diff options
Diffstat (limited to 'tools/testing')
464 files changed, 11775 insertions, 3546 deletions
diff --git a/tools/testing/cxl/test/cxl.c b/tools/testing/cxl/test/cxl.c index d0337c11f9ee..cc8948f49117 100644 --- a/tools/testing/cxl/test/cxl.c +++ b/tools/testing/cxl/test/cxl.c @@ -725,7 +725,7 @@ static void default_mock_decoder(struct cxl_decoder *cxld) cxld->reset = mock_decoder_reset; } -static int first_decoder(struct device *dev, void *data) +static int first_decoder(struct device *dev, const void *data) { struct cxl_decoder *cxld; diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 347c1e7b37bd..8d731bd63988 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -401,6 +401,10 @@ struct cxl_test_gen_media gen_media = { .channel = 1, .rank = 30, }, + .component_id = { 0x3, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .cme_threshold_ev_flags = 3, + .cme_count = { 33, 0, 0 }, + .sub_type = 0x2, }, }; @@ -429,6 +433,11 @@ struct cxl_test_dram dram = { .bank_group = 5, .bank = 2, .column = {0xDE, 0xAD}, + .component_id = { 0x1, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .sub_channel = 8, + .cme_threshold_ev_flags = 2, + .cvme_count = { 14, 0, 0 }, + .sub_type = 0x5, }, }; @@ -456,7 +465,10 @@ struct cxl_test_mem_module mem_module = { .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, - } + }, + /* .validity_flags = <set below> */ + .component_id = { 0x2, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .event_sub_type = 0x3, }, }; @@ -478,13 +490,18 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds, static void cxl_mock_add_event_logs(struct mock_event_store *mes) { - put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, + put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK | + CXL_GMER_VALID_COMPONENT | CXL_GMER_VALID_COMPONENT_ID_FORMAT, &gen_media.rec.media_hdr.validity_flags); put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | - CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, + CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN | CXL_DER_VALID_SUB_CHANNEL | + CXL_DER_VALID_COMPONENT | CXL_DER_VALID_COMPONENT_ID_FORMAT, &dram.rec.media_hdr.validity_flags); + put_unaligned_le16(CXL_MMER_VALID_COMPONENT | CXL_MMER_VALID_COMPONENT_ID_FORMAT, + &mem_module.rec.validity_flags); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); mes_add_event(mes, CXL_EVENT_TYPE_INFO, (struct cxl_event_record_raw *)&gen_media); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 450c7566c33f..af2594e4f35d 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -228,16 +228,16 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL"); -int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +int __wrap_cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - if (ops && ops->is_mock_dev(dev)) + if (ops && ops->is_mock_dev(cxlds->dev)) rc = 0; else - rc = cxl_dvsec_rr_decode(dev, port, info); + rc = cxl_dvsec_rr_decode(cxlds, info); put_cxl_mock_ops(index); return rc; diff --git a/tools/testing/ktest/examples/include/defaults.conf b/tools/testing/ktest/examples/include/defaults.conf index 63a1a83f4f0b..f6d8517a471e 100644 --- a/tools/testing/ktest/examples/include/defaults.conf +++ b/tools/testing/ktest/examples/include/defaults.conf @@ -46,7 +46,7 @@ CLEAR_LOG = 1 SSH_USER = root -# For accesing the machine, we will ssh to root@machine. +# For accessing the machine, we will ssh to root@machine. SSH := ssh ${SSH_USER}@${MACHINE} # Update this. The default here is ktest will ssh to the target box diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl index dacad94e2be4..8c8da966c641 100755 --- a/tools/testing/ktest/ktest.pl +++ b/tools/testing/ktest/ktest.pl @@ -1245,7 +1245,7 @@ sub __read_config { # Config variables are only active while reading the # config and can be defined anywhere. They also ignore # TEST_START and DEFAULTS, but are skipped if they are in - # on of these sections that have SKIP defined. + # one of these sections that have SKIP defined. # The save variable can be # defined multiple times and the new one simply overrides # the previous one. @@ -2419,6 +2419,11 @@ sub get_version { return if ($have_version); doprint "$make kernelrelease ... "; $version = `$make -s kernelrelease | tail -1`; + if (!length($version)) { + run_command "$make allnoconfig" or return 0; + doprint "$make kernelrelease ... "; + $version = `$make -s kernelrelease | tail -1`; + } chomp($version); doprint "$version\n"; $have_version = 1; @@ -2960,8 +2965,6 @@ sub run_bisect_test { my $failed = 0; my $result; - my $output; - my $ret; $in_bisect = 1; diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index b3b00269a52a..b0049be00c70 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -38,9 +38,6 @@ CONFIG_IWLWIFI=y CONFIG_DAMON=y CONFIG_DAMON_VADDR=y CONFIG_DAMON_PADDR=y -CONFIG_DEBUG_FS=y -CONFIG_DAMON_DBGFS=y -CONFIG_DAMON_DBGFS_DEPRECATED=y CONFIG_REGMAP_BUILD=y diff --git a/tools/testing/kunit/kunit.py b/tools/testing/kunit/kunit.py index 676fa99a8b19..7f9ae55fd6d5 100755 --- a/tools/testing/kunit/kunit.py +++ b/tools/testing/kunit/kunit.py @@ -312,7 +312,16 @@ def massage_argv(argv: Sequence[str]) -> Sequence[str]: return list(map(massage_arg, argv)) def get_default_jobs() -> int: - return len(os.sched_getaffinity(0)) + if sys.version_info >= (3, 13): + if (ncpu := os.process_cpu_count()) is not None: + return ncpu + raise RuntimeError("os.process_cpu_count() returned None") + # See https://github.com/python/cpython/blob/b61fece/Lib/os.py#L1175-L1186. + if sys.platform != "darwin": + return len(os.sched_getaffinity(0)) + if (ncpu := os.cpu_count()) is not None: + return ncpu + raise RuntimeError("os.cpu_count() returned None") def add_common_opts(parser: argparse.ArgumentParser) -> None: parser.add_argument('--build_dir', diff --git a/tools/testing/kunit/kunit_kernel.py b/tools/testing/kunit/kunit_kernel.py index e76d7894b6c5..d30f90eae9a4 100644 --- a/tools/testing/kunit/kunit_kernel.py +++ b/tools/testing/kunit/kunit_kernel.py @@ -125,6 +125,9 @@ class LinuxSourceTreeOperationsQemu(LinuxSourceTreeOperations): '-append', ' '.join(params + [self._kernel_command_line]), '-no-reboot', '-nographic', + '-accel', 'kvm', + '-accel', 'hvf', + '-accel', 'tcg', '-serial', self._serial] + self._extra_qemu_params # Note: shlex.join() does what we want, but requires python 3.8+. print('Running tests with:\n$', ' '.join(shlex.quote(arg) for arg in qemu_command)) diff --git a/tools/testing/kunit/qemu_configs/arm64.py b/tools/testing/kunit/qemu_configs/arm64.py index d3ff27024755..5c44d3a87e6d 100644 --- a/tools/testing/kunit/qemu_configs/arm64.py +++ b/tools/testing/kunit/qemu_configs/arm64.py @@ -9,4 +9,4 @@ CONFIG_SERIAL_AMBA_PL011_CONSOLE=y''', qemu_arch='aarch64', kernel_path='arch/arm64/boot/Image.gz', kernel_command_line='console=ttyAMA0', - extra_qemu_params=['-machine', 'virt', '-cpu', 'max,pauth-impdef=on']) + extra_qemu_params=['-machine', 'virt', '-cpu', 'max']) diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index cffaf2245d4f..eaff1b036989 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -227,6 +227,7 @@ static void *load_creator(void *ptr) unsigned long index = (3 << RADIX_TREE_MAP_SHIFT) - (1 << order); item_insert_order(tree, index, order); + xa_set_mark(tree, index, XA_MARK_1); item_delete_rcu(tree, index); } } @@ -242,8 +243,11 @@ static void *load_worker(void *ptr) rcu_register_thread(); while (!stop_iteration) { + unsigned long find_index = (2 << RADIX_TREE_MAP_SHIFT) + 1; struct item *item = xa_load(ptr, index); assert(!xa_is_internal(item)); + item = xa_find(ptr, &find_index, index, XA_MARK_1); + assert(!xa_is_internal(item)); } rcu_unregister_thread(); diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile index 2401e973c359..8daac70c2f9d 100644 --- a/tools/testing/selftests/Makefile +++ b/tools/testing/selftests/Makefile @@ -18,6 +18,7 @@ TARGETS += devices/error_logs TARGETS += devices/probe TARGETS += dmabuf-heaps TARGETS += drivers/dma-buf +TARGETS += drivers/ntsync TARGETS += drivers/s390x/uvdevice TARGETS += drivers/net TARGETS += drivers/net/bonding @@ -72,6 +73,7 @@ TARGETS += net/packetdrill TARGETS += net/rds TARGETS += net/tcp_ao TARGETS += nsfs +TARGETS += pci_endpoint TARGETS += pcie_bwctrl TARGETS += perf_events TARGETS += pidfd diff --git a/tools/testing/selftests/acct/acct_syscall.c b/tools/testing/selftests/acct/acct_syscall.c index e44e8fe1f4a3..87c044fb9293 100644 --- a/tools/testing/selftests/acct/acct_syscall.c +++ b/tools/testing/selftests/acct/acct_syscall.c @@ -24,7 +24,7 @@ int main(void) // Check if test is run a root if (geteuid()) { - ksft_test_result_skip("This test needs root to run!\n"); + ksft_exit_skip("This test needs root to run!\n"); return 1; } diff --git a/tools/testing/selftests/arm64/fp/kernel-test.c b/tools/testing/selftests/arm64/fp/kernel-test.c index 859345379044..348e8bef62c7 100644 --- a/tools/testing/selftests/arm64/fp/kernel-test.c +++ b/tools/testing/selftests/arm64/fp/kernel-test.c @@ -46,8 +46,7 @@ static void handle_kick_signal(int sig, siginfo_t *info, void *context) } static char *drivers[] = { - "crct10dif-arm64-ce", - /* "crct10dif-arm64-neon", - Same priority as generic */ + "crct10dif-arm64", "sha1-ce", "sha224-arm64", "sha224-arm64-neon", diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index e9c377001f93..e2a2c46c008b 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -18,7 +18,6 @@ feature urandom_read test_sockmap test_lirc_mode2_user -test_flow_dissector flow_dissector_load test_tcpnotify_user test_libbpf diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 0a016cd71cba..87551628e112 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -41,7 +41,7 @@ srctree := $(patsubst %/,%,$(dir $(srctree))) srctree := $(patsubst %/,%,$(dir $(srctree))) endif -CFLAGS += -g $(OPT_FLAGS) -rdynamic \ +CFLAGS += -g $(OPT_FLAGS) -rdynamic -std=gnu11 \ -Wall -Werror -fno-omit-frame-pointer \ $(GENFLAGS) $(SAN_CFLAGS) $(LIBELF_CFLAGS) \ -I$(CURDIR) -I$(INCLUDE_DIR) -I$(GENDIR) -I$(LIBDIR) \ @@ -54,21 +54,6 @@ PCAP_LIBS := $(shell $(PKG_CONFIG) --libs libpcap 2>/dev/null) LDLIBS += $(PCAP_LIBS) CFLAGS += $(PCAP_CFLAGS) -# The following tests perform type punning and they may break strict -# aliasing rules, which are exploited by both GCC and clang by default -# while optimizing. This can lead to broken programs. -progs/bind4_prog.c-CFLAGS := -fno-strict-aliasing -progs/bind6_prog.c-CFLAGS := -fno-strict-aliasing -progs/dynptr_fail.c-CFLAGS := -fno-strict-aliasing -progs/linked_list_fail.c-CFLAGS := -fno-strict-aliasing -progs/map_kptr_fail.c-CFLAGS := -fno-strict-aliasing -progs/syscall.c-CFLAGS := -fno-strict-aliasing -progs/test_pkt_md_access.c-CFLAGS := -fno-strict-aliasing -progs/test_sk_lookup.c-CFLAGS := -fno-strict-aliasing -progs/timer_crash.c-CFLAGS := -fno-strict-aliasing -progs/test_global_func9.c-CFLAGS := -fno-strict-aliasing -progs/verifier_nocsr.c-CFLAGS := -fno-strict-aliasing - # Some utility functions use LLVM libraries jit_disasm_helpers.c-CFLAGS = $(LLVM_CFLAGS) @@ -103,18 +88,6 @@ progs/btf_dump_test_case_packing.c-bpf_gcc-CFLAGS := -Wno-error progs/btf_dump_test_case_padding.c-bpf_gcc-CFLAGS := -Wno-error progs/btf_dump_test_case_syntax.c-bpf_gcc-CFLAGS := -Wno-error -# The following tests do type-punning, via the __imm_insn macro, from -# `struct bpf_insn' to long and then uses the value. This triggers an -# "is used uninitialized" warning in GCC due to strict-aliasing -# rules. -progs/verifier_ref_tracking.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_unpriv.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_cgroup_storage.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_ld_ind.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_map_ret_val.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_spill_fill.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_subprog_precision.c-bpf_gcc-CFLAGS := -fno-strict-aliasing -progs/verifier_uninit.c-bpf_gcc-CFLAGS := -fno-strict-aliasing endif ifneq ($(CLANG_CPUV4),) @@ -127,12 +100,10 @@ TEST_FILES = xsk_prereqs.sh $(wildcard progs/btf_dump_test_case_*.c) # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ - test_xdp_redirect.sh \ test_xdp_redirect_multi.sh \ test_tunnel.sh \ test_lwt_seg6local.sh \ test_lirc_mode2.sh \ - test_flow_dissector.sh \ test_xdp_vlan_mode_generic.sh \ test_xdp_vlan_mode_native.sh \ test_lwt_ip_encap.sh \ @@ -150,17 +121,16 @@ TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh ima_setup.sh verify_sig_setup.sh \ test_xdp_vlan.sh test_bpftool.py +TEST_KMODS := bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko +TEST_KMOD_TARGETS = $(addprefix $(OUTPUT)/,$(TEST_KMODS)) + # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = \ bench \ - bpf_testmod.ko \ - bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko \ - bpf_test_no_cfi.ko \ flow_dissector_load \ runqslower \ test_cpp \ - test_flow_dissector \ test_lirc_mode2_user \ veristat \ xdp_features \ @@ -183,8 +153,9 @@ override define CLEAN $(Q)$(RM) -r $(TEST_GEN_PROGS) $(Q)$(RM) -r $(TEST_GEN_PROGS_EXTENDED) $(Q)$(RM) -r $(TEST_GEN_FILES) + $(Q)$(RM) -r $(TEST_KMODS) $(Q)$(RM) -r $(EXTRA_CLEAN) - $(Q)$(MAKE) -C bpf_testmod clean + $(Q)$(MAKE) -C test_kmods clean $(Q)$(MAKE) docs-clean endef @@ -202,9 +173,9 @@ ifeq ($(shell expr $(MAKE_VERSION) \>= 4.4), 1) $(let OUTPUT,$(OUTPUT)/,\ $(eval include ../../../build/Makefile.feature)) else -OUTPUT := $(OUTPUT)/ +override OUTPUT := $(OUTPUT)/ $(eval include ../../../build/Makefile.feature) -OUTPUT := $(patsubst %/,%,$(OUTPUT)) +override OUTPUT := $(patsubst %/,%,$(OUTPUT)) endif endif @@ -250,7 +221,7 @@ endif # to build individual tests. # NOTE: Semicolon at the end is critical to override lib.mk's default static # rule for binaries. -$(notdir $(TEST_GEN_PROGS) \ +$(notdir $(TEST_GEN_PROGS) $(TEST_KMODS) \ $(TEST_GEN_PROGS_EXTENDED)): %: $(OUTPUT)/% ; # sort removes libbpf duplicates when not cross-building @@ -304,37 +275,19 @@ $(OUTPUT)/sign-file: ../../../../scripts/sign-file.c $< -o $@ \ $(shell $(PKG_CONFIG) --libs libcrypto 2> /dev/null || echo -lcrypto) -$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch]) - $(call msg,MOD,,$@) - $(Q)$(RM) bpf_testmod/bpf_testmod.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_testmod \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ - EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_testmod/bpf_testmod.ko $@ - -$(OUTPUT)/bpf_test_no_cfi.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_no_cfi/Makefile bpf_test_no_cfi/*.[ch]) - $(call msg,MOD,,$@) - $(Q)$(RM) bpf_test_no_cfi/bpf_test_no_cfi.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_test_no_cfi \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ +# This should really be a grouped target, but make versions before 4.3 don't +# support that for regular rules. However, pattern matching rules are implicitly +# treated as grouped even with older versions of make, so as a workaround, the +# subst() turns the rule into a pattern matching rule +$(addprefix test_kmods/,$(subst .ko,%ko,$(TEST_KMODS))): $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard test_kmods/Makefile test_kmods/*.[ch]) + $(Q)$(RM) test_kmods/*.ko test_kmods/*.mod.o # force re-compilation + $(Q)$(MAKE) $(submake_extras) -C test_kmods \ + RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_test_no_cfi/bpf_test_no_cfi.ko $@ -$(OUTPUT)/bpf_test_modorder_x.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_x/Makefile bpf_test_modorder_x/*.[ch]) +$(TEST_KMOD_TARGETS): $(addprefix test_kmods/,$(TEST_KMODS)) $(call msg,MOD,,$@) - $(Q)$(RM) bpf_test_modorder_x/bpf_test_modorder_x.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_test_modorder_x \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ - EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_test_modorder_x/bpf_test_modorder_x.ko $@ - -$(OUTPUT)/bpf_test_modorder_y.ko: $(VMLINUX_BTF) $(RESOLVE_BTFIDS) $(wildcard bpf_test_modorder_y/Makefile bpf_test_modorder_y/*.[ch]) - $(call msg,MOD,,$@) - $(Q)$(RM) bpf_test_modorder_y/bpf_test_modorder_y.ko # force re-compilation - $(Q)$(MAKE) $(submake_extras) -C bpf_test_modorder_y \ - RESOLVE_BTFIDS=$(RESOLVE_BTFIDS) \ - EXTRA_CFLAGS='' EXTRA_LDFLAGS='' - $(Q)cp bpf_test_modorder_y/bpf_test_modorder_y.ko $@ + $(Q)cp test_kmods/$(@F) $@ DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool @@ -479,10 +432,10 @@ $(shell $(1) $(2) -dM -E - </dev/null | grep -E 'MIPS(EL|EB)|_MIPS_SZ(PTR|LONG) endef # Determine target endianness. -IS_LITTLE_ENDIAN = $(shell $(CC) -dM -E - </dev/null | \ +IS_LITTLE_ENDIAN := $(shell $(CC) -dM -E - </dev/null | \ grep 'define __BYTE_ORDER__ __ORDER_LITTLE_ENDIAN__') -MENDIAN=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) -BPF_TARGET_ENDIAN=$(if $(IS_LITTLE_ENDIAN),--target=bpfel,--target=bpfeb) +MENDIAN:=$(if $(IS_LITTLE_ENDIAN),-mlittle-endian,-mbig-endian) +BPF_TARGET_ENDIAN:=$(if $(IS_LITTLE_ENDIAN),--target=bpfel,--target=bpfeb) ifneq ($(CROSS_COMPILE),) CLANG_TARGET_ARCH = --target=$(notdir $(CROSS_COMPILE:%-=%)) @@ -492,6 +445,8 @@ CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH)) BPF_CFLAGS = -g -Wall -Werror -D__TARGET_ARCH_$(SRCARCH) $(MENDIAN) \ -I$(INCLUDE_DIR) -I$(CURDIR) -I$(APIDIR) \ -I$(abspath $(OUTPUT)/../usr/include) \ + -std=gnu11 \ + -fno-strict-aliasing \ -Wno-compare-distinct-pointer-types # TODO: enable me -Wsign-compare @@ -759,14 +714,12 @@ TRUNNER_EXTRA_SOURCES := test_progs.c \ json_writer.c \ flow_dissector_load.h \ ip_check_defrag_frags.h -TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ - $(OUTPUT)/bpf_test_no_cfi.ko \ - $(OUTPUT)/bpf_test_modorder_x.ko \ - $(OUTPUT)/bpf_test_modorder_y.ko \ +TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ $(OUTPUT)/liburandom_read.so \ $(OUTPUT)/xdp_synproxy \ $(OUTPUT)/sign-file \ $(OUTPUT)/uprobe_multi \ + $(TEST_KMOD_TARGETS) \ ima_setup.sh \ verify_sig_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) \ @@ -833,9 +786,12 @@ $(OUTPUT)/xdp_features: xdp_features.c $(OUTPUT)/network_helpers.o $(OUTPUT)/xdp $(Q)$(CC) $(CFLAGS) $(filter %.a %.o %.c,$^) $(LDLIBS) -o $@ # Make sure we are able to include and link libbpf against c++. +CXXFLAGS += $(CFLAGS) +CXXFLAGS := $(subst -D_GNU_SOURCE=,,$(CXXFLAGS)) +CXXFLAGS := $(subst -std=gnu11,-std=gnu++11,$(CXXFLAGS)) $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ) $(call msg,CXX,,$@) - $(Q)$(CXX) $(subst -D_GNU_SOURCE=,,$(CFLAGS)) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ + $(Q)$(CXX) $(CXXFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@ # Benchmark runner $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ) @@ -893,12 +849,9 @@ $(OUTPUT)/uprobe_multi: uprobe_multi.c uprobe_multi.ld EXTRA_CLEAN := $(SCRATCH_DIR) $(HOST_SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ - feature bpftool \ + feature bpftool $(TEST_KMOD_TARGETS) \ $(addprefix $(OUTPUT)/,*.o *.d *.skel.h *.lskel.h *.subskel.h \ - no_alu32 cpuv4 bpf_gcc bpf_testmod.ko \ - bpf_test_no_cfi.ko \ - bpf_test_modorder_x.ko \ - bpf_test_modorder_y.ko \ + no_alu32 cpuv4 bpf_gcc \ liburandom_read.so) \ $(OUTPUT)/FEATURE-DUMP.selftests diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs index eb6a4fea8c79..f7f9e7088bb3 100644 --- a/tools/testing/selftests/bpf/Makefile.docs +++ b/tools/testing/selftests/bpf/Makefile.docs @@ -7,12 +7,6 @@ INSTALL ?= install RM ?= rm -f RMDIR ?= rmdir --ignore-fail-on-non-empty -ifeq ($(V),1) - Q = -else - Q = @ -endif - prefix ?= /usr/local mandir ?= $(prefix)/man man2dir = $(mandir)/man2 diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile deleted file mode 100644 index 40b25b98ad1b..000000000000 --- a/tools/testing/selftests/bpf/bpf_test_modorder_x/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_test_modorder_x.ko - -obj-m += bpf_test_modorder_x.o - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean - diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile b/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile deleted file mode 100644 index 52c3ab9d84e2..000000000000 --- a/tools/testing/selftests/bpf/bpf_test_modorder_y/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_test_modorder_y.ko - -obj-m += bpf_test_modorder_y.o - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean - diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile b/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile deleted file mode 100644 index ed5143b79edf..000000000000 --- a/tools/testing/selftests/bpf/bpf_test_no_cfi/Makefile +++ /dev/null @@ -1,19 +0,0 @@ -BPF_TEST_NO_CFI_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TEST_NO_CFI_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_test_no_cfi.ko - -obj-m += bpf_test_no_cfi.o - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TEST_NO_CFI_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TEST_NO_CFI_DIR) clean - diff --git a/tools/testing/selftests/bpf/bpf_testmod/Makefile b/tools/testing/selftests/bpf/bpf_testmod/Makefile deleted file mode 100644 index 15cb36c4483a..000000000000 --- a/tools/testing/selftests/bpf/bpf_testmod/Makefile +++ /dev/null @@ -1,20 +0,0 @@ -BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) - -ifeq ($(V),1) -Q = -else -Q = @ -endif - -MODULES = bpf_testmod.ko - -obj-m += bpf_testmod.o -CFLAGS_bpf_testmod.o = -I$(src) - -all: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules - -clean: - +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean - diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 4ca84c8d9116..c378d5d07e02 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -58,6 +58,7 @@ CONFIG_MPLS=y CONFIG_MPLS_IPTUNNEL=y CONFIG_MPLS_ROUTING=y CONFIG_MPTCP=y +CONFIG_NET_ACT_GACT=y CONFIG_NET_ACT_SKBMOD=y CONFIG_NET_CLS=y CONFIG_NET_CLS_ACT=y diff --git a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c index 66191ae9863c..79c3ccadb962 100644 --- a/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c +++ b/tools/testing/selftests/bpf/map_tests/map_in_map_batch_ops.c @@ -120,11 +120,12 @@ static void validate_fetch_results(int outer_map_fd, static void fetch_and_validate(int outer_map_fd, struct bpf_map_batch_opts *opts, - __u32 batch_size, bool delete_entries) + __u32 batch_size, bool delete_entries, + bool has_holes) { - __u32 *fetched_keys, *fetched_values, total_fetched = 0; - __u32 batch_key = 0, fetch_count, step_size; - int err, max_entries = OUTER_MAP_ENTRIES; + int err, max_entries = OUTER_MAP_ENTRIES - !!has_holes; + __u32 *fetched_keys, *fetched_values, total_fetched = 0, i; + __u32 batch_key = 0, fetch_count, step_size = batch_size; __u32 value_size = sizeof(__u32); /* Total entries needs to be fetched */ @@ -134,9 +135,8 @@ static void fetch_and_validate(int outer_map_fd, "Memory allocation failed for fetched_keys or fetched_values", "error=%s\n", strerror(errno)); - for (step_size = batch_size; - step_size <= max_entries; - step_size += batch_size) { + /* hash map may not always return full batch */ + for (i = 0; i < OUTER_MAP_ENTRIES; i++) { fetch_count = step_size; err = delete_entries ? bpf_map_lookup_and_delete_batch(outer_map_fd, @@ -155,6 +155,7 @@ static void fetch_and_validate(int outer_map_fd, if (err && errno == ENOSPC) { /* Fetch again with higher batch size */ total_fetched = 0; + step_size += batch_size; continue; } @@ -184,18 +185,19 @@ static void fetch_and_validate(int outer_map_fd, } static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, - enum bpf_map_type inner_map_type) + enum bpf_map_type inner_map_type, + bool has_holes) { + __u32 max_entries = OUTER_MAP_ENTRIES - !!has_holes; __u32 *outer_map_keys, *inner_map_fds; - __u32 max_entries = OUTER_MAP_ENTRIES; LIBBPF_OPTS(bpf_map_batch_opts, opts); __u32 value_size = sizeof(__u32); int batch_size[2] = {5, 10}; __u32 map_index, op_index; int outer_map_fd, ret; - outer_map_keys = calloc(max_entries, value_size); - inner_map_fds = calloc(max_entries, value_size); + outer_map_keys = calloc(OUTER_MAP_ENTRIES, value_size); + inner_map_fds = calloc(OUTER_MAP_ENTRIES, value_size); CHECK((!outer_map_keys || !inner_map_fds), "Memory allocation failed for outer_map_keys or inner_map_fds", "error=%s\n", strerror(errno)); @@ -209,6 +211,24 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, ((outer_map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS) ? 9 : 1000) - map_index; + /* This condition is only meaningful for array of maps. + * + * max_entries == OUTER_MAP_ENTRIES - 1 if it is true. Say + * max_entries is short for n, then outer_map_keys looks like: + * + * [n, n-1, ... 2, 1] + * + * We change it to + * + * [n, n-1, ... 2, 0] + * + * So it will leave key 1 as a hole. It will serve to test the + * correctness when batch on an array: a "non-exist" key might be + * actually allocated and returned from key iteration. + */ + if (has_holes) + outer_map_keys[max_entries - 1]--; + /* batch operation - map_update */ ret = bpf_map_update_batch(outer_map_fd, outer_map_keys, inner_map_fds, &max_entries, &opts); @@ -219,15 +239,17 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, /* batch operation - map_lookup */ for (op_index = 0; op_index < 2; ++op_index) fetch_and_validate(outer_map_fd, &opts, - batch_size[op_index], false); + batch_size[op_index], false, + has_holes); /* batch operation - map_lookup_delete */ if (outer_map_type == BPF_MAP_TYPE_HASH_OF_MAPS) fetch_and_validate(outer_map_fd, &opts, - max_entries, true /*delete*/); + max_entries, true /*delete*/, + has_holes); /* close all map fds */ - for (map_index = 0; map_index < max_entries; map_index++) + for (map_index = 0; map_index < OUTER_MAP_ENTRIES; map_index++) close(inner_map_fds[map_index]); close(outer_map_fd); @@ -237,16 +259,20 @@ static void _map_in_map_batch_ops(enum bpf_map_type outer_map_type, void test_map_in_map_batch_ops_array(void) { - _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, false); printf("%s:PASS with inner ARRAY map\n", __func__); - _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, false); printf("%s:PASS with inner HASH map\n", __func__); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_ARRAY, true); + printf("%s:PASS with inner ARRAY map with holes\n", __func__); + _map_in_map_batch_ops(BPF_MAP_TYPE_ARRAY_OF_MAPS, BPF_MAP_TYPE_HASH, true); + printf("%s:PASS with inner HASH map with holes\n", __func__); } void test_map_in_map_batch_ops_hash(void) { - _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY); + _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_ARRAY, false); printf("%s:PASS with inner ARRAY map\n", __func__); - _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH); + _map_in_map_batch_ops(BPF_MAP_TYPE_HASH_OF_MAPS, BPF_MAP_TYPE_HASH, false); printf("%s:PASS with inner HASH map\n", __func__); } diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c index 27784946b01b..80844a5fb1fe 100644 --- a/tools/testing/selftests/bpf/network_helpers.c +++ b/tools/testing/selftests/bpf/network_helpers.c @@ -21,7 +21,7 @@ #include <linux/limits.h> #include <linux/ip.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <netinet/tcp.h> #include <net/if.h> diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h index 5764155b6d25..ebec8a8d6f81 100644 --- a/tools/testing/selftests/bpf/network_helpers.h +++ b/tools/testing/selftests/bpf/network_helpers.h @@ -14,6 +14,7 @@ typedef __u16 __sum16; #include <linux/sockios.h> #include <linux/err.h> #include <netinet/tcp.h> +#include <netinet/udp.h> #include <bpf/bpf_endian.h> #include <net/if.h> @@ -105,6 +106,45 @@ static __u16 csum_fold(__u32 csum) return (__u16)~csum; } +static __wsum csum_partial(const void *buf, int len, __wsum sum) +{ + __u16 *p = (__u16 *)buf; + int num_u16 = len >> 1; + int i; + + for (i = 0; i < num_u16; i++) + sum += p[i]; + + return sum; +} + +static inline __sum16 build_ip_csum(struct iphdr *iph) +{ + __u32 sum = 0; + __u16 *p; + + iph->check = 0; + p = (void *)iph; + sum = csum_partial(p, iph->ihl << 2, 0); + + return csum_fold(sum); +} + +/** + * csum_tcpudp_magic - compute IP pseudo-header checksum + * + * Compute the IPv4 pseudo header checksum. The helper can take a + * accumulated sum from the transport layer to accumulate it and directly + * return the transport layer + * + * @saddr: IP source address + * @daddr: IP dest address + * @len: IP data size + * @proto: transport layer protocol + * @csum: The accumulated partial sum to add to the computation + * + * Returns the folded sum + */ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, __u32 len, __u8 proto, __wsum csum) @@ -120,6 +160,21 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, return csum_fold((__u32)s); } +/** + * csum_ipv6_magic - compute IPv6 pseudo-header checksum + * + * Compute the ipv6 pseudo header checksum. The helper can take a + * accumulated sum from the transport layer to accumulate it and directly + * return the transport layer + * + * @saddr: IPv6 source address + * @daddr: IPv6 dest address + * @len: IPv6 data size + * @proto: transport layer protocol + * @csum: The accumulated partial sum to add to the computation + * + * Returns the folded sum + */ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr, __u32 len, __u8 proto, @@ -139,6 +194,47 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, return csum_fold((__u32)s); } +/** + * build_udp_v4_csum - compute UDP checksum for UDP over IPv4 + * + * Compute the checksum to embed in UDP header, composed of the sum of IP + * pseudo-header checksum, UDP header checksum and UDP data checksum + * @iph IP header + * @udph UDP header, which must be immediately followed by UDP data + * + * Returns the total checksum + */ + +static inline __sum16 build_udp_v4_csum(const struct iphdr *iph, + const struct udphdr *udph) +{ + unsigned long sum; + + sum = csum_partial(udph, ntohs(udph->len), 0); + return csum_tcpudp_magic(iph->saddr, iph->daddr, ntohs(udph->len), + IPPROTO_UDP, sum); +} + +/** + * build_udp_v6_csum - compute UDP checksum for UDP over IPv6 + * + * Compute the checksum to embed in UDP header, composed of the sum of IPv6 + * pseudo-header checksum, UDP header checksum and UDP data checksum + * @ip6h IPv6 header + * @udph UDP header, which must be immediately followed by UDP data + * + * Returns the total checksum + */ +static inline __sum16 build_udp_v6_csum(const struct ipv6hdr *ip6h, + const struct udphdr *udph) +{ + unsigned long sum; + + sum = csum_partial(udph, ntohs(udph->len), 0); + return csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, ntohs(udph->len), + IPPROTO_UDP, sum); +} + struct tmonitor_ctx; #ifdef TRAFFIC_MONITOR diff --git a/tools/testing/selftests/bpf/prog_tests/btf_distill.c b/tools/testing/selftests/bpf/prog_tests/btf_distill.c index ca84726d5ac1..fb67ae195a73 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_distill.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_distill.c @@ -385,7 +385,7 @@ static void test_distilled_base_missing_err(void) "[2] INT 'int' size=8 bits_offset=0 nr_bits=64 encoding=SIGNED"); btf5 = btf__new_empty(); if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf")) - return; + goto cleanup; btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [1] int */ VALIDATE_RAW_BTF( btf5, @@ -478,7 +478,7 @@ static void test_distilled_base_multi_err2(void) "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED"); btf5 = btf__new_empty(); if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf")) - return; + goto cleanup; btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [1] int */ btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [2] int */ VALIDATE_RAW_BTF( @@ -601,6 +601,76 @@ cleanup: btf__free(base); } +/* If a needed composite type, which is the member of composite type + * in the split BTF, has a different size in the base BTF we wish to + * relocate with, btf__relocate() should error out. + */ +static void test_distilled_base_embedded_err(void) +{ + struct btf *btf1 = NULL, *btf2 = NULL, *btf3 = NULL, *btf4 = NULL, *btf5 = NULL; + + btf1 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf1, "empty_main_btf")) + return; + + btf__add_int(btf1, "int", 4, BTF_INT_SIGNED); /* [1] int */ + btf__add_struct(btf1, "s1", 4); /* [2] struct s1 { */ + btf__add_field(btf1, "f1", 1, 0, 0); /* int f1; */ + /* } */ + VALIDATE_RAW_BTF( + btf1, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's1' size=4 vlen=1\n" + "\t'f1' type_id=1 bits_offset=0"); + + btf2 = btf__new_empty_split(btf1); + if (!ASSERT_OK_PTR(btf2, "empty_split_btf")) + goto cleanup; + + btf__add_struct(btf2, "with_embedded", 8); /* [3] struct with_embedded { */ + btf__add_field(btf2, "e1", 2, 0, 0); /* struct s1 e1; */ + /* } */ + + VALIDATE_RAW_BTF( + btf2, + "[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", + "[2] STRUCT 's1' size=4 vlen=1\n" + "\t'f1' type_id=1 bits_offset=0", + "[3] STRUCT 'with_embedded' size=8 vlen=1\n" + "\t'e1' type_id=2 bits_offset=0"); + + if (!ASSERT_EQ(0, btf__distill_base(btf2, &btf3, &btf4), + "distilled_base") || + !ASSERT_OK_PTR(btf3, "distilled_base") || + !ASSERT_OK_PTR(btf4, "distilled_split") || + !ASSERT_EQ(2, btf__type_cnt(btf3), "distilled_base_type_cnt")) + goto cleanup; + + VALIDATE_RAW_BTF( + btf4, + "[1] STRUCT 's1' size=4 vlen=0", + "[2] STRUCT 'with_embedded' size=8 vlen=1\n" + "\t'e1' type_id=1 bits_offset=0"); + + btf5 = btf__new_empty(); + if (!ASSERT_OK_PTR(btf5, "empty_reloc_btf")) + goto cleanup; + + btf__add_int(btf5, "int", 4, BTF_INT_SIGNED); /* [1] int */ + /* struct with the same name but different size */ + btf__add_struct(btf5, "s1", 8); /* [2] struct s1 { */ + btf__add_field(btf5, "f1", 1, 0, 0); /* int f1; */ + /* } */ + + ASSERT_EQ(btf__relocate(btf4, btf5), -EINVAL, "relocate_split"); +cleanup: + btf__free(btf5); + btf__free(btf4); + btf__free(btf3); + btf__free(btf2); + btf__free(btf1); +} + void test_btf_distill(void) { if (test__start_subtest("distilled_base")) @@ -613,6 +683,8 @@ void test_btf_distill(void) test_distilled_base_multi_err(); if (test__start_subtest("distilled_base_multi_err2")) test_distilled_base_multi_err2(); + if (test__start_subtest("distilled_base_embedded_err")) + test_distilled_base_embedded_err(); if (test__start_subtest("distilled_base_vmlinux")) test_distilled_base_vmlinux(); if (test__start_subtest("distilled_endianness")) diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c new file mode 100644 index 000000000000..e1a90c10db8c --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/cgroup_skb_direct_packet_access.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> +#include "cgroup_skb_direct_packet_access.skel.h" + +void test_cgroup_skb_prog_run_direct_packet_access(void) +{ + int err; + struct cgroup_skb_direct_packet_access *skel; + char test_skb[64] = {}; + + LIBBPF_OPTS(bpf_test_run_opts, topts, + .data_in = test_skb, + .data_size_in = sizeof(test_skb), + ); + + skel = cgroup_skb_direct_packet_access__open_and_load(); + if (!ASSERT_OK_PTR(skel, "cgroup_skb_direct_packet_access__open_and_load")) + return; + + err = bpf_prog_test_run_opts(bpf_program__fd(skel->progs.direct_packet_access), &topts); + ASSERT_OK(err, "bpf_prog_test_run_opts err"); + ASSERT_EQ(topts.retval, 1, "retval"); + + ASSERT_NEQ(skel->bss->data_end, 0, "data_end"); + + cgroup_skb_direct_packet_access__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 1c682550e0e7..e10ea92c3fe2 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -2,7 +2,7 @@ #define _GNU_SOURCE #include <test_progs.h> #include "progs/core_reloc_types.h" -#include "bpf_testmod/bpf_testmod.h" +#include "test_kmods/bpf_testmod.h" #include <linux/limits.h> #include <sys/mman.h> #include <sys/syscall.h> diff --git a/tools/testing/selftests/bpf/prog_tests/fd_array.c b/tools/testing/selftests/bpf/prog_tests/fd_array.c new file mode 100644 index 000000000000..a1d52e73fb16 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/fd_array.c @@ -0,0 +1,441 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <test_progs.h> + +#include <linux/btf.h> +#include <bpf/bpf.h> + +#include "../test_btf.h" + +static inline int new_map(void) +{ + const char *name = NULL; + __u32 max_entries = 1; + __u32 value_size = 8; + __u32 key_size = 4; + + return bpf_map_create(BPF_MAP_TYPE_ARRAY, name, + key_size, value_size, + max_entries, NULL); +} + +static int new_btf(void) +{ + struct btf_blob { + struct btf_header btf_hdr; + __u32 types[8]; + __u32 str; + } raw_btf = { + .btf_hdr = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, + .hdr_len = sizeof(struct btf_header), + .type_len = sizeof(raw_btf.types), + .str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types), + .str_len = sizeof(raw_btf.str), + }, + .types = { + /* long */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 64, 8), /* [1] */ + /* unsigned long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + }, + }; + + return bpf_btf_load(&raw_btf, sizeof(raw_btf), NULL); +} + +#define Close(FD) do { \ + if ((FD) >= 0) { \ + close(FD); \ + FD = -1; \ + } \ +} while(0) + +static bool map_exists(__u32 id) +{ + int fd; + + fd = bpf_map_get_fd_by_id(id); + if (fd >= 0) { + close(fd); + return true; + } + return false; +} + +static bool btf_exists(__u32 id) +{ + int fd; + + fd = bpf_btf_get_fd_by_id(id); + if (fd >= 0) { + close(fd); + return true; + } + return false; +} + +static inline int bpf_prog_get_map_ids(int prog_fd, __u32 *nr_map_ids, __u32 *map_ids) +{ + __u32 len = sizeof(struct bpf_prog_info); + struct bpf_prog_info info; + int err; + + memset(&info, 0, len); + info.nr_map_ids = *nr_map_ids, + info.map_ids = ptr_to_u64(map_ids), + + err = bpf_prog_get_info_by_fd(prog_fd, &info, &len); + if (!ASSERT_OK(err, "bpf_prog_get_info_by_fd")) + return -1; + + *nr_map_ids = info.nr_map_ids; + + return 0; +} + +static int __load_test_prog(int map_fd, const int *fd_array, int fd_array_cnt) +{ + /* A trivial program which uses one map */ + struct bpf_insn insns[] = { + BPF_LD_MAP_FD(BPF_REG_1, map_fd), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem), + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + LIBBPF_OPTS(bpf_prog_load_opts, opts); + + opts.fd_array = fd_array; + opts.fd_array_cnt = fd_array_cnt; + + return bpf_prog_load(BPF_PROG_TYPE_XDP, NULL, "GPL", insns, ARRAY_SIZE(insns), &opts); +} + +static int load_test_prog(const int *fd_array, int fd_array_cnt) +{ + int map_fd; + int ret; + + map_fd = new_map(); + if (!ASSERT_GE(map_fd, 0, "new_map")) + return map_fd; + + ret = __load_test_prog(map_fd, fd_array, fd_array_cnt); + close(map_fd); + return ret; +} + +static bool check_expected_map_ids(int prog_fd, int expected, __u32 *map_ids, __u32 *nr_map_ids) +{ + int err; + + err = bpf_prog_get_map_ids(prog_fd, nr_map_ids, map_ids); + if (!ASSERT_OK(err, "bpf_prog_get_map_ids")) + return false; + if (!ASSERT_EQ(*nr_map_ids, expected, "unexpected nr_map_ids")) + return false; + + return true; +} + +/* + * Load a program, which uses one map. No fd_array maps are present. + * On return only one map is expected to be bound to prog. + */ +static void check_fd_array_cnt__no_fd_array(void) +{ + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + prog_fd = load_test_prog(NULL, 0); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + return; + nr_map_ids = ARRAY_SIZE(map_ids); + check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids); + close(prog_fd); +} + +/* + * Load a program, which uses one map, and pass two extra, non-equal, maps in + * fd_array with fd_array_cnt=2. On return three maps are expected to be bound + * to the program. + */ +static void check_fd_array_cnt__fd_array_ok(void) +{ + int extra_fds[2] = { -1, -1 }; + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + extra_fds[0] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + extra_fds[1] = new_map(); + if (!ASSERT_GE(extra_fds[1], 0, "new_map")) + goto cleanup; + prog_fd = load_test_prog(extra_fds, 2); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + nr_map_ids = ARRAY_SIZE(map_ids); + if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids)) + goto cleanup; + + /* maps should still exist when original file descriptors are closed */ + Close(extra_fds[0]); + Close(extra_fds[1]); + if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map_ids[0] should exist")) + goto cleanup; + if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map_ids[1] should exist")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[1]); + Close(extra_fds[0]); + Close(prog_fd); +} + +/* + * Load a program with a few extra maps duplicated in the fd_array. + * After the load maps should only be referenced once. + */ +static void check_fd_array_cnt__duplicated_maps(void) +{ + int extra_fds[4] = { -1, -1, -1, -1 }; + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + extra_fds[0] = extra_fds[2] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + extra_fds[1] = extra_fds[3] = new_map(); + if (!ASSERT_GE(extra_fds[1], 0, "new_map")) + goto cleanup; + prog_fd = load_test_prog(extra_fds, 4); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + nr_map_ids = ARRAY_SIZE(map_ids); + if (!check_expected_map_ids(prog_fd, 3, map_ids, &nr_map_ids)) + goto cleanup; + + /* maps should still exist when original file descriptors are closed */ + Close(extra_fds[0]); + Close(extra_fds[1]); + if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist")) + goto cleanup; + if (!ASSERT_EQ(map_exists(map_ids[1]), true, "map should exist")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[1]); + Close(extra_fds[0]); + Close(prog_fd); +} + +/* + * Check that if maps which are referenced by a program are + * passed in fd_array, then they will be referenced only once + */ +static void check_fd_array_cnt__referenced_maps_in_fd_array(void) +{ + int extra_fds[1] = { -1 }; + __u32 map_ids[16]; + __u32 nr_map_ids; + int prog_fd = -1; + + extra_fds[0] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + prog_fd = __load_test_prog(extra_fds[0], extra_fds, 1); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + nr_map_ids = ARRAY_SIZE(map_ids); + if (!check_expected_map_ids(prog_fd, 1, map_ids, &nr_map_ids)) + goto cleanup; + + /* map should still exist when original file descriptor is closed */ + Close(extra_fds[0]); + if (!ASSERT_EQ(map_exists(map_ids[0]), true, "map should exist")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[0]); + Close(prog_fd); +} + +static int get_btf_id_by_fd(int btf_fd, __u32 *id) +{ + struct bpf_btf_info info; + __u32 info_len = sizeof(info); + int err; + + memset(&info, 0, info_len); + err = bpf_btf_get_info_by_fd(btf_fd, &info, &info_len); + if (err) + return err; + if (id) + *id = info.id; + return 0; +} + +/* + * Check that fd_array operates properly for btfs. Namely, to check that + * passing a btf fd in fd_array increases its reference count, do the + * following: + * 1) Create a new btf, it's referenced only by a file descriptor, so refcnt=1 + * 2) Load a BPF prog with fd_array[0] = btf_fd; now btf's refcnt=2 + * 3) Close the btf_fd, now refcnt=1 + * Wait and check that BTF stil exists. + */ +static void check_fd_array_cnt__referenced_btfs(void) +{ + int extra_fds[1] = { -1 }; + int prog_fd = -1; + __u32 btf_id; + int tries; + int err; + + extra_fds[0] = new_btf(); + if (!ASSERT_GE(extra_fds[0], 0, "new_btf")) + goto cleanup; + prog_fd = load_test_prog(extra_fds, 1); + if (!ASSERT_GE(prog_fd, 0, "BPF_PROG_LOAD")) + goto cleanup; + + /* btf should still exist when original file descriptor is closed */ + err = get_btf_id_by_fd(extra_fds[0], &btf_id); + if (!ASSERT_GE(err, 0, "get_btf_id_by_fd")) + goto cleanup; + + Close(extra_fds[0]); + + if (!ASSERT_GE(kern_sync_rcu(), 0, "kern_sync_rcu 1")) + goto cleanup; + + if (!ASSERT_EQ(btf_exists(btf_id), true, "btf should exist")) + goto cleanup; + + Close(prog_fd); + + /* The program is freed by a workqueue, so no reliable + * way to sync, so just wait a bit (max ~1 second). */ + for (tries = 100; tries >= 0; tries--) { + usleep(1000); + + if (!btf_exists(btf_id)) + break; + + if (tries) + continue; + + PRINT_FAIL("btf should have been freed"); + } + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[0]); + Close(prog_fd); +} + +/* + * Test that a program with trash in fd_array can't be loaded: + * only map and BTF file descriptors should be accepted. + */ +static void check_fd_array_cnt__fd_array_with_trash(void) +{ + int extra_fds[3] = { -1, -1, -1 }; + int prog_fd = -1; + + extra_fds[0] = new_map(); + if (!ASSERT_GE(extra_fds[0], 0, "new_map")) + goto cleanup; + extra_fds[1] = new_btf(); + if (!ASSERT_GE(extra_fds[1], 0, "new_btf")) + goto cleanup; + + /* trash 1: not a file descriptor */ + extra_fds[2] = 0xbeef; + prog_fd = load_test_prog(extra_fds, 3); + if (!ASSERT_EQ(prog_fd, -EBADF, "prog should have been rejected with -EBADF")) + goto cleanup; + + /* trash 2: not a map or btf */ + extra_fds[2] = socket(AF_INET, SOCK_STREAM, 0); + if (!ASSERT_GE(extra_fds[2], 0, "socket")) + goto cleanup; + + prog_fd = load_test_prog(extra_fds, 3); + if (!ASSERT_EQ(prog_fd, -EINVAL, "prog should have been rejected with -EINVAL")) + goto cleanup; + + /* Validate that the prog is ok if trash is removed */ + Close(extra_fds[2]); + extra_fds[2] = new_btf(); + if (!ASSERT_GE(extra_fds[2], 0, "new_btf")) + goto cleanup; + + prog_fd = load_test_prog(extra_fds, 3); + if (!ASSERT_GE(prog_fd, 0, "prog should have been loaded")) + goto cleanup; + + /* some fds might be invalid, so ignore return codes */ +cleanup: + Close(extra_fds[2]); + Close(extra_fds[1]); + Close(extra_fds[0]); +} + +/* + * Test that a program with too big fd_array can't be loaded. + */ +static void check_fd_array_cnt__fd_array_too_big(void) +{ + int extra_fds[65]; + int prog_fd = -1; + int i; + + for (i = 0; i < 65; i++) { + extra_fds[i] = new_map(); + if (!ASSERT_GE(extra_fds[i], 0, "new_map")) + goto cleanup_fds; + } + + prog_fd = load_test_prog(extra_fds, 65); + ASSERT_EQ(prog_fd, -E2BIG, "prog should have been rejected with -E2BIG"); + +cleanup_fds: + while (i > 0) + Close(extra_fds[--i]); +} + +void test_fd_array_cnt(void) +{ + if (test__start_subtest("no-fd-array")) + check_fd_array_cnt__no_fd_array(); + + if (test__start_subtest("fd-array-ok")) + check_fd_array_cnt__fd_array_ok(); + + if (test__start_subtest("fd-array-dup-input")) + check_fd_array_cnt__duplicated_maps(); + + if (test__start_subtest("fd-array-ref-maps-in-array")) + check_fd_array_cnt__referenced_maps_in_fd_array(); + + if (test__start_subtest("fd-array-ref-btfs")) + check_fd_array_cnt__referenced_btfs(); + + if (test__start_subtest("fd-array-trash-input")) + check_fd_array_cnt__fd_array_with_trash(); + + if (test__start_subtest("fd-array-2big")) + check_fd_array_cnt__fd_array_too_big(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c index d50cbd8040d4..e59af2aa6601 100644 --- a/tools/testing/selftests/bpf/prog_tests/fill_link_info.c +++ b/tools/testing/selftests/bpf/prog_tests/fill_link_info.c @@ -171,6 +171,10 @@ static void test_kprobe_fill_link_info(struct test_fill_link_info *skel, /* See also arch_adjust_kprobe_addr(). */ if (skel->kconfig->CONFIG_X86_KERNEL_IBT) entry_offset = 4; + if (skel->kconfig->CONFIG_PPC64 && + skel->kconfig->CONFIG_KPROBES_ON_FTRACE && + !skel->kconfig->CONFIG_PPC_FTRACE_OUT_OF_LINE) + entry_offset = 4; err = verify_perf_link_info(link_fd, type, kprobe_addr, 0, entry_offset); ASSERT_OK(err, "verify_perf_link_info"); } else { diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c index cfcc90cb7ffb..08bae13248c4 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c @@ -7,39 +7,14 @@ #include "bpf_flow.skel.h" +#define TEST_NS "flow_dissector_ns" #define FLOW_CONTINUE_SADDR 0x7f00007f /* 127.0.0.127 */ +#define TEST_NAME_MAX_LEN 64 #ifndef IP_MF #define IP_MF 0x2000 #endif -#define CHECK_FLOW_KEYS(desc, got, expected) \ - _CHECK(memcmp(&got, &expected, sizeof(got)) != 0, \ - desc, \ - topts.duration, \ - "nhoff=%u/%u " \ - "thoff=%u/%u " \ - "addr_proto=0x%x/0x%x " \ - "is_frag=%u/%u " \ - "is_first_frag=%u/%u " \ - "is_encap=%u/%u " \ - "ip_proto=0x%x/0x%x " \ - "n_proto=0x%x/0x%x " \ - "flow_label=0x%x/0x%x " \ - "sport=%u/%u " \ - "dport=%u/%u\n", \ - got.nhoff, expected.nhoff, \ - got.thoff, expected.thoff, \ - got.addr_proto, expected.addr_proto, \ - got.is_frag, expected.is_frag, \ - got.is_first_frag, expected.is_first_frag, \ - got.is_encap, expected.is_encap, \ - got.ip_proto, expected.ip_proto, \ - got.n_proto, expected.n_proto, \ - got.flow_label, expected.flow_label, \ - got.sport, expected.sport, \ - got.dport, expected.dport) - struct ipv4_pkt { struct ethhdr eth; struct iphdr iph; @@ -89,6 +64,19 @@ struct dvlan_ipv6_pkt { struct tcphdr tcp; } __packed; +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +} gre_base_hdr; + +struct gre_minimal_pkt { + struct ethhdr eth; + struct iphdr iph; + struct gre_base_hdr gre_hdr; + struct iphdr iph_inner; + struct tcphdr tcp; +} __packed; + struct test { const char *name; union { @@ -98,6 +86,7 @@ struct test { struct ipv6_pkt ipv6; struct ipv6_frag_pkt ipv6_frag; struct dvlan_ipv6_pkt dvlan_ipv6; + struct gre_minimal_pkt gre_minimal; } pkt; struct bpf_flow_keys keys; __u32 flags; @@ -106,7 +95,6 @@ struct test { #define VLAN_HLEN 4 -static __u32 duration; struct test tests[] = { { .name = "ipv4", @@ -444,8 +432,137 @@ struct test tests[] = { }, .retval = BPF_FLOW_DISSECTOR_CONTINUE, }, + { + .name = "ip-gre", + .pkt.gre_minimal = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_GRE, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .gre_hdr = { + .flags = 0, + .protocol = __bpf_constant_htons(ETH_P_IP), + }, + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) * 2 + + sizeof(struct gre_base_hdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_TCP, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + .sport = 80, + .dport = 8080, + }, + .retval = BPF_OK, + }, + { + .name = "ip-gre-no-encap", + .pkt.ipip = { + .eth.h_proto = __bpf_constant_htons(ETH_P_IP), + .iph.ihl = 5, + .iph.protocol = IPPROTO_GRE, + .iph.tot_len = __bpf_constant_htons(MAGIC_BYTES), + .iph_inner.ihl = 5, + .iph_inner.protocol = IPPROTO_TCP, + .iph_inner.tot_len = + __bpf_constant_htons(MAGIC_BYTES - + sizeof(struct iphdr)), + .tcp.doff = 5, + .tcp.source = 80, + .tcp.dest = 8080, + }, + .keys = { + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .nhoff = ETH_HLEN, + .thoff = ETH_HLEN + sizeof(struct iphdr) + + sizeof(struct gre_base_hdr), + .addr_proto = ETH_P_IP, + .ip_proto = IPPROTO_GRE, + .n_proto = __bpf_constant_htons(ETH_P_IP), + .is_encap = true, + }, + .flags = BPF_FLOW_DISSECTOR_F_STOP_AT_ENCAP, + .retval = BPF_OK, + }, }; +void serial_test_flow_dissector_namespace(void) +{ + struct bpf_flow *skel; + struct nstoken *ns; + int err, prog_fd; + + skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) + return; + + prog_fd = bpf_program__fd(skel->progs._dissect); + if (!ASSERT_OK_FD(prog_fd, "get dissector fd")) + goto out_destroy_skel; + + /* We must be able to attach a flow dissector to root namespace */ + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (!ASSERT_OK(err, "attach on root namespace ok")) + goto out_destroy_skel; + + err = make_netns(TEST_NS); + if (!ASSERT_OK(err, "create non-root net namespace")) + goto out_destroy_skel; + + /* We must not be able to additionally attach a flow dissector to a + * non-root net namespace + */ + ns = open_netns(TEST_NS); + if (!ASSERT_OK_PTR(ns, "enter non-root net namespace")) + goto out_clean_ns; + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (!ASSERT_ERR(err, + "refuse new flow dissector in non-root net namespace")) + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + else + ASSERT_EQ(errno, EEXIST, + "refused because of already attached prog"); + close_netns(ns); + + /* If no flow dissector is attached to the root namespace, we must + * be able to attach one to a non-root net namespace + */ + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + ns = open_netns(TEST_NS); + ASSERT_OK_PTR(ns, "enter non-root net namespace"); + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + close_netns(ns); + ASSERT_OK(err, "accept new flow dissector in non-root net namespace"); + + /* If a flow dissector is attached to non-root net namespace, attaching + * a flow dissector to root namespace must fail + */ + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (!ASSERT_ERR(err, "refuse new flow dissector on root namespace")) + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + else + ASSERT_EQ(errno, EEXIST, + "refused because of already attached prog"); + + ns = open_netns(TEST_NS); + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); + close_netns(ns); +out_clean_ns: + remove_netns(TEST_NS); +out_destroy_skel: + bpf_flow__destroy(skel); +} + static int create_tap(const char *ifname) { struct ifreq ifr = { @@ -533,22 +650,27 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array) return 0; } -static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) +static void run_tests_skb_less(int tap_fd, struct bpf_map *keys, + char *test_suffix) { + char test_name[TEST_NAME_MAX_LEN]; int i, err, keys_fd; keys_fd = bpf_map__fd(keys); - if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd)) + if (!ASSERT_OK_FD(keys_fd, "bpf_map__fd")) return; for (i = 0; i < ARRAY_SIZE(tests); i++) { /* Keep in sync with 'flags' from eth_get_headlen. */ __u32 eth_get_headlen_flags = BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG; - LIBBPF_OPTS(bpf_test_run_opts, topts); struct bpf_flow_keys flow_keys = {}; __u32 key = (__u32)(tests[i].keys.sport) << 16 | tests[i].keys.dport; + snprintf(test_name, TEST_NAME_MAX_LEN, "%s-%s", tests[i].name, + test_suffix); + if (!test__start_subtest(test_name)) + continue; /* For skb-less case we can't pass input flags; run * only the tests that have a matching set of flags. @@ -558,78 +680,139 @@ static void run_tests_skb_less(int tap_fd, struct bpf_map *keys) continue; err = tx_tap(tap_fd, &tests[i].pkt, sizeof(tests[i].pkt)); - CHECK(err < 0, "tx_tap", "err %d errno %d\n", err, errno); + if (!ASSERT_EQ(err, sizeof(tests[i].pkt), "tx_tap")) + continue; /* check the stored flow_keys only if BPF_OK expected */ if (tests[i].retval != BPF_OK) continue; err = bpf_map_lookup_elem(keys_fd, &key, &flow_keys); - ASSERT_OK(err, "bpf_map_lookup_elem"); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + continue; - CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + ASSERT_MEMEQ(&flow_keys, &tests[i].keys, + sizeof(struct bpf_flow_keys), + "returned flow keys"); err = bpf_map_delete_elem(keys_fd, &key); ASSERT_OK(err, "bpf_map_delete_elem"); } } -static void test_skb_less_prog_attach(struct bpf_flow *skel, int tap_fd) +void test_flow_dissector_skb_less_direct_attach(void) { - int err, prog_fd; + int err, prog_fd, tap_fd; + struct bpf_flow *skel; + struct netns_obj *ns; - prog_fd = bpf_program__fd(skel->progs._dissect); - if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd)) + ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true); + if (!ASSERT_OK_PTR(ns, "create and open netns")) return; + skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) + goto out_clean_ns; + + err = init_prog_array(skel->obj, skel->maps.jmp_table); + if (!ASSERT_OK(err, "init_prog_array")) + goto out_destroy_skel; + + prog_fd = bpf_program__fd(skel->progs._dissect); + if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd")) + goto out_destroy_skel; + err = bpf_prog_attach(prog_fd, 0, BPF_FLOW_DISSECTOR, 0); - if (CHECK(err, "bpf_prog_attach", "err %d errno %d\n", err, errno)) - return; + if (!ASSERT_OK(err, "bpf_prog_attach")) + goto out_destroy_skel; + + tap_fd = create_tap("tap0"); + if (!ASSERT_OK_FD(tap_fd, "create_tap")) + goto out_destroy_skel; + err = ifup("tap0"); + if (!ASSERT_OK(err, "ifup")) + goto out_close_tap; - run_tests_skb_less(tap_fd, skel->maps.last_dissection); + run_tests_skb_less(tap_fd, skel->maps.last_dissection, + "non-skb-direct-attach"); err = bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); - CHECK(err, "bpf_prog_detach2", "err %d errno %d\n", err, errno); + ASSERT_OK(err, "bpf_prog_detach2"); + +out_close_tap: + close(tap_fd); +out_destroy_skel: + bpf_flow__destroy(skel); +out_clean_ns: + netns_free(ns); } -static void test_skb_less_link_create(struct bpf_flow *skel, int tap_fd) +void test_flow_dissector_skb_less_indirect_attach(void) { + int err, net_fd, tap_fd; + struct bpf_flow *skel; struct bpf_link *link; - int err, net_fd; + struct netns_obj *ns; - net_fd = open("/proc/self/ns/net", O_RDONLY); - if (CHECK(net_fd < 0, "open(/proc/self/ns/net)", "err %d\n", errno)) + ns = netns_new("flow_dissector_skb_less_indirect_attach_ns", true); + if (!ASSERT_OK_PTR(ns, "create and open netns")) return; + skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) + goto out_clean_ns; + + net_fd = open("/proc/self/ns/net", O_RDONLY); + if (!ASSERT_OK_FD(net_fd, "open(/proc/self/ns/net")) + goto out_destroy_skel; + + err = init_prog_array(skel->obj, skel->maps.jmp_table); + if (!ASSERT_OK(err, "init_prog_array")) + goto out_destroy_skel; + + tap_fd = create_tap("tap0"); + if (!ASSERT_OK_FD(tap_fd, "create_tap")) + goto out_close_ns; + err = ifup("tap0"); + if (!ASSERT_OK(err, "ifup")) + goto out_close_tap; + link = bpf_program__attach_netns(skel->progs._dissect, net_fd); if (!ASSERT_OK_PTR(link, "attach_netns")) - goto out_close; + goto out_close_tap; - run_tests_skb_less(tap_fd, skel->maps.last_dissection); + run_tests_skb_less(tap_fd, skel->maps.last_dissection, + "non-skb-indirect-attach"); err = bpf_link__destroy(link); - CHECK(err, "bpf_link__destroy", "err %d\n", err); -out_close: + ASSERT_OK(err, "bpf_link__destroy"); + +out_close_tap: + close(tap_fd); +out_close_ns: close(net_fd); +out_destroy_skel: + bpf_flow__destroy(skel); +out_clean_ns: + netns_free(ns); } -void test_flow_dissector(void) +void test_flow_dissector_skb(void) { - int i, err, prog_fd, keys_fd = -1, tap_fd; + char test_name[TEST_NAME_MAX_LEN]; struct bpf_flow *skel; + int i, err, prog_fd; skel = bpf_flow__open_and_load(); - if (CHECK(!skel, "skel", "failed to open/load skeleton\n")) + if (!ASSERT_OK_PTR(skel, "open/load skeleton")) return; - prog_fd = bpf_program__fd(skel->progs._dissect); - if (CHECK(prog_fd < 0, "bpf_program__fd", "err %d\n", prog_fd)) - goto out_destroy_skel; - keys_fd = bpf_map__fd(skel->maps.last_dissection); - if (CHECK(keys_fd < 0, "bpf_map__fd", "err %d\n", keys_fd)) - goto out_destroy_skel; err = init_prog_array(skel->obj, skel->maps.jmp_table); - if (CHECK(err, "init_prog_array", "err %d\n", err)) + if (!ASSERT_OK(err, "init_prog_array")) + goto out_destroy_skel; + + prog_fd = bpf_program__fd(skel->progs._dissect); + if (!ASSERT_OK_FD(prog_fd, "bpf_program__fd")) goto out_destroy_skel; for (i = 0; i < ARRAY_SIZE(tests); i++) { @@ -641,6 +824,10 @@ void test_flow_dissector(void) ); static struct bpf_flow_keys ctx = {}; + snprintf(test_name, TEST_NAME_MAX_LEN, "%s-skb", tests[i].name); + if (!test__start_subtest(test_name)) + continue; + if (tests[i].flags) { topts.ctx_in = &ctx; topts.ctx_size_in = sizeof(ctx); @@ -656,26 +843,12 @@ void test_flow_dissector(void) continue; ASSERT_EQ(topts.data_size_out, sizeof(flow_keys), "test_run data_size_out"); - CHECK_FLOW_KEYS(tests[i].name, flow_keys, tests[i].keys); + ASSERT_MEMEQ(&flow_keys, &tests[i].keys, + sizeof(struct bpf_flow_keys), + "returned flow keys"); } - /* Do the same tests but for skb-less flow dissector. - * We use a known path in the net/tun driver that calls - * eth_get_headlen and we manually export bpf_flow_keys - * via BPF map in this case. - */ - - tap_fd = create_tap("tap0"); - CHECK(tap_fd < 0, "create_tap", "tap_fd %d errno %d\n", tap_fd, errno); - err = ifup("tap0"); - CHECK(err, "ifup", "err %d errno %d\n", err, errno); - - /* Test direct prog attachment */ - test_skb_less_prog_attach(skel, tap_fd); - /* Test indirect prog attachment via link */ - test_skb_less_link_create(skel, tap_fd); - - close(tap_fd); out_destroy_skel: bpf_flow__destroy(skel); } + diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c new file mode 100644 index 000000000000..80b153d3ddec --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c @@ -0,0 +1,797 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <bpf/bpf.h> +#include <linux/bpf.h> +#include <bpf/libbpf.h> +#include <arpa/inet.h> +#include <asm/byteorder.h> +#include <netinet/udp.h> +#include <poll.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <unistd.h> +#include "test_progs.h" +#include "network_helpers.h" +#include "bpf_util.h" +#include "bpf_flow.skel.h" + +#define CFG_PORT_INNER 8000 +#define CFG_PORT_GUE 6080 +#define SUBTEST_NAME_MAX_LEN 32 +#define TEST_NAME_MAX_LEN (32 + SUBTEST_NAME_MAX_LEN) +#define MAX_SOURCE_PORTS 3 +#define TEST_PACKETS_COUNT 10 +#define TEST_PACKET_LEN 100 +#define TEST_PACKET_PATTERN 'a' +#define TEST_IPV4 "192.168.0.1/32" +#define TEST_IPV6 "100::a/128" +#define TEST_TUNNEL_REMOTE "127.0.0.2" +#define TEST_TUNNEL_LOCAL "127.0.0.1" + +#define INIT_ADDR4(addr4, port) \ + { \ + .sin_family = AF_INET, \ + .sin_port = __constant_htons(port), \ + .sin_addr.s_addr = __constant_htonl(addr4), \ + } + +#define INIT_ADDR6(addr6, port) \ + { \ + .sin6_family = AF_INET6, \ + .sin6_port = __constant_htons(port), \ + .sin6_addr = addr6, \ + } +#define TEST_IN4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 2, 0) +#define TEST_IN4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, CFG_PORT_INNER) +#define TEST_OUT4_SRC_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK + 1, 0) +#define TEST_OUT4_DST_ADDR_DEFAULT INIT_ADDR4(INADDR_LOOPBACK, 0) + +#define TEST_IN6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0) +#define TEST_IN6_DST_ADDR_DEFAULT \ + INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER) +#define TEST_OUT6_SRC_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0) +#define TEST_OUT6_DST_ADDR_DEFAULT INIT_ADDR6(IN6ADDR_LOOPBACK_INIT, 0) + +#define TEST_IN4_SRC_ADDR_DISSECT_CONTINUE INIT_ADDR4(INADDR_LOOPBACK + 126, 0) +#define TEST_IN4_SRC_ADDR_IPIP INIT_ADDR4((in_addr_t)0x01010101, 0) +#define TEST_IN4_DST_ADDR_IPIP INIT_ADDR4((in_addr_t)0xC0A80001, CFG_PORT_INNER) + +struct grehdr { + uint16_t unused; + uint16_t protocol; +} __packed; + +struct guehdr { + union { + struct { +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 hlen : 5, control : 1, version : 2; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 version : 2, control : 1, hlen : 5; +#else +#error "Please fix <asm/byteorder.h>" +#endif + __u8 proto_ctype; + __be16 flags; + }; + __be32 word; + }; +}; + +static char buf[ETH_DATA_LEN]; + +struct test_configuration { + char name[SUBTEST_NAME_MAX_LEN]; + int (*test_setup)(void); + void (*test_teardown)(void); + int source_ports[MAX_SOURCE_PORTS]; + int cfg_l3_inner; + struct sockaddr_in in_saddr4; + struct sockaddr_in in_daddr4; + struct sockaddr_in6 in_saddr6; + struct sockaddr_in6 in_daddr6; + int cfg_l3_outer; + struct sockaddr_in out_saddr4; + struct sockaddr_in out_daddr4; + struct sockaddr_in6 out_saddr6; + struct sockaddr_in6 out_daddr6; + int cfg_encap_proto; + uint8_t cfg_dsfield_inner; + uint8_t cfg_dsfield_outer; + int cfg_l3_extra; + struct sockaddr_in extra_saddr4; + struct sockaddr_in extra_daddr4; + struct sockaddr_in6 extra_saddr6; + struct sockaddr_in6 extra_daddr6; +}; + +static unsigned long util_gettime(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static void build_ipv4_header(void *header, uint8_t proto, uint32_t src, + uint32_t dst, int payload_len, uint8_t tos) +{ + struct iphdr *iph = header; + + iph->ihl = 5; + iph->version = 4; + iph->tos = tos; + iph->ttl = 8; + iph->tot_len = htons(sizeof(*iph) + payload_len); + iph->id = htons(1337); + iph->protocol = proto; + iph->saddr = src; + iph->daddr = dst; + iph->check = build_ip_csum((void *)iph); +} + +static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield) +{ + uint16_t val, *ptr = (uint16_t *)ip6h; + + val = ntohs(*ptr); + val &= 0xF00F; + val |= ((uint16_t)dsfield) << 4; + *ptr = htons(val); +} + +static void build_ipv6_header(void *header, uint8_t proto, + const struct sockaddr_in6 *src, + const struct sockaddr_in6 *dst, int payload_len, + uint8_t dsfield) +{ + struct ipv6hdr *ip6h = header; + + ip6h->version = 6; + ip6h->payload_len = htons(payload_len); + ip6h->nexthdr = proto; + ip6h->hop_limit = 8; + ipv6_set_dsfield(ip6h, dsfield); + + memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr)); + memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr)); +} + +static void build_udp_header(void *header, int payload_len, uint16_t sport, + uint16_t dport, int family) +{ + struct udphdr *udph = header; + int len = sizeof(*udph) + payload_len; + + udph->source = htons(sport); + udph->dest = htons(dport); + udph->len = htons(len); + udph->check = 0; + if (family == AF_INET) + udph->check = build_udp_v4_csum(header - sizeof(struct iphdr), + udph); + else + udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr), + udph); +} + +static void build_gue_header(void *header, uint8_t proto) +{ + struct guehdr *gueh = header; + + gueh->proto_ctype = proto; +} + +static void build_gre_header(void *header, uint16_t proto) +{ + struct grehdr *greh = header; + + greh->protocol = htons(proto); +} + +static int l3_length(int family) +{ + if (family == AF_INET) + return sizeof(struct iphdr); + else + return sizeof(struct ipv6hdr); +} + +static int build_packet(const struct test_configuration *test, uint16_t sport) +{ + int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0; + int el3_len = 0, packet_len; + + memset(buf, 0, ETH_DATA_LEN); + + if (test->cfg_l3_extra) + el3_len = l3_length(test->cfg_l3_extra); + + /* calculate header offsets */ + if (test->cfg_encap_proto) { + ol3_len = l3_length(test->cfg_l3_outer); + + if (test->cfg_encap_proto == IPPROTO_GRE) + ol4_len = sizeof(struct grehdr); + else if (test->cfg_encap_proto == IPPROTO_UDP) + ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr); + } + + il3_len = l3_length(test->cfg_l3_inner); + il4_len = sizeof(struct udphdr); + + packet_len = el3_len + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN; + if (!ASSERT_LE(packet_len, sizeof(buf), "check packet size")) + return -1; + + /* + * Fill packet from inside out, to calculate correct checksums. + * But create ip before udp headers, as udp uses ip for pseudo-sum. + */ + memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len, + TEST_PACKET_PATTERN, TEST_PACKET_LEN); + + /* add zero byte for udp csum padding */ + buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + TEST_PACKET_LEN] = + 0; + + switch (test->cfg_l3_inner) { + case PF_INET: + build_ipv4_header(buf + el3_len + ol3_len + ol4_len, + IPPROTO_UDP, test->in_saddr4.sin_addr.s_addr, + test->in_daddr4.sin_addr.s_addr, + il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_inner); + break; + case PF_INET6: + build_ipv6_header(buf + el3_len + ol3_len + ol4_len, + IPPROTO_UDP, &test->in_saddr6, + &test->in_daddr6, il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_inner); + break; + } + + build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len, + TEST_PACKET_LEN, sport, CFG_PORT_INNER, + test->cfg_l3_inner); + + if (!test->cfg_encap_proto) + return il3_len + il4_len + TEST_PACKET_LEN; + + switch (test->cfg_l3_outer) { + case PF_INET: + build_ipv4_header(buf + el3_len, test->cfg_encap_proto, + test->out_saddr4.sin_addr.s_addr, + test->out_daddr4.sin_addr.s_addr, + ol4_len + il3_len + il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_outer); + break; + case PF_INET6: + build_ipv6_header(buf + el3_len, test->cfg_encap_proto, + &test->out_saddr6, &test->out_daddr6, + ol4_len + il3_len + il4_len + TEST_PACKET_LEN, + test->cfg_dsfield_outer); + break; + } + + switch (test->cfg_encap_proto) { + case IPPROTO_UDP: + build_gue_header(buf + el3_len + ol3_len + ol4_len - + sizeof(struct guehdr), + test->cfg_l3_inner == PF_INET ? IPPROTO_IPIP : + IPPROTO_IPV6); + build_udp_header(buf + el3_len + ol3_len, + sizeof(struct guehdr) + il3_len + il4_len + + TEST_PACKET_LEN, + sport, CFG_PORT_GUE, test->cfg_l3_outer); + break; + case IPPROTO_GRE: + build_gre_header(buf + el3_len + ol3_len, + test->cfg_l3_inner == PF_INET ? ETH_P_IP : + ETH_P_IPV6); + break; + } + + switch (test->cfg_l3_extra) { + case PF_INET: + build_ipv4_header(buf, + test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP : + IPPROTO_IPV6, + test->extra_saddr4.sin_addr.s_addr, + test->extra_daddr4.sin_addr.s_addr, + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN, + 0); + break; + case PF_INET6: + build_ipv6_header(buf, + test->cfg_l3_outer == PF_INET ? IPPROTO_IPIP : + IPPROTO_IPV6, + &test->extra_saddr6, &test->extra_daddr6, + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN, + 0); + break; + } + + return el3_len + ol3_len + ol4_len + il3_len + il4_len + + TEST_PACKET_LEN; +} + +/* sender transmits encapsulated over RAW or unencap'd over UDP */ +static int setup_tx(const struct test_configuration *test) +{ + int family, fd, ret; + + if (test->cfg_l3_extra) + family = test->cfg_l3_extra; + else if (test->cfg_l3_outer) + family = test->cfg_l3_outer; + else + family = test->cfg_l3_inner; + + fd = socket(family, SOCK_RAW, IPPROTO_RAW); + if (!ASSERT_OK_FD(fd, "setup tx socket")) + return fd; + + if (test->cfg_l3_extra) { + if (test->cfg_l3_extra == PF_INET) + ret = connect(fd, (void *)&test->extra_daddr4, + sizeof(test->extra_daddr4)); + else + ret = connect(fd, (void *)&test->extra_daddr6, + sizeof(test->extra_daddr6)); + if (!ASSERT_OK(ret, "connect")) { + close(fd); + return ret; + } + } else if (test->cfg_l3_outer) { + /* connect to destination if not encapsulated */ + if (test->cfg_l3_outer == PF_INET) + ret = connect(fd, (void *)&test->out_daddr4, + sizeof(test->out_daddr4)); + else + ret = connect(fd, (void *)&test->out_daddr6, + sizeof(test->out_daddr6)); + if (!ASSERT_OK(ret, "connect")) { + close(fd); + return ret; + } + } else { + /* otherwise using loopback */ + if (test->cfg_l3_inner == PF_INET) + ret = connect(fd, (void *)&test->in_daddr4, + sizeof(test->in_daddr4)); + else + ret = connect(fd, (void *)&test->in_daddr6, + sizeof(test->in_daddr6)); + if (!ASSERT_OK(ret, "connect")) { + close(fd); + return ret; + } + } + + return fd; +} + +/* receiver reads unencapsulated UDP */ +static int setup_rx(const struct test_configuration *test) +{ + int fd, ret; + + fd = socket(test->cfg_l3_inner, SOCK_DGRAM, 0); + if (!ASSERT_OK_FD(fd, "socket rx")) + return fd; + + if (test->cfg_l3_inner == PF_INET) + ret = bind(fd, (void *)&test->in_daddr4, + sizeof(test->in_daddr4)); + else + ret = bind(fd, (void *)&test->in_daddr6, + sizeof(test->in_daddr6)); + if (!ASSERT_OK(ret, "bind rx")) { + close(fd); + return ret; + } + + return fd; +} + +static int do_tx(int fd, const char *pkt, int len) +{ + int ret; + + ret = write(fd, pkt, len); + return ret != len; +} + +static int do_poll(int fd, short events, int timeout) +{ + struct pollfd pfd; + int ret; + + pfd.fd = fd; + pfd.events = events; + + ret = poll(&pfd, 1, timeout); + return ret; +} + +static int do_rx(int fd) +{ + char rbuf; + int ret, num = 0; + + while (1) { + ret = recv(fd, &rbuf, 1, MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + break; + if (ret < 0) + return -1; + if (!ASSERT_EQ(rbuf, TEST_PACKET_PATTERN, "check pkt pattern")) + return -1; + num++; + } + + return num; +} + +static int run_test(const struct test_configuration *test, + int source_port_index) +{ + int fdt = -1, fdr = -1, len, tx = 0, rx = 0, err; + unsigned long tstop, tcur; + + fdr = setup_rx(test); + fdt = setup_tx(test); + if (!ASSERT_OK_FD(fdr, "setup rx") || !ASSERT_OK_FD(fdt, "setup tx")) { + err = -1; + goto out_close_sockets; + } + + len = build_packet(test, + (uint16_t)test->source_ports[source_port_index]); + if (!ASSERT_GT(len, 0, "build test packet")) + return -1; + + tcur = util_gettime(); + tstop = tcur; + + while (tx < TEST_PACKETS_COUNT) { + if (!ASSERT_OK(do_tx(fdt, buf, len), "do_tx")) + break; + tx++; + err = do_rx(fdr); + if (!ASSERT_GE(err, 0, "do_rx")) + break; + rx += err; + } + + /* read straggler packets, if any */ + if (rx < tx) { + tstop = util_gettime() + 100; + while (rx < tx) { + tcur = util_gettime(); + if (tcur >= tstop) + break; + + err = do_poll(fdr, POLLIN, tstop - tcur); + if (err < 0) + break; + err = do_rx(fdr); + if (err >= 0) + rx += err; + } + } + +out_close_sockets: + close(fdt); + close(fdr); + return rx; +} + +static int attach_and_configure_program(struct bpf_flow *skel) +{ + struct bpf_map *prog_array = skel->maps.jmp_table; + int main_prog_fd, sub_prog_fd, map_fd, i, err; + struct bpf_program *prog; + char prog_name[32]; + + main_prog_fd = bpf_program__fd(skel->progs._dissect); + if (main_prog_fd < 0) + return main_prog_fd; + + err = bpf_prog_attach(main_prog_fd, 0, BPF_FLOW_DISSECTOR, 0); + if (err) + return err; + + map_fd = bpf_map__fd(prog_array); + if (map_fd < 0) + return map_fd; + + for (i = 0; i < bpf_map__max_entries(prog_array); i++) { + snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i); + + prog = bpf_object__find_program_by_name(skel->obj, prog_name); + if (!prog) + return -1; + + sub_prog_fd = bpf_program__fd(prog); + if (sub_prog_fd < 0) + return -1; + + err = bpf_map_update_elem(map_fd, &i, &sub_prog_fd, BPF_ANY); + if (err) + return -1; + } + + return main_prog_fd; +} + +static void detach_program(struct bpf_flow *skel, int prog_fd) +{ + bpf_prog_detach2(prog_fd, 0, BPF_FLOW_DISSECTOR); +} + +static int set_port_drop(int pf, bool multi_port) +{ + char dst_port[16]; + + snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER); + + SYS(fail, "tc qdisc add dev lo ingress"); + SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s", + "dev lo", + "parent FFFF:", + "protocol", pf == PF_INET6 ? "ipv6" : "ip", + "pref 1337", + "flower", + "ip_proto udp", + "src_port", multi_port ? "8-10" : "9", + "dst_port", dst_port, + "action drop"); + return 0; + +fail_delete_qdisc: + SYS_NOFAIL("tc qdisc del dev lo ingress"); +fail: + return 1; +} + +static void remove_filter(void) +{ + SYS_NOFAIL("tc filter del dev lo ingress"); + SYS_NOFAIL("tc qdisc del dev lo ingress"); +} + +static int ipv4_setup(void) +{ + return set_port_drop(PF_INET, false); +} + +static int ipv6_setup(void) +{ + return set_port_drop(PF_INET6, false); +} + +static int port_range_setup(void) +{ + return set_port_drop(PF_INET, true); +} + +static int set_addresses(void) +{ + SYS(out, "ip -4 addr add %s dev lo", TEST_IPV4); + SYS(out_remove_ipv4, "ip -6 addr add %s dev lo", TEST_IPV6); + return 0; +out_remove_ipv4: + SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4); +out: + return -1; +} + +static void unset_addresses(void) +{ + SYS_NOFAIL("ip -4 addr del %s dev lo", TEST_IPV4); + SYS_NOFAIL("ip -6 addr del %s dev lo", TEST_IPV6); +} + +static int ipip_setup(void) +{ + if (!ASSERT_OK(set_addresses(), "configure addresses")) + return -1; + if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter")) + goto out_unset_addresses; + SYS(out_remove_filter, + "ip link add ipip_test type ipip remote %s local %s dev lo", + TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL); + SYS(out_clean_netif, "ip link set ipip_test up"); + return 0; + +out_clean_netif: + SYS_NOFAIL("ip link del ipip_test"); +out_remove_filter: + remove_filter(); +out_unset_addresses: + unset_addresses(); + return -1; +} + +static void ipip_shutdown(void) +{ + SYS_NOFAIL("ip link del ipip_test"); + remove_filter(); + unset_addresses(); +} + +static int gre_setup(void) +{ + if (!ASSERT_OK(set_addresses(), "configure addresses")) + return -1; + if (!ASSERT_OK(set_port_drop(PF_INET, false), "set filter")) + goto out_unset_addresses; + SYS(out_remove_filter, + "ip link add gre_test type gre remote %s local %s dev lo", + TEST_TUNNEL_REMOTE, TEST_TUNNEL_LOCAL); + SYS(out_clean_netif, "ip link set gre_test up"); + return 0; + +out_clean_netif: + SYS_NOFAIL("ip link del ipip_test"); +out_remove_filter: + remove_filter(); +out_unset_addresses: + unset_addresses(); + return -1; +} + +static void gre_shutdown(void) +{ + SYS_NOFAIL("ip link del gre_test"); + remove_filter(); + unset_addresses(); +} + +static const struct test_configuration tests_input[] = { + { + .name = "ipv4", + .test_setup = ipv4_setup, + .test_teardown = remove_filter, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT, + .in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT + }, + { + .name = "ipv4_continue_dissect", + .test_setup = ipv4_setup, + .test_teardown = remove_filter, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_DISSECT_CONTINUE, + .in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT }, + { + .name = "ipip", + .test_setup = ipip_setup, + .test_teardown = ipip_shutdown, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_IPIP, + .in_daddr4 = TEST_IN4_DST_ADDR_IPIP, + .out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT, + .out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT, + .cfg_l3_outer = PF_INET, + .cfg_encap_proto = IPPROTO_IPIP, + + }, + { + .name = "gre", + .test_setup = gre_setup, + .test_teardown = gre_shutdown, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_IPIP, + .in_daddr4 = TEST_IN4_DST_ADDR_IPIP, + .out_saddr4 = TEST_OUT4_SRC_ADDR_DEFAULT, + .out_daddr4 = TEST_OUT4_DST_ADDR_DEFAULT, + .cfg_l3_outer = PF_INET, + .cfg_encap_proto = IPPROTO_GRE, + }, + { + .name = "port_range", + .test_setup = port_range_setup, + .test_teardown = remove_filter, + .source_ports = { 7, 9, 11 }, + .cfg_l3_inner = PF_INET, + .in_saddr4 = TEST_IN4_SRC_ADDR_DEFAULT, + .in_daddr4 = TEST_IN4_DST_ADDR_DEFAULT }, + { + .name = "ipv6", + .test_setup = ipv6_setup, + .test_teardown = remove_filter, + .source_ports = { 8, 9, 10 }, + .cfg_l3_inner = PF_INET6, + .in_saddr6 = TEST_IN6_SRC_ADDR_DEFAULT, + .in_daddr6 = TEST_IN6_DST_ADDR_DEFAULT + }, +}; + +struct test_ctx { + struct bpf_flow *skel; + struct netns_obj *ns; + int prog_fd; +}; + +static int test_global_init(struct test_ctx *ctx) +{ + int err; + + ctx->skel = bpf_flow__open_and_load(); + if (!ASSERT_OK_PTR(ctx->skel, "open and load flow_dissector")) + return -1; + + ctx->ns = netns_new("flow_dissector_classification", true); + if (!ASSERT_OK_PTR(ctx->ns, "switch ns")) + goto out_destroy_skel; + + err = write_sysctl("/proc/sys/net/ipv4/conf/default/rp_filter", "0"); + err |= write_sysctl("/proc/sys/net/ipv4/conf/all/rp_filter", "0"); + err |= write_sysctl("/proc/sys/net/ipv4/conf/lo/rp_filter", "0"); + if (!ASSERT_OK(err, "configure net tunables")) + goto out_clean_ns; + + ctx->prog_fd = attach_and_configure_program(ctx->skel); + if (!ASSERT_OK_FD(ctx->prog_fd, "attach and configure program")) + goto out_clean_ns; + return 0; +out_clean_ns: + netns_free(ctx->ns); +out_destroy_skel: + bpf_flow__destroy(ctx->skel); + return -1; +} + +static void test_global_shutdown(struct test_ctx *ctx) +{ + detach_program(ctx->skel, ctx->prog_fd); + netns_free(ctx->ns); + bpf_flow__destroy(ctx->skel); +} + +void test_flow_dissector_classification(void) +{ + struct test_ctx ctx; + const struct test_configuration *test; + int i; + + if (test_global_init(&ctx)) + return; + + for (i = 0; i < ARRAY_SIZE(tests_input); i++) { + if (!test__start_subtest(tests_input[i].name)) + continue; + test = &tests_input[i]; + /* All tests are expected to have one rx-ok port first, + * then a non-working rx port, and finally a rx-ok port + */ + if (test->test_setup && + !ASSERT_OK(test->test_setup(), "init filter")) + continue; + + ASSERT_EQ(run_test(test, 0), TEST_PACKETS_COUNT, + "test first port"); + ASSERT_EQ(run_test(test, 1), 0, "test second port"); + ASSERT_EQ(run_test(test, 2), TEST_PACKETS_COUNT, + "test third port"); + if (test->test_teardown) + test->test_teardown(); + } + test_global_shutdown(&ctx); +} diff --git a/tools/testing/selftests/bpf/prog_tests/free_timer.c b/tools/testing/selftests/bpf/prog_tests/free_timer.c new file mode 100644 index 000000000000..b7b77a6b2979 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/free_timer.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ +#define _GNU_SOURCE +#include <unistd.h> +#include <sys/syscall.h> +#include <test_progs.h> + +#include "free_timer.skel.h" + +struct run_ctx { + struct bpf_program *start_prog; + struct bpf_program *overwrite_prog; + pthread_barrier_t notify; + int loop; + bool start; + bool stop; +}; + +static void start_threads(struct run_ctx *ctx) +{ + ctx->start = true; +} + +static void stop_threads(struct run_ctx *ctx) +{ + ctx->stop = true; + /* Guarantee the order between ->stop and ->start */ + __atomic_store_n(&ctx->start, true, __ATOMIC_RELEASE); +} + +static int wait_for_start(struct run_ctx *ctx) +{ + while (!__atomic_load_n(&ctx->start, __ATOMIC_ACQUIRE)) + usleep(10); + + return ctx->stop; +} + +static void *overwrite_timer_fn(void *arg) +{ + struct run_ctx *ctx = arg; + int loop, fd, err; + cpu_set_t cpuset; + long ret = 0; + + /* Pin on CPU 0 */ + CPU_ZERO(&cpuset); + CPU_SET(0, &cpuset); + pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); + + /* Is the thread being stopped ? */ + err = wait_for_start(ctx); + if (err) + return NULL; + + fd = bpf_program__fd(ctx->overwrite_prog); + loop = ctx->loop; + while (loop-- > 0) { + LIBBPF_OPTS(bpf_test_run_opts, opts); + + /* Wait for start thread to complete */ + pthread_barrier_wait(&ctx->notify); + + /* Overwrite timers */ + err = bpf_prog_test_run_opts(fd, &opts); + if (err) + ret |= 1; + else if (opts.retval) + ret |= 2; + + /* Notify start thread to start timers */ + pthread_barrier_wait(&ctx->notify); + } + + return (void *)ret; +} + +static void *start_timer_fn(void *arg) +{ + struct run_ctx *ctx = arg; + int loop, fd, err; + cpu_set_t cpuset; + long ret = 0; + + /* Pin on CPU 1 */ + CPU_ZERO(&cpuset); + CPU_SET(1, &cpuset); + pthread_setaffinity_np(pthread_self(), sizeof(cpuset), &cpuset); + + /* Is the thread being stopped ? */ + err = wait_for_start(ctx); + if (err) + return NULL; + + fd = bpf_program__fd(ctx->start_prog); + loop = ctx->loop; + while (loop-- > 0) { + LIBBPF_OPTS(bpf_test_run_opts, opts); + + /* Run the prog to start timer */ + err = bpf_prog_test_run_opts(fd, &opts); + if (err) + ret |= 4; + else if (opts.retval) + ret |= 8; + + /* Notify overwrite thread to do overwrite */ + pthread_barrier_wait(&ctx->notify); + + /* Wait for overwrite thread to complete */ + pthread_barrier_wait(&ctx->notify); + } + + return (void *)ret; +} + +void test_free_timer(void) +{ + struct free_timer *skel; + struct bpf_program *prog; + struct run_ctx ctx; + pthread_t tid[2]; + void *ret; + int err; + + skel = free_timer__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_load")) + return; + + memset(&ctx, 0, sizeof(ctx)); + + prog = bpf_object__find_program_by_name(skel->obj, "start_timer"); + if (!ASSERT_OK_PTR(prog, "find start prog")) + goto out; + ctx.start_prog = prog; + + prog = bpf_object__find_program_by_name(skel->obj, "overwrite_timer"); + if (!ASSERT_OK_PTR(prog, "find overwrite prog")) + goto out; + ctx.overwrite_prog = prog; + + pthread_barrier_init(&ctx.notify, NULL, 2); + ctx.loop = 10; + + err = pthread_create(&tid[0], NULL, start_timer_fn, &ctx); + if (!ASSERT_OK(err, "create start_timer")) + goto out; + + err = pthread_create(&tid[1], NULL, overwrite_timer_fn, &ctx); + if (!ASSERT_OK(err, "create overwrite_timer")) { + stop_threads(&ctx); + goto out; + } + + start_threads(&ctx); + + ret = NULL; + err = pthread_join(tid[0], &ret); + ASSERT_EQ(err | (long)ret, 0, "start_timer"); + ret = NULL; + err = pthread_join(tid[1], &ret); + ASSERT_EQ(err | (long)ret, 0, "overwrite_timer"); +out: + free_timer__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c index 66ab1cae923e..e19ef509ebf8 100644 --- a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c +++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_test.c @@ -397,6 +397,31 @@ cleanup: kprobe_multi_session_cookie__destroy(skel); } +static void test_unique_match(void) +{ + LIBBPF_OPTS(bpf_kprobe_multi_opts, opts); + struct kprobe_multi *skel = NULL; + struct bpf_link *link = NULL; + + skel = kprobe_multi__open_and_load(); + if (!ASSERT_OK_PTR(skel, "kprobe_multi__open_and_load")) + return; + + opts.unique_match = true; + skel->bss->pid = getpid(); + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, + "bpf_fentry_test*", &opts); + if (!ASSERT_ERR_PTR(link, "bpf_program__attach_kprobe_multi_opts")) + bpf_link__destroy(link); + + link = bpf_program__attach_kprobe_multi_opts(skel->progs.test_kprobe_manual, + "bpf_fentry_test8*", &opts); + if (ASSERT_OK_PTR(link, "bpf_program__attach_kprobe_multi_opts")) + bpf_link__destroy(link); + + kprobe_multi__destroy(skel); +} + static size_t symbol_hash(long key, void *ctx __maybe_unused) { return str_hash((const char *) key); @@ -765,5 +790,7 @@ void test_kprobe_multi_test(void) test_session_skel_api(); if (test__start_subtest("session_cookie")) test_session_cookie_skel_api(); + if (test__start_subtest("unique_match")) + test_unique_match(); RUN_TESTS(kprobe_multi_verifier); } diff --git a/tools/testing/selftests/bpf/prog_tests/missed.c b/tools/testing/selftests/bpf/prog_tests/missed.c index 70d90c43537c..ed8857ae914a 100644 --- a/tools/testing/selftests/bpf/prog_tests/missed.c +++ b/tools/testing/selftests/bpf/prog_tests/missed.c @@ -85,6 +85,7 @@ static void test_missed_kprobe_recursion(void) ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test3)), 1, "test3_recursion_misses"); ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test4)), 1, "test4_recursion_misses"); ASSERT_GE(get_missed_count(bpf_program__fd(skel->progs.test5)), 1, "test5_recursion_misses"); + ASSERT_EQ(get_missed_count(bpf_program__fd(skel->progs.test6)), 1, "test6_recursion_misses"); cleanup: missed_kprobe_recursion__destroy(skel); diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 884ad87783d5..1e3e4392dcca 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -111,31 +111,35 @@ out: static void test_sockmap_vsock_delete_on_close(void) { - int err, c, p, map; - const int zero = 0; - - err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); - if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) - return; + int map, c, p, err, zero = 0; map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); - if (!ASSERT_GE(map, 0, "bpf_map_create")) { - close(c); - goto out; - } + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; - err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); - close(c); - if (!ASSERT_OK(err, "bpf_map_update")) - goto out; + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; + + if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST)) + goto close_socks; + + xclose(c); + xclose(p); + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); ASSERT_OK(err, "after close(), bpf_map_update"); -out: - close(p); - close(map); +close_socks: + xclose(c); + xclose(p); +close_map: + xclose(map); } static void test_skmsg_helpers(enum bpf_map_type map_type) @@ -522,8 +526,8 @@ static void test_sockmap_skb_verdict_shutdown(void) if (!ASSERT_EQ(err, 1, "epoll_wait(fd)")) goto out_close; - n = recv(c1, &b, 1, SOCK_NONBLOCK); - ASSERT_EQ(n, 0, "recv_timeout(fin)"); + n = recv(c1, &b, 1, MSG_DONTWAIT); + ASSERT_EQ(n, 0, "recv(fin)"); out_close: close(c1); close(p1); @@ -531,57 +535,6 @@ out: test_sockmap_pass_prog__destroy(skel); } -static void test_sockmap_stream_pass(void) -{ - int zero = 0, sent, recvd; - int verdict, parser; - int err, map; - int c = -1, p = -1; - struct test_sockmap_pass_prog *pass = NULL; - char snd[256] = "0123456789"; - char rcv[256] = "0"; - - pass = test_sockmap_pass_prog__open_and_load(); - verdict = bpf_program__fd(pass->progs.prog_skb_verdict); - parser = bpf_program__fd(pass->progs.prog_skb_parser); - map = bpf_map__fd(pass->maps.sock_map_rx); - - err = bpf_prog_attach(parser, map, BPF_SK_SKB_STREAM_PARSER, 0); - if (!ASSERT_OK(err, "bpf_prog_attach stream parser")) - goto out; - - err = bpf_prog_attach(verdict, map, BPF_SK_SKB_STREAM_VERDICT, 0); - if (!ASSERT_OK(err, "bpf_prog_attach stream verdict")) - goto out; - - err = create_pair(AF_INET, SOCK_STREAM, &c, &p); - if (err) - goto out; - - /* sk_data_ready of 'p' will be replaced by strparser handler */ - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); - if (!ASSERT_OK(err, "bpf_map_update_elem(p)")) - goto out_close; - - /* - * as 'prog_skb_parser' return the original skb len and - * 'prog_skb_verdict' return SK_PASS, the kernel will just - * pass it through to original socket 'p' - */ - sent = xsend(c, snd, sizeof(snd), 0); - ASSERT_EQ(sent, sizeof(snd), "xsend(c)"); - - recvd = recv_timeout(p, rcv, sizeof(rcv), SOCK_NONBLOCK, - IO_TIMEOUT_SEC); - ASSERT_EQ(recvd, sizeof(rcv), "recv_timeout(p)"); - -out_close: - close(c); - close(p); - -out: - test_sockmap_pass_prog__destroy(pass); -} static void test_sockmap_skb_verdict_fionread(bool pass_prog) { @@ -628,7 +581,7 @@ static void test_sockmap_skb_verdict_fionread(bool pass_prog) ASSERT_EQ(avail, expected, "ioctl(FIONREAD)"); /* On DROP test there will be no data to read */ if (pass_prog) { - recvd = recv_timeout(c1, &buf, sizeof(buf), SOCK_NONBLOCK, IO_TIMEOUT_SEC); + recvd = recv_timeout(c1, &buf, sizeof(buf), MSG_DONTWAIT, IO_TIMEOUT_SEC); ASSERT_EQ(recvd, sizeof(buf), "recv_timeout(c0)"); } @@ -1061,6 +1014,34 @@ destroy: test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_vsock_unconnected(void) +{ + struct sockaddr_storage addr; + int map, s, zero = 0; + socklen_t alen; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; + + s = xsocket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) + goto close_map; + + /* Fail connect(), but trigger transport assignment. */ + init_addr_loopback(AF_VSOCK, &addr, &alen); + if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect")) + goto close_sock; + + ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update"); + +close_sock: + xclose(s); +close_map: + xclose(map); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1101,8 +1082,6 @@ void test_sockmap_basic(void) test_sockmap_progs_query(BPF_SK_SKB_VERDICT); if (test__start_subtest("sockmap skb_verdict shutdown")) test_sockmap_skb_verdict_shutdown(); - if (test__start_subtest("sockmap stream parser and verdict pass")) - test_sockmap_stream_pass(); if (test__start_subtest("sockmap skb_verdict fionread")) test_sockmap_skb_verdict_fionread(true); if (test__start_subtest("sockmap skb_verdict fionread on drop")) @@ -1127,4 +1106,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); if (test__start_subtest("sockmap skb_verdict vsock poll")) test_sockmap_skb_verdict_vsock_poll(); + if (test__start_subtest("sockmap vsock unconnected")) + test_sockmap_vsock_unconnected(); } diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c new file mode 100644 index 000000000000..621b3b71888e --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_strp.