_INIT_ERROR,
+ THERMOMETER_RUNTIME_ERROR
+};
+
+struct options {
+ int loglvl;
+ int logopt;
+ int overwrite;
+ int duration;
+ const char *config;
+ char postfix[PATH_MAX];
+ char output[PATH_MAX];
+};
+
+struct tz_regex {
+ regex_t regex;
+ int polling;
+};
+
+struct configuration {
+ struct tz_regex *tz_regex;
+ int nr_tz_regex;
+
+};
+
+struct tz {
+ FILE *file_out;
+ int fd_temp;
+ int fd_timer;
+ int polling;
+ const char *name;
+};
+
+struct thermometer {
+ struct tz *tz;
+ int nr_tz;
+};
+
+static struct tz_regex *configuration_tz_match(const char *expr,
+ struct configuration *config)
+{
+ int i;
+
+ for (i = 0; i < config->nr_tz_regex; i++) {
+
+ if (!regexec(&config->tz_regex[i].regex, expr, 0, NULL, 0))
+ return &config->tz_regex[i];
+ }
+
+ return NULL;
+}
+
+static int configuration_default_init(struct configuration *config)
+{
+ config->tz_regex = realloc(config->tz_regex, sizeof(*config->tz_regex) *
+ (config->nr_tz_regex + 1));
+
+ if (regcomp(&config->tz_regex[config->nr_tz_regex].regex, ".*",
+ REG_NOSUB | REG_EXTENDED)) {
+ ERROR("Invalid regular expression\n");
+ return -1;
+ }
+
+ config->tz_regex[config->nr_tz_regex].polling = 250;
+ config->nr_tz_regex = 1;
+
+ return 0;
+}
+
+static int configuration_init(const char *path, struct configuration *config)
+{
+ config_t cfg;
+
+ config_setting_t *tz;
+ int i, length;
+
+ if (path && access(path, F_OK)) {
+ ERROR("'%s' is not accessible\n", path);
+ return -1;
+ }
+
+ if (!path && !config->nr_tz_regex) {
+ INFO("No thermal zones configured, using wildcard for all of them\n");
+ return configuration_default_init(config);
+ }
+
+ config_init(&cfg);
+
+ if (!config_read_file(&cfg, path)) {
+ ERROR("Failed to parse %s:%d - %s\n", config_error_file(&cfg),
+ config_error_line(&cfg), config_error_text(&cfg));
+
+ return -1;
+ }
+
+ tz = config_lookup(&cfg, "thermal-zones");
+ if (!tz) {
+ ERROR("No thermal zone configured to be monitored\n");
+ return -1;
+ }
+
+ length = config_setting_length(tz);
+
+ INFO("Found %d thermal zone(s) regular expression\n", length);
+
+ for (i = 0; i < length; i++) {
+
+ config_setting_t *node;
+ const char *name;
+ int polling;
+
+ node = config_setting_get_elem(tz, i);
+ if (!node) {
+ ERROR("Missing node name '%d'\n", i);
+ return -1;
+ }
+
+ if (!config_setting_lookup_string(node, "name", &name)) {
+ ERROR("Thermal zone name not found\n");
+ return -1;
+ }
+
+ if (!config_setting_lookup_int(node, "polling", &polling)) {
+ ERROR("Polling value not found");
+ return -1;
+ }
+
+ config->tz_regex = realloc(config->tz_regex, sizeof(*config->tz_regex) *
+ (config->nr_tz_regex + 1));
+
+ if (regcomp(&config->tz_regex[config->nr_tz_regex].regex, name,
+ REG_NOSUB | REG_EXTENDED)) {
+ ERROR("Invalid regular expression '%s'\n", name);
+ continue;
+ }
+
+ config->tz_regex[config->nr_tz_regex].polling = polling;
+ config->nr_tz_regex++;
+
+ INFO("Thermal zone regular expression '%s' with polling %d\n",
+ name, polling);
+ }
+
+ return 0;
+}
+
+static void usage(const char *cmd)
+{
+ printf("%s Version: %s\n", cmd, VERSION);
+ printf("Usage: %s [options]\n", cmd);