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <netinet/tcp.h> +#include <test_progs.h> +#include "sockmap_helpers.h" +#include "test_skmsg_load_helpers.skel.h" +#include "test_sockmap_strp.skel.h" + +#define STRP_PKT_HEAD_LEN 4 +#define STRP_PKT_BODY_LEN 6 +#define STRP_PKT_FULL_LEN (STRP_PKT_HEAD_LEN + STRP_PKT_BODY_LEN) + +static const char packet[STRP_PKT_FULL_LEN] = "head+body\0"; +static const int test_packet_num = 100; + +/* Current implementation of tcp_bpf_recvmsg_parser() invokes data_ready + * with sk held if an skb exists in sk_receive_queue. Then for the + * data_ready implementation of strparser, it will delay the read + * operation if sk is held and EAGAIN is returned. + */ +static int sockmap_strp_consume_pre_data(int p) +{ + int recvd; + bool retried = false; + char rcv[10]; + +retry: + errno = 0; + recvd = recv_timeout(p, rcv, sizeof(rcv), 0, 1); + if (recvd < 0 && errno == EAGAIN && retried == false) { + /* On the first call, EAGAIN will certainly be returned. + * A 1-second wait is enough for the workqueue to finish. + */ + sleep(1); + retried = true; + goto retry; + } + + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv error or truncated data") || + !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN), + "data mismatch")) + return -1; + return 0; +} + +static struct test_sockmap_strp *sockmap_strp_init(int *out_map, bool pass, + bool need_parser) +{ + struct test_sockmap_strp *strp = NULL; + int verdict, parser; + int err; + + strp = test_sockmap_strp__open_and_load(); + *out_map = bpf_map__fd(strp->maps.sock_map); + + if (need_parser) + parser = bpf_program__fd(strp->progs.prog_skb_parser_partial); + else + parser = bpf_program__fd(strp->progs.prog_skb_parser); + + if (pass) + verdict = bpf_program__fd(strp->progs.prog_skb_verdict_pass); + else + verdict = bpf_program__fd(strp->progs.prog_skb_verdict); + + err = bpf_prog_attach(parser, *out_map, BPF_SK_SKB_STREAM_PARSER, 0); + if (!ASSERT_OK(err, "bpf_prog_attach stream parser")) + goto err; + + err = bpf_prog_attach(verdict, *out_map, BPF_SK_SKB_STREAM_VERDICT, 0); + if (!ASSERT_OK(err, "bpf_prog_attach stream verdict")) + goto err; + + return strp; +err: + test_sockmap_strp__destroy(strp); + return NULL; +} + +/* Dispatch packets to different socket by packet size: + * + * ------ ------ + * | pkt4 || pkt1 |... > remote socket + * ------ ------ / ------ ------ + * | pkt8 | pkt7 |... + * ------ ------ \ ------ ------ + * | pkt3 || pkt2 |... > local socket + * ------ ------ + */ +static void test_sockmap_strp_dispatch_pkt(int family, int sotype) +{ + int i, j, zero = 0, one = 1, recvd; + int err, map; + int c0 = -1, p0 = -1, c1 = -1, p1 = -1; + struct test_sockmap_strp *strp = NULL; + int test_cnt = 6; + char rcv[10]; + struct { + char data[7]; + int data_len; + int send_cnt; + int *receiver; + } send_dir[2] = { + /* data expected to deliver to local */ + {"llllll", 6, 0, &p0}, + /* data expected to deliver to remote */ + {"rrrrr", 5, 0, &c1} + }; + + strp = sockmap_strp_init(&map, false, false); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) + goto out; + + err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p0)")) + goto out_close; + + err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p1)")) + goto out_close; + + err = setsockopt(c1, IPPROTO_TCP, TCP_NODELAY, &zero, sizeof(zero)); + if (!ASSERT_OK(err, "setsockopt(TCP_NODELAY)")) + goto out_close; + + /* deliver data with data size greater than 5 to local */ + strp->data->verdict_max_size = 5; + + for (i = 0; i < test_cnt; i++) { + int d = i % 2; + + xsend(c0, send_dir[d].data, send_dir[d].data_len, 0); + send_dir[d].send_cnt++; + } + + for (i = 0; i < 2; i++) { + for (j = 0; j < send_dir[i].send_cnt; j++) { + int expected = send_dir[i].data_len; + + recvd = recv_timeout(*send_dir[i].receiver, rcv, + expected, MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, expected, "recv_timeout()")) + goto out_close; + if (!ASSERT_OK(memcmp(send_dir[i].data, rcv, recvd), + "data mismatch")) + goto out_close; + } + } +out_close: + close(c0); + close(c1); + close(p0); + close(p1); +out: + test_sockmap_strp__destroy(strp); +} + +/* We have multiple packets in one skb + * ------------ ------------ ------------ + * | packet1 | packet2 | ... + * ------------ ------------ ------------ + */ +static void test_sockmap_strp_multiple_pkt(int family, int sotype) +{ + int i, zero = 0; + int sent, recvd, total; + int err, map; + int c = -1, p = -1; + struct test_sockmap_strp *strp = NULL; + char *snd = NULL, *rcv = NULL; + + strp = sockmap_strp_init(&map, true, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_pair(family, sotype, &c, &p); + if (err) + goto out; + + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)")) + goto out_close; + + /* construct multiple packets in one buffer */ + total = test_packet_num * STRP_PKT_FULL_LEN; + snd = malloc(total); + rcv = malloc(total + 1); + if (!ASSERT_TRUE(snd, "malloc(snd)") || + !ASSERT_TRUE(rcv, "malloc(rcv)")) + goto out_close; + + for (i = 0; i < test_packet_num; i++) { + memcpy(snd + i * STRP_PKT_FULL_LEN, + packet, STRP_PKT_FULL_LEN); + } + + sent = xsend(c, snd, total, 0); + if (!ASSERT_EQ(sent, total, "xsend(c)")) + goto out_close; + + /* try to recv one more byte to avoid truncation check */ + recvd = recv_timeout(p, rcv, total + 1, MSG_DONTWAIT, IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, total, "recv(rcv)")) + goto out_close; + + /* we sent TCP segment with multiple encapsulation + * then check whether packets are handled correctly + */ + if (!ASSERT_OK(memcmp(snd, rcv, total), "data mismatch")) + goto out_close; + +out_close: + close(c); + close(p); + if (snd) + free(snd); + if (rcv) + free(rcv); +out: + test_sockmap_strp__destroy(strp); +} + +/* Test strparser with partial read */ +static void test_sockmap_strp_partial_read(int family, int sotype) +{ + int zero = 0, recvd, off; + int err, map; + int c = -1, p = -1; + struct test_sockmap_strp *strp = NULL; + char rcv[STRP_PKT_FULL_LEN + 1] = "0"; + + strp = sockmap_strp_init(&map, true, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_pair(family, sotype, &c, &p); + if (err) + goto out; + + /* sk_data_ready of 'p' will be replaced by strparser handler */ + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(zero, p)")) + goto out_close; + + /* 1.1 send partial head, 1 byte header left */ + off = STRP_PKT_HEAD_LEN - 1; + xsend(c, packet, off, 0); + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(-1, recvd, "partial head sent, expected no data")) + goto out_close; + + /* 1.2 send remaining head and body */ + xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0); + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data")) + goto out_close; + + /* 2.1 send partial head, 1 byte header left */ + off = STRP_PKT_HEAD_LEN - 1; + xsend(c, packet, off, 0); + + /* 2.2 send remaining head and partial body, 1 byte body left */ + xsend(c, packet + off, STRP_PKT_FULL_LEN - off - 1, 0); + off = STRP_PKT_FULL_LEN - 1; + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, 1); + if (!ASSERT_EQ(-1, recvd, "partial body sent, expected no data")) + goto out_close; + + /* 2.3 send remaining body */ + xsend(c, packet + off, STRP_PKT_FULL_LEN - off, 0); + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "expected full data")) + goto out_close; + +out_close: + close(c); + close(p); + +out: + test_sockmap_strp__destroy(strp); +} + +/* Test simple socket read/write with strparser + FIONREAD */ +static void test_sockmap_strp_pass(int family, int sotype, bool fionread) +{ + int zero = 0, pkt_size = STRP_PKT_FULL_LEN, sent, recvd, avail; + int err, map; + int c = -1, p = -1; + int test_cnt = 10, i; + struct test_sockmap_strp *strp = NULL; + char rcv[STRP_PKT_FULL_LEN + 1] = "0"; + + strp = sockmap_strp_init(&map, true, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + err = create_pair(family, sotype, &c, &p); + if (err) + goto out; + + /* inject some data before bpf process, it should be read + * correctly because we check sk_receive_queue in + * tcp_bpf_recvmsg_parser(). + */ + sent = xsend(c, packet, pkt_size, 0); + if (!ASSERT_EQ(sent, pkt_size, "xsend(pre-data)")) + goto out_close; + + /* sk_data_ready of 'p' will be replaced by strparser handler */ + err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p)")) + goto out_close; + + /* consume previous data we injected */ + if (sockmap_strp_consume_pre_data(p)) + goto out_close; + + /* Previously, we encountered issues such as deadlocks and + * sequence errors that resulted in the inability to read + * continuously. Therefore, we perform multiple iterations + * of testing here. + */ + for (i = 0; i < test_cnt; i++) { + sent = xsend(c, packet, pkt_size, 0); + if (!ASSERT_EQ(sent, pkt_size, "xsend(c)")) + goto out_close; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, pkt_size, "recv_timeout(p)") || + !ASSERT_OK(memcmp(packet, rcv, pkt_size), + "memcmp, data mismatch")) + goto out_close; + } + + if (fionread) { + sent = xsend(c, packet, pkt_size, 0); + if (!ASSERT_EQ(sent, pkt_size, "second xsend(c)")) + goto out_close; + + err = ioctl(p, FIONREAD, &avail); + if (!ASSERT_OK(err, "ioctl(FIONREAD) error") || + !ASSERT_EQ(avail, pkt_size, "ioctl(FIONREAD)")) + goto out_close; + + recvd = recv_timeout(p, rcv, sizeof(rcv), MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, pkt_size, "second recv_timeout(p)") || + !ASSERT_OK(memcmp(packet, rcv, pkt_size), + "second memcmp, data mismatch")) + goto out_close; + } + +out_close: + close(c); + close(p); + +out: + test_sockmap_strp__destroy(strp); +} + +/* Test strparser with verdict mode */ +static void test_sockmap_strp_verdict(int family, int sotype) +{ + int zero = 0, one = 1, sent, recvd, off; + int err, map; + int c0 = -1, p0 = -1, c1 = -1, p1 = -1; + struct test_sockmap_strp *strp = NULL; + char rcv[STRP_PKT_FULL_LEN + 1] = "0"; + + strp = sockmap_strp_init(&map, false, true); + if (!ASSERT_TRUE(strp, "sockmap_strp_init")) + return; + + /* We simulate a reverse proxy server. + * When p0 receives data from c0, we forward it to c1. + * From c1's perspective, it will consider this data + * as being sent by p1. + */ + err = create_socket_pairs(family, sotype, &c0, &c1, &p0, &p1); + if (!ASSERT_OK(err, "create_socket_pairs()")) + goto out; + + err = bpf_map_update_elem(map, &zero, &p0, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p0)")) + goto out_close; + + err = bpf_map_update_elem(map, &one, &p1, BPF_NOEXIST); + if (!ASSERT_OK(err, "bpf_map_update_elem(p1)")) + goto out_close; + + sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0); + if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "xsend(c0)")) + goto out_close; + + recvd = recv_timeout(c1, rcv, sizeof(rcv), MSG_DONTWAIT, + IO_TIMEOUT_SEC); + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "recv_timeout(c1)") || + !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN), + "received data does not match the sent data")) + goto out_close; + + /* send again to ensure the stream is functioning correctly. */ + sent = xsend(c0, packet, STRP_PKT_FULL_LEN, 0); + if (!ASSERT_EQ(sent, STRP_PKT_FULL_LEN, "second xsend(c0)")) + goto out_close; + + /* partial read */ + off = STRP_PKT_FULL_LEN / 2; + recvd = recv_timeout(c1, rcv, off, MSG_DONTWAIT, + IO_TIMEOUT_SEC); + recvd += recv_timeout(c1, rcv + off, sizeof(rcv) - off, MSG_DONTWAIT, + IO_TIMEOUT_SEC); + + if (!ASSERT_EQ(recvd, STRP_PKT_FULL_LEN, "partial recv_timeout(c1)") || + !ASSERT_OK(memcmp(packet, rcv, STRP_PKT_FULL_LEN), + "partial received data does not match the sent data")) + goto out_close; + +out_close: + close(c0); + close(c1); + close(p0); + close(p1); +out: + test_sockmap_strp__destroy(strp); +} + +void test_sockmap_strp(void) +{ + if (test__start_subtest("sockmap strp tcp pass")) + test_sockmap_strp_pass(AF_INET, SOCK_STREAM, false); + if (test__start_subtest("sockmap strp tcp v6 pass")) + test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, false); + if (test__start_subtest("sockmap strp tcp pass fionread")) + test_sockmap_strp_pass(AF_INET, SOCK_STREAM, true); + if (test__start_subtest("sockmap strp tcp v6 pass fionread")) + test_sockmap_strp_pass(AF_INET6, SOCK_STREAM, true); + if (test__start_subtest("sockmap strp tcp verdict")) + test_sockmap_strp_verdict(AF_INET, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp v6 verdict")) + test_sockmap_strp_verdict(AF_INET6, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp partial read")) + test_sockmap_strp_partial_read(AF_INET, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp multiple packets")) + test_sockmap_strp_multiple_pkt(AF_INET, SOCK_STREAM); + if (test__start_subtest("sockmap strp tcp dispatch")) + test_sockmap_strp_dispatch_pkt(AF_INET, SOCK_STREAM); +} diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c index 05d0e07da394..ba6b3ec1156a 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c @@ -2,7 +2,7 @@ #include <test_progs.h> #include "cgroup_helpers.h" -#include <linux/tcp.h> +#include <netinet/tcp.h> #include <linux/netlink.h> #include "sockopt_sk.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/verifier.c b/tools/testing/selftests/bpf/prog_tests/verifier.c index 3ee40ee9413a..8a0e1ff8a2dc 100644 --- a/tools/testing/selftests/bpf/prog_tests/verifier.c +++ b/tools/testing/selftests/bpf/prog_tests/verifier.c @@ -52,6 +52,8 @@ #include "verifier_map_ptr_mixing.skel.h" #include "verifier_map_ret_val.skel.h" #include "verifier_masking.skel.h" +#include "verifier_may_goto_1.skel.h" +#include "verifier_may_goto_2.skel.h" #include "verifier_meta_access.skel.h" #include "verifier_movsx.skel.h" #include "verifier_mtu.skel.h" @@ -98,6 +100,7 @@ #include "verifier_xdp_direct_packet_access.skel.h" #include "verifier_bits_iter.skel.h" #include "verifier_lsm.skel.h" +#include "irq.skel.h" #define MAX_ENTRIES 11 @@ -181,6 +184,8 @@ void test_verifier_map_ptr(void) { RUN(verifier_map_ptr); } void test_verifier_map_ptr_mixing(void) { RUN(verifier_map_ptr_mixing); } void test_verifier_map_ret_val(void) { RUN(verifier_map_ret_val); } void test_verifier_masking(void) { RUN(verifier_masking); } +void test_verifier_may_goto_1(void) { RUN(verifier_may_goto_1); } +void test_verifier_may_goto_2(void) { RUN(verifier_may_goto_2); } void test_verifier_meta_access(void) { RUN(verifier_meta_access); } void test_verifier_movsx(void) { RUN(verifier_movsx); } void test_verifier_netfilter_ctx(void) { RUN(verifier_netfilter_ctx); } @@ -225,6 +230,7 @@ void test_verifier_xdp(void) { RUN(verifier_xdp); } void test_verifier_xdp_direct_packet_access(void) { RUN(verifier_xdp_direct_packet_access); } void test_verifier_bits_iter(void) { RUN(verifier_bits_iter); } void test_verifier_lsm(void) { RUN(verifier_lsm); } +void test_irq(void) { RUN(irq); } void test_verifier_mtu(void) { RUN(verifier_mtu); } static int init_test_val_map(struct bpf_object *obj, char *map_name) diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c index 53d6ad8c2257..b2b2d85dbb1b 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c @@ -82,6 +82,8 @@ static void test_xdp_adjust_tail_grow2(void) /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ #if defined(__s390x__) int tailroom = 512; +#elif defined(__powerpc__) + int tailroom = 384; #else int tailroom = 320; #endif diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c index 6d8b54124cb3..fb952703653e 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c @@ -17,7 +17,7 @@ #include "network_helpers.h" #include <linux/if_bonding.h> #include <linux/limits.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <uapi/linux/netdev.h> #include "xdp_dummy.skel.h" diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c index c7f74f068e78..df27535995af 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c @@ -52,10 +52,10 @@ static void test_xdp_with_cpumap_helpers(void) ASSERT_EQ(info.id, val.bpf_prog.id, "Match program id to cpumap entry prog_id"); /* send a packet to trigger any potential bugs in there */ - char data[10] = {}; + char data[ETH_HLEN] = {}; DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c index 27ffed17d4be..461ab18705d5 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c @@ -23,7 +23,7 @@ static void test_xdp_with_devmap_helpers(void) __u32 len = sizeof(info); int err, dm_fd, dm_fd_redir, map_fd; struct nstoken *nstoken = NULL; - char data[10] = {}; + char data[ETH_HLEN] = {}; __u32 idx = 0; SYS(out_close, "ip netns add %s", TEST_NS); @@ -58,7 +58,7 @@ static void test_xdp_with_devmap_helpers(void) /* send a packet to trigger any potential bugs in there */ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); @@ -158,7 +158,7 @@ static void test_xdp_with_devmap_helpers_veth(void) struct nstoken *nstoken = NULL; __u32 len = sizeof(info); int err, dm_fd, dm_fd_redir, map_fd, ifindex_dst; - char data[10] = {}; + char data[ETH_HLEN] = {}; __u32 idx = 0; SYS(out_close, "ip netns add %s", TEST_NS); @@ -208,7 +208,7 @@ static void test_xdp_with_devmap_helpers_veth(void) /* send a packet to trigger any potential bugs in there */ DECLARE_LIBBPF_OPTS(bpf_test_run_opts, opts, .data_in = &data, - .data_size_in = 10, + .data_size_in = sizeof(data), .flags = BPF_F_TEST_XDP_LIVE_FRAMES, .repeat = 1, ); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index bad0ea167be7..7dac044664ac 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -7,10 +7,11 @@ #include <linux/if_link.h> #include <linux/ipv6.h> #include <linux/in6.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <bpf/bpf_endian.h> #include <uapi/linux/netdev.h> #include "test_xdp_do_redirect.skel.h" +#include "xdp_dummy.skel.h" struct udp_packet { struct ethhdr eth; @@ -246,3 +247,166 @@ out: SYS_NOFAIL("ip netns del testns"); test_xdp_do_redirect__destroy(skel); } + +#define NS_NB 3 +#define NS0 "NS0" +#define NS1 "NS1" +#define NS2 "NS2" +#define IPV4_NETWORK "10.1.1" +#define VETH1_INDEX 111 +#define VETH2_INDEX 222 + +struct test_data { + struct netns_obj *ns[NS_NB]; + u32 xdp_flags; +}; + +static void cleanup(struct test_data *data) +{ + int i; + + for (i = 0; i < NS_NB; i++) + netns_free(data->ns[i]); +} + +/** + * ping_setup - + * Create two veth peers and forward packets in-between using XDP + * + * ------------ ------------ + * | NS1 | | NS2 | + * | veth0 | | veth0 | + * | 10.1.1.1 | | 10.1.1.2 | + * -----|------ ------|----- + * | | + * | | + * -----|-----------------------|------- + * | veth1 veth2 | + * | (id:111) (id:222) | + * | | | | + * | ----- xdp forwarding ----- | + * | | + * | NS0 | + * ------------------------------------- + */ +static int ping_setup(struct test_data *data) +{ + int i; + + data->ns[0] = netns_new(NS0, false); + if (!ASSERT_OK_PTR(data->ns[0], "create ns")) + return -1; + + for (i = 1; i < NS_NB; i++) { + char ns_name[4] = {}; + + snprintf(ns_name, 4, "NS%d", i); + data->ns[i] = netns_new(ns_name, false); + if (!ASSERT_OK_PTR(data->ns[i], "create ns")) + goto fail; + + SYS(fail, + "ip -n %s link add veth%d index %d%d%d type veth peer name veth0 netns %s", + NS0, i, i, i, i, ns_name); + SYS(fail, "ip -n %s link set veth%d up", NS0, i); + + SYS(fail, "ip -n %s addr add %s.%d/24 dev veth0", ns_name, IPV4_NETWORK, i); + SYS(fail, "ip -n %s link set veth0 up", ns_name); + } + + return 0; + +fail: + cleanup(data); + return -1; +} + +static void ping_test(struct test_data *data) +{ + struct test_xdp_do_redirect *skel = NULL; + struct xdp_dummy *skel_dummy = NULL; + struct nstoken *nstoken = NULL; + int i, ret; + + skel_dummy = xdp_dummy__open_and_load(); + if (!ASSERT_OK_PTR(skel_dummy, "open and load xdp_dummy skeleton")) + goto close; + + for (i = 1; i < NS_NB; i++) { + char ns_name[4] = {}; + + snprintf(ns_name, 4, "NS%d", i); + nstoken = open_netns(ns_name); + if (!ASSERT_OK_PTR(nstoken, "open ns")) + goto close; + + ret = bpf_xdp_attach(if_nametoindex("veth0"), + bpf_program__fd(skel_dummy->progs.xdp_dummy_prog), + data->xdp_flags, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach dummy_prog")) + goto close; + + close_netns(nstoken); + nstoken = NULL; + } + + skel = test_xdp_do_redirect__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open and load skeleton")) + goto close; + + nstoken = open_netns(NS0); + if (!ASSERT_OK_PTR(nstoken, "open NS0")) + goto close; + + ret = bpf_xdp_attach(VETH2_INDEX, + bpf_program__fd(skel->progs.xdp_redirect_to_111), + data->xdp_flags, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + ret = bpf_xdp_attach(VETH1_INDEX, + bpf_program__fd(skel->progs.xdp_redirect_to_222), + data->xdp_flags, NULL); + if (!ASSERT_GE(ret, 0, "bpf_xdp_attach")) + goto close; + + close_netns(nstoken); + nstoken = NULL; + + nstoken = open_netns(NS1); + if (!ASSERT_OK_PTR(nstoken, "open NS1")) + goto close; + + SYS(close, "ping -c 1 %s.2 > /dev/null", IPV4_NETWORK); + +close: + close_netns(nstoken); + xdp_dummy__destroy(skel_dummy); + test_xdp_do_redirect__destroy(skel); +} + + +static void xdp_redirect_ping(u32 xdp_flags) +{ + struct test_data data = {}; + + if (ping_setup(&data) < 0) + return; + + data.xdp_flags = xdp_flags; + ping_test(&data); + cleanup(&data); +} + +void test_xdp_index_redirect(void) +{ + if (test__start_subtest("noflag")) + xdp_redirect_ping(0); + + if (test__start_subtest("drvflag")) + xdp_redirect_ping(XDP_FLAGS_DRV_MODE); + + if (test__start_subtest("skbflag")) + xdp_redirect_ping(XDP_FLAGS_SKB_MODE); +} + diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c index e1bf141d3401..3f9146d83d79 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c @@ -3,7 +3,7 @@ #include <network_helpers.h> #include <bpf/btf.h> #include <linux/if_link.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <net/if.h> #include <unistd.h> diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index c87ee2bf558c..3d47878ef6bf 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -10,7 +10,7 @@ #include <linux/errqueue.h> #include <linux/if_link.h> #include <linux/net_tstamp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <sys/mman.h> #include <net/if.h> #include <poll.h> @@ -133,23 +133,6 @@ static void close_xsk(struct xsk *xsk) munmap(xsk->umem_area, UMEM_SIZE); } -static void ip_csum(struct iphdr *iph) -{ - __u32 sum = 0; - __u16 *p; - int i; - - iph->check = 0; - p = (void *)iph; - for (i = 0; i < sizeof(*iph) / sizeof(*p); i++) - sum += p[i]; - - while (sum >> 16) - sum = (sum & 0xffff) + (sum >> 16); - - iph->check = ~sum; -} - static int generate_packet(struct xsk *xsk, __u16 dst_port) { struct xsk_tx_metadata *meta; @@ -192,7 +175,7 @@ static int generate_packet(struct xsk *xsk, __u16 dst_port) iph->protocol = IPPROTO_UDP; ASSERT_EQ(inet_pton(FAMILY, TX_ADDR, &iph->saddr), 1, "inet_pton(TX_ADDR)"); ASSERT_EQ(inet_pton(FAMILY, RX_ADDR, &iph->daddr), 1, "inet_pton(RX_ADDR)"); - ip_csum(iph); + iph->check = build_ip_csum(iph); udph->source = htons(UDP_SOURCE_PORT); udph->dest = htons(dst_port); diff --git a/tools/testing/selftests/bpf/progs/bad_struct_ops.c b/tools/testing/selftests/bpf/progs/bad_struct_ops.c index b7e175cd0af0..b3f77b4561c8 100644 --- a/tools/testing/selftests/bpf/progs/bad_struct_ops.c +++ b/tools/testing/selftests/bpf/progs/bad_struct_ops.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/cb_refs.c b/tools/testing/selftests/bpf/progs/cb_refs.c index 56c764df8196..5d6fc7f01ebb 100644 --- a/tools/testing/selftests/bpf/progs/cb_refs.c +++ b/tools/testing/selftests/bpf/progs/cb_refs.c @@ -2,7 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr *ptr; diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c b/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c new file mode 100644 index 000000000000..e32b07d802bb --- /dev/null +++ b/tools/testing/selftests/bpf/progs/cgroup_skb_direct_packet_access.c @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> + +__u32 data_end; + +SEC("cgroup_skb/ingress") +int direct_packet_access(struct __sk_buff *skb) +{ + data_end = skb->data_end; + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/dynptr_fail.c b/tools/testing/selftests/bpf/progs/dynptr_fail.c index dfd817d0348c..bd8f15229f5c 100644 --- a/tools/testing/selftests/bpf/progs/dynptr_fail.c +++ b/tools/testing/selftests/bpf/progs/dynptr_fail.c @@ -192,7 +192,7 @@ done: /* Can't add a dynptr to a map */ SEC("?raw_tp") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid read from stack") int add_dynptr_to_map1(void *ctx) { struct bpf_dynptr ptr; @@ -210,7 +210,7 @@ int add_dynptr_to_map1(void *ctx) /* Can't add a struct with an embedded dynptr to a map */ SEC("?raw_tp") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid read from stack") int add_dynptr_to_map2(void *ctx) { struct test_info x; @@ -398,7 +398,7 @@ int data_slice_missing_null_check2(void *ctx) * dynptr argument */ SEC("?raw_tp") -__failure __msg("invalid indirect read from stack") +__failure __msg("invalid read from stack") int invalid_helper1(void *ctx) { struct bpf_dynptr ptr; diff --git a/tools/testing/selftests/bpf/progs/epilogue_exit.c b/tools/testing/selftests/bpf/progs/epilogue_exit.c index 33d3a57bee90..35fec7c75bef 100644 --- a/tools/testing/selftests/bpf/progs/epilogue_exit.c +++ b/tools/testing/selftests/bpf/progs/epilogue_exit.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/epilogue_tailcall.c b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c index 7275dd594de0..153514691ba4 100644 --- a/tools/testing/selftests/bpf/progs/epilogue_tailcall.c +++ b/tools/testing/selftests/bpf/progs/epilogue_tailcall.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/exceptions_fail.c b/tools/testing/selftests/bpf/progs/exceptions_fail.c index fe0f3fa5aab6..8a0fdff89927 100644 --- a/tools/testing/selftests/bpf/progs/exceptions_fail.c +++ b/tools/testing/selftests/bpf/progs/exceptions_fail.c @@ -131,7 +131,7 @@ int reject_subprog_with_lock(void *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_rcu_read_lock-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region") int reject_with_rcu_read_lock(void *ctx) { bpf_rcu_read_lock(); @@ -147,7 +147,7 @@ __noinline static int throwing_subprog(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_rcu_read_lock-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_rcu_read_lock-ed region") int reject_subprog_with_rcu_read_lock(void *ctx) { bpf_rcu_read_lock(); diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c index 38034fb82530..02b82774469c 100644 --- a/tools/testing/selftests/bpf/progs/find_vma.c +++ b/tools/testing/selftests/bpf/progs/find_vma.c @@ -25,7 +25,7 @@ static long check_vma(struct task_struct *task, struct vm_area_struct *vma, { if (vma->vm_file) bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1, - vma->vm_file->f_path.dentry->d_iname); + vma->vm_file->f_path.dentry->d_shortname.string); /* check for VM_EXEC */ if (vma->vm_flags & VM_EXEC) diff --git a/tools/testing/selftests/bpf/progs/free_timer.c b/tools/testing/selftests/bpf/progs/free_timer.c new file mode 100644 index 000000000000..4501ae8fc414 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/free_timer.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2025. Huawei Technologies Co., Ltd */ +#include <linux/bpf.h> +#include <time.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_helpers.h> + +#define MAX_ENTRIES 8 + +struct map_value { + struct bpf_timer timer; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __type(key, int); + __type(value, struct map_value); + __uint(max_entries, MAX_ENTRIES); +} map SEC(".maps"); + +static int timer_cb(void *map, void *key, struct map_value *value) +{ + volatile int sum = 0; + int i; + + bpf_for(i, 0, 1024 * 1024) sum += i; + + return 0; +} + +static int start_cb(int key) +{ + struct map_value *value; + + value = bpf_map_lookup_elem(&map, (void *)&key); + if (!value) + return 0; + + bpf_timer_init(&value->timer, &map, CLOCK_MONOTONIC); + bpf_timer_set_callback(&value->timer, timer_cb); + /* Hope 100us will be enough to wake-up and run the overwrite thread */ + bpf_timer_start(&value->timer, 100000, BPF_F_TIMER_CPU_PIN); + + return 0; +} + +static int overwrite_cb(int key) +{ + struct map_value zero = {}; + + /* Free the timer which may run on other CPU */ + bpf_map_update_elem(&map, (void *)&key, &zero, BPF_ANY); + + return 0; +} + +SEC("syscall") +int BPF_PROG(start_timer) +{ + bpf_loop(MAX_ENTRIES, start_cb, NULL, 0); + return 0; +} + +SEC("syscall") +int BPF_PROG(overwrite_timer) +{ + bpf_loop(MAX_ENTRIES, overwrite_cb, NULL, 0); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/irq.c b/tools/testing/selftests/bpf/progs/irq.c new file mode 100644 index 000000000000..b0b53d980964 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/irq.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <vmlinux.h> +#include <bpf/bpf_helpers.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +unsigned long global_flags; + +extern void bpf_local_irq_save(unsigned long *) __weak __ksym; +extern void bpf_local_irq_restore(unsigned long *) __weak __ksym; +extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym; + +SEC("?tc") +__failure __msg("arg#0 doesn't point to an irq flag on stack") +int irq_save_bad_arg(struct __sk_buff *ctx) +{ + bpf_local_irq_save(&global_flags); + return 0; +} + +SEC("?tc") +__failure __msg("arg#0 doesn't point to an irq flag on stack") +int irq_restore_bad_arg(struct __sk_buff *ctx) +{ + bpf_local_irq_restore(&global_flags); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_2(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_save(&flags3); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3_minus_2(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_save(&flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_restore(&flags2); + return 0; +} + +static __noinline void local_irq_save(unsigned long *flags) +{ + bpf_local_irq_save(flags); +} + +static __noinline void local_irq_restore(unsigned long *flags) +{ + bpf_local_irq_restore(flags); +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_1_subprog(struct __sk_buff *ctx) +{ + unsigned long flags; + + local_irq_save(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_2_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + + local_irq_save(&flags1); + local_irq_save(&flags2); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + return 0; +} + +SEC("?tc") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_local_irq_save-ed region") +int irq_restore_missing_3_minus_2_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + local_irq_restore(&flags3); + local_irq_restore(&flags2); + return 0; +} + +SEC("?tc") +__success +int irq_balance(struct __sk_buff *ctx) +{ + unsigned long flags; + + local_irq_save(&flags); + local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__success +int irq_balance_n(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + local_irq_restore(&flags3); + local_irq_restore(&flags2); + local_irq_restore(&flags1); + return 0; +} + +static __noinline void local_irq_balance(void) +{ + unsigned long flags; + + local_irq_save(&flags); + local_irq_restore(&flags); +} + +static __noinline void local_irq_balance_n(void) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save(&flags1); + local_irq_save(&flags2); + local_irq_save(&flags3); + local_irq_restore(&flags3); + local_irq_restore(&flags2); + local_irq_restore(&flags1); +} + +SEC("?tc") +__success +int irq_balance_subprog(struct __sk_buff *ctx) +{ + local_irq_balance(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("sleepable helper bpf_copy_from_user#") +int irq_sleepable_helper(void *ctx) +{ + unsigned long flags; + u32 data; + + local_irq_save(&flags); + bpf_copy_from_user(&data, sizeof(data), NULL); + local_irq_restore(&flags); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("kernel func bpf_copy_from_user_str is sleepable within IRQ-disabled region") +int irq_sleepable_kfunc(void *ctx) +{ + unsigned long flags; + u32 data; + + local_irq_save(&flags); + bpf_copy_from_user_str(&data, sizeof(data), NULL, 0); + local_irq_restore(&flags); + return 0; +} + +int __noinline global_local_irq_balance(void) +{ + local_irq_balance_n(); + return 0; +} + +SEC("?tc") +__failure __msg("global function calls are not allowed with IRQs disabled") +int irq_global_subprog(struct __sk_buff *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + global_local_irq_balance(); + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_ooo(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_restore(&flags1); + bpf_local_irq_restore(&flags2); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_ooo_3(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags2); + bpf_local_irq_restore(&flags2); + bpf_local_irq_save(&flags3); + bpf_local_irq_restore(&flags1); + bpf_local_irq_restore(&flags3); + return 0; +} + +static __noinline void local_irq_save_3(unsigned long *flags1, unsigned long *flags2, + unsigned long *flags3) +{ + local_irq_save(flags1); + local_irq_save(flags2); + local_irq_save(flags3); +} + +SEC("?tc") +__success +int irq_restore_3_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save_3(&flags1, &flags2, &flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_restore(&flags2); + bpf_local_irq_restore(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_4_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + unsigned long flags4; + + local_irq_save_3(&flags1, &flags2, &flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_save(&flags4); + bpf_local_irq_restore(&flags4); + bpf_local_irq_restore(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_restore_ooo_3_subprog(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags2; + unsigned long flags3; + + local_irq_save_3(&flags1, &flags2, &flags3); + bpf_local_irq_restore(&flags3); + bpf_local_irq_restore(&flags2); + bpf_local_irq_save(&flags3); + bpf_local_irq_restore(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_restore_invalid(struct __sk_buff *ctx) +{ + unsigned long flags1; + unsigned long flags = 0xfaceb00c; + + bpf_local_irq_save(&flags1); + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("expected uninitialized") +int irq_save_invalid(struct __sk_buff *ctx) +{ + unsigned long flags1; + + bpf_local_irq_save(&flags1); + bpf_local_irq_save(&flags1); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_restore_iter(struct __sk_buff *ctx) +{ + struct bpf_iter_num it; + + bpf_iter_num_new(&it, 0, 42); + bpf_local_irq_restore((unsigned long *)&it); + return 0; +} + +SEC("?tc") +__failure __msg("Unreleased reference id=1") +int irq_save_iter(struct __sk_buff *ctx) +{ + struct bpf_iter_num it; + + /* Ensure same sized slot has st->ref_obj_id set, so we reject based on + * slot_type != STACK_IRQ_FLAG... + */ + _Static_assert(sizeof(it) == sizeof(unsigned long), "broken iterator size"); + + bpf_iter_num_new(&it, 0, 42); + bpf_local_irq_save((unsigned long *)&it); + bpf_local_irq_restore((unsigned long *)&it); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_flag_overwrite(struct __sk_buff *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + flags = 0xdeadbeef; + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("expected an initialized") +int irq_flag_overwrite_partial(struct __sk_buff *ctx) +{ + unsigned long flags; + + bpf_local_irq_save(&flags); + *(((char *)&flags) + 1) = 0xff; + bpf_local_irq_restore(&flags); + return 0; +} + +SEC("?tc") +__failure __msg("cannot restore irq state out of order") +int irq_ooo_refs_array(struct __sk_buff *ctx) +{ + unsigned long flags[4]; + struct { int i; } *p; + + /* refs=1 */ + bpf_local_irq_save(&flags[0]); + + /* refs=1,2 */ + p = bpf_obj_new(typeof(*p)); + if (!p) { + bpf_local_irq_restore(&flags[0]); + return 0; + } + + /* refs=1,2,3 */ + bpf_local_irq_save(&flags[1]); + + /* refs=1,2,3,4 */ + bpf_local_irq_save(&flags[2]); + + /* Now when we remove ref=2, the verifier must not break the ordering in + * the refs array between 1,3,4. With an older implementation, the + * verifier would swap the last element with the removed element, but to + * maintain the stack property we need to use memmove. + */ + bpf_obj_drop(p); + + /* Save and restore to reset active_irq_id to 3, as the ordering is now + * refs=1,4,3. When restoring the linear scan will find prev_id in order + * as 3 instead of 4. + */ + bpf_local_irq_save(&flags[3]); + bpf_local_irq_restore(&flags[3]); + + /* With the incorrect implementation, we can release flags[1], flags[2], + * and flags[0], i.e. in the wrong order. + */ + bpf_local_irq_restore(&flags[1]); + bpf_local_irq_restore(&flags[2]); + bpf_local_irq_restore(&flags[0]); + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 7c969c127573..190822b2f08b 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -524,11 +524,11 @@ int iter_subprog_iters(const void *ctx) } struct { - __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(type, BPF_MAP_TYPE_HASH); __type(key, int); __type(value, int); __uint(max_entries, 1000); -} arr_map SEC(".maps"); +} hash_map SEC(".maps"); SEC("?raw_tp") __failure __msg("invalid mem access 'scalar'") @@ -539,7 +539,7 @@ int iter_err_too_permissive1(const void *ctx) MY_PID_GUARD(); - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); if (!map_val) return 0; @@ -561,12 +561,12 @@ int iter_err_too_permissive2(const void *ctx) MY_PID_GUARD(); - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); if (!map_val) return 0; bpf_repeat(1000000) { - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); } *map_val = 123; @@ -585,7 +585,7 @@ int iter_err_too_permissive3(const void *ctx) MY_PID_GUARD(); bpf_repeat(1000000) { - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); found = true; } @@ -606,7 +606,7 @@ int iter_tricky_but_fine(const void *ctx) MY_PID_GUARD(); bpf_repeat(1000000) { - map_val = bpf_map_lookup_elem(&arr_map, &key); + map_val = bpf_map_lookup_elem(&hash_map, &key); if (map_val) { found = true; break; diff --git a/tools/testing/selftests/bpf/progs/iters_testmod.c b/tools/testing/selftests/bpf/progs/iters_testmod.c index df1d3db60b1b..9e4b45201e69 100644 --- a/tools/testing/selftests/bpf/progs/iters_testmod.c +++ b/tools/testing/selftests/bpf/progs/iters_testmod.c @@ -4,7 +4,7 @@ #include "bpf_experimental.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/jit_probe_mem.c b/tools/testing/selftests/bpf/progs/jit_probe_mem.c index f9789e668297..82190d79de37 100644 --- a/tools/testing/selftests/bpf/progs/jit_probe_mem.c +++ b/tools/testing/selftests/bpf/progs/jit_probe_mem.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" static struct prog_test_ref_kfunc __kptr *v; long total_sum = -1; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c index 7632d9ecb253..b9670e9a6e3d 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_destructive.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_destructive_test(void) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c index 08fae306539c..a1963497f0bf 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_fail.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_fail.c @@ -2,7 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct syscall_test_args { __u8 data[16]; diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_race.c b/tools/testing/selftests/bpf/progs/kfunc_call_race.c index d532af07decf..48f64827cd93 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_race.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_race.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_fail(struct __sk_buff *ctx) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c index f502f755f567..8b86113a0126 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c @@ -2,7 +2,7 @@ /* Copyright (c) 2021 Facebook */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_call_test4(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c index 2380c75e74ce..8e150e85b50d 100644 --- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c +++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2021 Facebook */ -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" extern const int bpf_prog_active __ksym; int active_res = -1; diff --git a/tools/testing/selftests/bpf/progs/local_kptr_stash.c b/tools/testing/selftests/bpf/progs/local_kptr_stash.c index b092a72b2c9d..d736506a4c80 100644 --- a/tools/testing/selftests/bpf/progs/local_kptr_stash.c +++ b/tools/testing/selftests/bpf/progs/local_kptr_stash.c @@ -6,7 +6,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "../bpf_experimental.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct plain_local; diff --git a/tools/testing/selftests/bpf/progs/map_kptr.c b/tools/testing/selftests/bpf/progs/map_kptr.c index ab0ce1d01a4a..edaba481db9d 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr.c +++ b/tools/testing/selftests/bpf/progs/map_kptr.c @@ -2,7 +2,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct map_value { struct prog_test_ref_kfunc __kptr_untrusted *unref_ptr; diff --git a/tools/testing/selftests/bpf/progs/map_kptr_fail.c b/tools/testing/selftests/bpf/progs/map_kptr_fail.c index 450bb373b179..4c0ff01f1a96 100644 --- a/tools/testing/selftests/bpf/progs/map_kptr_fail.c +++ b/tools/testing/selftests/bpf/progs/map_kptr_fail.c @@ -4,7 +4,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_core_read.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" struct map_value { char buf[8]; @@ -345,7 +345,7 @@ int reject_indirect_global_func_access(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("Unreleased reference id=5 alloc_insn=") +__failure __msg("Unreleased reference id=4 alloc_insn=") int kptr_xchg_ref_state(struct __sk_buff *ctx) { struct prog_test_ref_kfunc *p; diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe.c b/tools/testing/selftests/bpf/progs/missed_kprobe.c index 7f9ef701f5de..51a4fe64c917 100644 --- a/tools/testing/selftests/bpf/progs/missed_kprobe.c +++ b/tools/testing/selftests/bpf/progs/missed_kprobe.c @@ -2,7 +2,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c index 8ea71cbd6c45..29c18d869ec1 100644 --- a/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c +++ b/tools/testing/selftests/bpf/progs/missed_kprobe_recursion.c @@ -2,7 +2,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; @@ -46,3 +46,9 @@ int test5(struct pt_regs *ctx) { return 0; } + +SEC("kprobe.session/bpf_kfunc_common_test") +int test6(struct pt_regs *ctx) +{ + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/nested_acquire.c b/tools/testing/selftests/bpf/progs/nested_acquire.c index 8e521a21d995..49ad7b9adf56 100644 --- a/tools/testing/selftests/bpf/progs/nested_acquire.c +++ b/tools/testing/selftests/bpf/progs/nested_acquire.c @@ -4,7 +4,7 @@ #include <bpf/bpf_tracing.h> #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/preempt_lock.c b/tools/testing/selftests/bpf/progs/preempt_lock.c index 885377e83607..6c5797bf0ead 100644 --- a/tools/testing/selftests/bpf/progs/preempt_lock.c +++ b/tools/testing/selftests/bpf/progs/preempt_lock.c @@ -5,8 +5,10 @@ #include "bpf_misc.h" #include "bpf_experimental.h" +extern int bpf_copy_from_user_str(void *dst, u32 dst__sz, const void *unsafe_ptr__ign, u64 flags) __weak __ksym; + SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_1(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -14,7 +16,7 @@ int preempt_lock_missing_1(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_2(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -23,7 +25,7 @@ int preempt_lock_missing_2(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_3(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -33,7 +35,7 @@ int preempt_lock_missing_3(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_3_minus_2(struct __sk_buff *ctx) { bpf_preempt_disable(); @@ -55,7 +57,7 @@ static __noinline void preempt_enable(void) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_1_subprog(struct __sk_buff *ctx) { preempt_disable(); @@ -63,7 +65,7 @@ int preempt_lock_missing_1_subprog(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_2_subprog(struct __sk_buff *ctx) { preempt_disable(); @@ -72,7 +74,7 @@ int preempt_lock_missing_2_subprog(struct __sk_buff *ctx) } SEC("?tc") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_preempt_disable-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_preempt_disable-ed region") int preempt_lock_missing_2_minus_1_subprog(struct __sk_buff *ctx) { preempt_disable(); @@ -113,6 +115,18 @@ int preempt_sleepable_helper(void *ctx) return 0; } +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("kernel func bpf_copy_from_user_str is sleepable within non-preemptible region") +int preempt_sleepable_kfunc(void *ctx) +{ + u32 data; + + bpf_preempt_disable(); + bpf_copy_from_user_str(&data, sizeof(data), NULL, 0); + bpf_preempt_enable(); + return 0; +} + int __noinline preempt_global_subprog(void) { preempt_balance_subprog(); diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue.c b/tools/testing/selftests/bpf/progs/pro_epilogue.c index 44bc3f06b4b6..d97d6e07ef5c 100644 --- a/tools/testing/selftests/bpf/progs/pro_epilogue.c +++ b/tools/testing/selftests/bpf/progs/pro_epilogue.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c index 3529e53be355..6048d79be48b 100644 --- a/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c +++ b/tools/testing/selftests/bpf/progs/pro_epilogue_goto_start.c @@ -4,8 +4,8 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/sock_addr_kern.c b/tools/testing/selftests/bpf/progs/sock_addr_kern.c index 8386bb15ccdc..84ad515eafd6 100644 --- a/tools/testing/selftests/bpf/progs/sock_addr_kern.c +++ b/tools/testing/selftests/bpf/progs/sock_addr_kern.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Google LLC */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("syscall") int init_sock(struct init_sock_args *args) diff --git a/tools/testing/selftests/bpf/progs/struct_ops_detach.c b/tools/testing/selftests/bpf/progs/struct_ops_detach.c index d7fdcabe7d90..284a5b008e0c 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_detach.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_detach.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_helpers.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c index 3c822103bd40..d8cc99f5c2e2 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_forgotten_cb.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c index b450f72e744a..ccab3935aa42 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c index 6283099ec383..8b5515f4f724 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_maybe_null_fail.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_module.c b/tools/testing/selftests/bpf/progs/struct_ops_module.c index 4c56d4a9d9f4..71c420c3a5a6 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_module.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_module.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c index 9efcc6e4d356..5b23ea817f1f 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_multi_pages.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c index fa2021388485..5d0937fa07be 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_nulled_out_cb.c @@ -2,7 +2,7 @@ /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ #include <vmlinux.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c index 8ea57e5348ab..0e4d2ff63ab8 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c index 1f55ec4cee37..58d5d8dc2235 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_fail.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c index f2f300d50988..31e58389bb8b 100644 --- a/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c +++ b/tools/testing/selftests/bpf/progs/struct_ops_private_stack_recur.c @@ -3,7 +3,7 @@ #include <vmlinux.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/syscall.c b/tools/testing/selftests/bpf/progs/syscall.c index 0f4dfb770c32..b698cc62a371 100644 --- a/tools/testing/selftests/bpf/progs/syscall.c +++ b/tools/testing/selftests/bpf/progs/syscall.c @@ -76,9 +76,9 @@ static int btf_load(void) .magic = BTF_MAGIC, .version = BTF_VERSION, .hdr_len = sizeof(struct btf_header), - .type_len = sizeof(__u32) * 8, - .str_off = sizeof(__u32) * 8, - .str_len = sizeof(__u32), + .type_len = sizeof(raw_btf.types), + .str_off = offsetof(struct btf_blob, str) - offsetof(struct btf_blob, types), + .str_len = sizeof(raw_btf.str), }, .types = { /* long */ diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c index 683c8aaa63da..f344c6835e84 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c @@ -15,7 +15,7 @@ #include <linux/ipv6.h> #include <linux/pkt_cls.h> #include <linux/tcp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.h b/tools/testing/selftests/bpf/progs/test_cls_redirect.h index 233b089d1fba..eb55cb8a3dbd 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect.h +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.h @@ -10,7 +10,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> -#include <linux/udp.h> +#include <netinet/udp.h> /* offsetof() is used in static asserts, and the libbpf-redefined CO-RE * friendly version breaks compilation for older clang versions <= 15 diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c index 464515b824b9..d0f7670351e5 100644 --- a/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c +++ b/tools/testing/selftests/bpf/progs/test_cls_redirect_dynptr.c @@ -15,7 +15,7 @@ #include <linux/ipv6.h> #include <linux/pkt_cls.h> #include <linux/tcp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> diff --git a/tools/testing/selftests/bpf/progs/test_fill_link_info.c b/tools/testing/selftests/bpf/progs/test_fill_link_info.c index 6afa834756e9..fac33a14f200 100644 --- a/tools/testing/selftests/bpf/progs/test_fill_link_info.c +++ b/tools/testing/selftests/bpf/progs/test_fill_link_info.c @@ -6,13 +6,20 @@ #include <stdbool.h> extern bool CONFIG_X86_KERNEL_IBT __kconfig __weak; +extern bool CONFIG_PPC_FTRACE_OUT_OF_LINE __kconfig __weak; +extern bool CONFIG_KPROBES_ON_FTRACE __kconfig __weak; +extern bool CONFIG_PPC64 __kconfig __weak; -/* This function is here to have CONFIG_X86_KERNEL_IBT - * used and added to object BTF. +/* This function is here to have CONFIG_X86_KERNEL_IBT, + * CONFIG_PPC_FTRACE_OUT_OF_LINE, CONFIG_KPROBES_ON_FTRACE, + * CONFIG_PPC6 used and added to object BTF. */ int unused(void) { - return CONFIG_X86_KERNEL_IBT ? 0 : 1; + return CONFIG_X86_KERNEL_IBT || + CONFIG_PPC_FTRACE_OUT_OF_LINE || + CONFIG_KPROBES_ON_FTRACE || + CONFIG_PPC64 ? 0 : 1; } SEC("kprobe") diff --git a/tools/testing/selftests/bpf/progs/test_global_func10.c b/tools/testing/selftests/bpf/progs/test_global_func10.c index 5da001ca57a5..09d027bd3ea8 100644 --- a/tools/testing/selftests/bpf/progs/test_global_func10.c +++ b/tools/testing/selftests/bpf/progs/test_global_func10.c @@ -26,7 +26,7 @@ __noinline int foo(const struct Big *big) } SEC("cgroup_skb/ingress") -__failure __msg("invalid indirect access to stack") +__failure __msg("invalid read from stack") int global_func10(struct __sk_buff *skb) { const struct Small small = {.x = skb->len }; diff --git a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c index 7ac7e1de34d8..0ad1bf1ede8d 100644 --- a/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_kfunc_param_nullable.c @@ -4,7 +4,7 @@ #include <bpf/bpf_helpers.h> #include "bpf_misc.h" #include "bpf_kfuncs.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" SEC("tc") int kfunc_dynptr_nullable_test1(struct __sk_buff *skb) diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c index cc1a012d038f..fb07f5773888 100644 --- a/tools/testing/selftests/bpf/progs/test_module_attach.c +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -5,7 +5,7 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> #include <bpf/bpf_core_read.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" __u32 raw_tp_read_sz = 0; diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_strp.c b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c new file mode 100644 index 000000000000..dde3d5bec515 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_sockmap_strp.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> +int verdict_max_size = 10000; +struct { + __uint(type, BPF_MAP_TYPE_SOCKMAP); + __uint(max_entries, 20); + __type(key, int); + __type(value, int); +} sock_map SEC(".maps"); + +SEC("sk_skb/stream_verdict") +int prog_skb_verdict(struct __sk_buff *skb) +{ + __u32 one = 1; + + if (skb->len > verdict_max_size) + return SK_PASS; + + return bpf_sk_redirect_map(skb, &sock_map, one, 0); +} + +SEC("sk_skb/stream_verdict") +int prog_skb_verdict_pass(struct __sk_buff *skb) +{ + return SK_PASS; +} + +SEC("sk_skb/stream_parser") +int prog_skb_parser(struct __sk_buff *skb) +{ + return skb->len; +} + +SEC("sk_skb/stream_parser") +int prog_skb_parser_partial(struct __sk_buff *skb) +{ + /* agreement with the test program on a 4-byte size header + * and 6-byte body. + */ + if (skb->len < 4) { + /* need more header to determine full length */ + return 0; + } + /* return full length decoded from header. + * the return value may be larger than skb->len which + * means framework must wait body coming. + */ + return 10; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c index bba3e37f749b..39ff06f2c834 100644 --- a/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c +++ b/tools/testing/selftests/bpf/progs/test_tp_btf_nullable.c @@ -3,7 +3,7 @@ #include "vmlinux.h" #include <bpf/bpf_helpers.h> #include <bpf/bpf_tracing.h> -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" #include "bpf_misc.h" SEC("tp_btf/bpf_testmod_test_nullable_bare") diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c index 81bb38d72ced..dc74d8cf9e3f 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c @@ -10,6 +10,8 @@ int _xdp_adjust_tail_grow(struct xdp_md *xdp) /* SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) */ #if defined(__TARGET_ARCH_s390) int tailroom = 512; +#elif defined(__TARGET_ARCH_powerpc) + int tailroom = 384; #else int tailroom = 320; #endif diff --git a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c index 3abf068b8446..5928ed0911ca 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_do_redirect.c @@ -98,6 +98,18 @@ int xdp_count_pkts(struct xdp_md *xdp) return XDP_DROP; } +SEC("xdp") +int xdp_redirect_to_111(struct xdp_md *xdp) +{ + return bpf_redirect(111, 0); +} + +SEC("xdp") +int xdp_redirect_to_222(struct xdp_md *xdp) +{ + return bpf_redirect(222, 0); +} + SEC("tc") int tc_count_pkts(struct __sk_buff *skb) { diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c deleted file mode 100644 index b778cad45485..000000000000 --- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c +++ /dev/null @@ -1,26 +0,0 @@ -/* Copyright (c) 2017 VMware - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ -#include <linux/bpf.h> -#include <bpf/bpf_helpers.h> - -SEC("redirect_to_111") -int xdp_redirect_to_111(struct xdp_md *xdp) -{ - return bpf_redirect(111, 0); -} -SEC("redirect_to_222") -int xdp_redirect_to_222(struct xdp_md *xdp) -{ - return bpf_redirect(222, 0); -} - -char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/uninit_stack.c b/tools/testing/selftests/bpf/progs/uninit_stack.c index 8a403470e557..046a204c8fc6 100644 --- a/tools/testing/selftests/bpf/progs/uninit_stack.c +++ b/tools/testing/selftests/bpf/progs/uninit_stack.c @@ -70,7 +70,8 @@ __naked int helper_uninit_to_misc(void *ctx) r1 = r10; \ r1 += -128; \ r2 = 32; \ - call %[bpf_trace_printk]; \ + r3 = 0; \ + call %[bpf_probe_read_user]; \ /* Call to dummy() forces print_verifier_state(..., true), \ * thus showing the stack state, matched by __msg(). \ */ \ @@ -79,7 +80,7 @@ __naked int helper_uninit_to_misc(void *ctx) exit; \ " : - : __imm(bpf_trace_printk), + : __imm(bpf_probe_read_user), __imm(dummy) : __clobber_all); } diff --git a/tools/testing/selftests/bpf/progs/unsupported_ops.c b/tools/testing/selftests/bpf/progs/unsupported_ops.c index 9180365a3568..8aa2e0dd624e 100644 --- a/tools/testing/selftests/bpf/progs/unsupported_ops.c +++ b/tools/testing/selftests/bpf/progs/unsupported_ops.c @@ -4,7 +4,7 @@ #include <vmlinux.h> #include <bpf/bpf_tracing.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod.h" +#include "../test_kmods/bpf_testmod.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_array_access.c b/tools/testing/selftests/bpf/progs/verifier_array_access.c index 4195aa824ba5..0a187ff725cc 100644 --- a/tools/testing/selftests/bpf/progs/verifier_array_access.c +++ b/tools/testing/selftests/bpf/progs/verifier_array_access.c @@ -29,6 +29,20 @@ struct { } map_array_wo SEC(".maps"); struct { + __uint(type, BPF_MAP_TYPE_PERCPU_ARRAY); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, struct test_val); +} map_array_pcpu SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __uint(max_entries, 2); + __type(key, __u32); + __type(value, struct test_val); +} map_array SEC(".maps"); + +struct { __uint(type, BPF_MAP_TYPE_HASH); __uint(max_entries, 1); __type(key, long long); @@ -525,4 +539,193 @@ l0_%=: exit; \ : __clobber_all); } +SEC("socket") +__description("valid map access into an array using constant without nullness") +__success __retval(4) __log_level(2) +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}") +unsigned int an_array_with_a_constant_no_nullness(void) +{ + /* Need 8-byte alignment for spill tracking */ + __u32 __attribute__((aligned(8))) key = 1; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("valid multiple map access into an array using constant without nullness") +__success __retval(8) __log_level(2) +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -16) = {{(0|r[0-9])}}") +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}") +unsigned int multiple_array_with_a_constant_no_nullness(void) +{ + __u32 __attribute__((aligned(8))) key = 1; + __u32 __attribute__((aligned(8))) key2 = 0; + struct test_val *val, *val2; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + val2 = bpf_map_lookup_elem(&map_array, &key2); + val2->index = offsetof(struct test_val, foo); + + return val->index + val2->index; +} + +SEC("socket") +__description("valid map access into an array using natural aligned 32-bit constant 0 without nullness") +__success __retval(4) +unsigned int an_array_with_a_32bit_constant_0_no_nullness(void) +{ + /* Unlike the above tests, 32-bit zeroing is precisely tracked even + * if writes are not aligned to BPF_REG_SIZE. This tests that our + * STACK_ZERO handling functions. + */ + struct test_val *val; + __u32 key = 0; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("valid map access into a pcpu array using constant without nullness") +__success __retval(4) __log_level(2) +__msg("mark_precise: frame0: regs= stack=-8 before {{[0-9]}}: ({{[a-f0-9]+}}) *(u32 *)(r10 -8) = {{(1|r[0-9])}}") +unsigned int a_pcpu_array_with_a_constant_no_nullness(void) +{ + __u32 __attribute__((aligned(8))) key = 1; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_array_pcpu, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid map access into an array using constant without nullness") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int an_array_with_a_constant_no_nullness_out_of_bounds(void) +{ + /* Out of bounds */ + __u32 __attribute__((aligned(8))) key = 3; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid map access into an array using constant smaller than key_size") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int an_array_with_a_constant_too_small(void) +{ + __u32 __attribute__((aligned(8))) key; + struct test_val *val; + + /* Mark entire key as STACK_MISC */ + bpf_probe_read_user(&key, sizeof(key), NULL); + + /* Spilling only the bottom byte results in a tnum const of 1. + * We want to check that the verifier rejects it, as the spill is < 4B. + */ + *(__u8 *)&key = 1; + val = bpf_map_lookup_elem(&map_array, &key); + + /* Should fail, as verifier cannot prove in-bound lookup */ + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid map access into an array using constant larger than key_size") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int an_array_with_a_constant_too_big(void) +{ + struct test_val *val; + __u64 key = 1; + + /* Even if the constant value is < max_entries, if the spill size is + * larger than the key size, the set bits may not be where we expect them + * to be on different endian architectures. + */ + val = bpf_map_lookup_elem(&map_array, &key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("invalid elided lookup using const and non-const key") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int mixed_const_and_non_const_key_lookup(void) +{ + __u32 __attribute__((aligned(8))) key; + struct test_val *val; + __u32 rand; + + rand = bpf_get_prandom_u32(); + key = rand > 42 ? 1 : rand; + val = bpf_map_lookup_elem(&map_array, &key); + + return val->index; +} + +SEC("socket") +__failure __msg("invalid read from stack R2 off=4096 size=4") +__naked void key_lookup_at_invalid_fp(void) +{ + asm volatile (" \ + r1 = %[map_array] ll; \ + r2 = r10; \ + r2 += 4096; \ + call %[bpf_map_lookup_elem]; \ + r0 = *(u64*)(r0 + 0); \ + exit; \ +" : + : __imm(bpf_map_lookup_elem), + __imm_addr(map_array) + : __clobber_all); +} + +volatile __u32 __attribute__((aligned(8))) global_key; + +SEC("socket") +__description("invalid elided lookup using non-stack key") +__failure __msg("R0 invalid mem access 'map_value_or_null'") +unsigned int non_stack_key_lookup(void) +{ + struct test_val *val; + + global_key = 1; + val = bpf_map_lookup_elem(&map_array, (void *)&global_key); + val->index = offsetof(struct test_val, foo); + + return val->index; +} + +SEC("socket") +__description("doesn't reject UINT64_MAX as s64 for irrelevant maps") +__success __retval(42) +unsigned int doesnt_reject_irrelevant_maps(void) +{ + __u64 key = 0xFFFFFFFFFFFFFFFF; + struct test_val *val; + + val = bpf_map_lookup_elem(&map_hash_48b, &key); + if (val) + return val->index; + + return 42; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c index 8d77cc5323d3..fb62e09f2114 100644 --- a/tools/testing/selftests/bpf/progs/verifier_basic_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_basic_stack.c @@ -28,7 +28,7 @@ __naked void stack_out_of_bounds(void) SEC("socket") __description("uninitialized stack1") __success __log_level(4) __msg("stack depth 8") -__failure_unpriv __msg_unpriv("invalid indirect read from stack") +__failure_unpriv __msg_unpriv("invalid read from stack") __naked void uninitialized_stack1(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c index a0bb7fb40ea5..0eb33bb801b5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_bounds.c +++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c @@ -1200,4 +1200,138 @@ l0_%=: r0 = 0; \ : __clobber_all); } +SEC("tc") +__description("multiply mixed sign bounds. test 1") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=0x1bc16d5cd4927ee1,smax=umax=0x1bc16d674ec80000,smax32=0x7ffffeff,umax32=0xfffffeff,var_off=(0x1bc16d4000000000; 0x3ffffffeff))") +__naked void mult_mixed0_sign(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xf;" + "r6 -= 1000000000;" + "r7 &= 0xf;" + "r7 -= 2000000000;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiply mixed sign bounds. test 2") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=smin32=-100,smax=smax32=200)") +__naked void mult_mixed1_sign(void) +{ + asm volatile ( + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xf;" + "r6 -= 0xa;" + "r7 &= 0xf;" + "r7 -= 0x14;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiply negative bounds") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar(smin=umin=smin32=umin32=0x3ff280b0,smax=umax=smax32=umax32=0x3fff0001,var_off=(0x3ff00000; 0xf81ff))") +__naked void mult_sign_bounds(void) +{ + asm volatile ( + "r8 = 0x7fff;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xa;" + "r6 -= r8;" + "r7 &= 0xf;" + "r7 -= r8;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiply bounds that don't cross signed boundary") +__success __log_level(2) +__msg("r8 *= r6 {{.*}}; R6_w=scalar(smin=smin32=0,smax=umax=smax32=umax32=11,var_off=(0x0; 0xb)) R8_w=scalar(smin=0,smax=umax=0x7b96bb0a94a3a7cd,var_off=(0x0; 0x7fffffffffffffff))") +__naked void mult_no_sign_crossing(void) +{ + asm volatile ( + "r6 = 0xb;" + "r8 = 0xb3c3f8c99262687 ll;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= r7;" + "r8 *= r6;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiplication overflow, result in unbounded reg. test 1") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar()") +__naked void mult_unsign_ovf(void) +{ + asm volatile ( + "r8 = 0x7ffffffffff ll;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0x7fffffff;" + "r7 &= r8;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} + +SEC("tc") +__description("multiplication overflow, result in unbounded reg. test 2") +__success __log_level(2) +__msg("r6 *= r7 {{.*}}; R6_w=scalar()") +__naked void mult_sign_ovf(void) +{ + asm volatile ( + "r8 = 0x7ffffffff ll;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "call %[bpf_get_prandom_u32];" + "r7 = r0;" + "r6 &= 0xa;" + "r6 -= r8;" + "r7 &= 0x7fffffff;" + "r6 *= r7;" + "exit" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_skb_store_bytes) + : __clobber_all); +} char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_const_or.c b/tools/testing/selftests/bpf/progs/verifier_const_or.c index ba8922b2eebd..68c568c3c3a0 100644 --- a/tools/testing/selftests/bpf/progs/verifier_const_or.c +++ b/tools/testing/selftests/bpf/progs/verifier_const_or.c @@ -25,7 +25,7 @@ __naked void constant_should_keep_constant_type(void) SEC("tracepoint") __description("constant register |= constant should not bypass stack boundary checks") -__failure __msg("invalid indirect access to stack R1 off=-48 size=58") +__failure __msg("invalid write to stack R1 off=-48 size=58") __naked void not_bypass_stack_boundary_checks_1(void) { asm volatile (" \ @@ -62,7 +62,7 @@ __naked void register_should_keep_constant_type(void) SEC("tracepoint") __description("constant register |= constant register should not bypass stack boundary checks") -__failure __msg("invalid indirect access to stack R1 off=-48 size=58") +__failure __msg("invalid write to stack R1 off=-48 size=58") __naked void not_bypass_stack_boundary_checks_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c index 50c6b22606f6..f2c54e4d89eb 100644 --- a/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c +++ b/tools/testing/selftests/bpf/progs/verifier_helper_access_var_len.c @@ -67,7 +67,7 @@ SEC("socket") __description("helper access to variable memory: stack, bitwise AND, zero included") /* in privileged mode reads from uninitialized stack locations are permitted */ __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -64+0 size 64") +__msg_unpriv("invalid read from stack R2 off -64+0 size 64") __retval(0) __naked void stack_bitwise_and_zero_included(void) { @@ -100,7 +100,7 @@ __naked void stack_bitwise_and_zero_included(void) SEC("tracepoint") __description("helper access to variable memory: stack, bitwise AND + JMP, wrong max") -__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__failure __msg("invalid write to stack R1 off=-64 size=65") __naked void bitwise_and_jmp_wrong_max(void) { asm volatile (" \ @@ -187,7 +187,7 @@ l0_%=: r0 = 0; \ SEC("tracepoint") __description("helper access to variable memory: stack, JMP, bounds + offset") -__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__failure __msg("invalid write to stack R1 off=-64 size=65") __naked void memory_stack_jmp_bounds_offset(void) { asm volatile (" \ @@ -211,7 +211,7 @@ l0_%=: r0 = 0; \ SEC("tracepoint") __description("helper access to variable memory: stack, JMP, wrong max") -__failure __msg("invalid indirect access to stack R1 off=-64 size=65") +__failure __msg("invalid write to stack R1 off=-64 size=65") __naked void memory_stack_jmp_wrong_max(void) { asm volatile (" \ @@ -260,7 +260,7 @@ SEC("socket") __description("helper access to variable memory: stack, JMP, no min check") /* in privileged mode reads from uninitialized stack locations are permitted */ __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -64+0 size 64") +__msg_unpriv("invalid read from stack R2 off -64+0 size 64") __retval(0) __naked void stack_jmp_no_min_check(void) { @@ -750,7 +750,7 @@ SEC("socket") __description("helper access to variable memory: 8 bytes leak") /* in privileged mode reads from uninitialized stack locations are permitted */ __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -64+32 size 64") +__msg_unpriv("invalid read from stack R2 off -64+32 size 64") __retval(0) __naked void variable_memory_8_bytes_leak(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c index 5f2efb895edb..59e34d558654 100644 --- a/tools/testing/selftests/bpf/progs/verifier_int_ptr.c +++ b/tools/testing/selftests/bpf/progs/verifier_int_ptr.c @@ -96,7 +96,7 @@ __naked void arg_ptr_to_long_misaligned(void) SEC("cgroup/sysctl") __description("arg pointer to long size < sizeof(long)") -__failure __msg("invalid indirect access to stack R4 off=-4 size=8") +__failure __msg("invalid write to stack R4 off=-4 size=8") __naked void to_long_size_sizeof_long(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c index 4eaab1468eb7..7d088ba99ea5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_map_in_map.c +++ b/tools/testing/selftests/bpf/progs/verifier_map_in_map.c @@ -47,7 +47,7 @@ l0_%=: r0 = 0; \ SEC("xdp") __description("map in map state pruning") -__success __msg("processed 26 insns") +__success __msg("processed 15 insns") __log_level(2) __retval(0) __flag(BPF_F_TEST_STATE_FREQ) __naked void map_in_map_state_pruning(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c new file mode 100644 index 000000000000..e81097c96fe2 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_1.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> +#include "../../../include/linux/filter.h" +#include "bpf_misc.h" + +SEC("raw_tp") +__description("may_goto 0") +__arch_x86_64 +__xlated("0: r0 = 1") +__xlated("1: exit") +__success +__naked void may_goto_simple(void) +{ + asm volatile ( + ".8byte %[may_goto];" + "r0 = 1;" + ".8byte %[may_goto];" + "exit;" + : + : __imm_insn(may_goto, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("batch 2 of may_goto 0") +__arch_x86_64 +__xlated("0: r0 = 1") +__xlated("1: exit") +__success +__naked void may_goto_batch_0(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto1];" + "r0 = 1;" + ".8byte %[may_goto1];" + ".8byte %[may_goto1];" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("may_goto batch with offsets 2/1/0") +__arch_x86_64 +__xlated("0: r0 = 1") +__xlated("1: exit") +__success +__naked void may_goto_batch_1(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto2];" + ".8byte %[may_goto3];" + "r0 = 1;" + ".8byte %[may_goto1];" + ".8byte %[may_goto2];" + ".8byte %[may_goto3];" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)), + __imm_insn(may_goto2, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 1 /* offset */, 0)), + __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +SEC("raw_tp") +__description("may_goto batch with offsets 2/0") +__arch_x86_64 +__xlated("0: *(u64 *)(r10 -8) = 8388608") +__xlated("1: r11 = *(u64 *)(r10 -8)") +__xlated("2: if r11 == 0x0 goto pc+3") +__xlated("3: r11 -= 1") +__xlated("4: *(u64 *)(r10 -8) = r11") +__xlated("5: r0 = 1") +__xlated("6: r0 = 2") +__xlated("7: exit") +__success +__naked void may_goto_batch_2(void) +{ + asm volatile ( + ".8byte %[may_goto1];" + ".8byte %[may_goto3];" + "r0 = 1;" + "r0 = 2;" + "exit;" + : + : __imm_insn(may_goto1, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 2 /* offset */, 0)), + __imm_insn(may_goto3, BPF_RAW_INSN(BPF_JMP | BPF_JCOND, 0, 0, 0 /* offset */, 0)) + : __clobber_all); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c b/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c new file mode 100644 index 000000000000..b891faf50660 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/verifier_may_goto_2.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */ + +#include "bpf_misc.h" +#include "bpf_experimental.h" + +int gvar; + +SEC("raw_tp") +__description("C code with may_goto 0") +__success +int may_goto_c_code(void) +{ + int i, tmp[3]; + + for (i = 0; i < 3 && can_loop; i++) + tmp[i] = 0; + + for (i = 0; i < 3 && can_loop; i++) + tmp[i] = gvar - i; + + for (i = 0; i < 3 && can_loop; i++) + gvar += tmp[i]; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_mtu.c b/tools/testing/selftests/bpf/progs/verifier_mtu.c index 4ccf1ebc42d1..256956ea1ac5 100644 --- a/tools/testing/selftests/bpf/progs/verifier_mtu.c +++ b/tools/testing/selftests/bpf/progs/verifier_mtu.c @@ -8,7 +8,7 @@ SEC("tc/ingress") __description("uninit/mtu: write rejected") __success __caps_unpriv(CAP_BPF|CAP_NET_ADMIN) -__failure_unpriv __msg_unpriv("invalid indirect read from stack") +__failure_unpriv __msg_unpriv("invalid read from stack") int tc_uninit_mtu(struct __sk_buff *ctx) { __u32 mtu; diff --git a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c index 7cc83acac727..c689665e07b9 100644 --- a/tools/testing/selftests/bpf/progs/verifier_raw_stack.c +++ b/tools/testing/selftests/bpf/progs/verifier_raw_stack.c @@ -236,7 +236,7 @@ __naked void load_bytes_spilled_regs_data(void) SEC("tc") __description("raw_stack: skb_load_bytes, invalid access 1") -__failure __msg("invalid indirect access to stack R3 off=-513 size=8") +__failure __msg("invalid write to stack R3 off=-513 size=8") __naked void load_bytes_invalid_access_1(void) { asm volatile (" \ @@ -255,7 +255,7 @@ __naked void load_bytes_invalid_access_1(void) SEC("tc") __description("raw_stack: skb_load_bytes, invalid access 2") -__failure __msg("invalid indirect access to stack R3 off=-1 size=8") +__failure __msg("invalid write to stack R3 off=-1 size=8") __naked void load_bytes_invalid_access_2(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c index 3f679de73229..d9d7b05cf6d2 100644 --- a/tools/testing/selftests/bpf/progs/verifier_spin_lock.c +++ b/tools/testing/selftests/bpf/progs/verifier_spin_lock.c @@ -187,7 +187,7 @@ l0_%=: r6 = r0; \ SEC("cgroup/skb") __description("spin_lock: test6 missing unlock") -__failure __msg("BPF_EXIT instruction cannot be used inside bpf_spin_lock-ed region") +__failure __msg("BPF_EXIT instruction in main prog cannot be used inside bpf_spin_lock-ed region") __failure_unpriv __msg_unpriv("") __naked void spin_lock_test6_missing_unlock(void) { @@ -530,4 +530,30 @@ l1_%=: exit; \ : __clobber_all); } +SEC("tc") +__description("spin_lock: loop within a locked region") +__success __failure_unpriv __msg_unpriv("") +__retval(0) +int bpf_loop_inside_locked_region(void) +{ + const int zero = 0; + struct val *val; + int i, j = 0; + + val = bpf_map_lookup_elem(&map_spin_lock, &zero); + if (!val) + return -1; + + bpf_spin_lock(&val->l); + bpf_for(i, 0, 10) { + j++; + /* Silence "unused variable" warnings. */ + if (j == 10) + break; + } + bpf_spin_unlock(&val->l); + + return 0; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c index 7ea535bfbacd..a4a5e2071604 100644 --- a/tools/testing/selftests/bpf/progs/verifier_unpriv.c +++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c @@ -199,7 +199,7 @@ __naked void pass_pointer_to_helper_function(void) SEC("socket") __description("unpriv: indirectly pass pointer on stack to helper function") __success __failure_unpriv -__msg_unpriv("invalid indirect read from stack R2 off -8+0 size 8") +__msg_unpriv("invalid read from stack R2 off -8+0 size 8") __retval(0) __naked void on_stack_to_helper_function(void) { diff --git a/tools/testing/selftests/bpf/progs/verifier_var_off.c b/tools/testing/selftests/bpf/progs/verifier_var_off.c index c810f4f6f479..1d36d01b746e 100644 --- a/tools/testing/selftests/bpf/progs/verifier_var_off.c +++ b/tools/testing/selftests/bpf/progs/verifier_var_off.c @@ -203,7 +203,7 @@ __naked void stack_write_clobbers_spilled_regs(void) SEC("sockops") __description("indirect variable-offset stack access, unbounded") -__failure __msg("invalid unbounded variable-offset indirect access to stack R4") +__failure __msg("invalid unbounded variable-offset write to stack R4") __naked void variable_offset_stack_access_unbounded(void) { asm volatile (" \ @@ -236,7 +236,7 @@ l0_%=: r0 = 0; \ SEC("lwt_in") __description("indirect variable-offset stack access, max out of bound") -__failure __msg("invalid variable-offset indirect access to stack R2") +__failure __msg("invalid variable-offset read from stack R2") __naked void access_max_out_of_bound(void) { asm volatile (" \ @@ -269,7 +269,7 @@ __naked void access_max_out_of_bound(void) */ SEC("socket") __description("indirect variable-offset stack access, zero-sized, max out of bound") -__failure __msg("invalid variable-offset indirect access to stack R1") +__failure __msg("invalid variable-offset write to stack R1") __naked void zero_sized_access_max_out_of_bound(void) { asm volatile (" \ @@ -294,7 +294,7 @@ __naked void zero_sized_access_max_out_of_bound(void) SEC("lwt_in") __description("indirect variable-offset stack access, min out of bound") -__failure __msg("invalid variable-offset indirect access to stack R2") +__failure __msg("invalid variable-offset read from stack R2") __naked void access_min_out_of_bound(void) { asm volatile (" \ diff --git a/tools/testing/selftests/bpf/progs/wq.c b/tools/testing/selftests/bpf/progs/wq.c index f8d3ae0c29ae..2f1ba08c293e 100644 --- a/tools/testing/selftests/bpf/progs/wq.c +++ b/tools/testing/selftests/bpf/progs/wq.c @@ -5,7 +5,7 @@ #include "bpf_experimental.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/wq_failures.c b/tools/testing/selftests/bpf/progs/wq_failures.c index 25b51a72fe0f..4240211a1900 100644 --- a/tools/testing/selftests/bpf/progs/wq_failures.c +++ b/tools/testing/selftests/bpf/progs/wq_failures.c @@ -5,7 +5,7 @@ #include "bpf_experimental.h" #include <bpf/bpf_helpers.h> #include "bpf_misc.h" -#include "../bpf_testmod/bpf_testmod_kfunc.h" +#include "../test_kmods/bpf_testmod_kfunc.h" char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py index 0ed67b6b31dd..238121fda5b6 100755 --- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py +++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py @@ -66,7 +66,7 @@ class ArrayParser(BlockParser): def __init__(self, reader, array_name): self.array_name = array_name - self.start_marker = re.compile(f'(static )?const bool {self.array_name}\[.*\] = {{\n') + self.start_marker = re.compile(fr'(static )?const bool {self.array_name}\[.*\] = {{\n') super().__init__(reader) def search_block(self): @@ -80,7 +80,7 @@ class ArrayParser(BlockParser): Parse a block and return data as a dictionary. Items to extract must be on separate lines in the file. """ - pattern = re.compile('\[(BPF_\w*)\]\s*= (true|false),?$') + pattern = re.compile(r'\[(BPF_\w*)\]\s*= (true|false),?$') entries = set() while True: line = self.reader.readline() @@ -178,7 +178,7 @@ class FileExtractor(object): @enum_name: name of the enum to parse """ start_marker = re.compile(f'enum {enum_name} {{\n') - pattern = re.compile('^\s*(BPF_\w+),?(\s+/\*.*\*/)?$') + pattern = re.compile(r'^\s*(BPF_\w+),?(\s+/\*.*\*/)?$') end_marker = re.compile('^};') parser = BlockParser(self.reader) parser.search_block(start_marker) @@ -226,8 +226,8 @@ class FileExtractor(object): @block_name: name of the blog to parse, 'TYPE' in the example """ - start_marker = re.compile(f'\*{block_name}\* := {{') - pattern = re.compile('\*\*([\w/-]+)\*\*') + start_marker = re.compile(fr'\*{block_name}\* := {{') + pattern = re.compile(r'\*\*([\w/-]+)\*\*') end_marker = re.compile('}\n') return self.__get_description_list(start_marker, pattern, end_marker) @@ -245,8 +245,8 @@ class FileExtractor(object): @block_name: name of the blog to parse, 'TYPE' in the example """ - start_marker = re.compile(f'"\s*{block_name} := {{') - pattern = re.compile('([\w/]+) [|}]') + start_marker = re.compile(fr'"\s*{block_name} := {{') + pattern = re.compile(r'([\w/]+) [|}]') end_marker = re.compile('}') return self.__get_description_list(start_marker, pattern, end_marker) @@ -264,8 +264,8 @@ class FileExtractor(object): @macro: macro starting the block, 'HELP_SPEC_OPTIONS' in the example """ - start_marker = re.compile(f'"\s*{macro}\s*" [|}}]') - pattern = re.compile('([\w-]+) ?(?:\||}[ }\]])') + start_marker = re.compile(fr'"\s*{macro}\s*" [|}}]') + pattern = re.compile(r'([\w-]+) ?(?:\||}[ }\]])') end_marker = re.compile('}\\\\n') return self.__get_description_list(start_marker, pattern, end_marker) @@ -283,8 +283,8 @@ class FileExtractor(object): @block_name: name of the blog to parse, 'TYPE' in the example """ - start_marker = re.compile(f'local {block_name}=\'') - pattern = re.compile('(?:.*=\')?([\w/]+)') + start_marker = re.compile(fr'local {block_name}=\'') + pattern = re.compile(r'(?:.*=\')?([\w/]+)') end_marker = re.compile('\'$') return self.__get_description_list(start_marker, pattern, end_marker) @@ -316,7 +316,7 @@ class MainHeaderFileExtractor(SourceFileExtractor): {'-p', '-d', '--pretty', '--debug', '--json', '-j'} """ start_marker = re.compile(f'"OPTIONS :=') - pattern = re.compile('([\w-]+) ?(?:\||}[ }\]"])') + pattern = re.compile(r'([\w-]+) ?