+ printf("\t-h, --help\t\tthis help\n");
+ printf("\t-o, --output <dir>\toutput directory for temperature capture\n");
+ printf("\t-c, --config <file>\tconfiguration file\n");
+ printf("\t-d, --duration <seconds>\tcapture duration\n");
+ printf("\t-l, --loglevel <level>\tlog level: ");
+ printf("DEBUG, INFO, NOTICE, WARN, ERROR\n");
+ printf("\t-p, --postfix <string>\tpostfix to be happened at the end of the files\n");
+ printf("\t-s, --syslog\t\toutput to syslog\n");
+ printf("\t-w, --overwrite\t\toverwrite the temperature capture files if they exist\n");
+ printf("\n");
+ exit(0);
+}
+
+static int options_init(int argc, char *argv[], struct options *options)
+{
+ int opt;
+ time_t now = time(NULL);
+
+ struct option long_options[] = {
+ { "help", no_argument, NULL, 'h' },
+ { "config", required_argument, NULL, 'c' },
+ { "duration", required_argument, NULL, 'd' },
+ { "loglevel", required_argument, NULL, 'l' },
+ { "postfix", required_argument, NULL, 'p' },
+ { "output", required_argument, NULL, 'o' },
+ { "syslog", required_argument, NULL, 's' },
+ { "overwrite", no_argument, NULL, 'w' },
+ { 0, 0, 0, 0 }
+ };
+
+ strftime(options->postfix, sizeof(options->postfix),
+ "-%Y-%m-%d_%H:%M:%S", gmtime(&now));
+
+ while (1) {
+
+ int optindex = 0;
+
+ opt = getopt_long(argc, argv, "ho:c:d:l:p:sw", long_options, &optindex);
+ if (opt == -1)
+ break;
+
+ switch (opt) {
+ case 'c':
+ options->config = optarg;
+ break;
+ case 'd':
+ options->duration = atoi(optarg) * 1000;
+ break;
+ case 'l':
+ options->loglvl = log_str2level(optarg);
+ break;
+ case 'h':
+ usage(basename(argv[0]));
+ break;
+ case 'p':
+ strcpy(options->postfix, optarg);
+ break;
+ case 'o':
+ strcpy(options->output, optarg);
+ break;
+ case 's':
+ options->logopt = TO_SYSLOG;
+ break;
+ case 'w':
+ options->overwrite = 1;
+ break;
+ default: /* '?' */
+ ERROR("Usage: %s --help\n", argv[0]);
+ return -1;
+ }
+ }
+
+ return 0;
+}
+
+static int thermometer_add_tz(const char *path, const char *name, int polling,
+ struct thermometer *thermometer)
+{
+ int fd;
+ char tz_path[PATH_MAX];
+
+ sprintf(tz_path, CLASS_THERMAL"/%s/temp", path);
+
+ fd = open(tz_path, O_RDONLY);
+ if (fd < 0) {
+ ERROR("Failed to open '%s': %m\n", tz_path);
+ return -1;
+ }
+
+ thermometer->tz = realloc(thermometer->tz,
+ sizeof(*thermometer->tz) * (thermometer->nr_tz + 1));
+ if (!thermometer->tz) {
+ ERROR("Failed to allocate thermometer->tz\n");
+ return -1;
+ }
+
+ thermometer->tz[thermometer->nr_tz].fd_temp = fd;
+ thermometer->tz[thermometer->nr_tz].name = strdup(name);
+ thermometer->tz[thermometer->nr_tz].polling = polling;
+ thermometer->nr_tz++;
+
+ INFO("Added thermal zone '%s->%s (polling:%d)'\n", path, name, polling);
+
+ return 0;
+}
+
+static int thermometer_init(struct configuration *config,
+ struct thermometer *thermometer)
+{
+ DIR *dir;
+ struct dirent *dirent;
+ struct tz_regex *tz_regex;
+ const char *tz_dirname = "thermal_zone";
+
+ if (mainloop_init()) {
+ ERROR("Failed to start mainloop\n");
+ return -1;
+ }
+
+ dir = opendir(CLASS_THERMAL);
+ if (!dir) {
+ ERROR("failed to open '%s'\n", CLASS_THERMAL);