(?:\||}[ }\]"])') end_marker = re.compile('#define') parser = InlineListParser(self.reader) @@ -338,8 +338,8 @@ class ManSubstitutionsExtractor(SourceFileExtractor): {'-p', '-d', '--pretty', '--debug', '--json', '-j'} """ - start_marker = re.compile('\|COMMON_OPTIONS\| replace:: {') - pattern = re.compile('\*\*([\w/-]+)\*\*') + start_marker = re.compile(r'\|COMMON_OPTIONS\| replace:: {') + pattern = re.compile(r'\*\*([\w/-]+)\*\*') end_marker = re.compile('}$') parser = InlineListParser(self.reader) diff --git a/tools/testing/selftests/bpf/test_flow_dissector.c b/tools/testing/selftests/bpf/test_flow_dissector.c deleted file mode 100644 index 571cc076dd7d..000000000000 --- a/tools/testing/selftests/bpf/test_flow_dissector.c +++ /dev/null @@ -1,780 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Inject packets with all sorts of encapsulation into the kernel. - * - * IPv4/IPv6 outer layer 3 - * GRE/GUE/BARE outer layer 4, where bare is IPIP/SIT/IPv4-in-IPv6/.. - * IPv4/IPv6 inner layer 3 - */ - -#define _GNU_SOURCE - -#include <stddef.h> -#include <arpa/inet.h> -#include <asm/byteorder.h> -#include <error.h> -#include <errno.h> -#include <linux/if_packet.h> -#include <linux/if_ether.h> -#include <linux/ipv6.h> -#include <netinet/ip.h> -#include <netinet/in.h> -#include <netinet/udp.h> -#include <poll.h> -#include <stdbool.h> -#include <stdlib.h> -#include <stdio.h> -#include <string.h> -#include <sys/ioctl.h> -#include <sys/socket.h> -#include <sys/stat.h> -#include <sys/time.h> -#include <sys/types.h> -#include <unistd.h> - -#define CFG_PORT_INNER 8000 - -/* Add some protocol definitions that do not exist in userspace */ - -struct grehdr { - uint16_t unused; - uint16_t protocol; -} __attribute__((packed)); - -struct guehdr { - union { - struct { -#if defined(__LITTLE_ENDIAN_BITFIELD) - __u8 hlen:5, - control:1, - version:2; -#elif defined (__BIG_ENDIAN_BITFIELD) - __u8 version:2, - control:1, - hlen:5; -#else -#error "Please fix <asm/byteorder.h>" -#endif - __u8 proto_ctype; - __be16 flags; - }; - __be32 word; - }; -}; - -static uint8_t cfg_dsfield_inner; -static uint8_t cfg_dsfield_outer; -static uint8_t cfg_encap_proto; -static bool cfg_expect_failure = false; -static int cfg_l3_extra = AF_UNSPEC; /* optional SIT prefix */ -static int cfg_l3_inner = AF_UNSPEC; -static int cfg_l3_outer = AF_UNSPEC; -static int cfg_num_pkt = 10; -static int cfg_num_secs = 0; -static char cfg_payload_char = 'a'; -static int cfg_payload_len = 100; -static int cfg_port_gue = 6080; -static bool cfg_only_rx; -static bool cfg_only_tx; -static int cfg_src_port = 9; - -static char buf[ETH_DATA_LEN]; - -#define INIT_ADDR4(name, addr4, port) \ - static struct sockaddr_in name = { \ - .sin_family = AF_INET, \ - .sin_port = __constant_htons(port), \ - .sin_addr.s_addr = __constant_htonl(addr4), \ - }; - -#define INIT_ADDR6(name, addr6, port) \ - static struct sockaddr_in6 name = { \ - .sin6_family = AF_INET6, \ - .sin6_port = __constant_htons(port), \ - .sin6_addr = addr6, \ - }; - -INIT_ADDR4(in_daddr4, INADDR_LOOPBACK, CFG_PORT_INNER) -INIT_ADDR4(in_saddr4, INADDR_LOOPBACK + 2, 0) -INIT_ADDR4(out_daddr4, INADDR_LOOPBACK, 0) -INIT_ADDR4(out_saddr4, INADDR_LOOPBACK + 1, 0) -INIT_ADDR4(extra_daddr4, INADDR_LOOPBACK, 0) -INIT_ADDR4(extra_saddr4, INADDR_LOOPBACK + 1, 0) - -INIT_ADDR6(in_daddr6, IN6ADDR_LOOPBACK_INIT, CFG_PORT_INNER) -INIT_ADDR6(in_saddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(out_daddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(out_saddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(extra_daddr6, IN6ADDR_LOOPBACK_INIT, 0) -INIT_ADDR6(extra_saddr6, IN6ADDR_LOOPBACK_INIT, 0) - -static unsigned long util_gettime(void) -{ - struct timeval tv; - - gettimeofday(&tv, NULL); - return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); -} - -static void util_printaddr(const char *msg, struct sockaddr *addr) -{ - unsigned long off = 0; - char nbuf[INET6_ADDRSTRLEN]; - - switch (addr->sa_family) { - case PF_INET: - off = __builtin_offsetof(struct sockaddr_in, sin_addr); - break; - case PF_INET6: - off = __builtin_offsetof(struct sockaddr_in6, sin6_addr); - break; - default: - error(1, 0, "printaddr: unsupported family %u\n", - addr->sa_family); - } - - if (!inet_ntop(addr->sa_family, ((void *) addr) + off, nbuf, - sizeof(nbuf))) - error(1, errno, "inet_ntop"); - - fprintf(stderr, "%s: %s\n", msg, nbuf); -} - -static unsigned long add_csum_hword(const uint16_t *start, int num_u16) -{ - unsigned long sum = 0; - int i; - - for (i = 0; i < num_u16; i++) - sum += start[i]; - - return sum; -} - -static uint16_t build_ip_csum(const uint16_t *start, int num_u16, - unsigned long sum) -{ - sum += add_csum_hword(start, num_u16); - - while (sum >> 16) - sum = (sum & 0xffff) + (sum >> 16); - - return ~sum; -} - -static void build_ipv4_header(void *header, uint8_t proto, - uint32_t src, uint32_t dst, - int payload_len, uint8_t tos) -{ - struct iphdr *iph = header; - - iph->ihl = 5; - iph->version = 4; - iph->tos = tos; - iph->ttl = 8; - iph->tot_len = htons(sizeof(*iph) + payload_len); - iph->id = htons(1337); - iph->protocol = proto; - iph->saddr = src; - iph->daddr = dst; - iph->check = build_ip_csum((void *) iph, iph->ihl << 1, 0); -} - -static void ipv6_set_dsfield(struct ipv6hdr *ip6h, uint8_t dsfield) -{ - uint16_t val, *ptr = (uint16_t *)ip6h; - - val = ntohs(*ptr); - val &= 0xF00F; - val |= ((uint16_t) dsfield) << 4; - *ptr = htons(val); -} - -static void build_ipv6_header(void *header, uint8_t proto, - struct sockaddr_in6 *src, - struct sockaddr_in6 *dst, - int payload_len, uint8_t dsfield) -{ - struct ipv6hdr *ip6h = header; - - ip6h->version = 6; - ip6h->payload_len = htons(payload_len); - ip6h->nexthdr = proto; - ip6h->hop_limit = 8; - ipv6_set_dsfield(ip6h, dsfield); - - memcpy(&ip6h->saddr, &src->sin6_addr, sizeof(ip6h->saddr)); - memcpy(&ip6h->daddr, &dst->sin6_addr, sizeof(ip6h->daddr)); -} - -static uint16_t build_udp_v4_csum(const struct iphdr *iph, - const struct udphdr *udph, - int num_words) -{ - unsigned long pseudo_sum; - int num_u16 = sizeof(iph->saddr); /* halfwords: twice byte len */ - - pseudo_sum = add_csum_hword((void *) &iph->saddr, num_u16); - pseudo_sum += htons(IPPROTO_UDP); - pseudo_sum += udph->len; - return build_ip_csum((void *) udph, num_words, pseudo_sum); -} - -static uint16_t build_udp_v6_csum(const struct ipv6hdr *ip6h, - const struct udphdr *udph, - int num_words) -{ - unsigned long pseudo_sum; - int num_u16 = sizeof(ip6h->saddr); /* halfwords: twice byte len */ - - pseudo_sum = add_csum_hword((void *) &ip6h->saddr, num_u16); - pseudo_sum += htons(ip6h->nexthdr); - pseudo_sum += ip6h->payload_len; - return build_ip_csum((void *) udph, num_words, pseudo_sum); -} - -static void build_udp_header(void *header, int payload_len, - uint16_t dport, int family) -{ - struct udphdr *udph = header; - int len = sizeof(*udph) + payload_len; - - udph->source = htons(cfg_src_port); - udph->dest = htons(dport); - udph->len = htons(len); - udph->check = 0; - if (family == AF_INET) - udph->check = build_udp_v4_csum(header - sizeof(struct iphdr), - udph, len >> 1); - else - udph->check = build_udp_v6_csum(header - sizeof(struct ipv6hdr), - udph, len >> 1); -} - -static void build_gue_header(void *header, uint8_t proto) -{ - struct guehdr *gueh = header; - - gueh->proto_ctype = proto; -} - -static void build_gre_header(void *header, uint16_t proto) -{ - struct grehdr *greh = header; - - greh->protocol = htons(proto); -} - -static int l3_length(int family) -{ - if (family == AF_INET) - return sizeof(struct iphdr); - else - return sizeof(struct ipv6hdr); -} - -static int build_packet(void) -{ - int ol3_len = 0, ol4_len = 0, il3_len = 0, il4_len = 0; - int el3_len = 0; - - if (cfg_l3_extra) - el3_len = l3_length(cfg_l3_extra); - - /* calculate header offsets */ - if (cfg_encap_proto) { - ol3_len = l3_length(cfg_l3_outer); - - if (cfg_encap_proto == IPPROTO_GRE) - ol4_len = sizeof(struct grehdr); - else if (cfg_encap_proto == IPPROTO_UDP) - ol4_len = sizeof(struct udphdr) + sizeof(struct guehdr); - } - - il3_len = l3_length(cfg_l3_inner); - il4_len = sizeof(struct udphdr); - - if (el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len >= - sizeof(buf)) - error(1, 0, "packet too large\n"); - - /* - * Fill packet from inside out, to calculate correct checksums. - * But create ip before udp headers, as udp uses ip for pseudo-sum. - */ - memset(buf + el3_len + ol3_len + ol4_len + il3_len + il4_len, - cfg_payload_char, cfg_payload_len); - - /* add zero byte for udp csum padding */ - buf[el3_len + ol3_len + ol4_len + il3_len + il4_len + cfg_payload_len] = 0; - - switch (cfg_l3_inner) { - case PF_INET: - build_ipv4_header(buf + el3_len + ol3_len + ol4_len, - IPPROTO_UDP, - in_saddr4.sin_addr.s_addr, - in_daddr4.sin_addr.s_addr, - il4_len + cfg_payload_len, - cfg_dsfield_inner); - break; - case PF_INET6: - build_ipv6_header(buf + el3_len + ol3_len + ol4_len, - IPPROTO_UDP, - &in_saddr6, &in_daddr6, - il4_len + cfg_payload_len, - cfg_dsfield_inner); - break; - } - - build_udp_header(buf + el3_len + ol3_len + ol4_len + il3_len, - cfg_payload_len, CFG_PORT_INNER, cfg_l3_inner); - - if (!cfg_encap_proto) - return il3_len + il4_len + cfg_payload_len; - - switch (cfg_l3_outer) { - case PF_INET: - build_ipv4_header(buf + el3_len, cfg_encap_proto, - out_saddr4.sin_addr.s_addr, - out_daddr4.sin_addr.s_addr, - ol4_len + il3_len + il4_len + cfg_payload_len, - cfg_dsfield_outer); - break; - case PF_INET6: - build_ipv6_header(buf + el3_len, cfg_encap_proto, - &out_saddr6, &out_daddr6, - ol4_len + il3_len + il4_len + cfg_payload_len, - cfg_dsfield_outer); - break; - } - - switch (cfg_encap_proto) { - case IPPROTO_UDP: - build_gue_header(buf + el3_len + ol3_len + ol4_len - - sizeof(struct guehdr), - cfg_l3_inner == PF_INET ? IPPROTO_IPIP - : IPPROTO_IPV6); - build_udp_header(buf + el3_len + ol3_len, - sizeof(struct guehdr) + il3_len + il4_len + - cfg_payload_len, - cfg_port_gue, cfg_l3_outer); - break; - case IPPROTO_GRE: - build_gre_header(buf + el3_len + ol3_len, - cfg_l3_inner == PF_INET ? ETH_P_IP - : ETH_P_IPV6); - break; - } - - switch (cfg_l3_extra) { - case PF_INET: - build_ipv4_header(buf, - cfg_l3_outer == PF_INET ? IPPROTO_IPIP - : IPPROTO_IPV6, - extra_saddr4.sin_addr.s_addr, - extra_daddr4.sin_addr.s_addr, - ol3_len + ol4_len + il3_len + il4_len + - cfg_payload_len, 0); - break; - case PF_INET6: - build_ipv6_header(buf, - cfg_l3_outer == PF_INET ? IPPROTO_IPIP - : IPPROTO_IPV6, - &extra_saddr6, &extra_daddr6, - ol3_len + ol4_len + il3_len + il4_len + - cfg_payload_len, 0); - break; - } - - return el3_len + ol3_len + ol4_len + il3_len + il4_len + - cfg_payload_len; -} - -/* sender transmits encapsulated over RAW or unencap'd over UDP */ -static int setup_tx(void) -{ - int family, fd, ret; - - if (cfg_l3_extra) - family = cfg_l3_extra; - else if (cfg_l3_outer) - family = cfg_l3_outer; - else - family = cfg_l3_inner; - - fd = socket(family, SOCK_RAW, IPPROTO_RAW); - if (fd == -1) - error(1, errno, "socket tx"); - - if (cfg_l3_extra) { - if (cfg_l3_extra == PF_INET) - ret = connect(fd, (void *) &extra_daddr4, - sizeof(extra_daddr4)); - else - ret = connect(fd, (void *) &extra_daddr6, - sizeof(extra_daddr6)); - if (ret) - error(1, errno, "connect tx"); - } else if (cfg_l3_outer) { - /* connect to destination if not encapsulated */ - if (cfg_l3_outer == PF_INET) - ret = connect(fd, (void *) &out_daddr4, - sizeof(out_daddr4)); - else - ret = connect(fd, (void *) &out_daddr6, - sizeof(out_daddr6)); - if (ret) - error(1, errno, "connect tx"); - } else { - /* otherwise using loopback */ - if (cfg_l3_inner == PF_INET) - ret = connect(fd, (void *) &in_daddr4, - sizeof(in_daddr4)); - else - ret = connect(fd, (void *) &in_daddr6, - sizeof(in_daddr6)); - if (ret) - error(1, errno, "connect tx"); - } - - return fd; -} - -/* receiver reads unencapsulated UDP */ -static int setup_rx(void) -{ - int fd, ret; - - fd = socket(cfg_l3_inner, SOCK_DGRAM, 0); - if (fd == -1) - error(1, errno, "socket rx"); - - if (cfg_l3_inner == PF_INET) - ret = bind(fd, (void *) &in_daddr4, sizeof(in_daddr4)); - else - ret = bind(fd, (void *) &in_daddr6, sizeof(in_daddr6)); - if (ret) - error(1, errno, "bind rx"); - - return fd; -} - -static int do_tx(int fd, const char *pkt, int len) -{ - int ret; - - ret = write(fd, pkt, len); - if (ret == -1) - error(1, errno, "send"); - if (ret != len) - error(1, errno, "send: len (%d < %d)\n", ret, len); - - return 1; -} - -static int do_poll(int fd, short events, int timeout) -{ - struct pollfd pfd; - int ret; - - pfd.fd = fd; - pfd.events = events; - - ret = poll(&pfd, 1, timeout); - if (ret == -1) - error(1, errno, "poll"); - if (ret && !(pfd.revents & POLLIN)) - error(1, errno, "poll: unexpected event 0x%x\n", pfd.revents); - - return ret; -} - -static int do_rx(int fd) -{ - char rbuf; - int ret, num = 0; - - while (1) { - ret = recv(fd, &rbuf, 1, MSG_DONTWAIT); - if (ret == -1 && errno == EAGAIN) - break; - if (ret == -1) - error(1, errno, "recv"); - if (rbuf != cfg_payload_char) - error(1, 0, "recv: payload mismatch"); - num++; - } - - return num; -} - -static int do_main(void) -{ - unsigned long tstop, treport, tcur; - int fdt = -1, fdr = -1, len, tx = 0, rx = 0; - - if (!cfg_only_tx) - fdr = setup_rx(); - if (!cfg_only_rx) - fdt = setup_tx(); - - len = build_packet(); - - tcur = util_gettime(); - treport = tcur + 1000; - tstop = tcur + (cfg_num_secs * 1000); - - while (1) { - if (!cfg_only_rx) - tx += do_tx(fdt, buf, len); - - if (!cfg_only_tx) - rx += do_rx(fdr); - - if (cfg_num_secs) { - tcur = util_gettime(); - if (tcur >= tstop) - break; - if (tcur >= treport) { - fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx); - tx = 0; - rx = 0; - treport = tcur + 1000; - } - } else { - if (tx == cfg_num_pkt) - break; - } - } - - /* read straggler packets, if any */ - if (rx < tx) { - tstop = util_gettime() + 100; - while (rx < tx) { - tcur = util_gettime(); - if (tcur >= tstop) - break; - - do_poll(fdr, POLLIN, tstop - tcur); - rx += do_rx(fdr); - } - } - - fprintf(stderr, "pkts: tx=%u rx=%u\n", tx, rx); - - if (fdr != -1 && close(fdr)) - error(1, errno, "close rx"); - if (fdt != -1 && close(fdt)) - error(1, errno, "close tx"); - - /* - * success (== 0) only if received all packets - * unless failure is expected, in which case none must arrive. - */ - if (cfg_expect_failure) - return rx != 0; - else - return rx != tx; -} - - -static void __attribute__((noreturn)) usage(const char *filepath) -{ - fprintf(stderr, "Usage: %s [-e gre|gue|bare|none] [-i 4|6] [-l len] " - "[-O 4|6] [-o 4|6] [-n num] [-t secs] [-R] [-T] " - "[-s <osrc> [-d <odst>] [-S <isrc>] [-D <idst>] " - "[-x <otos>] [-X <itos>] [-f <isport>] [-F]\n", - filepath); - exit(1); -} - -static void parse_addr(int family, void *addr, const char *optarg) -{ - int ret; - - ret = inet_pton(family, optarg, addr); - if (ret == -1) - error(1, errno, "inet_pton"); - if (ret == 0) - error(1, 0, "inet_pton: bad string"); -} - -static void parse_addr4(struct sockaddr_in *addr, const char *optarg) -{ - parse_addr(AF_INET, &addr->sin_addr, optarg); -} - -static void parse_addr6(struct sockaddr_in6 *addr, const char *optarg) -{ - parse_addr(AF_INET6, &addr->sin6_addr, optarg); -} - -static int parse_protocol_family(const char *filepath, const char *optarg) -{ - if (!strcmp(optarg, "4")) - return PF_INET; - if (!strcmp(optarg, "6")) - return PF_INET6; - - usage(filepath); -} - -static void parse_opts(int argc, char **argv) -{ - int c; - - while ((c = getopt(argc, argv, "d:D:e:f:Fhi:l:n:o:O:Rs:S:t:Tx:X:")) != -1) { - switch (c) { - case 'd': - if (cfg_l3_outer == AF_UNSPEC) - error(1, 0, "-d must be preceded by -o"); - if (cfg_l3_outer == AF_INET) - parse_addr4(&out_daddr4, optarg); - else - parse_addr6(&out_daddr6, optarg); - break; - case 'D': - if (cfg_l3_inner == AF_UNSPEC) - error(1, 0, "-D must be preceded by -i"); - if (cfg_l3_inner == AF_INET) - parse_addr4(&in_daddr4, optarg); - else - parse_addr6(&in_daddr6, optarg); - break; - case 'e': - if (!strcmp(optarg, "gre")) - cfg_encap_proto = IPPROTO_GRE; - else if (!strcmp(optarg, "gue")) - cfg_encap_proto = IPPROTO_UDP; - else if (!strcmp(optarg, "bare")) - cfg_encap_proto = IPPROTO_IPIP; - else if (!strcmp(optarg, "none")) - cfg_encap_proto = IPPROTO_IP; /* == 0 */ - else - usage(argv[0]); - break; - case 'f': - cfg_src_port = strtol(optarg, NULL, 0); - break; - case 'F': - cfg_expect_failure = true; - break; - case 'h': - usage(argv[0]); - break; - case 'i': - if (!strcmp(optarg, "4")) - cfg_l3_inner = PF_INET; - else if (!strcmp(optarg, "6")) - cfg_l3_inner = PF_INET6; - else - usage(argv[0]); - break; - case 'l': - cfg_payload_len = strtol(optarg, NULL, 0); - break; - case 'n': - cfg_num_pkt = strtol(optarg, NULL, 0); - break; - case 'o': - cfg_l3_outer = parse_protocol_family(argv[0], optarg); - break; - case 'O': - cfg_l3_extra = parse_protocol_family(argv[0], optarg); - break; - case 'R': - cfg_only_rx = true; - break; - case 's': - if (cfg_l3_outer == AF_INET) - parse_addr4(&out_saddr4, optarg); - else - parse_addr6(&out_saddr6, optarg); - break; - case 'S': - if (cfg_l3_inner == AF_INET) - parse_addr4(&in_saddr4, optarg); - else - parse_addr6(&in_saddr6, optarg); - break; - case 't': - cfg_num_secs = strtol(optarg, NULL, 0); - break; - case 'T': - cfg_only_tx = true; - break; - case 'x': - cfg_dsfield_outer = strtol(optarg, NULL, 0); - break; - case 'X': - cfg_dsfield_inner = strtol(optarg, NULL, 0); - break; - } - } - - if (cfg_only_rx && cfg_only_tx) - error(1, 0, "options: cannot combine rx-only and tx-only"); - - if (cfg_encap_proto && cfg_l3_outer == AF_UNSPEC) - error(1, 0, "options: must specify outer with encap"); - else if ((!cfg_encap_proto) && cfg_l3_outer != AF_UNSPEC) - error(1, 0, "options: cannot combine no-encap and outer"); - else if ((!cfg_encap_proto) && cfg_l3_extra != AF_UNSPEC) - error(1, 0, "options: cannot combine no-encap and extra"); - - if (cfg_l3_inner == AF_UNSPEC) - cfg_l3_inner = AF_INET6; - if (cfg_l3_inner == AF_INET6 && cfg_encap_proto == IPPROTO_IPIP) - cfg_encap_proto = IPPROTO_IPV6; - - /* RFC 6040 4.2: - * on decap, if outer encountered congestion (CE == 0x3), - * but inner cannot encode ECN (NoECT == 0x0), then drop packet. - */ - if (((cfg_dsfield_outer & 0x3) == 0x3) && - ((cfg_dsfield_inner & 0x3) == 0x0)) - cfg_expect_failure = true; -} - -static void print_opts(void) -{ - if (cfg_l3_inner == PF_INET6) { - util_printaddr("inner.dest6", (void *) &in_daddr6); - util_printaddr("inner.source6", (void *) &in_saddr6); - } else { - util_printaddr("inner.dest4", (void *) &in_daddr4); - util_printaddr("inner.source4", (void *) &in_saddr4); - } - - if (!cfg_l3_outer) - return; - - fprintf(stderr, "encap proto: %u\n", cfg_encap_proto); - - if (cfg_l3_outer == PF_INET6) { - util_printaddr("outer.dest6", (void *) &out_daddr6); - util_printaddr("outer.source6", (void *) &out_saddr6); - } else { - util_printaddr("outer.dest4", (void *) &out_daddr4); - util_printaddr("outer.source4", (void *) &out_saddr4); - } - - if (!cfg_l3_extra) - return; - - if (cfg_l3_outer == PF_INET6) { - util_printaddr("extra.dest6", (void *) &extra_daddr6); - util_printaddr("extra.source6", (void *) &extra_saddr6); - } else { - util_printaddr("extra.dest4", (void *) &extra_daddr4); - util_printaddr("extra.source4", (void *) &extra_saddr4); - } - -} - -int main(int argc, char **argv) -{ - parse_opts(argc, argv); - print_opts(); - return do_main(); -} diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh deleted file mode 100755 index 4b298863797a..000000000000 --- a/tools/testing/selftests/bpf/test_flow_dissector.sh +++ /dev/null @@ -1,178 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Load BPF flow dissector and verify it correctly dissects traffic - -BPF_FILE="bpf_flow.bpf.o" -export TESTNAME=test_flow_dissector -unmount=0 - -# Kselftest framework requirement - SKIP code is 4. -ksft_skip=4 - -msg="skip all tests:" -if [ $UID != 0 ]; then - echo $msg please run this as root >&2 - exit $ksft_skip -fi - -# This test needs to be run in a network namespace with in_netns.sh. Check if -# this is the case and run it with in_netns.sh if it is being run in the root -# namespace. -if [[ -z $(ip netns identify $$) ]]; then - err=0 - if bpftool="$(which bpftool)"; then - echo "Testing global flow dissector..." - - $bpftool prog loadall $BPF_FILE /sys/fs/bpf/flow \ - type flow_dissector - - if ! unshare --net $bpftool prog attach pinned \ - /sys/fs/bpf/flow/_dissect flow_dissector; then - echo "Unexpected unsuccessful attach in namespace" >&2 - err=1 - fi - - $bpftool prog attach pinned /sys/fs/bpf/flow/_dissect \ - flow_dissector - - if unshare --net $bpftool prog attach pinned \ - /sys/fs/bpf/flow/_dissect flow_dissector; then - echo "Unexpected successful attach in namespace" >&2 - err=1 - fi - - if ! $bpftool prog detach pinned \ - /sys/fs/bpf/flow/_dissect flow_dissector; then - echo "Failed to detach flow dissector" >&2 - err=1 - fi - - rm -rf /sys/fs/bpf/flow - else - echo "Skipping root flow dissector test, bpftool not found" >&2 - fi - - # Run the rest of the tests in a net namespace. - ../net/in_netns.sh "$0" "$@" - err=$(( $err + $? )) - - if (( $err == 0 )); then - echo "selftests: $TESTNAME [PASS]"; - else - echo "selftests: $TESTNAME [FAILED]"; - fi - - exit $err -fi - -# Determine selftest success via shell exit code -exit_handler() -{ - set +e - - # Cleanup - tc filter del dev lo ingress pref 1337 2> /dev/null - tc qdisc del dev lo ingress 2> /dev/null - ./flow_dissector_load -d 2> /dev/null - if [ $unmount -ne 0 ]; then - umount bpffs 2> /dev/null - fi -} - -# Exit script immediately (well catched by trap handler) if any -# program/thing exits with a non-zero status. -set -e - -# (Use 'trap -l' to list meaning of numbers) -trap exit_handler 0 2 3 6 9 - -# Mount BPF file system -if /bin/mount | grep /sys/fs/bpf > /dev/null; then - echo "bpffs already mounted" -else - echo "bpffs not mounted. Mounting..." - unmount=1 - /bin/mount bpffs /sys/fs/bpf -t bpf -fi - -# Attach BPF program -./flow_dissector_load -p $BPF_FILE -s _dissect - -# Setup -tc qdisc add dev lo ingress -echo 0 > /proc/sys/net/ipv4/conf/default/rp_filter -echo 0 > /proc/sys/net/ipv4/conf/all/rp_filter -echo 0 > /proc/sys/net/ipv4/conf/lo/rp_filter - -echo "Testing IPv4..." -# Drops all IP/UDP packets coming from port 9 -tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \ - udp src_port 9 action drop - -# Send 10 IPv4/UDP packets from port 8. Filter should not drop any. -./test_flow_dissector -i 4 -f 8 -# Send 10 IPv4/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 4 -f 9 -F -# Send 10 IPv4/UDP packets from port 10. Filter should not drop any. -./test_flow_dissector -i 4 -f 10 - -echo "Testing IPv4 from 127.0.0.127 (fallback to generic dissector)..." -# Send 10 IPv4/UDP packets from port 8. Filter should not drop any. -./test_flow_dissector -i 4 -S 127.0.0.127 -f 8 -# Send 10 IPv4/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 4 -S 127.0.0.127 -f 9 -F -# Send 10 IPv4/UDP packets from port 10. Filter should not drop any. -./test_flow_dissector -i 4 -S 127.0.0.127 -f 10 - -echo "Testing IPIP..." -# Send 10 IPv4/IPv4/UDP packets from port 8. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 8 -# Send 10 IPv4/IPv4/UDP packets from port 9. Filter should drop all. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 9 -F -# Send 10 IPv4/IPv4/UDP packets from port 10. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e bare -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 10 - -echo "Testing IPv4 + GRE..." -# Send 10 IPv4/GRE/IPv4/UDP packets from port 8. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 8 -# Send 10 IPv4/GRE/IPv4/UDP packets from port 9. Filter should drop all. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 9 -F -# Send 10 IPv4/GRE/IPv4/UDP packets from port 10. Filter should not drop any. -./with_addr.sh ./with_tunnels.sh ./test_flow_dissector -o 4 -e gre -i 4 \ - -D 192.168.0.1 -S 1.1.1.1 -f 10 - -tc filter del dev lo ingress pref 1337 - -echo "Testing port range..." -# Drops all IP/UDP packets coming from port 8-10 -tc filter add dev lo parent ffff: protocol ip pref 1337 flower ip_proto \ - udp src_port 8-10 action drop - -# Send 10 IPv4/UDP packets from port 7. Filter should not drop any. -./test_flow_dissector -i 4 -f 7 -# Send 10 IPv4/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 4 -f 9 -F -# Send 10 IPv4/UDP packets from port 11. Filter should not drop any. -./test_flow_dissector -i 4 -f 11 - -tc filter del dev lo ingress pref 1337 - -echo "Testing IPv6..." -# Drops all IPv6/UDP packets coming from port 9 -tc filter add dev lo parent ffff: protocol ipv6 pref 1337 flower ip_proto \ - udp src_port 9 action drop - -# Send 10 IPv6/UDP packets from port 8. Filter should not drop any. -./test_flow_dissector -i 6 -f 8 -# Send 10 IPv6/UDP packets from port 9. Filter should drop all. -./test_flow_dissector -i 6 -f 9 -F -# Send 10 IPv6/UDP packets from port 10. Filter should not drop any. -./test_flow_dissector -i 6 -f 10 - -exit 0 diff --git a/tools/testing/selftests/bpf/bpf_testmod/.gitignore b/tools/testing/selftests/bpf/test_kmods/.gitignore index ded513777281..ded513777281 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/.gitignore +++ b/tools/testing/selftests/bpf/test_kmods/.gitignore diff --git a/tools/testing/selftests/bpf/test_kmods/Makefile b/tools/testing/selftests/bpf/test_kmods/Makefile new file mode 100644 index 000000000000..d4e50c4509c9 --- /dev/null +++ b/tools/testing/selftests/bpf/test_kmods/Makefile @@ -0,0 +1,21 @@ +TEST_KMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(TEST_KMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_testmod.ko bpf_test_no_cfi.ko bpf_test_modorder_x.ko \ + bpf_test_modorder_y.ko + +$(foreach m,$(MODULES),$(eval obj-m += $(m:.ko=.o))) + +CFLAGS_bpf_testmod.o = -I$(src) + +all: + $(Q)$(MAKE) -C $(KDIR) M=$(TEST_KMOD_DIR) modules + +clean: + $(Q)$(MAKE) -C $(KDIR) M=$(TEST_KMOD_DIR) clean diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c index 0cc747fa912f..0cc747fa912f 100644 --- a/tools/testing/selftests/bpf/bpf_test_modorder_x/bpf_test_modorder_x.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_x.c diff --git a/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c index c627ee085d13..c627ee085d13 100644 --- a/tools/testing/selftests/bpf/bpf_test_modorder_y/bpf_test_modorder_y.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_modorder_y.c diff --git a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c b/tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c index 948eb3962732..948eb3962732 100644 --- a/tools/testing/selftests/bpf/bpf_test_no_cfi/bpf_test_no_cfi.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_test_no_cfi.c diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h index aeef86b3da74..aeef86b3da74 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod-events.h diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index cc9dde507aba..cc9dde507aba 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h index 356803d1c10e..356803d1c10e 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.h diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h index b58817938deb..b58817938deb 100644 --- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod_kfunc.h +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 6088d8222d59..c9e745d49493 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -1282,6 +1282,21 @@ void crash_handler(int signum) backtrace_symbols_fd(bt, sz, STDERR_FILENO); } +void hexdump(const char *prefix, const void *buf, size_t len) +{ + for (int i = 0; i < len; i++) { + if (!(i % 16)) { + if (i) + fprintf(stdout, "\n"); + fprintf(stdout, "%s", prefix); + } + if (i && !(i % 8) && (i % 16)) + fprintf(stdout, "\t"); + fprintf(stdout, "%02X ", ((uint8_t *)(buf))[i]); + } + fprintf(stdout, "\n"); +} + static void sigint_handler(int signum) { int i; diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index 74de33ae37e5..404d0d4915d5 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -185,6 +185,7 @@ void test__end_subtest(void); void test__skip(void); void test__fail(void); int test__join_cgroup(const char *path); +void hexdump(const char *prefix, const void *buf, size_t len); #define PRINT_FAIL(format...) \ ({ \ @@ -344,6 +345,20 @@ int test__join_cgroup(const char *path); ___ok; \ }) +#define ASSERT_MEMEQ(actual, expected, len, name) ({ \ + static int duration = 0; \ + const void *__act = actual; \ + const void *__exp = expected; \ + int __len = len; \ + bool ___ok = memcmp(__act, __exp, __len) == 0; \ + CHECK(!___ok, (name), "unexpected memory mismatch\n"); \ + fprintf(stdout, "actual:\n"); \ + hexdump("\t", __act, __len); \ + fprintf(stdout, "expected:\n"); \ + hexdump("\t", __exp, __len); \ + ___ok; \ +}) + #define ASSERT_OK(res, name) ({ \ static int duration = 0; \ long long ___res = (res); \ diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh index 7989ec608454..cb55a908bb0d 100755 --- a/tools/testing/selftests/bpf/test_tc_tunnel.sh +++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh @@ -305,6 +305,7 @@ else client_connect verify_data server_listen + wait_for_port ${port} ${netcat_opt} fi # serverside, use BPF for decap diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh deleted file mode 100755 index 0746a4fde9d3..000000000000 --- a/tools/testing/selftests/bpf/test_xdp_redirect.sh +++ /dev/null @@ -1,79 +0,0 @@ -#!/bin/bash -# Create 2 namespaces with two veth peers, and -# forward packets in-between using generic XDP -# -# NS1(veth11) NS2(veth22) -# | | -# | | -# (veth1, ------ (veth2, -# id:111) id:222) -# | xdp forwarding | -# ------------------ - -readonly NS1="ns1-$(mktemp -u XXXXXX)" -readonly NS2="ns2-$(mktemp -u XXXXXX)" -ret=0 - -setup() -{ - - local xdpmode=$1 - - ip netns add ${NS1} - ip netns add ${NS2} - - ip link add veth1 index 111 type veth peer name veth11 netns ${NS1} - ip link add veth2 index 222 type veth peer name veth22 netns ${NS2} - - ip link set veth1 up - ip link set veth2 up - ip -n ${NS1} link set dev veth11 up - ip -n ${NS2} link set dev veth22 up - - ip -n ${NS1} addr add 10.1.1.11/24 dev veth11 - ip -n ${NS2} addr add 10.1.1.22/24 dev veth22 -} - -cleanup() -{ - ip link del veth1 2> /dev/null - ip link del veth2 2> /dev/null - ip netns del ${NS1} 2> /dev/null - ip netns del ${NS2} 2> /dev/null -} - -test_xdp_redirect() -{ - local xdpmode=$1 - - setup - - ip link set dev veth1 $xdpmode off &> /dev/null - if [ $? -ne 0 ];then - echo "selftests: test_xdp_redirect $xdpmode [SKIP]" - return 0 - fi - - ip -n ${NS1} link set veth11 $xdpmode obj xdp_dummy.bpf.o sec xdp &> /dev/null - ip -n ${NS2} link set veth22 $xdpmode obj xdp_dummy.bpf.o sec xdp &> /dev/null - ip link set dev veth1 $xdpmode obj test_xdp_redirect.bpf.o sec redirect_to_222 &> /dev/null - ip link set dev veth2 $xdpmode obj test_xdp_redirect.bpf.o sec redirect_to_111 &> /dev/null - - if ip netns exec ${NS1} ping -c 1 10.1.1.22 &> /dev/null && - ip netns exec ${NS2} ping -c 1 10.1.1.11 &> /dev/null; then - echo "selftests: test_xdp_redirect $xdpmode [PASS]"; - else - ret=1 - echo "selftests: test_xdp_redirect $xdpmode [FAILED]"; - fi - - cleanup -} - -set -e -trap cleanup 2 3 6 9 - -test_xdp_redirect xdpgeneric -test_xdp_redirect xdpdrv - -exit $ret diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c index 7afc2619ab14..18596ae0b0c1 100644 --- a/tools/testing/selftests/bpf/verifier/calls.c +++ b/tools/testing/selftests/bpf/verifier/calls.c @@ -2252,7 +2252,7 @@ BPF_EXIT_INSN(), }, .fixup_map_hash_48b = { 7 }, - .errstr_unpriv = "invalid indirect read from stack R2 off -8+0 size 8", + .errstr_unpriv = "invalid read from stack R2 off -8+0 size 8", .result_unpriv = REJECT, /* in privileged mode reads from uninitialized stack locations are permitted */ .result = ACCEPT, diff --git a/tools/testing/selftests/bpf/verifier/map_kptr.c b/tools/testing/selftests/bpf/verifier/map_kptr.c index f420c0312aa0..4b39f8472f9b 100644 --- a/tools/testing/selftests/bpf/verifier/map_kptr.c +++ b/tools/testing/selftests/bpf/verifier/map_kptr.c @@ -373,7 +373,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .fixup_map_kptr = { 1 }, .result = REJECT, - .errstr = "Unreleased reference id=5 alloc_insn=20", + .errstr = "Unreleased reference id=4 alloc_insn=20", .fixup_kfunc_btf_id = { { "bpf_kfunc_call_test_acquire", 15 }, } diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c index e12ef953fba8..06af5029885b 100644 --- a/tools/testing/selftests/bpf/veristat.c +++ b/tools/testing/selftests/bpf/veristat.c @@ -21,11 +21,20 @@ #include <gelf.h> #include <float.h> #include <math.h> +#include <limits.h> #ifndef ARRAY_SIZE #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0])) #endif +#ifndef max +#define max(a, b) ((a) > (b) ? (a) : (b)) +#endif + +#ifndef min +#define min(a, b) ((a) < (b) ? (a) : (b)) +#endif + enum stat_id { VERDICT, DURATION, @@ -34,6 +43,11 @@ enum stat_id { PEAK_STATES, MAX_STATES_PER_INSN, MARK_READ_MAX_LEN, + SIZE, + JITED_SIZE, + STACK, + PROG_TYPE, + ATTACH_TYPE, FILE_NAME, PROG_NAME, @@ -203,7 +217,8 @@ const char argp_program_doc[] = "\n" "USAGE: veristat <obj-file> [<obj-file>...]\n" " OR: veristat -C <baseline.csv> <comparison.csv>\n" -" OR: veristat -R <results.csv>\n"; +" OR: veristat -R <results.csv>\n" +" OR: veristat -vl2 <to_analyze.bpf.o>\n"; enum { OPT_LOG_FIXED = 1000, @@ -215,7 +230,7 @@ static const struct argp_option opts[] = { { "version", 'V', NULL, 0, "Print version" }, { "verbose", 'v', NULL, 0, "Verbose mode" }, { "debug", 'd', NULL, 0, "Debug mode (turns on libbpf debug logging)" }, - { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode)" }, + { "log-level", 'l', "LEVEL", 0, "Verifier log level (default 0 for normal mode, 1 for verbose mode, 2 for full verification log)" }, { "log-fixed", OPT_LOG_FIXED, NULL, 0, "Disable verifier log rotation" }, { "log-size", OPT_LOG_SIZE, "BYTES", 0, "Customize verifier log size (default to 16MB)" }, { "top-n", 'n', "N", 0, "Emit only up to first N results." }, @@ -640,19 +655,21 @@ cleanup: } static const struct stat_specs default_output_spec = { - .spec_cnt = 7, + .spec_cnt = 8, .ids = { FILE_NAME, PROG_NAME, VERDICT, DURATION, - TOTAL_INSNS, TOTAL_STATES, PEAK_STATES, + TOTAL_INSNS, TOTAL_STATES, SIZE, JITED_SIZE }, }; static const struct stat_specs default_csv_output_spec = { - .spec_cnt = 9, + .spec_cnt = 14, .ids = { FILE_NAME, PROG_NAME, VERDICT, DURATION, TOTAL_INSNS, TOTAL_STATES, PEAK_STATES, MAX_STATES_PER_INSN, MARK_READ_MAX_LEN, + SIZE, JITED_SIZE, PROG_TYPE, ATTACH_TYPE, + STACK, }, }; @@ -688,6 +705,11 @@ static struct stat_def { [PEAK_STATES] = { "Peak states", {"peak_states"}, }, [MAX_STATES_PER_INSN] = { "Max states per insn", {"max_states_per_insn"}, }, [MARK_READ_MAX_LEN] = { "Max mark read length", {"max_mark_read_len", "mark_read"}, }, + [SIZE] = { "Program size", {"prog_size"}, }, + [JITED_SIZE] = { "Jited size", {"prog_size_jited"}, }, + [STACK] = {"Stack depth", {"stack_depth", "stack"}, }, + [PROG_TYPE] = { "Program type", {"prog_type"}, }, + [ATTACH_TYPE] = { "Attach type", {"attach_type", }, }, }; static bool parse_stat_id_var(const char *name, size_t len, int *id, @@ -835,7 +857,8 @@ static char verif_log_buf[64 * 1024]; static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats *s) { const char *cur; - int pos, lines; + int pos, lines, sub_stack, cnt = 0; + char *state = NULL, *token, stack[512]; buf[buf_sz - 1] = '\0'; @@ -853,15 +876,22 @@ static int parse_verif_log(char * const buf, size_t buf_sz, struct verif_stats * if (1 == sscanf(cur, "verification time %ld usec\n", &s->stats[DURATION])) continue; - if (6 == sscanf(cur, "processed %ld insns (limit %*d) max_states_per_insn %ld total_states %ld peak_states %ld mark_read %ld", + if (5 == sscanf(cur, "processed %ld insns (limit %*d) max_states_per_insn %ld total_states %ld peak_states %ld mark_read %ld", &s->stats[TOTAL_INSNS], &s->stats[MAX_STATES_PER_INSN], &s->stats[TOTAL_STATES], &s->stats[PEAK_STATES], &s->stats[MARK_READ_MAX_LEN])) continue; - } + if (1 == sscanf(cur, "stack depth %511s", stack)) + continue; + } + while ((token = strtok_r(cnt++ ? NULL : stack, "+", &state))) { + if (sscanf(token, "%d", &sub_stack) == 0) + break; + s->stats[STACK] += sub_stack; + } return 0; } @@ -884,7 +914,7 @@ static int line_cnt_cmp(const void *a, const void *b) const struct line_cnt *b_cnt = (const struct line_cnt *)b; if (a_cnt->cnt != b_cnt->cnt) - return a_cnt->cnt < b_cnt->cnt ? -1 : 1; + return a_cnt->cnt > b_cnt->cnt ? -1 : 1; return strcmp(a_cnt->line, b_cnt->line); } @@ -1032,6 +1062,41 @@ static int guess_prog_type_by_ctx_name(const char *ctx_name, return -ESRCH; } +/* Make sure only target program is referenced from struct_ops map, + * otherwise libbpf would automatically set autocreate for all + * referenced programs. + * See libbpf.c:bpf_object_adjust_struct_ops_autoload. + */ +static void mask_unrelated_struct_ops_progs(struct bpf_object *obj, + struct bpf_map *map, + struct bpf_program *prog) +{ + struct btf *btf = bpf_object__btf(obj); + const struct btf_type *t, *mt; + struct btf_member *m; + int i, moff; + size_t data_sz, ptr_sz = sizeof(void *); + void *data; + + t = btf__type_by_id(btf, bpf_map__btf_value_type_id(map)); + if (!btf_is_struct(t)) + return; + + data = bpf_map__initial_value(map, &data_sz); + for (i = 0; i < btf_vlen(t); i++) { + m = &btf_members(t)[i]; + mt = btf__type_by_id(btf, m->type); + if (!btf_is_ptr(mt)) + continue; + moff = m->offset / 8; + if (moff + ptr_sz > data_sz) + continue; + if (memcmp(data + moff, &prog, ptr_sz) == 0) + continue; + memset(data + moff, 0, ptr_sz); + } +} + static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const char *filename) { struct bpf_map *map; @@ -1047,6 +1112,9 @@ static void fixup_obj(struct bpf_object *obj, struct bpf_program *prog, const ch case BPF_MAP_TYPE_INODE_STORAGE: case BPF_MAP_TYPE_CGROUP_STORAGE: break; + case BPF_MAP_TYPE_STRUCT_OPS: + mask_unrelated_struct_ops_progs(obj, map, prog); + break; default: if (bpf_map__max_entries(map) == 0) bpf_map__set_max_entries(map, 1); @@ -1146,8 +1214,11 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf char *buf; int buf_sz, log_level; struct verif_stats *stats; + struct bpf_prog_info info; + __u32 info_len = sizeof(info); int err = 0; void *tmp; + int fd; if (!should_process_file_prog(base_filename, bpf_program__name(prog))) { env.progs_skipped++; @@ -1196,6 +1267,15 @@ static int process_prog(const char *filename, struct bpf_object *obj, struct bpf stats->file_name = strdup(base_filename); stats->prog_name = strdup(bpf_program__name(prog)); stats->stats[VERDICT] = err == 0; /* 1 - success, 0 - failure */ + stats->stats[SIZE] = bpf_program__insn_cnt(prog); + stats->stats[PROG_TYPE] = bpf_program__type(prog); + stats->stats[ATTACH_TYPE] = bpf_program__expected_attach_type(prog); + + memset(&info, 0, info_len); + fd = bpf_program__fd(prog); + if (fd > 0 && bpf_prog_get_info_by_fd(fd, &info, &info_len) == 0) + stats->stats[JITED_SIZE] = info.jited_prog_len; + parse_verif_log(buf, buf_sz, stats); if (env.verbose) { @@ -1309,6 +1389,11 @@ static int cmp_stat(const struct verif_stats *s1, const struct verif_stats *s2, case PROG_NAME: cmp = strcmp(s1->prog_name, s2->prog_name); break; + case ATTACH_TYPE: + case PROG_TYPE: + case SIZE: + case JITED_SIZE: + case STACK: case VERDICT: case DURATION: case TOTAL_INSNS: @@ -1523,12 +1608,27 @@ static void prepare_value(const struct verif_stats *s, enum stat_id id, else *str = s->stats[VERDICT] ? "success" : "failure"; break; + case ATTACH_TYPE: + if (!s) + *str = "N/A"; + else + *str = libbpf_bpf_attach_type_str(s->stats[ATTACH_TYPE]) ?: "N/A"; + break; + case PROG_TYPE: + if (!s) + *str = "N/A"; + else + *str = libbpf_bpf_prog_type_str(s->stats[PROG_TYPE]) ?: "N/A"; + break; case DURATION: case TOTAL_INSNS: case TOTAL_STATES: case PEAK_STATES: case MAX_STATES_PER_INSN: case MARK_READ_MAX_LEN: + case STACK: + case SIZE: + case JITED_SIZE: *val = s ? s->stats[id] : 0; break; default: @@ -1612,7 +1712,10 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats case TOTAL_STATES: case PEAK_STATES: case MAX_STATES_PER_INSN: - case MARK_READ_MAX_LEN: { + case MARK_READ_MAX_LEN: + case SIZE: + case JITED_SIZE: + case STACK: { long val; int err, n; @@ -1625,6 +1728,42 @@ static int parse_stat_value(const char *str, enum stat_id id, struct verif_stats st->stats[id] = val; break; } + case PROG_TYPE: { + enum bpf_prog_type prog_type = 0; + const char *type; + + while ((type = libbpf_bpf_prog_type_str(prog_type))) { + if (strcmp(type, str) == 0) { + st->stats[id] = prog_type; + break; + } + prog_type++; + } + + if (!type) { + fprintf(stderr, "Unrecognized prog type %s\n", str); + return -EINVAL; + } + break; + } + case ATTACH_TYPE: { + enum bpf_attach_type attach_type = 0; + const char *type; + + while ((type = libbpf_bpf_attach_type_str(attach_type))) { + if (strcmp(type, str) == 0) { + st->stats[id] = attach_type; + break; + } + attach_type++; + } + + if (!type) { + fprintf(stderr, "Unrecognized attach type %s\n", str); + return -EINVAL; + } + break; + } default: fprintf(stderr, "Unrecognized stat #%d\n", id); return -EINVAL; diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index e38675d9b118..6f7b15d6c6ed 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -27,7 +27,7 @@ #include <linux/errqueue.h> #include <linux/if_link.h> #include <linux/net_tstamp.h> -#include <linux/udp.h> +#include <netinet/udp.h> #include <linux/sockios.h> #include <linux/if_xdp.h> #include <sys/mman.h> diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh index 3f45512fb512..7406c24be1ac 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # Test the special cpuset v1 hotplug case where a cpuset become empty of diff --git a/tools/testing/selftests/damon/.gitignore b/tools/testing/selftests/damon/.gitignore index 2ab675fecb6b..2f0297657c81 100644 --- a/tools/testing/selftests/damon/.gitignore +++ b/tools/testing/selftests/damon/.gitignore @@ -1,6 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only -huge_count_read_write -debugfs_target_ids_read_before_terminate_race -debugfs_target_ids_pid_leak access_memory access_memory_even diff --git a/tools/testing/selftests/damon/Makefile b/tools/testing/selftests/damon/Makefile index 812f656260fb..ecbf07afc6dd 100644 --- a/tools/testing/selftests/damon/Makefile +++ b/tools/testing/selftests/damon/Makefile @@ -1,15 +1,11 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for damon selftests -TEST_GEN_FILES += huge_count_read_write -TEST_GEN_FILES += debugfs_target_ids_read_before_terminate_race -TEST_GEN_FILES += debugfs_target_ids_pid_leak TEST_GEN_FILES += access_memory access_memory_even -TEST_FILES = _chk_dependency.sh _debugfs_common.sh _damon_sysfs.py +TEST_FILES = _chk_dependency.sh _damon_sysfs.py # functionality tests -TEST_PROGS = debugfs_attrs.sh debugfs_schemes.sh debugfs_target_ids.sh TEST_PROGS += sysfs.sh TEST_PROGS += sysfs_update_schemes_tried_regions_wss_estimation.py TEST_PROGS += damos_quota.py damos_quota_goal.py damos_apply_interval.py @@ -17,11 +13,6 @@ TEST_PROGS += damos_tried_regions.py damon_nr_regions.py TEST_PROGS += reclaim.sh lru_sort.sh # regression tests (reproducers of previously found bugs) -TEST_PROGS += debugfs_empty_targets.sh debugfs_huge_count_read_write.sh -TEST_PROGS += debugfs_duplicate_context_creation.sh -TEST_PROGS += debugfs_rm_non_contexts.sh -TEST_PROGS += debugfs_target_ids_read_before_terminate_race.sh -TEST_PROGS += debugfs_target_ids_pid_leak.sh TEST_PROGS += sysfs_update_removed_scheme_dir.sh TEST_PROGS += sysfs_update_schemes_tried_regions_hang.py diff --git a/tools/testing/selftests/damon/config b/tools/testing/selftests/damon/config index 0daf38974eb0..a68a9fead5dc 100644 --- a/tools/testing/selftests/damon/config +++ b/tools/testing/selftests/damon/config @@ -1,6 +1,5 @@ CONFIG_DAMON=y CONFIG_DAMON_SYSFS=y -CONFIG_DAMON_DBGFS=y CONFIG_DAMON_PADDR=y CONFIG_DAMON_VADDR=y CONFIG_DAMON_RECLAIM=y diff --git a/tools/testing/selftests/damon/debugfs_attrs.sh b/tools/testing/selftests/damon/debugfs_attrs.sh deleted file mode 100755 index 902e312bca89..000000000000 --- a/tools/testing/selftests/damon/debugfs_attrs.sh +++ /dev/null @@ -1,17 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test attrs file -# =============== - -file="$DBGFS/attrs" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5" "$orig_content" "valid input" -test_write_fail "$file" "1 2 3 4" "$orig_content" "no enough fields" -test_write_fail "$file" "1 2 3 5 4" "$orig_content" \ - "min_nr_regions > max_nr_regions" -test_content "$file" "$orig_content" "1 2 3 4 5" "successfully written" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh b/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh deleted file mode 100755 index bd6c22d96ead..000000000000 --- a/tools/testing/selftests/damon/debugfs_duplicate_context_creation.sh +++ /dev/null @@ -1,27 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test duplicated context creation -# ================================ - -if ! echo foo > "$DBGFS/mk_contexts" -then - echo "context creation failed" - exit 1 -fi - -if echo foo > "$DBGFS/mk_contexts" 2> /dev/null -then - echo "duplicate context creation success" - exit 1 -fi - -if ! echo foo > "$DBGFS/rm_contexts" -then - echo "context deletion failed" - exit 1 -fi - -exit 0 diff --git a/tools/testing/selftests/damon/debugfs_empty_targets.sh b/tools/testing/selftests/damon/debugfs_empty_targets.sh deleted file mode 100755 index effbea33dc16..000000000000 --- a/tools/testing/selftests/damon/debugfs_empty_targets.sh +++ /dev/null @@ -1,21 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test empty targets case -# ======================= - -orig_target_ids=$(cat "$DBGFS/target_ids") -echo "" > "$DBGFS/target_ids" - -if [ -f "$DBGFS/monitor_on_DEPRECATED" ] -then - monitor_on_file="$DBGFS/monitor_on_DEPRECATED" -else - monitor_on_file="$DBGFS/monitor_on" -fi - -orig_monitor_on=$(cat "$monitor_on_file") -test_write_fail "$monitor_on_file" "on" "orig_monitor_on" "empty target ids" -echo "$orig_target_ids" > "$DBGFS/target_ids" diff --git a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh b/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh deleted file mode 100755 index 922cadac2950..000000000000 --- a/tools/testing/selftests/damon/debugfs_huge_count_read_write.sh +++ /dev/null @@ -1,22 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test huge count read write -# ========================== - -dmesg -C - -for file in "$DBGFS/"* -do - ./huge_count_read_write "$file" -done - -if dmesg | grep -q WARNING -then - dmesg - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh b/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh deleted file mode 100755 index f3ffeb1343cf..000000000000 --- a/tools/testing/selftests/damon/debugfs_rm_non_contexts.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test putting non-ctx files/dirs to rm_contexts file -# =================================================== - -dmesg -C - -for file in "$DBGFS/"* -do - (echo "$(basename "$f")" > "$DBGFS/rm_contexts") &> /dev/null - if dmesg | grep -q BUG - then - dmesg - exit 1 - fi -done diff --git a/tools/testing/selftests/damon/debugfs_schemes.sh b/tools/testing/selftests/damon/debugfs_schemes.sh deleted file mode 100755 index 5b39ab44731c..000000000000 --- a/tools/testing/selftests/damon/debugfs_schemes.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test schemes file -# ================= - -file="$DBGFS/schemes" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4 5 6 4 0 0 0 1 2 3 1 100 3 2 1" \ - "$orig_content" "valid input" -test_write_fail "$file" "1 2 -3 4 5 6 3 0 0 0 1 2 3 1 100 3 2 1" "$orig_content" "multi lines" -test_write_succ "$file" "" "$orig_content" "disabling" -test_write_fail "$file" "2 1 2 1 10 1 3 10 1 1 1 1 1 1 1 1 2 3" \ - "$orig_content" "wrong condition ranges" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids.sh b/tools/testing/selftests/damon/debugfs_target_ids.sh deleted file mode 100755 index 49aeabdb0aae..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids.sh +++ /dev/null @@ -1,19 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -source _debugfs_common.sh - -# Test target_ids file -# ==================== - -file="$DBGFS/target_ids" -orig_content=$(cat "$file") - -test_write_succ "$file" "1 2 3 4" "$orig_content" "valid input" -test_write_succ "$file" "1 2 abc 4" "$orig_content" "still valid input" -test_content "$file" "$orig_content" "1 2" "non-integer was there" -test_write_succ "$file" "abc 2 3" "$orig_content" "the file allows wrong input" -test_content "$file" "$orig_content" "" "wrong input written" -test_write_succ "$file" "" "$orig_content" "empty input" -test_content "$file" "$orig_content" "" "empty input written" -echo "$orig_content" > "$file" diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c deleted file mode 100644 index 0cc2eef7d142..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.c +++ /dev/null @@ -1,68 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ - -#define _GNU_SOURCE - -#include <fcntl.h> -#include <stdbool.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <sys/time.h> -#include <unistd.h> - -#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" - -static void write_targetid_exit(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - char pid_str[128]; - - snprintf(pid_str, sizeof(pid_str), "%d", getpid()); - write(target_ids_fd, pid_str, sizeof(pid_str)); - close(target_ids_fd); - exit(0); -} - -unsigned long msec_timestamp(void) -{ - struct timeval tv; - - gettimeofday(&tv, NULL); - return tv.tv_sec * 1000UL + tv.tv_usec / 1000; -} - -int main(int argc, char *argv[]) -{ - unsigned long start_ms; - int time_to_run, nr_forks = 0; - - if (argc != 2) { - fprintf(stderr, "Usage: %s <msecs to run>\n", argv[0]); - exit(1); - } - time_to_run = atoi(argv[1]); - - start_ms = msec_timestamp(); - while (true) { - int pid = fork(); - - if (pid < 0) { - fprintf(stderr, "fork() failed\n"); - exit(1); - } - if (pid == 0) - write_targetid_exit(); - wait(NULL); - nr_forks++; - - if (msec_timestamp() - start_ms > time_to_run) - break; - } - printf("%d\n", nr_forks); - return 0; -} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh b/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh deleted file mode 100755 index 31fe33c2b032..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_pid_leak.sh +++ /dev/null @@ -1,22 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -before=$(grep "^pid " /proc/slabinfo | awk '{print $2}') - -nr_leaks=$(./debugfs_target_ids_pid_leak 1000) -expected_after_max=$((before + nr_leaks / 2)) - -after=$(grep "^pid " /proc/slabinfo | awk '{print $2}') - -echo > /sys/kernel/debug/damon/target_ids - -echo "tried $nr_leaks pid leak" -echo "number of active pid slabs: $before -> $after" -echo "(up to $expected_after_max expected)" -if [ $after -gt $expected_after_max ] -then - echo "maybe pids are leaking" - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c deleted file mode 100644 index b06f52a8ce2d..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.c +++ /dev/null @@ -1,80 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ -#define _GNU_SOURCE - -#include <fcntl.h> -#include <stdbool.h> -#include <stdint.h> -#include <stdio.h> -#include <stdlib.h> -#include <sys/types.h> -#include <sys/wait.h> -#include <time.h> -#include <unistd.h> - -#define DBGFS_MONITOR_ON "/sys/kernel/debug/damon/monitor_on_DEPRECATED" -#define DBGFS_TARGET_IDS "/sys/kernel/debug/damon/target_ids" - -static void turn_damon_on_exit(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - int monitor_on_fd = open(DBGFS_MONITOR_ON, O_RDWR); - char pid_str[128]; - - snprintf(pid_str, sizeof(pid_str), "%d", getpid()); - write(target_ids_fd, pid_str, sizeof(pid_str)); - write(monitor_on_fd, "on\n", 3); - close(target_ids_fd); - close(monitor_on_fd); - usleep(1000); - exit(0); -} - -static void try_race(void) -{ - int target_ids_fd = open(DBGFS_TARGET_IDS, O_RDWR); - int pid = fork(); - int buf[256]; - - if (pid < 0) { - fprintf(stderr, "fork() failed\n"); - exit(1); - } - if (pid == 0) - turn_damon_on_exit(); - while (true) { - int status; - - read(target_ids_fd, buf, sizeof(buf)); - if (waitpid(-1, &status, WNOHANG) == pid) - break; - } - close(target_ids_fd); -} - -static inline uint64_t ts_to_ms(struct timespec *ts) -{ - return (uint64_t)ts->tv_sec * 1000 + (uint64_t)ts->tv_nsec / 1000000; -} - -int main(int argc, char *argv[]) -{ - struct timespec start_time, now; - int runtime_ms; - - if (argc != 2) { - fprintf(stderr, "Usage: %s <runtime in ms>\n", argv[0]); - exit(1); - } - runtime_ms = atoi(argv[1]); - clock_gettime(CLOCK_MONOTONIC, &start_time); - while (true) { - try_race(); - clock_gettime(CLOCK_MONOTONIC, &now); - if (ts_to_ms(&now) - ts_to_ms(&start_time) > runtime_ms) - break; - } - return 0; -} diff --git a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh b/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh deleted file mode 100755 index fc793c4c9aea..000000000000 --- a/tools/testing/selftests/damon/debugfs_target_ids_read_before_terminate_race.sh +++ /dev/null @@ -1,14 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 - -dmesg -C - -./debugfs_target_ids_read_before_terminate_race 5000 - -if dmesg | grep -q dbgfs_target_ids_read -then - dmesg - exit 1 -else - exit 0 -fi diff --git a/tools/testing/selftests/damon/huge_count_read_write.c b/tools/testing/selftests/damon/huge_count_read_write.c deleted file mode 100644 index 53e69a669668..000000000000 --- a/tools/testing/selftests/damon/huge_count_read_write.c +++ /dev/null @@ -1,46 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Author: SeongJae Park <sj@kernel.org> - */ - -#include <fcntl.h> -#include <stdlib.h> -#include <unistd.h> -#include <stdio.h> - -#pragma GCC diagnostic push -#if __GNUC__ >= 11 && __GNUC_MINOR__ >= 1 -/* Ignore read(2) overflow and write(2) overread compile warnings */ -#pragma GCC diagnostic ignored "-Wstringop-overread" -#pragma GCC diagnostic ignored "-Wstringop-overflow" -#endif - -void write_read_with_huge_count(char *file) -{ - int filedesc = open(file, O_RDWR); - char buf[256]; - int ret; - - printf("%s %s\n", __func__, file); - if (filedesc < 0) { - fprintf(stderr, "failed opening %s\n", file); - exit(1); - } - - write(filedesc, "", 0xfffffffful); - ret = read(filedesc, buf, 0xfffffffful); - close(filedesc); -} - -#pragma GCC diagnostic pop - -int main(int argc, char *argv[]) -{ - if (argc != 2) { - fprintf(stderr, "Usage: %s <file>\n", argv[0]); - exit(1); - } - write_read_with_huge_count(argv[1]); - - return 0; -} diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py index 394971b25c0b..873f5219e41d 100755 --- a/tools/testing/selftests/drivers/net/hds.py +++ b/tools/testing/selftests/drivers/net/hds.py @@ -2,17 +2,54 @@ # SPDX-License-Identifier: GPL-2.0 import errno +import os from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx -from lib.py import EthtoolFamily, NlError +from lib.py import CmdExitFailure, EthtoolFamily, NlError from lib.py import NetDrvEnv +from lib.py import defer, ethtool, ip -def get_hds(cfg, netnl) -> None: + +def _get_hds_mode(cfg, netnl) -> str: try: rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) except NlError as e: raise KsftSkipEx('ring-get not supported by device') if 'tcp-data-split' not in rings: raise KsftSkipEx('tcp-data-split not supported by device') + return rings['tcp-data-split'] + + +def _xdp_onoff(cfg): + test_dir = os.path.dirname(os.path.realpath(__file__)) + prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o" + ip("link set dev %s xdp obj %s sec xdp" % + (cfg.ifname, prog)) + ip("link set dev %s xdp off" % cfg.ifname) + + +def _ioctl_ringparam_modify(cfg, netnl) -> None: + """ + Helper for performing a hopefully unimportant IOCTL SET. + IOCTL does not support HDS, so it should not affect the HDS config. + """ + try: + rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}}) + except NlError as e: + raise KsftSkipEx('ring-get not supported by device') + + if 'tx' not in rings: + raise KsftSkipEx('setting Tx ring size not supported') + + try: + ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] // 2}") + except CmdExitFailure as e: + ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] * 2}") + defer(ethtool, f"-G {cfg.ifname} tx {rings['tx']}") + + +def get_hds(cfg, netnl) -> None: + _get_hds_mode(cfg, netnl) + def get_hds_thresh(cfg, netnl) -> None: try: @@ -104,6 +141,103 @@ def set_hds_thresh_gt(cfg, netnl) -> None: netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt}) ksft_eq(e.exception.nl_msg.error, -errno.EINVAL) + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _xdp_onoff(cfg) + + +def enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + +def set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "auto" / UNKNOWN mode, XDP installation should work. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _xdp_onoff(cfg) + + +def enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) # Trigger skip if not supported + + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + +def ioctl(cfg, netnl) -> None: + mode1 = _get_hds_mode(cfg, netnl) + _ioctl_ringparam_modify(cfg, netnl) + mode2 = _get_hds_mode(cfg, netnl) + + ksft_eq(mode1, mode2) + + +def ioctl_set_xdp(cfg, netnl) -> None: + """ + Like set_xdp(), but we perturb the settings via the legacy ioctl. + """ + mode = _get_hds_mode(cfg, netnl) + if mode == 'enabled': + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + _ioctl_ringparam_modify(cfg, netnl) + + _xdp_onoff(cfg) + + +def ioctl_enabled_set_xdp(cfg, netnl) -> None: + """ + Enable single-buffer XDP on the device. + When HDS is in "enabled" mode, XDP installation should not work. + """ + _get_hds_mode(cfg, netnl) # Trigger skip if not supported + + netnl.rings_set({'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'enabled'}) + defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex}, + 'tcp-data-split': 'unknown'}) + + with ksft_raises(CmdExitFailure) as e: + _xdp_onoff(cfg) + + def main() -> None: with NetDrvEnv(__file__, queue_count=3) as cfg: ksft_run([get_hds, @@ -112,7 +246,12 @@ def main() -> None: set_hds_enable, set_hds_thresh_zero, set_hds_thresh_max, - set_hds_thresh_gt], + set_hds_thresh_gt, + set_xdp, + enabled_set_xdp, + ioctl, + ioctl_set_xdp, + ioctl_enabled_set_xdp], args=(cfg, EthtoolFamily())) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index ca8a7edff3dd..319aaa004c40 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -252,6 +252,7 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True): try: # this targets queue 4, which doesn't exist ntuple2 = ethtool_create(cfg, "-N", flow) + defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}") except CmdExitFailure: pass else: @@ -259,7 +260,13 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True): # change the table to target queues 0 and 2 ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0") # ntuple rule therefore targets queues 1 and 3 - ntuple2 = ethtool_create(cfg, "-N", flow) + try: + ntuple2 = ethtool_create(cfg, "-N", flow) + except CmdExitFailure: + ksft_pr("Driver does not support rss + queue offset") + return + + defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}") # should replace existing filter ksft_eq(ntuple, ntuple2) _send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3), diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 384cfa3d38a6..92c2f0376c08 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -142,7 +142,7 @@ function pre_ethtool { } function check_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 local -n expected=$2 local last=$3 @@ -212,7 +212,7 @@ function check_tables { } function print_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 read -a have < $path tree $NSIM_DEV_DFS/ @@ -641,7 +641,7 @@ for port in 0 1; do NSIM_NETDEV=`get_netdev_name old_netdevs` ip link set dev $NSIM_NETDEV up - echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error msg="1 - create VxLANs v6" exp0=( 0 0 0 0 ) @@ -663,7 +663,7 @@ for port in 0 1; do new_geneve gnv0 20000 msg="2 - destroy GENEVE" - echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error exp1=( `mke 20000 2` 0 0 0 ) del_dev gnv0 @@ -764,7 +764,7 @@ for port in 0 1; do msg="create VxLANs v4" new_vxlan vxlan0 10000 $NSIM_NETDEV - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes down" @@ -775,7 +775,7 @@ for port in 0 1; do fi check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes up again" @@ -789,7 +789,7 @@ for port in 0 1; do del_dev vxlan0 check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="destroy NIC" @@ -896,7 +896,7 @@ msg="vacate VxLAN in overflow table" exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) del_dev vxlan2 -echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset +echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="tunnels destroyed 2" diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py index 38303da957ee..8a518905a9f9 100755 --- a/tools/testing/selftests/drivers/net/queues.py +++ b/tools/testing/selftests/drivers/net/queues.py @@ -45,10 +45,9 @@ def addremove_queues(cfg, nl) -> None: netnl = EthtoolFamily() channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}}) - if channels['combined-count'] == 0: - rx_type = 'rx' - else: - rx_type = 'combined' + rx_type = 'rx' + if channels.get('combined-count', 0) > 0: + rx_type = 'combined' expected = curr_queues - 1 cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10) diff --git a/tools/testing/selftests/drivers/ntsync/.gitignore b/tools/testing/selftests/drivers/ntsync/.gitignore new file mode 100644 index 000000000000..848573a3d3ea --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/.gitignore @@ -0,0 +1 @@ +ntsync diff --git a/tools/testing/selftests/drivers/ntsync/Makefile b/tools/testing/selftests/drivers/ntsync/Makefile new file mode 100644 index 000000000000..dbf2b055c0b2 --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/Makefile @@ -0,0 +1,7 @@ +# SPDX-LICENSE-IDENTIFIER: GPL-2.0-only +TEST_GEN_PROGS := ntsync + +CFLAGS += $(KHDR_INCLUDES) +LDLIBS += -lpthread + +include ../../lib.mk diff --git a/tools/testing/selftests/drivers/ntsync/config b/tools/testing/selftests/drivers/ntsync/config new file mode 100644 index 000000000000..60539c826d06 --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/config @@ -0,0 +1 @@ +CONFIG_WINESYNC=y diff --git a/tools/testing/selftests/drivers/ntsync/ntsync.c b/tools/testing/selftests/drivers/ntsync/ntsync.c new file mode 100644 index 000000000000..3aad311574c4 --- /dev/null +++ b/tools/testing/selftests/drivers/ntsync/ntsync.c @@ -0,0 +1,1343 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Various unit tests for the "ntsync" synchronization primitive driver. + * + * Copyright (C) 2021-2022 Elizabeth Figura <zfigura@codeweavers.com> + */ + +#define _GNU_SOURCE +#include <sys/ioctl.h> +#include <sys/stat.h> +#include <fcntl.h> +#include <time.h> +#include <pthread.h> +#include <linux/ntsync.h> +#include "../../kselftest_harness.h" + +static int read_sem_state(int sem, __u32 *count, __u32 *max) +{ + struct ntsync_sem_args args; + int ret; + + memset(&args, 0xcc, sizeof(args)); + ret = ioctl(sem, NTSYNC_IOC_SEM_READ, &args); + *count = args.count; + *max = args.max; + return ret; +} + +#define check_sem_state(sem, count, max) \ + ({ \ + __u32 __count, __max; \ + int ret = read_sem_state((sem), &__count, &__max); \ + EXPECT_EQ(0, ret); \ + EXPECT_EQ((count), __count); \ + EXPECT_EQ((max), __max); \ + }) + +static int release_sem(int sem, __u32 *count) +{ + return ioctl(sem, NTSYNC_IOC_SEM_RELEASE, count); +} + +static int read_mutex_state(int mutex, __u32 *count, __u32 *owner) +{ + struct ntsync_mutex_args args; + int ret; + + memset(&args, 0xcc, sizeof(args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &args); + *count = args.count; + *owner = args.owner; + return ret; +} + +#define check_mutex_state(mutex, count, owner) \ + ({ \ + __u32 __count, __owner; \ + int ret = read_mutex_state((mutex), &__count, &__owner); \ + EXPECT_EQ(0, ret); \ + EXPECT_EQ((count), __count); \ + EXPECT_EQ((owner), __owner); \ + }) + +static int unlock_mutex(int mutex, __u32 owner, __u32 *count) +{ + struct ntsync_mutex_args args; + int ret; + + args.owner = owner; + args.count = 0xdeadbeef; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_UNLOCK, &args); + *count = args.count; + return ret; +} + +static int read_event_state(int event, __u32 *signaled, __u32 *manual) +{ + struct ntsync_event_args args; + int ret; + + memset(&args, 0xcc, sizeof(args)); + ret = ioctl(event, NTSYNC_IOC_EVENT_READ, &args); + *signaled = args.signaled; + *manual = args.manual; + return ret; +} + +#define check_event_state(event, signaled, manual) \ + ({ \ + __u32 __signaled, __manual; \ + int ret = read_event_state((event), &__signaled, &__manual); \ + EXPECT_EQ(0, ret); \ + EXPECT_EQ((signaled), __signaled); \ + EXPECT_EQ((manual), __manual); \ + }) + +static int wait_objs(int fd, unsigned long request, __u32 count, + const int *objs, __u32 owner, int alert, __u32 *index) +{ + struct ntsync_wait_args args = {0}; + struct timespec timeout; + int ret; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + args.timeout = timeout.tv_sec * 1000000000 + timeout.tv_nsec; + args.count = count; + args.objs = (uintptr_t)objs; + args.owner = owner; + args.index = 0xdeadbeef; + args.alert = alert; + ret = ioctl(fd, request, &args); + *index = args.index; + return ret; +} + +static int wait_any(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ANY, count, objs, owner, 0, index); +} + +static int wait_all(int fd, __u32 count, const int *objs, __u32 owner, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ALL, count, objs, owner, 0, index); +} + +static int wait_any_alert(int fd, __u32 count, const int *objs, + __u32 owner, int alert, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ANY, + count, objs, owner, alert, index); +} + +static int wait_all_alert(int fd, __u32 count, const int *objs, + __u32 owner, int alert, __u32 *index) +{ + return wait_objs(fd, NTSYNC_IOC_WAIT_ALL, + count, objs, owner, alert, index); +} + +TEST(semaphore_state) +{ + struct ntsync_sem_args sem_args; + struct timespec timeout; + __u32 count, index; + int fd, ret, sem; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 3; + sem_args.max = 2; + sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_EQ(-1, sem); + EXPECT_EQ(EINVAL, errno); + + sem_args.count = 2; + sem_args.max = 2; + sem = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, sem); + check_sem_state(sem, 2, 2); + + count = 0; + ret = release_sem(sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + check_sem_state(sem, 2, 2); + + count = 1; + ret = release_sem(sem, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOVERFLOW, errno); + check_sem_state(sem, 2, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(sem, 1, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(sem, 0, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + count = 3; + ret = release_sem(sem, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOVERFLOW, errno); + check_sem_state(sem, 0, 2); + + count = 2; + ret = release_sem(sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(sem, 2, 2); + + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + ret = wait_any(fd, 1, &sem, 123, &index); + EXPECT_EQ(0, ret); + + count = 1; + ret = release_sem(sem, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(sem, 1, 2); + + count = ~0u; + ret = release_sem(sem, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOVERFLOW, errno); + check_sem_state(sem, 1, 2); + + close(sem); + + close(fd); +} + +TEST(mutex_state) +{ + struct ntsync_mutex_args mutex_args; + __u32 owner, count, index; + struct timespec timeout; + int fd, ret, mutex; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + mutex_args.owner = 123; + mutex_args.count = 0; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_EQ(-1, mutex); + EXPECT_EQ(EINVAL, errno); + + mutex_args.owner = 0; + mutex_args.count = 2; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_EQ(-1, mutex); + EXPECT_EQ(EINVAL, errno); + + mutex_args.owner = 123; + mutex_args.count = 2; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, mutex); + check_mutex_state(mutex, 2, 123); + + ret = unlock_mutex(mutex, 0, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + ret = unlock_mutex(mutex, 456, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EPERM, errno); + check_mutex_state(mutex, 2, 123); + + ret = unlock_mutex(mutex, 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + check_mutex_state(mutex, 1, 123); + + ret = unlock_mutex(mutex, 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, count); + check_mutex_state(mutex, 0, 0); + + ret = unlock_mutex(mutex, 123, &count); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EPERM, errno); + + ret = wait_any(fd, 1, &mutex, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 456); + + ret = wait_any(fd, 1, &mutex, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 2, 456); + + ret = unlock_mutex(mutex, 456, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + check_mutex_state(mutex, 1, 456); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + owner = 0; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + owner = 123; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EPERM, errno); + check_mutex_state(mutex, 1, 456); + + owner = 456; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + memset(&mutex_args, 0xcc, sizeof(mutex_args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, mutex_args.count); + EXPECT_EQ(0, mutex_args.owner); + + memset(&mutex_args, 0xcc, sizeof(mutex_args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, mutex_args.count); + EXPECT_EQ(0, mutex_args.owner); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 123); + + owner = 123; + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + memset(&mutex_args, 0xcc, sizeof(mutex_args)); + ret = ioctl(mutex, NTSYNC_IOC_MUTEX_READ, &mutex_args); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, mutex_args.count); + EXPECT_EQ(0, mutex_args.owner); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 123); + + close(mutex); + + mutex_args.owner = 0; + mutex_args.count = 0; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, mutex); + check_mutex_state(mutex, 0, 0); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_mutex_state(mutex, 1, 123); + + close(mutex); + + mutex_args.owner = 123; + mutex_args.count = ~0u; + mutex = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, mutex); + check_mutex_state(mutex, ~0u, 123); + + ret = wait_any(fd, 1, &mutex, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + close(mutex); + + close(fd); +} + +TEST(manual_event_state) +{ + struct ntsync_event_args event_args; + __u32 index, signaled; + int fd, event, ret; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + event_args.manual = 1; + event_args.signaled = 0; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + check_event_state(event, 0, 1); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 1, 1); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 1, 1); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_event_state(event, 1, 1); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 0, 1); + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 1); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 0, 1); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 1); + + close(event); + + close(fd); +} + +TEST(auto_event_state) +{ + struct ntsync_event_args event_args; + __u32 index, signaled; + int fd, event, ret; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + event_args.manual = 0; + event_args.signaled = 1; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + check_event_state(event, 1, 0); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 1, 0); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_event_state(event, 0, 0); + + signaled = 0xdeadbeef; + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 0); + + ret = wait_any(fd, 1, &event, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + check_event_state(event, 0, 0); + + ret = ioctl(event, NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(event, 0, 0); + + close(event); + + close(fd); +} + +TEST(test_wait_any) +{ + int objs[NTSYNC_MAX_WAIT_COUNT + 1], fd, ret; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 owner, index, count, i; + struct timespec timeout; + + clock_gettime(CLOCK_MONOTONIC, &timeout); + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 2; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 0; + mutex_args.count = 0; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 0, 0); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 0, 0); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 1, 123); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 1, 123); + + ret = wait_any(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 2, 123); + + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + owner = 123; + ret = ioctl(objs[1], NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + EXPECT_EQ(1, index); + + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + + close(objs[1]); + + /* test waiting on the same object twice */ + + count = 2; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + objs[1] = objs[0]; + ret = wait_any(fd, 2, objs, 456, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 1, 3); + + ret = wait_any(fd, 0, NULL, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + for (i = 1; i < NTSYNC_MAX_WAIT_COUNT + 1; ++i) + objs[i] = objs[0]; + + ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_any(fd, NTSYNC_MAX_WAIT_COUNT + 1, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + ret = wait_any(fd, -1, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + close(objs[0]); + + close(fd); +} + +TEST(test_wait_all) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 owner, index, count; + int objs[2], fd, ret; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 2; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 0; + mutex_args.count = 0; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 123); + + ret = wait_all(fd, 2, objs, 456, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 123); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 2, 123); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + check_sem_state(objs[0], 0, 3); + check_mutex_state(objs[1], 2, 123); + + count = 3; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 2, 3); + check_mutex_state(objs[1], 3, 123); + + owner = 123; + ret = ioctl(objs[1], NTSYNC_IOC_MUTEX_KILL, &owner); + EXPECT_EQ(0, ret); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EOWNERDEAD, errno); + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 123); + + close(objs[1]); + + event_args.manual = true; + event_args.signaled = true; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, objs[1]); + + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + check_sem_state(objs[0], 0, 3); + check_event_state(objs[1], 1, 1); + + close(objs[1]); + + /* test waiting on the same object twice */ + objs[1] = objs[0]; + ret = wait_all(fd, 2, objs, 123, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(EINVAL, errno); + + close(objs[0]); + + close(fd); +} + +struct wake_args { + int fd; + int obj; +}; + +struct wait_args { + int fd; + unsigned long request; + struct ntsync_wait_args *args; + int ret; + int err; +}; + +static void *wait_thread(void *arg) +{ + struct wait_args *args = arg; + + args->ret = ioctl(args->fd, args->request, args->args); + args->err = errno; + return NULL; +} + +static __u64 get_abs_timeout(unsigned int ms) +{ + struct timespec timeout; + clock_gettime(CLOCK_MONOTONIC, &timeout); + return (timeout.tv_sec * 1000000000) + timeout.tv_nsec + (ms * 1000000); +} + +static int wait_for_thread(pthread_t thread, unsigned int ms) +{ + struct timespec timeout; + + clock_gettime(CLOCK_REALTIME, &timeout); + timeout.tv_nsec += ms * 1000000; + timeout.tv_sec += (timeout.tv_nsec / 1000000000); + timeout.tv_nsec %= 1000000000; + return pthread_timedjoin_np(thread, NULL, &timeout); +} + +TEST(wake_any) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + struct wait_args thread_args; + __u32 count, index, signaled; + int objs[2], fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 0; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 123; + mutex_args.count = 1; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + /* test waking the semaphore */ + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + wait_args.owner = 456; + wait_args.index = 0xdeadbeef; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ANY; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(objs[0], 0, 3); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(0, wait_args.index); + + /* test waking the mutex */ + + /* first grab it again for owner 123 */ + ret = wait_any(fd, 1, &objs[1], 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.owner = 456; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = unlock_mutex(objs[1], 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, count); + + ret = pthread_tryjoin_np(thread, NULL); + EXPECT_EQ(EBUSY, ret); + + ret = unlock_mutex(objs[1], 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, mutex_args.count); + check_mutex_state(objs[1], 1, 456); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + close(objs[1]); + + /* test waking events */ + + event_args.manual = false; + event_args.signaled = false; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, objs[1]); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 0, 0); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 0, 0); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + close(objs[1]); + + event_args.manual = true; + event_args.signaled = false; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, objs[1]); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 1, 1); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + + wait_args.timeout = get_abs_timeout(1000); + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(objs[1], NTSYNC_IOC_EVENT_PULSE, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + check_event_state(objs[1], 0, 1); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(1, wait_args.index); + + /* delete an object while it's being waited on */ + + wait_args.timeout = get_abs_timeout(200); + wait_args.owner = 123; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + close(objs[0]); + close(objs[1]); + + ret = wait_for_thread(thread, 200); + EXPECT_EQ(0, ret); + EXPECT_EQ(-1, thread_args.ret); + EXPECT_EQ(ETIMEDOUT, thread_args.err); + + close(fd); +} + +TEST(wake_all) +{ + struct ntsync_event_args manual_event_args = {0}; + struct ntsync_event_args auto_event_args = {0}; + struct ntsync_mutex_args mutex_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + struct wait_args thread_args; + __u32 count, index, signaled; + int objs[4], fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 0; + sem_args.max = 3; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + mutex_args.owner = 123; + mutex_args.count = 1; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, objs[1]); + + manual_event_args.manual = true; + manual_event_args.signaled = true; + objs[2] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &manual_event_args); + EXPECT_LE(0, objs[2]); + + auto_event_args.manual = false; + auto_event_args.signaled = true; + objs[3] = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &auto_event_args); + EXPECT_EQ(0, objs[3]); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 4; + wait_args.owner = 456; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ALL; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + + ret = pthread_tryjoin_np(thread, NULL); + EXPECT_EQ(EBUSY, ret); + + check_sem_state(objs[0], 1, 3); + + ret = wait_any(fd, 1, &objs[0], 123, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = unlock_mutex(objs[1], 123, &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, count); + + ret = pthread_tryjoin_np(thread, NULL); + EXPECT_EQ(EBUSY, ret); + + check_mutex_state(objs[1], 0, 0); + + ret = ioctl(objs[2], NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + + count = 2; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, count); + check_sem_state(objs[0], 2, 3); + + ret = ioctl(objs[3], NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, signaled); + + ret = ioctl(objs[2], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + ret = ioctl(objs[3], NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, signaled); + + check_sem_state(objs[0], 1, 3); + check_mutex_state(objs[1], 1, 456); + check_event_state(objs[2], 1, 1); + check_event_state(objs[3], 0, 0); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + + /* delete an object while it's being waited on */ + + wait_args.timeout = get_abs_timeout(200); + wait_args.owner = 123; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + close(objs[0]); + close(objs[1]); + close(objs[2]); + close(objs[3]); + + ret = wait_for_thread(thread, 200); + EXPECT_EQ(0, ret); + EXPECT_EQ(-1, thread_args.ret); + EXPECT_EQ(ETIMEDOUT, thread_args.err); + + close(fd); +} + +TEST(alert_any) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + __u32 index, count, signaled; + struct wait_args thread_args; + int objs[2], event, fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 0; + sem_args.max = 2; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + sem_args.count = 1; + sem_args.max = 2; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[1]); + + event_args.manual = true; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + ret = wait_any_alert(fd, 0, NULL, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_any_alert(fd, 0, NULL, 123, event, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(1, index); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + /* test wakeup via alert */ + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + wait_args.owner = 123; + wait_args.index = 0xdeadbeef; + wait_args.alert = event; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ANY; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(2, wait_args.index); + + close(event); + + /* test with an auto-reset event */ + + event_args.manual = false; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + count = 1; + ret = release_sem(objs[0], &count); + EXPECT_EQ(0, ret); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + ret = wait_any_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + close(event); + + close(objs[0]); + close(objs[1]); + + close(fd); +} + +TEST(alert_all) +{ + struct ntsync_event_args event_args = {0}; + struct ntsync_wait_args wait_args = {0}; + struct ntsync_sem_args sem_args = {0}; + struct wait_args thread_args; + __u32 index, count, signaled; + int objs[2], event, fd, ret; + pthread_t thread; + + fd = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd); + + sem_args.count = 2; + sem_args.max = 2; + objs[0] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[0]); + + sem_args.count = 1; + sem_args.max = 2; + objs[1] = ioctl(fd, NTSYNC_IOC_CREATE_SEM, &sem_args); + EXPECT_LE(0, objs[1]); + + event_args.manual = true; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + /* test wakeup via alert */ + + ret = ioctl(event, NTSYNC_IOC_EVENT_RESET, &signaled); + EXPECT_EQ(0, ret); + + wait_args.timeout = get_abs_timeout(1000); + wait_args.objs = (uintptr_t)objs; + wait_args.count = 2; + wait_args.owner = 123; + wait_args.index = 0xdeadbeef; + wait_args.alert = event; + thread_args.fd = fd; + thread_args.args = &wait_args; + thread_args.request = NTSYNC_IOC_WAIT_ALL; + ret = pthread_create(&thread, NULL, wait_thread, &thread_args); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(ETIMEDOUT, ret); + + ret = ioctl(event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + ret = wait_for_thread(thread, 100); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, thread_args.ret); + EXPECT_EQ(2, wait_args.index); + + close(event); + + /* test with an auto-reset event */ + + event_args.manual = false; + event_args.signaled = true; + event = ioctl(fd, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, event); + + count = 2; + ret = release_sem(objs[1], &count); + EXPECT_EQ(0, ret); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(0, index); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(0, ret); + EXPECT_EQ(2, index); + + ret = wait_all_alert(fd, 2, objs, 123, event, &index); + EXPECT_EQ(-1, ret); + EXPECT_EQ(ETIMEDOUT, errno); + + close(event); + + close(objs[0]); + close(objs[1]); + + close(fd); +} + +#define STRESS_LOOPS 10000 +#define STRESS_THREADS 4 + +static unsigned int stress_counter; +static int stress_device, stress_start_event, stress_mutex; + +static void *stress_thread(void *arg) +{ + struct ntsync_wait_args wait_args = {0}; + __u32 index, count, i; + int ret; + + wait_args.timeout = UINT64_MAX; + wait_args.count = 1; + wait_args.objs = (uintptr_t)&stress_start_event; + wait_args.owner = gettid(); + wait_args.index = 0xdeadbeef; + + ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args); + + wait_args.objs = (uintptr_t)&stress_mutex; + + for (i = 0; i < STRESS_LOOPS; ++i) { + ioctl(stress_device, NTSYNC_IOC_WAIT_ANY, &wait_args); + + ++stress_counter; + + unlock_mutex(stress_mutex, wait_args.owner, &count); + } + + return NULL; +} + +TEST(stress_wait) +{ + struct ntsync_event_args event_args; + struct ntsync_mutex_args mutex_args; + pthread_t threads[STRESS_THREADS]; + __u32 signaled, i; + int ret; + + stress_device = open("/dev/ntsync", O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, stress_device); + + mutex_args.owner = 0; + mutex_args.count = 0; + stress_mutex = ioctl(stress_device, NTSYNC_IOC_CREATE_MUTEX, &mutex_args); + EXPECT_LE(0, stress_mutex); + + event_args.manual = 1; + event_args.signaled = 0; + stress_start_event = ioctl(stress_device, NTSYNC_IOC_CREATE_EVENT, &event_args); + EXPECT_LE(0, stress_start_event); + + for (i = 0; i < STRESS_THREADS; ++i) + pthread_create(&threads[i], NULL, stress_thread, NULL); + + ret = ioctl(stress_start_event, NTSYNC_IOC_EVENT_SET, &signaled); + EXPECT_EQ(0, ret); + + for (i = 0; i < STRESS_THREADS; ++i) { + ret = pthread_join(threads[i], NULL); + EXPECT_EQ(0, ret); + } + + EXPECT_EQ(STRESS_LOOPS * STRESS_THREADS, stress_counter); + + close(stress_start_event); + close(stress_mutex); + close(stress_device); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/efivarfs/efivarfs.sh b/tools/testing/selftests/efivarfs/efivarfs.sh index d374878cc0ba..c62544b966ae 100755 --- a/tools/testing/selftests/efivarfs/efivarfs.sh +++ b/tools/testing/selftests/efivarfs/efivarfs.sh @@ -76,11 +76,11 @@ test_create_empty() : > $file - if [ ! -e $file ]; then - echo "$file can not be created without writing" >&2 + if [ -e $file ]; then + echo "$file can be created without writing" >&2 + file_cleanup $file exit 1 fi - file_cleanup $file } test_create_read() @@ -89,10 +89,13 @@ test_create_read() ./create-read $file if [ $? -ne 0 ]; then echo "create and read $file failed" + exit 1 + fi + if [ -e $file ]; then + echo "file still exists and should not" file_cleanup $file exit 1 fi - file_cleanup $file } test_delete() @@ -202,6 +205,158 @@ test_invalid_filenames() exit $ret } +test_no_set_size() +{ + local attrs='\x07\x00\x00\x00' + local file=$efivarfs_mount/$FUNCNAME-$test_guid + local ret=0 + + printf "$attrs\x00" > $file + [ -e $file -a -s $file ] || exit 1 + chattr -i $file + : > $file + if [ $? != 0 ]; then + echo "variable file failed to accept truncation" + ret=1 + elif [ -e $file -a ! -s $file ]; then + echo "file can be truncated to zero size" + ret=1 + fi + rm $file || exit 1 + + exit $ret +} + +setup_test_multiple() +{ + ## + # we're going to do multi-threaded tests, so create a set of + # pipes for synchronization. We use pipes 1..3 to start the + # stalled shell job and pipes 4..6 as indicators that the job + # has started. If you need more than 3 jobs the two +3's below + # need increasing + ## + + declare -ag p + + # empty is because arrays number from 0 but jobs number from 1 + p[0]="" + + for f in 1 2 3 4 5 6; do + p[$f]=/tmp/efivarfs_pipe${f} + mknod ${p[$f]} p + done + + declare -g var=$efivarfs_mount/test_multiple-$test_guid + + cleanup() { + for f in ${p[@]}; do + rm -f ${f} + done + if [ -e $var ]; then + file_cleanup $var + fi + } + trap cleanup exit + + waitstart() { + cat ${p[$[$1+3]]} > /dev/null + } + + waitpipe() { + echo 1 > ${p[$[$1+3]]} + cat ${p[$1]} > /dev/null + } + + endjob() { + echo 1 > ${p[$1]} + wait -n %$1 + } +} + +test_multiple_zero_size() +{ + ## + # check for remove on last close, set up three threads all + # holding the variable (one write and two reads) and then + # close them sequentially (waiting for completion) and check + # the state of the variable + ## + + { waitpipe 1; echo 1; } > $var 2> /dev/null & + waitstart 1 + # zero length file should exist + [ -e $var ] || exit 1 + # second and third delayed close + { waitpipe 2; } < $var & + waitstart 2 + { waitpipe 3; } < $var & + waitstart 3 + # close first fd + endjob 1 + # var should only be deleted on last close + [ -e $var ] || exit 1 + # close second fd + endjob 2 + [ -e $var ] || exit 1 + # file should go on last close + endjob 3 + [ ! -e $var ] || exit 1 +} + +test_multiple_create() +{ + ## + # set multiple threads to access the variable but delay + # the final write to check the close of 2 and 3. The + # final write should succeed in creating the variable + ## + { waitpipe 1; printf '\x07\x00\x00\x00\x54'; } > $var & + waitstart 1 + [ -e $var -a ! -s $var ] || exit 1 + { waitpipe 2; } < $var & + waitstart 2 + { waitpipe 3; } < $var & + waitstart 3 + # close second and third fds + endjob 2 + # var should only be created (have size) on last close + [ -e $var -a ! -s $var ] || exit 1 + endjob 3 + [ -e $var -a ! -s $var ] || exit 1 + # close first fd + endjob 1 + # variable should still exist + [ -s $var ] || exit 1 + file_cleanup $var +} + +test_multiple_delete_on_write() { + ## + # delete the variable on final write; seqencing similar + # to test_multiple_create() + ## + printf '\x07\x00\x00\x00\x54' > $var + chattr -i $var + { waitpipe 1; printf '\x07\x00\x00\x00'; } > $var & + waitstart 1 + [ -e $var -a -s $var ] || exit 1 + { waitpipe 2; } < $var & + waitstart 2 + { waitpipe 3; } < $var & + waitstart 3 + # close first fd; write should set variable size to zero + endjob 1 + # var should only be deleted on last close + [ -e $var -a ! -s $var ] || exit 1 + endjob 2 + [ -e $var ] || exit 1 + # close last fd + endjob 3 + # variable should now be removed + [ ! -e $var ] || exit 1 +} + check_prereqs rc=0 @@ -214,5 +369,10 @@ run_test test_zero_size_delete run_test test_open_unlink run_test test_valid_filenames run_test test_invalid_filenames +run_test test_no_set_size +setup_test_multiple +run_test test_multiple_zero_size +run_test test_multiple_create +run_test test_multiple_delete_on_write exit $rc diff --git a/tools/testing/selftests/exec/.gitignore b/tools/testing/selftests/exec/.gitignore index a0dc5d4bf733..7f3d1ae762ec 100644 --- a/tools/testing/selftests/exec/.gitignore +++ b/tools/testing/selftests/exec/.gitignore @@ -9,9 +9,13 @@ execveat.ephemeral execveat.denatured non-regular null-argv +/check-exec +/false +/inc /load_address.