+ return -1;
+ }
+
+ while ((dirent = readdir(dir))) {
+ char tz_type[THERMAL_NAME_LENGTH];
+ char tz_path[PATH_MAX];
+ FILE *tz_file;
+
+ if (strncmp(dirent->d_name, tz_dirname, strlen(tz_dirname)))
+ continue;
+
+ sprintf(tz_path, CLASS_THERMAL"/%s/type", dirent->d_name);
+
+ tz_file = fopen(tz_path, "r");
+ if (!tz_file) {
+ ERROR("Failed to open '%s': %m", tz_path);
+ continue;
+ }
+
+ fscanf(tz_file, "%s", tz_type);
+
+ fclose(tz_file);
+
+ tz_regex = configuration_tz_match(tz_type, config);
+ if (!tz_regex)
+ continue;
+
+ if (thermometer_add_tz(dirent->d_name, tz_type,
+ tz_regex->polling, thermometer))
+ continue;
+ }
+
+ closedir(dir);
+
+ return 0;
+}
+
+static int timer_temperature_callback(int fd, void *arg)
+{
+ struct tz *tz = arg;
+ char buf[16] = { 0 };
+
+ pread(tz->fd_temp, buf, sizeof(buf), 0);
+
+ fprintf(tz->file_out, "%ld %s", getuptimeofday_ms(), buf);
+
+ read(fd, buf, sizeof(buf));
+
+ return 0;
+}
+
+static int thermometer_start(struct thermometer *thermometer,
+ struct options *options)
+{
+ struct itimerspec timer_it = { 0 };
+ char *path;
+ FILE *f;
+ int i;
+
+ INFO("Capturing %d thermal zone(s) temperature...\n", thermometer->nr_tz);
+
+ if (access(options->output, F_OK) && mkdir(options->output, 0700)) {
+ ERROR("Failed to create directory '%s'\n", options->output);
+ return -1;
+ }
+
+ for (i = 0; i < thermometer->nr_tz; i++) {
+
+ asprintf(&path, "%s/%s%s", options->output,
+ thermometer->tz[i].name, options->postfix);
+
+ if (!options->overwrite && !access(path, F_OK)) {
+ ERROR("'%s' already exists\n", path);
+ return -1;
+ }
+
+ f = fopen(path, "w");
+ if (!f) {
+ ERROR("Failed to create '%s':%m\n", path);
+ return -1;
+ }
+
+ fprintf(f, "timestamp(ms) %s(°mC)\n", thermometer->tz[i].name);
+
+ thermometer->tz[i].file_out = f;
+
+ DEBUG("Created '%s' file for thermal zone '%s'\n", path, thermometer->tz[i].name);
+
+ /*
+ * Create polling timer
+ */
+ thermometer->tz[i].fd_timer = timerfd_create(CLOCK_MONOTONIC, 0);
+ if (thermometer->tz[i].fd_timer < 0) {
+ ERROR("Failed to create timer for '%s': %m\n",
+ thermometer->tz[i].name);
+ return -1;
+ }
+
+ DEBUG("Watching '%s' every %d ms\n",
+ thermometer->tz[i].name, thermometer->tz[i].polling);
+
+ timer_it.it_interval = timer_it.it_value =
+ msec_to_timespec(thermometer->tz[i].polling);
+
+ if (timerfd_settime(thermometer->tz[i].fd_timer, 0,
+ &timer_it, NULL) < 0)
+ return -1;
+
+ if (mainloop_add(thermometer->tz[i].fd_timer,
+ timer_temperature_callback,
+ &thermometer->tz[i]))
+ return -1;
+ }
+
+ return 0;
+}
+
+static int thermometer_execute(int argc, char *argv[], char *const envp[], pid_t *pid)
+{
+ if (!argc)
+ return 0;
+
+ *pid = fork();
+ if (*pid < 0) {
+ ERROR("Failed to fork process: %m");
+ return -1;
+ }
+
+ if (!(*pid)) {
+ execvpe(argv[0], argv, envp);
+ exit(1);
+ }
+
+ return 0;
+}
+
+static int kill_process(__maybe_unused int fd, void *arg)
+{
+ pid_t pid = *(pid_t *)arg;
+
+ if (kill(pid, SIGTERM))
+ ERROR("Failed to send SIGTERM signal to '%d': %p\n", pid);
+ else if (waitpid(pid, NULL, 0))
+ ERROR("Failed to wait pid '%d': %p\n", pid);