* !load_address.c /recursion-depth +/set-exec xxxxxxxx* pipe S_I*.test diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile index ba012bc5aab9..45a3cfc435cf 100644 --- a/tools/testing/selftests/exec/Makefile +++ b/tools/testing/selftests/exec/Makefile @@ -1,26 +1,33 @@ # SPDX-License-Identifier: GPL-2.0 CFLAGS = -Wall CFLAGS += -Wno-nonnull +CFLAGS += $(KHDR_INCLUDES) + +LDLIBS += -lcap ALIGNS := 0x1000 0x200000 0x1000000 ALIGN_PIES := $(patsubst %,load_address.%,$(ALIGNS)) ALIGN_STATIC_PIES := $(patsubst %,load_address.static.%,$(ALIGNS)) ALIGNMENT_TESTS := $(ALIGN_PIES) $(ALIGN_STATIC_PIES) -TEST_PROGS := binfmt_script.py +TEST_PROGS := binfmt_script.py check-exec-tests.sh TEST_GEN_PROGS := execveat non-regular $(ALIGNMENT_TESTS) +TEST_GEN_PROGS_EXTENDED := false inc set-exec script-exec.inc script-noexec.inc TEST_GEN_FILES := execveat.symlink execveat.denatured script subdir # Makefile is a run-time dependency, since it's accessed by the execveat test TEST_FILES := Makefile TEST_GEN_PROGS += recursion-depth TEST_GEN_PROGS += null-argv +TEST_GEN_PROGS += check-exec EXTRA_CLEAN := $(OUTPUT)/subdir.moved $(OUTPUT)/execveat.moved $(OUTPUT)/xxxxx* \ $(OUTPUT)/S_I*.test include ../lib.mk +CHECK_EXEC_SAMPLES := $(top_srcdir)/samples/check-exec + $(OUTPUT)/subdir: mkdir -p $@ $(OUTPUT)/script: Makefile @@ -38,3 +45,13 @@ $(OUTPUT)/load_address.0x%: load_address.c $(OUTPUT)/load_address.static.0x%: load_address.c $(CC) $(CFLAGS) $(LDFLAGS) -Wl,-z,max-page-size=$(lastword $(subst ., ,$@)) \ -fPIE -static-pie $< -o $@ +$(OUTPUT)/false: false.c + $(CC) $(CFLAGS) $(LDFLAGS) -static $< -o $@ +$(OUTPUT)/inc: $(CHECK_EXEC_SAMPLES)/inc.c + $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ +$(OUTPUT)/set-exec: $(CHECK_EXEC_SAMPLES)/set-exec.c + $(CC) $(CFLAGS) $(LDFLAGS) $< -o $@ +$(OUTPUT)/script-exec.inc: $(CHECK_EXEC_SAMPLES)/script-exec.inc + cp $< $@ +$(OUTPUT)/script-noexec.inc: $(CHECK_EXEC_SAMPLES)/script-noexec.inc + cp $< $@ diff --git a/tools/testing/selftests/exec/check-exec-tests.sh b/tools/testing/selftests/exec/check-exec-tests.sh new file mode 100755 index 000000000000..87102906ae3c --- /dev/null +++ b/tools/testing/selftests/exec/check-exec-tests.sh @@ -0,0 +1,205 @@ +#!/usr/bin/env bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test the "inc" interpreter. +# +# See include/uapi/linux/securebits.h, include/uapi/linux/fcntl.h and +# samples/check-exec/inc.c +# +# Copyright © 2024 Microsoft Corporation + +set -u -e -o pipefail + +EXPECTED_OUTPUT="1" +exec 2>/dev/null + +DIR="$(dirname $(readlink -f "$0"))" +source "${DIR}"/../kselftest/ktap_helpers.sh + +exec_direct() { + local expect="$1" + local script="$2" + shift 2 + local ret=0 + local out + + # Updates PATH for `env` to execute the `inc` interpreter. + out="$(PATH="." "$@" "${script}")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for direct file execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for direct file execution: ${out}" + return 1 + fi +} + +exec_indirect() { + local expect="$1" + local script="$2" + shift 2 + local ret=0 + local out + + # Script passed as argument. + out="$("$@" ./inc "${script}")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for indirect file execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for indirect file execution: ${out}" + return 1 + fi +} + +exec_stdin_reg() { + local expect="$1" + local script="$2" + shift 2 + local ret=0 + local out + + # Executing stdin must be allowed if the related file is executable. + out="$("$@" ./inc -i < "${script}")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for stdin regular file execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for stdin regular file execution: ${out}" + return 1 + fi +} + +exec_stdin_pipe() { + local expect="$1" + shift + local ret=0 + local out + + # A pipe is not executable. + out="$(cat script-exec.inc | "$@" ./inc -i)" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for stdin pipe execution: ${ret}" + return 1 + fi +} + +exec_argument() { + local expect="$1" + local ret=0 + shift + local out + + # Script not coming from a file must not be executed. + out="$("$@" ./inc -c "$(< script-exec.inc)")" || ret=$? + + if [[ ${ret} -ne ${expect} ]]; then + echo "ERROR: Wrong expectation for arbitrary argument execution: ${ret}" + return 1 + fi + if [[ ${ret} -eq 0 && "${out}" != "${EXPECTED_OUTPUT}" ]]; then + echo "ERROR: Wrong output for arbitrary argument execution: ${out}" + return 1 + fi +} + +exec_interactive() { + exec_stdin_pipe "$@" + exec_argument "$@" +} + +ktap_test() { + ktap_test_result "$*" "$@" +} + +ktap_print_header +ktap_set_plan 28 + +# Without secbit configuration, nothing is changed. + +ktap_print_msg "By default, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc +ktap_test exec_indirect 0 script-exec.inc + +ktap_print_msg "By default, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc + +ktap_print_msg "By default, non-executable scripts are allowed to be interpreted, but not directly executed." +# We get 126 because of direct execution by Bash. +ktap_test exec_direct 126 script-noexec.inc +ktap_test exec_indirect 0 script-noexec.inc + +ktap_print_msg "By default, non-executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-noexec.inc + +ktap_print_msg "By default, interactive commands are allowed to be interpreted." +ktap_test exec_interactive 0 + +# With only file restriction: protect non-malicious users from inadvertent errors (e.g. python ~/Downloads/*.py). + +ktap_print_msg "With -f, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc ./set-exec -f -- +ktap_test exec_indirect 0 script-exec.inc ./set-exec -f -- + +ktap_print_msg "With -f, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc ./set-exec -f -- + +ktap_print_msg "With -f, non-executable scripts are not allowed to be executed nor interpreted." +# Direct execution of non-executable script is alwayse denied by the kernel. +ktap_test exec_direct 1 script-noexec.inc ./set-exec -f -- +ktap_test exec_indirect 1 script-noexec.inc ./set-exec -f -- + +ktap_print_msg "With -f, non-executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-noexec.inc ./set-exec -f -- + +ktap_print_msg "With -f, interactive commands are allowed to be interpreted." +ktap_test exec_interactive 0 ./set-exec -f -- + +# With only denied interactive commands: check or monitor script content (e.g. with LSM). + +ktap_print_msg "With -i, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc ./set-exec -i -- +ktap_test exec_indirect 0 script-exec.inc ./set-exec -i -- + +ktap_print_msg "With -i, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc ./set-exec -i -- + +ktap_print_msg "With -i, non-executable scripts are allowed to be interpreted, but not directly executed." +# Direct execution of non-executable script is alwayse denied by the kernel. +ktap_test exec_direct 1 script-noexec.inc ./set-exec -i -- +ktap_test exec_indirect 0 script-noexec.inc ./set-exec -i -- + +ktap_print_msg "With -i, non-executable stdin is not allowed to be interpreted." +ktap_test exec_stdin_reg 1 script-noexec.inc ./set-exec -i -- + +ktap_print_msg "With -i, interactive commands are not allowed to be interpreted." +ktap_test exec_interactive 1 ./set-exec -i -- + +# With both file restriction and denied interactive commands: only allow executable scripts. + +ktap_print_msg "With -fi, executable scripts are allowed to be interpreted and executed." +ktap_test exec_direct 0 script-exec.inc ./set-exec -fi -- +ktap_test exec_indirect 0 script-exec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, executable stdin is allowed to be interpreted." +ktap_test exec_stdin_reg 0 script-exec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, non-executable scripts are not allowed to be interpreted nor executed." +# Direct execution of non-executable script is alwayse denied by the kernel. +ktap_test exec_direct 1 script-noexec.inc ./set-exec -fi -- +ktap_test exec_indirect 1 script-noexec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, non-executable stdin is not allowed to be interpreted." +ktap_test exec_stdin_reg 1 script-noexec.inc ./set-exec -fi -- + +ktap_print_msg "With -fi, interactive commands are not allowed to be interpreted." +ktap_test exec_interactive 1 ./set-exec -fi -- + +ktap_finished diff --git a/tools/testing/selftests/exec/check-exec.c b/tools/testing/selftests/exec/check-exec.c new file mode 100644 index 000000000000..55bce47e56b7 --- /dev/null +++ b/tools/testing/selftests/exec/check-exec.c @@ -0,0 +1,463 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test execveat(2) with AT_EXECVE_CHECK, and prctl(2) with + * SECBIT_EXEC_RESTRICT_FILE, SECBIT_EXEC_DENY_INTERACTIVE, and their locked + * counterparts. + * + * Copyright © 2018-2020 ANSSI + * Copyright © 2024 Microsoft Corporation + * + * Author: Mickaël Salaün <mic@digikod.net> + */ + +#include <asm-generic/unistd.h> +#include <errno.h> +#include <fcntl.h> +#include <linux/prctl.h> +#include <linux/securebits.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/capability.h> +#include <sys/mount.h> +#include <sys/prctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/syscall.h> +#include <sys/sysmacros.h> +#include <unistd.h> + +/* Defines AT_EXECVE_CHECK without type conflicts. */ +#define _ASM_GENERIC_FCNTL_H +#include <linux/fcntl.h> + +#include "../kselftest_harness.h" + +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + +static void drop_privileges(struct __test_metadata *const _metadata) +{ + const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED; + cap_t cap_p; + + if ((cap_get_secbits() & noroot) != noroot) + EXPECT_EQ(0, cap_set_secbits(noroot)); + + cap_p = cap_get_proc(); + EXPECT_NE(NULL, cap_p); + EXPECT_NE(-1, cap_clear(cap_p)); + + /* + * Drops everything, especially CAP_SETPCAP, CAP_DAC_OVERRIDE, and + * CAP_DAC_READ_SEARCH. + */ + EXPECT_NE(-1, cap_set_proc(cap_p)); + EXPECT_NE(-1, cap_free(cap_p)); +} + +static int test_secbits_set(const unsigned int secbits) +{ + int err; + + err = prctl(PR_SET_SECUREBITS, secbits); + if (err) + return errno; + return 0; +} + +FIXTURE(access) +{ + int memfd, pipefd; + int pipe_fds[2], socket_fds[2]; +}; + +FIXTURE_VARIANT(access) +{ + const bool mount_exec; + const bool file_exec; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_exec_file_exec) { + /* clang-format on */ + .mount_exec = true, + .file_exec = true, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_exec_file_noexec) { + /* clang-format on */ + .mount_exec = true, + .file_exec = false, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_noexec_file_exec) { + /* clang-format on */ + .mount_exec = false, + .file_exec = true, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(access, mount_noexec_file_noexec) { + /* clang-format on */ + .mount_exec = false, + .file_exec = false, +}; + +static const char binary_path[] = "./false"; +static const char workdir_path[] = "./test-mount"; +static const char reg_file_path[] = "./test-mount/regular_file"; +static const char dir_path[] = "./test-mount/directory"; +static const char block_dev_path[] = "./test-mount/block_device"; +static const char char_dev_path[] = "./test-mount/character_device"; +static const char fifo_path[] = "./test-mount/fifo"; + +FIXTURE_SETUP(access) +{ + int procfd_path_size; + static const char path_template[] = "/proc/self/fd/%d"; + char procfd_path[sizeof(path_template) + 10]; + + /* Makes sure we are not already restricted nor locked. */ + EXPECT_EQ(0, test_secbits_set(0)); + + /* + * Cleans previous workspace if any error previously happened (don't + * check errors). + */ + umount(workdir_path); + rmdir(workdir_path); + + /* Creates a clean mount point. */ + ASSERT_EQ(0, mkdir(workdir_path, 00700)); + ASSERT_EQ(0, mount("test", workdir_path, "tmpfs", + MS_MGC_VAL | (variant->mount_exec ? 0 : MS_NOEXEC), + "mode=0700,size=9m")); + + /* Creates a regular file. */ + ASSERT_EQ(0, mknod(reg_file_path, + S_IFREG | (variant->file_exec ? 0700 : 0600), 0)); + /* Creates a directory. */ + ASSERT_EQ(0, mkdir(dir_path, variant->file_exec ? 0700 : 0600)); + /* Creates a character device: /dev/null. */ + ASSERT_EQ(0, mknod(char_dev_path, S_IFCHR | 0400, makedev(1, 3))); + /* Creates a block device: /dev/loop0 */ + ASSERT_EQ(0, mknod(block_dev_path, S_IFBLK | 0400, makedev(7, 0))); + /* Creates a fifo. */ + ASSERT_EQ(0, mknod(fifo_path, S_IFIFO | 0600, 0)); + + /* Creates a regular file without user mount point. */ + self->memfd = memfd_create("test-exec-probe", MFD_CLOEXEC); + ASSERT_LE(0, self->memfd); + /* Sets mode, which must be ignored by the exec check. */ + ASSERT_EQ(0, fchmod(self->memfd, variant->file_exec ? 0700 : 0600)); + + /* Creates a pipefs file descriptor. */ + ASSERT_EQ(0, pipe(self->pipe_fds)); + procfd_path_size = snprintf(procfd_path, sizeof(procfd_path), + path_template, self->pipe_fds[0]); + ASSERT_LT(procfd_path_size, sizeof(procfd_path)); + self->pipefd = open(procfd_path, O_RDWR | O_CLOEXEC); + ASSERT_LE(0, self->pipefd); + ASSERT_EQ(0, fchmod(self->pipefd, variant->file_exec ? 0700 : 0600)); + + /* Creates a socket file descriptor. */ + ASSERT_EQ(0, socketpair(AF_UNIX, SOCK_DGRAM | SOCK_CLOEXEC, 0, + self->socket_fds)); +} + +FIXTURE_TEARDOWN_PARENT(access) +{ + /* There is no need to unlink the test files. */ + EXPECT_EQ(0, umount(workdir_path)); + EXPECT_EQ(0, rmdir(workdir_path)); +} + +static void fill_exec_fd(struct __test_metadata *_metadata, const int fd_out) +{ + char buf[1024]; + size_t len; + int fd_in; + + fd_in = open(binary_path, O_CLOEXEC | O_RDONLY); + ASSERT_LE(0, fd_in); + /* Cannot use copy_file_range(2) because of EXDEV. */ + len = read(fd_in, buf, sizeof(buf)); + EXPECT_LE(0, len); + while (len > 0) { + EXPECT_EQ(len, write(fd_out, buf, len)) + { + TH_LOG("Failed to write: %s (%d)", strerror(errno), + errno); + } + len = read(fd_in, buf, sizeof(buf)); + EXPECT_LE(0, len); + } + EXPECT_EQ(0, close(fd_in)); +} + +static void fill_exec_path(struct __test_metadata *_metadata, + const char *const path) +{ + int fd_out; + + fd_out = open(path, O_CLOEXEC | O_WRONLY); + ASSERT_LE(0, fd_out) + { + TH_LOG("Failed to open %s: %s", path, strerror(errno)); + } + fill_exec_fd(_metadata, fd_out); + EXPECT_EQ(0, close(fd_out)); +} + +static void test_exec_fd(struct __test_metadata *_metadata, const int fd, + const int err_code) +{ + char *const argv[] = { "", NULL }; + int access_ret, access_errno; + + /* + * If we really execute fd, filled with the "false" binary, the current + * thread will exits with an error, which will be interpreted by the + * test framework as an error. With AT_EXECVE_CHECK, we only check a + * potential successful execution. + */ + access_ret = sys_execveat(fd, "", argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); + access_errno = errno; + if (err_code) { + EXPECT_EQ(-1, access_ret); + EXPECT_EQ(err_code, access_errno) + { + TH_LOG("Wrong error for execveat(2): %s (%d)", + strerror(access_errno), errno); + } + } else { + EXPECT_EQ(0, access_ret) + { + TH_LOG("Access denied: %s", strerror(access_errno)); + } + } +} + +static void test_exec_path(struct __test_metadata *_metadata, + const char *const path, const int err_code) +{ + int flags = O_CLOEXEC; + int fd; + + /* Do not block on pipes. */ + if (path == fifo_path) + flags |= O_NONBLOCK; + + fd = open(path, flags | O_RDONLY); + ASSERT_LE(0, fd) + { + TH_LOG("Failed to open %s: %s", path, strerror(errno)); + } + test_exec_fd(_metadata, fd, err_code); + EXPECT_EQ(0, close(fd)); +} + +/* Tests that we don't get ENOEXEC. */ +TEST_F(access, regular_file_empty) +{ + const int exec = variant->mount_exec && variant->file_exec; + + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); +} + +TEST_F(access, regular_file_elf) +{ + const int exec = variant->mount_exec && variant->file_exec; + + fill_exec_path(_metadata, reg_file_path); + + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_path(_metadata, reg_file_path, exec ? 0 : EACCES); +} + +/* Tests that we don't get ENOEXEC. */ +TEST_F(access, memfd_empty) +{ + const int exec = variant->file_exec; + + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); +} + +TEST_F(access, memfd_elf) +{ + const int exec = variant->file_exec; + + fill_exec_fd(_metadata, self->memfd); + + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); + + drop_privileges(_metadata); + test_exec_fd(_metadata, self->memfd, exec ? 0 : EACCES); +} + +TEST_F(access, non_regular_files) +{ + test_exec_path(_metadata, dir_path, EACCES); + test_exec_path(_metadata, block_dev_path, EACCES); + test_exec_path(_metadata, char_dev_path, EACCES); + test_exec_path(_metadata, fifo_path, EACCES); + test_exec_fd(_metadata, self->socket_fds[0], EACCES); + test_exec_fd(_metadata, self->pipefd, EACCES); +} + +/* clang-format off */ +FIXTURE(secbits) {}; +/* clang-format on */ + +FIXTURE_VARIANT(secbits) +{ + const bool is_privileged; + const int error; +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(secbits, priv) { + /* clang-format on */ + .is_privileged = true, + .error = 0, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(secbits, unpriv) { + /* clang-format on */ + .is_privileged = false, + .error = EPERM, +}; + +FIXTURE_SETUP(secbits) +{ + /* Makes sure no exec bits are set. */ + EXPECT_EQ(0, test_secbits_set(0)); + EXPECT_EQ(0, prctl(PR_GET_SECUREBITS)); + + if (!variant->is_privileged) + drop_privileges(_metadata); +} + +FIXTURE_TEARDOWN(secbits) +{ +} + +TEST_F(secbits, legacy) +{ + EXPECT_EQ(variant->error, test_secbits_set(0)); +} + +#define CHILD(...) \ + do { \ + pid_t child = vfork(); \ + EXPECT_LE(0, child); \ + if (child == 0) { \ + __VA_ARGS__; \ + _exit(0); \ + } \ + } while (0) + +TEST_F(secbits, exec) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(0, test_secbits_set(secbits)); + EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS)); + CHILD(EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS))); + + secbits |= SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(0, test_secbits_set(secbits)); + EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS)); + CHILD(EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS))); + + secbits &= ~(SECBIT_EXEC_RESTRICT_FILE | SECBIT_EXEC_DENY_INTERACTIVE); + EXPECT_EQ(0, test_secbits_set(secbits)); + EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS)); + CHILD(EXPECT_EQ(secbits, prctl(PR_GET_SECUREBITS))); +} + +TEST_F(secbits, check_locked_set) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(0, test_secbits_set(secbits)); + secbits |= SECBIT_EXEC_RESTRICT_FILE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock set but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_F(secbits, check_locked_unset) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_RESTRICT_FILE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock unset but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_RESTRICT_FILE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_F(secbits, restrict_locked_set) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(0, test_secbits_set(secbits)); + secbits |= SECBIT_EXEC_DENY_INTERACTIVE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock set but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_F(secbits, restrict_locked_unset) +{ + unsigned int secbits = prctl(PR_GET_SECUREBITS); + + secbits |= SECBIT_EXEC_DENY_INTERACTIVE_LOCKED; + EXPECT_EQ(0, test_secbits_set(secbits)); + + /* Checks lock unset but unchanged. */ + EXPECT_EQ(variant->error, test_secbits_set(secbits)); + CHILD(EXPECT_EQ(variant->error, test_secbits_set(secbits))); + + secbits &= ~SECBIT_EXEC_DENY_INTERACTIVE; + EXPECT_EQ(EPERM, test_secbits_set(0)); + CHILD(EXPECT_EQ(EPERM, test_secbits_set(0))); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/exec/config b/tools/testing/selftests/exec/config new file mode 100644 index 000000000000..c308079867b3 --- /dev/null +++ b/tools/testing/selftests/exec/config @@ -0,0 +1,2 @@ +CONFIG_BLK_DEV=y +CONFIG_BLK_DEV_LOOP=y diff --git a/tools/testing/selftests/exec/false.c b/tools/testing/selftests/exec/false.c new file mode 100644 index 000000000000..104383ec3a79 --- /dev/null +++ b/tools/testing/selftests/exec/false.c @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 +int main(void) +{ + return 1; +} diff --git a/tools/testing/selftests/filesystems/statmount/.gitignore b/tools/testing/selftests/filesystems/statmount/.gitignore index 82a4846cbc4b..973363ad66a2 100644 --- a/tools/testing/selftests/filesystems/statmount/.gitignore +++ b/tools/testing/selftests/filesystems/statmount/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only +statmount_test_ns /*_test diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index 8eb6aa606a0d..46d289611ce8 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -383,6 +383,10 @@ static void test_statmount_mnt_point(void) return; } + if (!(sm->mask & STATMOUNT_MNT_POINT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_POINT in mask\n"); + return; + } if (strcmp(sm->str + sm->mnt_point, "/") != 0) { ksft_test_result_fail("unexpected mount point: '%s' != '/'\n", sm->str + sm->mnt_point); @@ -408,6 +412,10 @@ static void test_statmount_mnt_root(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_ROOT in mask\n"); + return; + } mnt_root = sm->str + sm->mnt_root; last_root = strrchr(mnt_root, '/'); if (last_root) @@ -437,6 +445,10 @@ static void test_statmount_fs_type(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_FS_TYPE)) { + ksft_test_result_fail("missing STATMOUNT_FS_TYPE in mask\n"); + return; + } fs_type = sm->str + sm->fs_type; for (s = known_fs; s != NULL; s++) { if (strcmp(fs_type, *s) == 0) @@ -464,6 +476,11 @@ static void test_statmount_mnt_opts(void) return; } + if (!(sm->mask & STATMOUNT_MNT_BASIC)) { + ksft_test_result_fail("missing STATMOUNT_MNT_BASIC in mask\n"); + return; + } + while (getline(&line, &len, f_mountinfo) != -1) { int i; char *p, *p2; @@ -514,7 +531,10 @@ static void test_statmount_mnt_opts(void) if (p2) *p2 = '\0'; - statmount_opts = sm->str + sm->mnt_opts; + if (sm->mask & STATMOUNT_MNT_OPTS) + statmount_opts = sm->str + sm->mnt_opts; + else + statmount_opts = ""; if (strcmp(statmount_opts, p) != 0) ksft_test_result_fail( "unexpected mount options: '%s' != '%s'\n", diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile index a1e955d2de4c..49d96bb16355 100644 --- a/tools/testing/selftests/ftrace/Makefile +++ b/tools/testing/selftests/ftrace/Makefile @@ -6,4 +6,6 @@ TEST_PROGS := ftracetest-ktap TEST_FILES := test.d settings EXTRA_CLEAN := $(OUTPUT)/logs/* +TEST_GEN_PROGS = poll + include ../lib.mk diff --git a/tools/testing/selftests/ftrace/poll.c b/tools/testing/selftests/ftrace/poll.c new file mode 100644 index 000000000000..53258f7515e7 --- /dev/null +++ b/tools/testing/selftests/ftrace/poll.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Simple poll on a file. + * + * Copyright (c) 2024 Google LLC. + */ + +#include <errno.h> +#include <fcntl.h> +#include <poll.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#define BUFSIZE 4096 + +/* + * Usage: + * poll [-I|-P] [-t timeout] FILE + */ +int main(int argc, char *argv[]) +{ + struct pollfd pfd = {.events = POLLIN}; + char buf[BUFSIZE]; + int timeout = -1; + int ret, opt; + + while ((opt = getopt(argc, argv, "IPt:")) != -1) { + switch (opt) { + case 'I': + pfd.events = POLLIN; + break; + case 'P': + pfd.events = POLLPRI; + break; + case 't': + timeout = atoi(optarg); + break; + default: + fprintf(stderr, "Usage: %s [-I|-P] [-t timeout] FILE\n", + argv[0]); + return -1; + } + } + if (optind >= argc) { + fprintf(stderr, "Error: Polling file is not specified\n"); + return -1; + } + + pfd.fd = open(argv[optind], O_RDONLY); + if (pfd.fd < 0) { + fprintf(stderr, "failed to open %s", argv[optind]); + perror("open"); + return -1; + } + + /* Reset poll by read if POLLIN is specified. */ + if (pfd.events & POLLIN) + do {} while (read(pfd.fd, buf, BUFSIZE) == BUFSIZE); + + ret = poll(&pfd, 1, timeout); + if (ret < 0 && errno != EINTR) { + perror("poll"); + return -1; + } + close(pfd.fd); + + /* If timeout happned (ret == 0), exit code is 1 */ + if (ret == 0) + return 1; + + return 0; +} diff --git a/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc index 35e8d47d6072..8a7ce647a60d 100644 --- a/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc +++ b/tools/testing/selftests/ftrace/test.d/00basic/mount_options.tc @@ -15,11 +15,11 @@ find_alternate_gid() { tac /etc/group | grep -v ":$original_gid:" | head -1 | cut -d: -f3 } -mount_tracefs_with_options() { +remount_tracefs_with_options() { local mount_point="$1" local options="$2" - mount -t tracefs -o "$options" nodev "$mount_point" + mount -t tracefs -o "remount,$options" nodev "$mount_point" setup } @@ -81,7 +81,7 @@ test_gid_mount_option() { # Unmount existing tracefs instance and mount with new GID unmount_tracefs "$mount_point" - mount_tracefs_with_options "$mount_point" "$new_options" + remount_tracefs_with_options "$mount_point" "$new_options" check_gid "$mount_point" "$other_group" @@ -92,7 +92,7 @@ test_gid_mount_option() { # Unmount and remount with the original GID unmount_tracefs "$mount_point" - mount_tracefs_with_options "$mount_point" "$mount_options" + remount_tracefs_with_options "$mount_point" "$mount_options" check_gid "$mount_point" "$original_group" } diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc index dc25bcf4f9e2..73f6c6fcecab 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc @@ -7,12 +7,42 @@ echo 0 > events/enable echo > dynamic_events PLACE=$FUNCTION_FORK +PLACE2="kmem_cache_free" +PLACE3="schedule_timeout" + +# Some functions may have BPF programs attached, therefore +# count already enabled_functions before tests start +ocnt=`cat enabled_functions | wc -l` echo "f:myevent1 $PLACE" >> dynamic_events + +# Make sure the event is attached and is the only one +grep -q $PLACE enabled_functions +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $((ocnt + 1)) ]; then + exit_fail +fi + echo "f:myevent2 $PLACE%return" >> dynamic_events +# It should till be the only attached function +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $((ocnt + 1)) ]; then + exit_fail +fi + +# add another event +echo "f:myevent3 $PLACE2" >> dynamic_events + +grep -q $PLACE2 enabled_functions +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $((ocnt + 2)) ]; then + exit_fail +fi + grep -q myevent1 dynamic_events grep -q myevent2 dynamic_events +grep -q myevent3 dynamic_events test -d events/fprobes/myevent1 test -d events/fprobes/myevent2 @@ -21,6 +51,34 @@ echo "-:myevent2" >> dynamic_events grep -q myevent1 dynamic_events ! grep -q myevent2 dynamic_events +# should still have 2 left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $((ocnt + 2)) ]; then + exit_fail +fi + echo > dynamic_events +# Should have none left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $ocnt ]; then + exit_fail +fi + +echo "f:myevent4 $PLACE" >> dynamic_events + +# Should only have one enabled +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $((ocnt + 1)) ]; then + exit_fail +fi + +echo > dynamic_events + +# Should have none left +cnt=`cat enabled_functions | wc -l` +if [ $cnt -ne $ocnt ]; then + exit_fail +fi + clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc index a275decdc880..86c76679c56e 100644 --- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc +++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_uprobe.tc @@ -6,8 +6,10 @@ echo 0 > events/enable echo > dynamic_events +REALBIN=`readlink -f /bin/sh` + echo 'cat /proc/$$/maps' | /bin/sh | \ - grep "r-xp .*/bin/.*sh$" | \ + grep "r-xp .*${REALBIN}$" | \ awk '{printf "p:myevent %s:0x%s\n", $6,$3 }' >> uprobe_events grep -q myevent uprobe_events diff --git a/tools/testing/selftests/ftrace/test.d/event/event-mod.tc b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc new file mode 100644 index 000000000000..175243cd9ab7 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/event/event-mod.tc @@ -0,0 +1,191 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event tracing - enable/disable with module event +# requires: set_event "Can enable module events via: :mod:":README +# flags: instance + +rmmod trace-events-sample ||: +if ! modprobe trace-events-sample ; then + echo "No trace-events sample module - please make CONFIG_SAMPLE_TRACE_EVENTS=m" + exit_unresolved; +fi +trap "rmmod trace-events-sample" EXIT + +# Set events for the module +echo ":mod:trace-events-sample" > set_event + +test_all_enabled() { + + # Check if more than one is enabled + grep -q sample-trace:foo_bar set_event + grep -q sample-trace:foo_bar_with_cond set_event + grep -q sample-trace:foo_bar_with_fn set_event + + # All of them should be enabled. Check via the enable file + val=`cat events/sample-trace/enable` + if [ $val -ne 1 ]; then + exit_fail + fi +} + +clear_events() { + echo > set_event + val=`cat events/enable` + if [ "$val" != "0" ]; then + exit_fail + fi + count=`cat set_event | wc -l` + if [ $count -ne 0 ]; then + exit_fail + fi +} + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo And the set_event file is empty + +cnt=`wc -l set_event` +if [ $cnt -ne 0 ]; then + exit_fail +fi + +echo now enable all events +echo 1 > events/enable + +echo Confirm the events are enabled again +val=`cat events/sample-trace/enable` +if [ $val -ne 1 ]; then + exit_fail +fi + +echo disable just the module events +echo '!:mod:trace-events-sample' >> set_event + +echo Should have mix of events enabled +val=`cat events/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +echo Confirm the module events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo 0 > events/enable + +echo now enable the system events +echo 'sample-trace:mod:trace-events-sample' > set_event + +test_all_enabled + +echo clear all events +echo 0 > events/enable + +echo Confirm the events are disabled +val=`cat events/sample-trace/enable` +if [ $val -ne 0 ]; then + exit_fail +fi + +echo Test enabling foo_bar only +echo 'foo_bar:mod:trace-events-sample' > set_event + +grep -q sample-trace:foo_bar set_event + +echo make sure nothing is found besides foo_bar +if grep -q -v sample-trace:foo_bar set_event ; then + exit_fail +fi + +echo Append another using the system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event + +grep -q sample-trace:foo_bar set_event +grep -q sample-trace:foo_bar_with_cond set_event + +count=`cat set_event | wc -l` + +if [ $count -ne 2 ]; then + exit_fail +fi + +clear_events + +rmmod trace-events-sample + +echo ':mod:trace-events-sample' > set_event + +echo make sure that the module shows up, and '-' is converted to '_' +grep -q '\*:\*:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable just the system events +echo 'sample-trace:mod:trace-events-sample' > set_event +grep -q 'sample-trace:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +test_all_enabled + +clear_events + +rmmod trace-events-sample + +echo Enable event with just event name +echo 'foo_bar:mod:trace-events-sample' > set_event +grep -q 'foo_bar:mod:trace_events_sample' set_event + +echo Enable another event with both system and event name +echo 'sample-trace:foo_bar_with_cond:mod:trace-events-sample' >> set_event +grep -q 'sample-trace:foo_bar_with_cond:mod:trace_events_sample' set_event +echo Make sure the other event was still there +grep -q 'foo_bar:mod:trace_events_sample' set_event + +modprobe trace-events-sample + +echo There should be no :mod: cached events +if grep -q ':mod:' set_event; then + exit_fail +fi + +echo two events should be enabled +count=`cat set_event | wc -l` +if [ $count -ne 2 ]; then + exit_fail +fi + +echo only two events should be enabled +val=`cat events/sample-trace/enable` +if [ "$val" != "X" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +val=`cat events/sample-trace/foo_bar_with_cond/enable` +if [ "$val" != "1" ]; then + exit_fail +fi + +clear_trace diff --git a/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc new file mode 100644 index 000000000000..8d275e3238d9 --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/trigger/trigger-hist-poll.tc @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: event trigger - test poll wait on histogram +# requires: set_event events/sched/sched_process_free/trigger events/sched/sched_process_free/hist +# flags: instance + +POLL=${FTRACETEST_ROOT}/poll + +if [ ! -x ${POLL} ]; then + echo "poll program is not compiled!" + exit_unresolved +fi + +EVENT=events/sched/sched_process_free/ + +# Check poll ops is supported. Before implementing poll on hist file, it +# returns soon with POLLIN | POLLOUT, but not POLLPRI. + +# This must wait >1 sec and return 1 (timeout). +set +e +${POLL} -I -t 1000 ${EVENT}/hist +ret=$? +set -e +if [ ${ret} != 1 ]; then + echo "poll on hist file is not supported" + exit_unsupported +fi + +# Test POLLIN +echo > trace +echo 'hist:key=comm if comm =="sleep"' > ${EVENT}/trigger +echo 1 > ${EVENT}/enable + +# This sleep command will exit after 2 seconds. +sleep 2 & +BGPID=$! +# if timeout happens, poll returns 1. +${POLL} -I -t 4000 ${EVENT}/hist +echo 0 > tracing_on + +if [ -d /proc/${BGPID} ]; then + echo "poll exits too soon" + kill -KILL ${BGPID} ||: + exit_fail +fi + +if ! grep -qw "sleep" trace; then + echo "poll exits before event happens" + exit_fail +fi + +# Test POLLPRI +echo > trace +echo 1 > tracing_on + +# This sleep command will exit after 2 seconds. +sleep 2 & +BGPID=$! +# if timeout happens, poll returns 1. +${POLL} -P -t 4000 ${EVENT}/hist +echo 0 > tracing_on + +if [ -d /proc/${BGPID} ]; then + echo "poll exits too soon" + kill -KILL ${BGPID} ||: + exit_fail +fi + +if ! grep -qw "sleep" trace; then + echo "poll exits before event happens" + exit_fail +fi + +exit_pass diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 6fb66a687f17..bbc29ed9c60a 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -46,12 +46,6 @@ remove_chip() { rmdir $CONFIGFS_DIR/$CHIP || fail "Unable to remove the chip" } -configfs_cleanup() { - for CHIP in `ls $CONFIGFS_DIR/`; do - remove_chip $CHIP - done -} - create_chip() { local CHIP=$1 @@ -105,6 +99,13 @@ disable_chip() { echo 0 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to disable the chip" } +configfs_cleanup() { + for CHIP in `ls $CONFIGFS_DIR/`; do + disable_chip $CHIP + remove_chip $CHIP + done +} + configfs_chip_name() { local CHIP=$1 local BANK=$2 @@ -181,6 +182,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/bank/chip_name` || fail "chip_name doesn't work" +disable_chip chip remove_chip chip echo "1.2. chip_name returns 'none' if the chip is still pending" @@ -195,6 +197,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/dev_name` || fail "dev_name doesn't work" +disable_chip chip remove_chip chip echo "2. Creating and configuring simulated chips" @@ -204,6 +207,7 @@ create_chip chip create_bank chip bank enable_chip chip test "`get_chip_num_lines chip bank`" = "1" || fail "default number of lines is not 1" +disable_chip chip remove_chip chip echo "2.2. Number of lines can be specified" @@ -212,6 +216,7 @@ create_bank chip bank set_num_lines chip bank 16 enable_chip chip test "`get_chip_num_lines chip bank`" = "16" || fail "number of lines is not 16" +disable_chip chip remove_chip chip echo "2.3. Label can be set" @@ -220,6 +225,7 @@ create_bank chip bank set_label chip bank foobar enable_chip chip test "`get_chip_label chip bank`" = "foobar" || fail "label is incorrect" +disable_chip chip remove_chip chip echo "2.4. Label can be left empty" @@ -227,6 +233,7 @@ create_chip chip create_bank chip bank enable_chip chip test -z "`cat $CONFIGFS_DIR/chip/bank/label`" || fail "label is not empty" +disable_chip chip remove_chip chip echo "2.5. Line names can be configured" @@ -238,6 +245,7 @@ set_line_name chip bank 2 bar enable_chip chip test "`get_line_name chip bank 0`" = "foo" || fail "line name is incorrect" test "`get_line_name chip bank 2`" = "bar" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.6. Line config can remain unused if offset is greater than number of lines" @@ -248,6 +256,7 @@ set_line_name chip bank 5 foobar enable_chip chip test "`get_line_name chip bank 0`" = "" || fail "line name is incorrect" test "`get_line_name chip bank 1`" = "" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.7. Line configfs directory names are sanitized" @@ -267,6 +276,7 @@ for CHIP in $CHIPS; do enable_chip $CHIP done for CHIP in $CHIPS; do + disable_chip $CHIP remove_chip $CHIP done @@ -278,6 +288,7 @@ echo foobar > $CONFIGFS_DIR/chip/bank/label 2> /dev/null && \ fail "Setting label of a live chip should fail" echo 8 > $CONFIGFS_DIR/chip/bank/num_lines 2> /dev/null && \ fail "Setting number of lines of a live chip should fail" +disable_chip chip remove_chip chip echo "2.10. Can't create line items when chip is live" @@ -285,6 +296,7 @@ create_chip chip create_bank chip bank enable_chip chip mkdir $CONFIGFS_DIR/chip/bank/line0 2> /dev/null && fail "Creating line item should fail" +disable_chip chip remove_chip chip echo "2.11. Probe errors are propagated to user-space" @@ -316,6 +328,7 @@ mkdir -p $CONFIGFS_DIR/chip/bank/line4/hog enable_chip chip $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 4 2> /dev/null && \ fail "Setting the value of a hogged line shouldn't succeed" +disable_chip chip remove_chip chip echo "3. Controlling simulated chips" @@ -331,6 +344,7 @@ test "$?" = "1" || fail "pull set incorrectly" sysfs_set_pull chip bank 0 pull-down $BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 1 test "$?" = "0" || fail "pull set incorrectly" +disable_chip chip remove_chip chip echo "3.2. Pull can be read from sysfs" @@ -344,6 +358,7 @@ SYSFS_PATH=/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull test `cat $SYSFS_PATH` = "pull-down" || fail "reading the pull failed" sysfs_set_pull chip bank 0 pull-up test `cat $SYSFS_PATH` = "pull-up" || fail "reading the pull failed" +disable_chip chip remove_chip chip echo "3.3. Incorrect input in sysfs is rejected" @@ -355,6 +370,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull" echo foobar > $SYSFS_PATH 2> /dev/null && fail "invalid input not detected" +disable_chip chip remove_chip chip echo "3.4. Can't write to value" @@ -365,6 +381,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" echo 1 > $SYSFS_PATH 2> /dev/null && fail "writing to 'value' succeeded unexpectedly" +disable_chip chip remove_chip chip echo "4. Simulated GPIO chips are functional" @@ -382,6 +399,7 @@ $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 0 & sleep 0.1 # FIXME Any better way? test `cat $SYSFS_PATH` = "1" || fail "incorrect value read from sysfs" kill $! +disable_chip chip remove_chip chip echo "4.2. Bias settings work correctly" @@ -394,6 +412,7 @@ CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" +disable_chip chip remove_chip chip echo "GPIO $MODULE test PASS" diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile index 0336353bd15f..2839d2612ce3 100644 --- a/tools/testing/selftests/hid/Makefile +++ b/tools/testing/selftests/hid/Makefile @@ -43,10 +43,8 @@ TEST_GEN_PROGS = hid_bpf hidraw # $3 - target (assumed to be file); only file name will be emitted; # $4 - optional extra arg, emitted as-is, if provided. ifeq ($(V),1) -Q = msg = else -Q = @ msg = @printf ' %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))"; MAKEFLAGS += --no-print-directory submake_extras := feature_display=0 diff --git a/tools/testing/selftests/ipc/msgque.c b/tools/testing/selftests/ipc/msgque.c index c75ea4094870..e9dbb84c100a 100644 --- a/tools/testing/selftests/ipc/msgque.c +++ b/tools/testing/selftests/ipc/msgque.c @@ -194,7 +194,7 @@ int fill_msgque(struct msgque_data *msgque) int main(int argc, char **argv) { - int msg, pid, err; + int err; struct msgque_data msgque; if (getuid() != 0) diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h index 29fedf609611..cdf91b0ca40f 100644 --- a/tools/testing/selftests/kselftest.h +++ b/tools/testing/selftests/kselftest.h @@ -18,7 +18,8 @@ * ksft_print_msg(fmt, ...); * ksft_perror(msg); * - * and finally report the pass/fail/skip/xfail state of the test with one of: + * and finally report the pass/fail/skip/xfail/xpass state of the test + * with one of: * * ksft_test_result(condition, fmt, ...); * ksft_test_result_report(result, fmt, ...); @@ -26,6 +27,7 @@ * ksft_test_result_fail(fmt, ...); * ksft_test_result_skip(fmt, ...); * ksft_test_result_xfail(fmt, ...); + * ksft_test_result_xpass(fmt, ...); * ksft_test_result_error(fmt, ...); * ksft_test_result_code(exit_code, test_name, fmt, ...); * @@ -147,6 +149,11 @@ static inline void ksft_set_plan(unsigned int plan) static inline void ksft_print_cnts(void) { + if (ksft_cnt.ksft_xskip > 0) + printf( + "# %u skipped test(s) detected. Consider enabling relevant config options to improve coverage.