+
+ mainloop_exit();
+
+ return 0;
+}
+
+static int exit_mainloop(__maybe_unused int fd, __maybe_unused void *arg)
+{
+ mainloop_exit();
+ return 0;
+}
+
+static int thermometer_wait(struct options *options, pid_t pid)
+{
+ int fd;
+ sigset_t mask;
+
+ /*
+ * If there is a duration specified, we will exit the mainloop
+ * and gracefully close all the files which will flush the
+ * file system cache
+ */
+ if (options->duration) {
+ struct itimerspec timer_it = { 0 };
+
+ timer_it.it_value = msec_to_timespec(options->duration);
+
+ fd = timerfd_create(CLOCK_MONOTONIC, 0);
+ if (fd < 0) {
+ ERROR("Failed to create duration timer: %m\n");
+ return -1;
+ }
+
+ if (timerfd_settime(fd, 0, &timer_it, NULL)) {
+ ERROR("Failed to set timer time: %m\n");
+ return -1;
+ }
+
+ if (mainloop_add(fd, pid < 0 ? exit_mainloop : kill_process, &pid)) {
+ ERROR("Failed to set timer exit mainloop callback\n");
+ return -1;
+ }
+ }
+
+ /*
+ * We want to catch any keyboard interrupt, as well as child
+ * signals if any in order to exit properly
+ */
+ sigemptyset(&mask);
+ sigaddset(&mask, SIGINT);
+ sigaddset(&mask, SIGQUIT);
+ sigaddset(&mask, SIGCHLD);
+
+ if (sigprocmask(SIG_BLOCK, &mask, NULL)) {
+ ERROR("Failed to set sigprocmask: %m\n");
+ return -1;
+ }
+
+ fd = signalfd(-1, &mask, 0);
+ if (fd < 0) {
+ ERROR("Failed to set the signalfd: %m\n");
+ return -1;
+ }
+
+ if (mainloop_add(fd, exit_mainloop, NULL)) {
+ ERROR("Failed to set timer exit mainloop callback\n");
+ return -1;
+ }
+
+ return mainloop(-1);
+}
+
+static int thermometer_stop(struct thermometer *thermometer)
+{
+ int i;
+
+ INFO("Closing/flushing output files\n");
+
+ for (i = 0; i < thermometer->nr_tz; i++)
+ fclose(thermometer->tz[i].file_out);
+
+ return 0;
+}
+
+int main(int argc, char *argv[], char *const envp[])
+{
+ struct options options = {
+ .loglvl = LOG_DEBUG,
+ .logopt = TO_STDOUT,
+ .output = ".",
+ };
+ struct configuration config = { 0 };
+ struct thermometer thermometer = { 0 };
+
+ pid_t pid = -1;
+
+ if (options_init(argc, argv, &options))
+ return THERMOMETER_OPTION_ERROR;
+
+ if (log_init(options.loglvl, argv[0], options.logopt))
+ return THERMOMETER_LOG_ERROR;
+
+ if (configuration_init(options.config, &config))
+ return THERMOMETER_CONFIG_ERROR;
+
+ if (uptimeofday_init())
+ return THERMOMETER_TIME_ERROR;
+
+ if (thermometer_init(&config, &thermometer))
+ return THERMOMETER_INIT_ERROR;
+
+ if (thermometer_start(&thermometer, &options))
+ return THERMOMETER_RUNTIME_ERROR;
+
+ if (thermometer_execute(argc - optind, &argv[optind], envp, &pid))
+ return THERMOMETER_RUNTIME_ERROR;
+
+ if (thermometer_wait(&options, pid))
+ return THERMOMETER_RUNTIME_ERROR;
+
+ if (thermometer_stop(&thermometer))
+ return THERMOMETER_RUNTIME_ERROR;
+
+ return THERMOMETER_SUCCESS;
+}
diff --git a/tools/thermal/thermometer/thermometer.conf b/tools/thermal/thermometer/thermometer.conf
new file mode 100644
index 000000000000..02c6dab3b1b3
--- /dev/null
+++ b/tools/thermal/thermometer/thermometer.conf
@@ -0,0 +1,5 @@
+
+thermal-zones = (
+ { name = "cpu[0-9]-thermal";
+ polling = 100; }
+ )