\n", + ksft_cnt.ksft_xskip + ); if (ksft_plan != ksft_test_num()) printf("# Planned tests != run tests (%u != %u)\n", ksft_plan, ksft_test_num()); @@ -227,6 +234,20 @@ static inline __printf(1, 2) void ksft_test_result_xfail(const char *msg, ...) va_end(args); } +static inline __printf(1, 2) void ksft_test_result_xpass(const char *msg, ...) +{ + int saved_errno = errno; + va_list args; + + ksft_cnt.ksft_xpass++; + + va_start(args, msg); + printf("ok %u # XPASS ", ksft_test_num()); + errno = saved_errno; + vprintf(msg, args); + va_end(args); +} + static inline __printf(1, 2) void ksft_test_result_skip(const char *msg, ...) { int saved_errno = errno; @@ -318,6 +339,9 @@ void ksft_test_result_code(int exit_code, const char *test_name, case KSFT_XFAIL: \ ksft_test_result_xfail(fmt, ##__VA_ARGS__); \ break; \ + case KSFT_XPASS: \ + ksft_test_result_xpass(fmt, ##__VA_ARGS__); \ + break; \ case KSFT_SKIP: \ ksft_test_result_skip(fmt, ##__VA_ARGS__); \ break; \ @@ -403,7 +427,7 @@ static inline __noreturn __printf(1, 2) void ksft_exit_skip(const char *msg, ... */ if (ksft_plan || ksft_test_num()) { ksft_cnt.ksft_xskip++; - printf("ok %d # SKIP ", 1 + ksft_test_num()); + printf("ok %u # SKIP ", 1 + ksft_test_num()); } else { printf("1..0 # SKIP "); } diff --git a/tools/testing/selftests/kselftest/ksft.py b/tools/testing/selftests/kselftest/ksft.py index bf215790a89d..0e030837fc17 100644 --- a/tools/testing/selftests/kselftest/ksft.py +++ b/tools/testing/selftests/kselftest/ksft.py @@ -27,6 +27,9 @@ def set_plan(num_tests): def print_cnts(): + if ksft_cnt['skip'] > 0: + print(f"# {ksft_cnt['skip']} skipped test(s) detected. Consider enabling relevant config options to improve coverage.") + print( f"# Totals: pass:{ksft_cnt['pass']} fail:{ksft_cnt['fail']} xfail:0 xpass:0 skip:{ksft_cnt['skip']} error:0" ) diff --git a/tools/testing/selftests/kselftest/ktap_helpers.sh b/tools/testing/selftests/kselftest/ktap_helpers.sh index 05a461890671..32dbfe9da2c4 100644 --- a/tools/testing/selftests/kselftest/ktap_helpers.sh +++ b/tools/testing/selftests/kselftest/ktap_helpers.sh @@ -41,7 +41,7 @@ ktap_skip_all() { __ktap_test() { result="$1" description="$2" - directive="$3" # optional + directive="${3:-}" # optional local directive_str= [ ! -z "$directive" ] && directive_str="# $directive" @@ -118,5 +118,9 @@ ktap_finished() { } ktap_print_totals() { + if [ "$KTAP_CNT_SKIP" -gt 0 ]; then + echo "# $KTAP_CNT_SKIP skipped test(s) detected. " \ + "Consider enabling relevant config options to improve coverage." + fi echo "# Totals: pass:$KTAP_CNT_PASS fail:$KTAP_CNT_FAIL xfail:$KTAP_CNT_XFAIL xpass:0 skip:$KTAP_CNT_SKIP error:0" } diff --git a/tools/testing/selftests/kselftest_harness.h b/tools/testing/selftests/kselftest_harness.h index a5a72415e37b..666c9fde76da 100644 --- a/tools/testing/selftests/kselftest_harness.h +++ b/tools/testing/selftests/kselftest_harness.h @@ -760,33 +760,33 @@ /* Report with actual signedness to avoid weird output. */ \ switch (is_signed_type(__exp) * 2 + is_signed_type(__seen)) { \ case 0: { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%llu)", \ + uintmax_t __exp_print = (uintmax_t)__exp; \ + uintmax_t __seen_print = (uintmax_t)__seen; \ + __TH_LOG("Expected %s (%ju) %s %s (%ju)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 1: { \ - unsigned long long __exp_print = (uintptr_t)__exp; \ - long long __seen_print = (intptr_t)__seen; \ - __TH_LOG("Expected %s (%llu) %s %s (%lld)", \ + uintmax_t __exp_print = (uintmax_t)__exp; \ + intmax_t __seen_print = (intmax_t)__seen; \ + __TH_LOG("Expected %s (%ju) %s %s (%jd)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 2: { \ - long long __exp_print = (intptr_t)__exp; \ - unsigned long long __seen_print = (uintptr_t)__seen; \ - __TH_LOG("Expected %s (%lld) %s %s (%llu)", \ + intmax_t __exp_print = (intmax_t)__exp; \ + uintmax_t __seen_print = (uintmax_t)__seen; \ + __TH_LOG("Expected %s (%jd) %s %s (%ju)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ } \ case 3: { \ - long long __exp_print = (intptr_t)__exp; \ - long long __seen_print = (intptr_t)__seen; \ - __TH_LOG("Expected %s (%lld) %s %s (%lld)", \ + intmax_t __exp_print = (intmax_t)__exp; \ + intmax_t __seen_print = (intmax_t)__seen; \ + __TH_LOG("Expected %s (%jd) %s %s (%jd)", \ _expected_str, __exp_print, #_t, \ _seen_str, __seen_print); \ break; \ diff --git a/tools/testing/selftests/kvm/.gitignore b/tools/testing/selftests/kvm/.gitignore index 7f57abf936e7..1d41a046a7bf 100644 --- a/tools/testing/selftests/kvm/.gitignore +++ b/tools/testing/selftests/kvm/.gitignore @@ -9,3 +9,4 @@ !config !settings !Makefile +!Makefile.kvm
\ No newline at end of file diff --git a/tools/testing/selftests/kvm/Makefile b/tools/testing/selftests/kvm/Makefile index 41593d2e7de9..20af35a91d6f 100644 --- a/tools/testing/selftests/kvm/Makefile +++ b/tools/testing/selftests/kvm/Makefile @@ -1,347 +1,16 @@ # SPDX-License-Identifier: GPL-2.0-only -include ../../../build/Build.include - -all: - top_srcdir = ../../../.. include $(top_srcdir)/scripts/subarch.include ARCH ?= $(SUBARCH) -ifeq ($(ARCH),x86) - ARCH_DIR := x86_64 -else ifeq ($(ARCH),arm64) - ARCH_DIR := aarch64 -else ifeq ($(ARCH),s390) - ARCH_DIR := s390x -else - ARCH_DIR := $(ARCH) -endif - -LIBKVM += lib/assert.c -LIBKVM += lib/elf.c -LIBKVM += lib/guest_modes.c -LIBKVM += lib/io.c -LIBKVM += lib/kvm_util.c -LIBKVM += lib/memstress.c -LIBKVM += lib/guest_sprintf.c -LIBKVM += lib/rbtree.c -LIBKVM += lib/sparsebit.c -LIBKVM += lib/test_util.c -LIBKVM += lib/ucall_common.c -LIBKVM += lib/userfaultfd_util.c - -LIBKVM_STRING += lib/string_override.c - -LIBKVM_x86_64 += lib/x86_64/apic.c -LIBKVM_x86_64 += lib/x86_64/handlers.S -LIBKVM_x86_64 += lib/x86_64/hyperv.c -LIBKVM_x86_64 += lib/x86_64/memstress.c -LIBKVM_x86_64 += lib/x86_64/pmu.c -LIBKVM_x86_64 += lib/x86_64/processor.c -LIBKVM_x86_64 += lib/x86_64/sev.c -LIBKVM_x86_64 += lib/x86_64/svm.c -LIBKVM_x86_64 += lib/x86_64/ucall.c -LIBKVM_x86_64 += lib/x86_64/vmx.c - -LIBKVM_aarch64 += lib/aarch64/gic.c -LIBKVM_aarch64 += lib/aarch64/gic_v3.c -LIBKVM_aarch64 += lib/aarch64/gic_v3_its.c -LIBKVM_aarch64 += lib/aarch64/handlers.S -LIBKVM_aarch64 += lib/aarch64/processor.c -LIBKVM_aarch64 += lib/aarch64/spinlock.c -LIBKVM_aarch64 += lib/aarch64/ucall.c -LIBKVM_aarch64 += lib/aarch64/vgic.c - -LIBKVM_s390x += lib/s390x/diag318_test_handler.c -LIBKVM_s390x += lib/s390x/processor.c -LIBKVM_s390x += lib/s390x/ucall.c -LIBKVM_s390x += lib/s390x/facility.c - -LIBKVM_riscv += lib/riscv/handlers.S -LIBKVM_riscv += lib/riscv/processor.c -LIBKVM_riscv += lib/riscv/ucall.c - -# Non-compiled test targets -TEST_PROGS_x86_64 += x86_64/nx_huge_pages_test.sh - -# Compiled test targets -TEST_GEN_PROGS_x86_64 = x86_64/cpuid_test -TEST_GEN_PROGS_x86_64 += x86_64/cr4_cpuid_sync_test -TEST_GEN_PROGS_x86_64 += x86_64/dirty_log_page_splitting_test -TEST_GEN_PROGS_x86_64 += x86_64/feature_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/exit_on_emulation_failure_test -TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test -TEST_GEN_PROGS_x86_64 += x86_64/hwcr_msr_test -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_evmcs -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_extended_hypercalls -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_ipi -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_svm_test -TEST_GEN_PROGS_x86_64 += x86_64/hyperv_tlb_flush -TEST_GEN_PROGS_x86_64 += x86_64/kvm_clock_test -TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test -TEST_GEN_PROGS_x86_64 += x86_64/monitor_mwait_test -TEST_GEN_PROGS_x86_64 += x86_64/nested_exceptions_test -TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test -TEST_GEN_PROGS_x86_64 += x86_64/pmu_counters_test -TEST_GEN_PROGS_x86_64 += x86_64/pmu_event_filter_test -TEST_GEN_PROGS_x86_64 += x86_64/private_mem_conversions_test -TEST_GEN_PROGS_x86_64 += x86_64/private_mem_kvm_exits_test -TEST_GEN_PROGS_x86_64 += x86_64/set_boot_cpu_id -TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test -TEST_GEN_PROGS_x86_64 += x86_64/smaller_maxphyaddr_emulation_test -TEST_GEN_PROGS_x86_64 += x86_64/smm_test -TEST_GEN_PROGS_x86_64 += x86_64/state_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_shutdown_test -TEST_GEN_PROGS_x86_64 += x86_64/svm_nested_soft_inject_test -TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync -TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test -TEST_GEN_PROGS_x86_64 += x86_64/ucna_injection_test -TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test -TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_apic_access_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_close_while_nested_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_dirty_log_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_exception_with_invalid_guest_state -TEST_GEN_PROGS_x86_64 += x86_64/vmx_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_invalid_nested_guest_state -TEST_GEN_PROGS_x86_64 += x86_64/vmx_set_nested_state_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_tsc_adjust_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_nested_tsc_scaling_test -TEST_GEN_PROGS_x86_64 += x86_64/apic_bus_clock_test -TEST_GEN_PROGS_x86_64 += x86_64/xapic_ipi_test -TEST_GEN_PROGS_x86_64 += x86_64/xapic_state_test -TEST_GEN_PROGS_x86_64 += x86_64/xcr0_cpuid_test -TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test -TEST_GEN_PROGS_x86_64 += x86_64/debug_regs -TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test -TEST_GEN_PROGS_x86_64 += x86_64/vmx_pmu_caps_test -TEST_GEN_PROGS_x86_64 += x86_64/xen_shinfo_test -TEST_GEN_PROGS_x86_64 += x86_64/xen_vmcall_test -TEST_GEN_PROGS_x86_64 += x86_64/sev_init2_tests -TEST_GEN_PROGS_x86_64 += x86_64/sev_migrate_tests -TEST_GEN_PROGS_x86_64 += x86_64/sev_smoke_test -TEST_GEN_PROGS_x86_64 += x86_64/amx_test -TEST_GEN_PROGS_x86_64 += x86_64/max_vcpuid_cap_test -TEST_GEN_PROGS_x86_64 += x86_64/triple_fault_event_test -TEST_GEN_PROGS_x86_64 += x86_64/recalc_apic_map_test -TEST_GEN_PROGS_x86_64 += access_tracking_perf_test -TEST_GEN_PROGS_x86_64 += coalesced_io_test -TEST_GEN_PROGS_x86_64 += demand_paging_test -TEST_GEN_PROGS_x86_64 += dirty_log_test -TEST_GEN_PROGS_x86_64 += dirty_log_perf_test -TEST_GEN_PROGS_x86_64 += guest_memfd_test -TEST_GEN_PROGS_x86_64 += guest_print_test -TEST_GEN_PROGS_x86_64 += hardware_disable_test -TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus -TEST_GEN_PROGS_x86_64 += kvm_page_table_test -TEST_GEN_PROGS_x86_64 += max_guest_memory_test -TEST_GEN_PROGS_x86_64 += memslot_modification_stress_test -TEST_GEN_PROGS_x86_64 += memslot_perf_test -TEST_GEN_PROGS_x86_64 += rseq_test -TEST_GEN_PROGS_x86_64 += set_memory_region_test -TEST_GEN_PROGS_x86_64 += steal_time -TEST_GEN_PROGS_x86_64 += kvm_binary_stats_test -TEST_GEN_PROGS_x86_64 += system_counter_offset_test -TEST_GEN_PROGS_x86_64 += pre_fault_memory_test - -# Compiled outputs used by test targets -TEST_GEN_PROGS_EXTENDED_x86_64 += x86_64/nx_huge_pages_test - -TEST_GEN_PROGS_aarch64 += aarch64/aarch32_id_regs -TEST_GEN_PROGS_aarch64 += aarch64/arch_timer_edge_cases -TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions -TEST_GEN_PROGS_aarch64 += aarch64/hypercalls -TEST_GEN_PROGS_aarch64 += aarch64/mmio_abort -TEST_GEN_PROGS_aarch64 += aarch64/page_fault_test -TEST_GEN_PROGS_aarch64 += aarch64/psci_test -TEST_GEN_PROGS_aarch64 += aarch64/set_id_regs -TEST_GEN_PROGS_aarch64 += aarch64/smccc_filter -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 += aarch64/vgic_lpi_stress -TEST_GEN_PROGS_aarch64 += aarch64/vpmu_counter_access -TEST_GEN_PROGS_aarch64 += aarch64/no-vgic-v3 -TEST_GEN_PROGS_aarch64 += access_tracking_perf_test -TEST_GEN_PROGS_aarch64 += arch_timer -TEST_GEN_PROGS_aarch64 += coalesced_io_test -TEST_GEN_PROGS_aarch64 += demand_paging_test -TEST_GEN_PROGS_aarch64 += dirty_log_test -TEST_GEN_PROGS_aarch64 += dirty_log_perf_test -TEST_GEN_PROGS_aarch64 += guest_print_test -TEST_GEN_PROGS_aarch64 += get-reg-list -TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus -TEST_GEN_PROGS_aarch64 += kvm_page_table_test -TEST_GEN_PROGS_aarch64 += memslot_modification_stress_test -TEST_GEN_PROGS_aarch64 += memslot_perf_test -TEST_GEN_PROGS_aarch64 += rseq_test -TEST_GEN_PROGS_aarch64 += set_memory_region_test -TEST_GEN_PROGS_aarch64 += steal_time -TEST_GEN_PROGS_aarch64 += kvm_binary_stats_test - -TEST_GEN_PROGS_s390x = s390x/memop -TEST_GEN_PROGS_s390x += s390x/resets -TEST_GEN_PROGS_s390x += s390x/sync_regs_test -TEST_GEN_PROGS_s390x += s390x/tprot -TEST_GEN_PROGS_s390x += s390x/cmma_test -TEST_GEN_PROGS_s390x += s390x/debug_test -TEST_GEN_PROGS_s390x += s390x/cpumodel_subfuncs_test -TEST_GEN_PROGS_s390x += s390x/shared_zeropage_test -TEST_GEN_PROGS_s390x += s390x/ucontrol_test -TEST_GEN_PROGS_s390x += demand_paging_test -TEST_GEN_PROGS_s390x += dirty_log_test -TEST_GEN_PROGS_s390x += guest_print_test -TEST_GEN_PROGS_s390x += kvm_create_max_vcpus -TEST_GEN_PROGS_s390x += kvm_page_table_test -TEST_GEN_PROGS_s390x += rseq_test -TEST_GEN_PROGS_s390x += set_memory_region_test -TEST_GEN_PROGS_s390x += kvm_binary_stats_test - -TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test -TEST_GEN_PROGS_riscv += riscv/ebreak_test -TEST_GEN_PROGS_riscv += arch_timer -TEST_GEN_PROGS_riscv += coalesced_io_test -TEST_GEN_PROGS_riscv += demand_paging_test -TEST_GEN_PROGS_riscv += dirty_log_test -TEST_GEN_PROGS_riscv += get-reg-list -TEST_GEN_PROGS_riscv += guest_print_test -TEST_GEN_PROGS_riscv += kvm_binary_stats_test -TEST_GEN_PROGS_riscv += kvm_create_max_vcpus -TEST_GEN_PROGS_riscv += kvm_page_table_test -TEST_GEN_PROGS_riscv += set_memory_region_test -TEST_GEN_PROGS_riscv += steal_time - -SPLIT_TESTS += arch_timer -SPLIT_TESTS += get-reg-list - -TEST_PROGS += $(TEST_PROGS_$(ARCH_DIR)) -TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH_DIR)) -TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH_DIR)) -LIBKVM += $(LIBKVM_$(ARCH_DIR)) - -OVERRIDE_TARGETS = 1 - -# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most -# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, -# which causes the environment variable to override the makefile). -include ../lib.mk - -INSTALL_HDR_PATH = $(top_srcdir)/usr -LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ -LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include +ifeq ($(ARCH),$(filter $(ARCH),arm64 s390 riscv x86 x86_64)) +# Top-level selftests allows ARCH=x86_64 :-( ifeq ($(ARCH),x86_64) -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/x86/include -else -LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include + ARCH := x86 endif -CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ - -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ - -fno-builtin-memcmp -fno-builtin-memcpy \ - -fno-builtin-memset -fno-builtin-strnlen \ - -fno-stack-protector -fno-PIE -fno-strict-aliasing \ - -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \ - -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH_DIR) \ - -I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) -ifeq ($(ARCH),s390) - CFLAGS += -march=z10 -endif -ifeq ($(ARCH),x86) -ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0) - CFLAGS += -march=x86-64-v2 -endif -endif -ifeq ($(ARCH),arm64) -tools_dir := $(top_srcdir)/tools -arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ - -ifneq ($(abs_objdir),) -arm64_hdr_outdir := $(abs_objdir)/tools/ +include Makefile.kvm else -arm64_hdr_outdir := $(tools_dir)/ -endif - -GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/ -CFLAGS += -I$(GEN_HDRS) - -$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*) - $(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir) +# Empty targets for unsupported architectures +all: +clean: endif - -no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ - $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) - -# On s390, build the testcases KVM-enabled -pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \ - $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) - -LDLIBS += -ldl -LDFLAGS += -pthread $(no-pie-option) $(pgste-option) - -LIBKVM_C := $(filter %.c,$(LIBKVM)) -LIBKVM_S := $(filter %.S,$(LIBKVM)) -LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) -LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) -LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) -LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) -SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) -SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH_DIR)/%.o, $(SPLIT_TESTS)) - -TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) -TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) -TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) -TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) -TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ)) --include $(TEST_DEP_FILES) - -$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH_DIR) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) - -$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \ -$(TEST_GEN_PROGS_EXTENDED): %: %.o - $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@ -$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH_DIR)/%.o - $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@ -$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH_DIR)/%.o: $(ARCH_DIR)/%.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -EXTRA_CLEAN += $(GEN_HDRS) \ - $(LIBKVM_OBJS) \ - $(SPLIT_TEST_GEN_OBJ) \ - $(TEST_DEP_FILES) \ - $(TEST_GEN_OBJ) \ - cscope.* - -$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS) - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS) - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ - -# Compile the string overrides as freestanding to prevent the compiler from -# generating self-referential code, e.g. without "freestanding" the compiler may -# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion. -$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c - $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ - -$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) -$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS) -$(TEST_GEN_PROGS): $(LIBKVM_OBJS) -$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) -$(TEST_GEN_OBJ): $(GEN_HDRS) - -cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. -cscope: - $(RM) cscope.* - (find $(include_paths) -name '*.h' \ - -exec realpath --relative-base=$(PWD) {} \;; \ - find . -name '*.c' \ - -exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files - cscope -b diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm new file mode 100644 index 000000000000..4277b983cace --- /dev/null +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -0,0 +1,330 @@ +# SPDX-License-Identifier: GPL-2.0-only +include ../../../build/Build.include + +all: + +LIBKVM += lib/assert.c +LIBKVM += lib/elf.c +LIBKVM += lib/guest_modes.c +LIBKVM += lib/io.c +LIBKVM += lib/kvm_util.c +LIBKVM += lib/memstress.c +LIBKVM += lib/guest_sprintf.c +LIBKVM += lib/rbtree.c +LIBKVM += lib/sparsebit.c +LIBKVM += lib/test_util.c +LIBKVM += lib/ucall_common.c +LIBKVM += lib/userfaultfd_util.c + +LIBKVM_STRING += lib/string_override.c + +LIBKVM_x86 += lib/x86/apic.c +LIBKVM_x86 += lib/x86/handlers.S +LIBKVM_x86 += lib/x86/hyperv.c +LIBKVM_x86 += lib/x86/memstress.c +LIBKVM_x86 += lib/x86/pmu.c +LIBKVM_x86 += lib/x86/processor.c +LIBKVM_x86 += lib/x86/sev.c +LIBKVM_x86 += lib/x86/svm.c +LIBKVM_x86 += lib/x86/ucall.c +LIBKVM_x86 += lib/x86/vmx.c + +LIBKVM_arm64 += lib/arm64/gic.c +LIBKVM_arm64 += lib/arm64/gic_v3.c +LIBKVM_arm64 += lib/arm64/gic_v3_its.c +LIBKVM_arm64 += lib/arm64/handlers.S +LIBKVM_arm64 += lib/arm64/processor.c +LIBKVM_arm64 += lib/arm64/spinlock.c +LIBKVM_arm64 += lib/arm64/ucall.c +LIBKVM_arm64 += lib/arm64/vgic.c + +LIBKVM_s390 += lib/s390/diag318_test_handler.c +LIBKVM_s390 += lib/s390/processor.c +LIBKVM_s390 += lib/s390/ucall.c +LIBKVM_s390 += lib/s390/facility.c + +LIBKVM_riscv += lib/riscv/handlers.S +LIBKVM_riscv += lib/riscv/processor.c +LIBKVM_riscv += lib/riscv/ucall.c + +# Non-compiled test targets +TEST_PROGS_x86 += x86/nx_huge_pages_test.sh + +# Compiled test targets +TEST_GEN_PROGS_x86 = x86/cpuid_test +TEST_GEN_PROGS_x86 += x86/cr4_cpuid_sync_test +TEST_GEN_PROGS_x86 += x86/dirty_log_page_splitting_test +TEST_GEN_PROGS_x86 += x86/feature_msrs_test +TEST_GEN_PROGS_x86 += x86/exit_on_emulation_failure_test +TEST_GEN_PROGS_x86 += x86/fix_hypercall_test +TEST_GEN_PROGS_x86 += x86/hwcr_msr_test +TEST_GEN_PROGS_x86 += x86/hyperv_clock +TEST_GEN_PROGS_x86 += x86/hyperv_cpuid +TEST_GEN_PROGS_x86 += x86/hyperv_evmcs +TEST_GEN_PROGS_x86 += x86/hyperv_extended_hypercalls +TEST_GEN_PROGS_x86 += x86/hyperv_features +TEST_GEN_PROGS_x86 += x86/hyperv_ipi +TEST_GEN_PROGS_x86 += x86/hyperv_svm_test +TEST_GEN_PROGS_x86 += x86/hyperv_tlb_flush +TEST_GEN_PROGS_x86 += x86/kvm_clock_test +TEST_GEN_PROGS_x86 += x86/kvm_pv_test +TEST_GEN_PROGS_x86 += x86/monitor_mwait_test +TEST_GEN_PROGS_x86 += x86/nested_exceptions_test +TEST_GEN_PROGS_x86 += x86/platform_info_test +TEST_GEN_PROGS_x86 += x86/pmu_counters_test +TEST_GEN_PROGS_x86 += x86/pmu_event_filter_test +TEST_GEN_PROGS_x86 += x86/private_mem_conversions_test +TEST_GEN_PROGS_x86 += x86/private_mem_kvm_exits_test +TEST_GEN_PROGS_x86 += x86/set_boot_cpu_id +TEST_GEN_PROGS_x86 += x86/set_sregs_test +TEST_GEN_PROGS_x86 += x86/smaller_maxphyaddr_emulation_test +TEST_GEN_PROGS_x86 += x86/smm_test +TEST_GEN_PROGS_x86 += x86/state_test +TEST_GEN_PROGS_x86 += x86/vmx_preemption_timer_test +TEST_GEN_PROGS_x86 += x86/svm_vmcall_test +TEST_GEN_PROGS_x86 += x86/svm_int_ctl_test +TEST_GEN_PROGS_x86 += x86/svm_nested_shutdown_test +TEST_GEN_PROGS_x86 += x86/svm_nested_soft_inject_test +TEST_GEN_PROGS_x86 += x86/tsc_scaling_sync +TEST_GEN_PROGS_x86 += x86/sync_regs_test +TEST_GEN_PROGS_x86 += x86/ucna_injection_test +TEST_GEN_PROGS_x86 += x86/userspace_io_test +TEST_GEN_PROGS_x86 += x86/userspace_msr_exit_test +TEST_GEN_PROGS_x86 += x86/vmx_apic_access_test +TEST_GEN_PROGS_x86 += x86/vmx_close_while_nested_test +TEST_GEN_PROGS_x86 += x86/vmx_dirty_log_test +TEST_GEN_PROGS_x86 += x86/vmx_exception_with_invalid_guest_state +TEST_GEN_PROGS_x86 += x86/vmx_msrs_test +TEST_GEN_PROGS_x86 += x86/vmx_invalid_nested_guest_state +TEST_GEN_PROGS_x86 += x86/vmx_set_nested_state_test +TEST_GEN_PROGS_x86 += x86/vmx_tsc_adjust_test +TEST_GEN_PROGS_x86 += x86/vmx_nested_tsc_scaling_test +TEST_GEN_PROGS_x86 += x86/apic_bus_clock_test +TEST_GEN_PROGS_x86 += x86/xapic_ipi_test +TEST_GEN_PROGS_x86 += x86/xapic_state_test +TEST_GEN_PROGS_x86 += x86/xcr0_cpuid_test +TEST_GEN_PROGS_x86 += x86/xss_msr_test +TEST_GEN_PROGS_x86 += x86/debug_regs +TEST_GEN_PROGS_x86 += x86/tsc_msrs_test +TEST_GEN_PROGS_x86 += x86/vmx_pmu_caps_test +TEST_GEN_PROGS_x86 += x86/xen_shinfo_test +TEST_GEN_PROGS_x86 += x86/xen_vmcall_test +TEST_GEN_PROGS_x86 += x86/sev_init2_tests +TEST_GEN_PROGS_x86 += x86/sev_migrate_tests +TEST_GEN_PROGS_x86 += x86/sev_smoke_test +TEST_GEN_PROGS_x86 += x86/amx_test +TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test +TEST_GEN_PROGS_x86 += x86/triple_fault_event_test +TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test +TEST_GEN_PROGS_x86 += access_tracking_perf_test +TEST_GEN_PROGS_x86 += coalesced_io_test +TEST_GEN_PROGS_x86 += demand_paging_test +TEST_GEN_PROGS_x86 += dirty_log_test +TEST_GEN_PROGS_x86 += dirty_log_perf_test +TEST_GEN_PROGS_x86 += guest_memfd_test +TEST_GEN_PROGS_x86 += guest_print_test +TEST_GEN_PROGS_x86 += hardware_disable_test +TEST_GEN_PROGS_x86 += kvm_create_max_vcpus +TEST_GEN_PROGS_x86 += kvm_page_table_test +TEST_GEN_PROGS_x86 += memslot_modification_stress_test +TEST_GEN_PROGS_x86 += memslot_perf_test +TEST_GEN_PROGS_x86 += mmu_stress_test +TEST_GEN_PROGS_x86 += rseq_test +TEST_GEN_PROGS_x86 += set_memory_region_test +TEST_GEN_PROGS_x86 += steal_time +TEST_GEN_PROGS_x86 += kvm_binary_stats_test +TEST_GEN_PROGS_x86 += system_counter_offset_test +TEST_GEN_PROGS_x86 += pre_fault_memory_test + +# Compiled outputs used by test targets +TEST_GEN_PROGS_EXTENDED_x86 += x86/nx_huge_pages_test + +TEST_GEN_PROGS_arm64 += arm64/aarch32_id_regs +TEST_GEN_PROGS_arm64 += arm64/arch_timer_edge_cases +TEST_GEN_PROGS_arm64 += arm64/debug-exceptions +TEST_GEN_PROGS_arm64 += arm64/hypercalls +TEST_GEN_PROGS_arm64 += arm64/mmio_abort +TEST_GEN_PROGS_arm64 += arm64/page_fault_test +TEST_GEN_PROGS_arm64 += arm64/psci_test +TEST_GEN_PROGS_arm64 += arm64/set_id_regs +TEST_GEN_PROGS_arm64 += arm64/smccc_filter +TEST_GEN_PROGS_arm64 += arm64/vcpu_width_config +TEST_GEN_PROGS_arm64 += arm64/vgic_init +TEST_GEN_PROGS_arm64 += arm64/vgic_irq +TEST_GEN_PROGS_arm64 += arm64/vgic_lpi_stress +TEST_GEN_PROGS_arm64 += arm64/vpmu_counter_access +TEST_GEN_PROGS_arm64 += arm64/no-vgic-v3 +TEST_GEN_PROGS_arm64 += access_tracking_perf_test +TEST_GEN_PROGS_arm64 += arch_timer +TEST_GEN_PROGS_arm64 += coalesced_io_test +TEST_GEN_PROGS_arm64 += demand_paging_test +TEST_GEN_PROGS_arm64 += dirty_log_test +TEST_GEN_PROGS_arm64 += dirty_log_perf_test +TEST_GEN_PROGS_arm64 += guest_print_test +TEST_GEN_PROGS_arm64 += get-reg-list +TEST_GEN_PROGS_arm64 += kvm_create_max_vcpus +TEST_GEN_PROGS_arm64 += kvm_page_table_test +TEST_GEN_PROGS_arm64 += memslot_modification_stress_test +TEST_GEN_PROGS_arm64 += memslot_perf_test +TEST_GEN_PROGS_arm64 += mmu_stress_test +TEST_GEN_PROGS_arm64 += rseq_test +TEST_GEN_PROGS_arm64 += set_memory_region_test +TEST_GEN_PROGS_arm64 += steal_time +TEST_GEN_PROGS_arm64 += kvm_binary_stats_test + +TEST_GEN_PROGS_s390 = s390/memop +TEST_GEN_PROGS_s390 += s390/resets +TEST_GEN_PROGS_s390 += s390/sync_regs_test +TEST_GEN_PROGS_s390 += s390/tprot +TEST_GEN_PROGS_s390 += s390/cmma_test +TEST_GEN_PROGS_s390 += s390/debug_test +TEST_GEN_PROGS_s390 += s390/cpumodel_subfuncs_test +TEST_GEN_PROGS_s390 += s390/shared_zeropage_test +TEST_GEN_PROGS_s390 += s390/ucontrol_test +TEST_GEN_PROGS_s390 += demand_paging_test +TEST_GEN_PROGS_s390 += dirty_log_test +TEST_GEN_PROGS_s390 += guest_print_test +TEST_GEN_PROGS_s390 += kvm_create_max_vcpus +TEST_GEN_PROGS_s390 += kvm_page_table_test +TEST_GEN_PROGS_s390 += rseq_test +TEST_GEN_PROGS_s390 += set_memory_region_test +TEST_GEN_PROGS_s390 += kvm_binary_stats_test + +TEST_GEN_PROGS_riscv += riscv/sbi_pmu_test +TEST_GEN_PROGS_riscv += riscv/ebreak_test +TEST_GEN_PROGS_riscv += arch_timer +TEST_GEN_PROGS_riscv += coalesced_io_test +TEST_GEN_PROGS_riscv += demand_paging_test +TEST_GEN_PROGS_riscv += dirty_log_test +TEST_GEN_PROGS_riscv += get-reg-list +TEST_GEN_PROGS_riscv += guest_print_test +TEST_GEN_PROGS_riscv += kvm_binary_stats_test +TEST_GEN_PROGS_riscv += kvm_create_max_vcpus +TEST_GEN_PROGS_riscv += kvm_page_table_test +TEST_GEN_PROGS_riscv += set_memory_region_test +TEST_GEN_PROGS_riscv += steal_time + +SPLIT_TESTS += arch_timer +SPLIT_TESTS += get-reg-list + +TEST_PROGS += $(TEST_PROGS_$(ARCH)) +TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH)) +TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH)) +LIBKVM += $(LIBKVM_$(ARCH)) + +OVERRIDE_TARGETS = 1 + +# lib.mak defines $(OUTPUT), prepends $(OUTPUT)/ to $(TEST_GEN_PROGS), and most +# importantly defines, i.e. overwrites, $(CC) (unless `make -e` or `make CC=`, +# which causes the environment variable to override the makefile). +include ../lib.mk + +INSTALL_HDR_PATH = $(top_srcdir)/usr +LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/ +LINUX_TOOL_INCLUDE = $(top_srcdir)/tools/include +LINUX_TOOL_ARCH_INCLUDE = $(top_srcdir)/tools/arch/$(ARCH)/include +CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \ + -Wno-gnu-variable-sized-type-not-at-end -MD -MP -DCONFIG_64BIT \ + -fno-builtin-memcmp -fno-builtin-memcpy \ + -fno-builtin-memset -fno-builtin-strnlen \ + -fno-stack-protector -fno-PIE -fno-strict-aliasing \ + -I$(LINUX_TOOL_INCLUDE) -I$(LINUX_TOOL_ARCH_INCLUDE) \ + -I$(LINUX_HDR_PATH) -Iinclude -I$(<D) -Iinclude/$(ARCH) \ + -I ../rseq -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES) +ifeq ($(ARCH),s390) + CFLAGS += -march=z10 +endif +ifeq ($(ARCH),x86) +ifeq ($(shell echo "void foo(void) { }" | $(CC) -march=x86-64-v2 -x c - -c -o /dev/null 2>/dev/null; echo "$$?"),0) + CFLAGS += -march=x86-64-v2 +endif +endif +ifeq ($(ARCH),arm64) +tools_dir := $(top_srcdir)/tools +arm64_tools_dir := $(tools_dir)/arch/arm64/tools/ + +ifneq ($(abs_objdir),) +arm64_hdr_outdir := $(abs_objdir)/tools/ +else +arm64_hdr_outdir := $(tools_dir)/ +endif + +GEN_HDRS := $(arm64_hdr_outdir)arch/arm64/include/generated/ +CFLAGS += -I$(GEN_HDRS) + +$(GEN_HDRS): $(wildcard $(arm64_tools_dir)/*) + $(MAKE) -C $(arm64_tools_dir) OUTPUT=$(arm64_hdr_outdir) +endif + +no-pie-option := $(call try-run, echo 'int main(void) { return 0; }' | \ + $(CC) -Werror $(CFLAGS) -no-pie -x c - -o "$$TMP", -no-pie) + +# On s390, build the testcases KVM-enabled +pgste-option = $(call try-run, echo 'int main(void) { return 0; }' | \ + $(CC) -Werror -Wl$(comma)--s390-pgste -x c - -o "$$TMP",-Wl$(comma)--s390-pgste) + +LDLIBS += -ldl +LDFLAGS += -pthread $(no-pie-option) $(pgste-option) + +LIBKVM_C := $(filter %.c,$(LIBKVM)) +LIBKVM_S := $(filter %.S,$(LIBKVM)) +LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C)) +LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S)) +LIBKVM_STRING_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_STRING)) +LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(LIBKVM_STRING_OBJ) +SPLIT_TEST_GEN_PROGS := $(patsubst %, $(OUTPUT)/%, $(SPLIT_TESTS)) +SPLIT_TEST_GEN_OBJ := $(patsubst %, $(OUTPUT)/$(ARCH)/%.o, $(SPLIT_TESTS)) + +TEST_GEN_OBJ = $(patsubst %, %.o, $(TEST_GEN_PROGS)) +TEST_GEN_OBJ += $(patsubst %, %.o, $(TEST_GEN_PROGS_EXTENDED)) +TEST_DEP_FILES = $(patsubst %.o, %.d, $(TEST_GEN_OBJ)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(LIBKVM_OBJS)) +TEST_DEP_FILES += $(patsubst %.o, %.d, $(SPLIT_TEST_GEN_OBJ)) +-include $(TEST_DEP_FILES) + +$(shell mkdir -p $(sort $(OUTPUT)/$(ARCH) $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)))) + +$(filter-out $(SPLIT_TEST_GEN_PROGS), $(TEST_GEN_PROGS)) \ +$(TEST_GEN_PROGS_EXTENDED): %: %.o + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $< $(LIBKVM_OBJS) $(LDLIBS) -o $@ +$(TEST_GEN_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +$(SPLIT_TEST_GEN_PROGS): $(OUTPUT)/%: $(OUTPUT)/%.o $(OUTPUT)/$(ARCH)/%.o + $(CC) $(CFLAGS) $(CPPFLAGS) $(LDFLAGS) $(TARGET_ARCH) $^ $(LDLIBS) -o $@ +$(SPLIT_TEST_GEN_OBJ): $(OUTPUT)/$(ARCH)/%.o: $(ARCH)/%.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +EXTRA_CLEAN += $(GEN_HDRS) \ + $(LIBKVM_OBJS) \ + $(SPLIT_TEST_GEN_OBJ) \ + $(TEST_DEP_FILES) \ + $(TEST_GEN_OBJ) \ + cscope.* + +$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c $(GEN_HDRS) + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S $(GEN_HDRS) + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@ + +# Compile the string overrides as freestanding to prevent the compiler from +# generating self-referential code, e.g. without "freestanding" the compiler may +# "optimize" memcmp() by invoking memcmp(), thus causing infinite recursion. +$(LIBKVM_STRING_OBJ): $(OUTPUT)/%.o: %.c + $(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c -ffreestanding $< -o $@ + +$(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS)))) +$(SPLIT_TEST_GEN_OBJ): $(GEN_HDRS) +$(TEST_GEN_PROGS): $(LIBKVM_OBJS) +$(TEST_GEN_PROGS_EXTENDED): $(LIBKVM_OBJS) +$(TEST_GEN_OBJ): $(GEN_HDRS) + +cscope: include_paths = $(LINUX_TOOL_INCLUDE) $(LINUX_HDR_PATH) include lib .. +cscope: + $(RM) cscope.* + (find $(include_paths) -name '*.h' \ + -exec realpath --relative-base=$(PWD) {} \;; \ + find . -name '*.c' \ + -exec realpath --relative-base=$(PWD) {} \;) | sort -u > cscope.files + cscope -b diff --git a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c index 8e5bd07a3727..cef8f7323ceb 100644 --- a/tools/testing/selftests/kvm/aarch64/aarch32_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/aarch32_id_regs.c @@ -97,7 +97,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) uint64_t reg_id = raz_wi_reg_ids[i]; uint64_t val; - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); /* @@ -106,7 +106,7 @@ static void test_user_raz_wi(struct kvm_vcpu *vcpu) */ vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); } } @@ -126,14 +126,14 @@ static void test_user_raz_invariant(struct kvm_vcpu *vcpu) uint64_t reg_id = raz_invariant_reg_ids[i]; uint64_t val; - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); r = __vcpu_set_reg(vcpu, reg_id, BAD_ID_REG_VAL); TEST_ASSERT(r < 0 && errno == EINVAL, "unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); - vcpu_get_reg(vcpu, reg_id, &val); + val = vcpu_get_reg(vcpu, reg_id); TEST_ASSERT_EQ(val, 0); } } @@ -144,10 +144,10 @@ static bool vcpu_aarch64_only(struct kvm_vcpu *vcpu) { uint64_t val, el0; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); - return el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY; + return el0 == ID_AA64PFR0_EL1_EL0_IMP; } int main(void) diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer.c b/tools/testing/selftests/kvm/arm64/arch_timer.c index eeba1cc87ff8..eeba1cc87ff8 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer.c diff --git a/tools/testing/selftests/kvm/aarch64/arch_timer_edge_cases.c b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c index a36a7e2db434..a36a7e2db434 100644 --- a/tools/testing/selftests/kvm/aarch64/arch_timer_edge_cases.c +++ b/tools/testing/selftests/kvm/arm64/arch_timer_edge_cases.c diff --git a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c b/tools/testing/selftests/kvm/arm64/debug-exceptions.c index ff7a949fc96a..c7fb55c9135b 100644 --- a/tools/testing/selftests/kvm/aarch64/debug-exceptions.c +++ b/tools/testing/selftests/kvm/arm64/debug-exceptions.c @@ -501,7 +501,7 @@ void test_single_step_from_userspace(int test_cnt) TEST_ASSERT(ss_enable, "Unexpected KVM_EXIT_DEBUG"); /* Check if the current pc is expected. */ - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); + pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); TEST_ASSERT(!test_pc || pc == test_pc, "Unexpected pc 0x%lx (expected 0x%lx)", pc, test_pc); @@ -583,7 +583,7 @@ int main(int argc, char *argv[]) uint64_t aa64dfr0; vm = vm_create_with_one_vcpu(&vcpu, guest_code); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &aa64dfr0); + aa64dfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); __TEST_REQUIRE(debug_version(aa64dfr0) >= 6, "Armv8 debug architecture not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/aarch64/get-reg-list.c b/tools/testing/selftests/kvm/arm64/get-reg-list.c index d43fb3f49050..d43fb3f49050 100644 --- a/tools/testing/selftests/kvm/aarch64/get-reg-list.c +++ b/tools/testing/selftests/kvm/arm64/get-reg-list.c diff --git a/tools/testing/selftests/kvm/aarch64/hypercalls.c b/tools/testing/selftests/kvm/arm64/hypercalls.c index 9d192ce0078d..ec54ec7726e9 100644 --- a/tools/testing/selftests/kvm/aarch64/hypercalls.c +++ b/tools/testing/selftests/kvm/arm64/hypercalls.c @@ -173,7 +173,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) const struct kvm_fw_reg_info *reg_info = &fw_reg_info[i]; /* First 'read' should be an upper limit of the features supported */ - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), "Expected all the features to be set for reg: 0x%lx; expected: 0x%lx; read: 0x%lx", reg_info->reg, FW_REG_ULIMIT_VAL(reg_info->max_feat_bit), val); @@ -184,7 +184,7 @@ static void test_fw_regs_before_vm_start(struct kvm_vcpu *vcpu) "Failed to clear all the features of reg: 0x%lx; ret: %d", reg_info->reg, errno); - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg); @@ -214,7 +214,7 @@ static void test_fw_regs_after_vm_start(struct kvm_vcpu *vcpu) * Before starting the VM, the test clears all the bits. * Check if that's still the case. */ - vcpu_get_reg(vcpu, reg_info->reg, &val); + val = vcpu_get_reg(vcpu, reg_info->reg); TEST_ASSERT(val == 0, "Expected all the features to be cleared for reg: 0x%lx", reg_info->reg); diff --git a/tools/testing/selftests/kvm/aarch64/mmio_abort.c b/tools/testing/selftests/kvm/arm64/mmio_abort.c index 8b7a80a51b1c..8b7a80a51b1c 100644 --- a/tools/testing/selftests/kvm/aarch64/mmio_abort.c +++ b/tools/testing/selftests/kvm/arm64/mmio_abort.c diff --git a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c index 58304bbc2036..ebd70430c89d 100644 --- a/tools/testing/selftests/kvm/aarch64/no-vgic-v3.c +++ b/tools/testing/selftests/kvm/arm64/no-vgic-v3.c @@ -164,7 +164,7 @@ int main(int argc, char *argv[]) uint64_t pfr0; vm = vm_create_with_one_vcpu(&vcpu, NULL); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &pfr0); + pfr0 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); __TEST_REQUIRE(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_GIC), pfr0), "GICv3 not supported."); kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/aarch64/page_fault_test.c b/tools/testing/selftests/kvm/arm64/page_fault_test.c index ec33a8f9c908..ec33a8f9c908 100644 --- a/tools/testing/selftests/kvm/aarch64/page_fault_test.c +++ b/tools/testing/selftests/kvm/arm64/page_fault_test.c diff --git a/tools/testing/selftests/kvm/aarch64/psci_test.c b/tools/testing/selftests/kvm/arm64/psci_test.c index eaa7655fefc1..ab491ee9e5f7 100644 --- a/tools/testing/selftests/kvm/aarch64/psci_test.c +++ b/tools/testing/selftests/kvm/arm64/psci_test.c @@ -111,8 +111,8 @@ static void assert_vcpu_reset(struct kvm_vcpu *vcpu) { uint64_t obs_pc, obs_x0; - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &obs_pc); - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0]), &obs_x0); + obs_pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); + obs_x0 = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.regs[0])); TEST_ASSERT(obs_pc == CPU_ON_ENTRY_ADDR, "unexpected target cpu pc: %lx (expected: %lx)", @@ -152,7 +152,7 @@ static void host_test_cpu_on(void) */ vcpu_power_off(target); - vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &target_mpidr); + target_mpidr = vcpu_get_reg(target, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1)); vcpu_args_set(source, 1, target_mpidr & MPIDR_HWID_BITMASK); enter_guest(source); @@ -244,7 +244,7 @@ static void host_test_system_off2(void) setup_vm(guest_test_system_off2, &source, &target); - vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION, &psci_version); + psci_version = vcpu_get_reg(target, KVM_REG_ARM_PSCI_VERSION); TEST_ASSERT(psci_version >= PSCI_VERSION(1, 3), "Unexpected PSCI version %lu.%lu", diff --git a/tools/testing/selftests/kvm/aarch64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 3a97c160b5fe..217541fe6536 100644 --- a/tools/testing/selftests/kvm/aarch64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -345,7 +345,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, uint64_t mask = ftr_bits->mask; uint64_t val, new_val, ftr; - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; ftr = get_safe_value(ftr_bits, ftr); @@ -355,7 +355,7 @@ static uint64_t test_reg_set_success(struct kvm_vcpu *vcpu, uint64_t reg, val |= ftr; vcpu_set_reg(vcpu, reg, val); - vcpu_get_reg(vcpu, reg, &new_val); + new_val = vcpu_get_reg(vcpu, reg); TEST_ASSERT_EQ(new_val, val); return new_val; @@ -369,7 +369,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, uint64_t val, old_val, ftr; int r; - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); ftr = (val & mask) >> shift; ftr = get_invalid_value(ftr_bits, ftr); @@ -383,7 +383,7 @@ static void test_reg_set_fail(struct kvm_vcpu *vcpu, uint64_t reg, TEST_ASSERT(r < 0 && errno == EINVAL, "Unexpected KVM_SET_ONE_REG error: r=%d, errno=%d", r, errno); - vcpu_get_reg(vcpu, reg, &val); + val = vcpu_get_reg(vcpu, reg); TEST_ASSERT_EQ(val, old_val); } @@ -470,7 +470,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) } /* Get the id register value */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); /* Try to set MPAM=0. This should always be possible. */ val &= ~ID_AA64PFR0_EL1_MPAM_MASK; @@ -507,7 +507,7 @@ static void test_user_set_mpam_reg(struct kvm_vcpu *vcpu) } /* Get the id register value */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR1_EL1)); /* Try to set MPAM_frac=0. This should always be possible. */ val &= ~ID_AA64PFR1_EL1_MPAM_frac_MASK; @@ -575,7 +575,7 @@ static void test_clidr(struct kvm_vcpu *vcpu) uint64_t clidr; int level; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1), &clidr); + clidr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CLIDR_EL1)); /* find the first empty level in the cache hierarchy */ for (level = 1; level < 7; level++) { @@ -600,7 +600,7 @@ static void test_ctr(struct kvm_vcpu *vcpu) { u64 ctr; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0), &ctr); + ctr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CTR_EL0)); ctr &= ~CTR_EL0_DIC_MASK; if (ctr & CTR_EL0_IminLine_MASK) ctr--; @@ -616,7 +616,7 @@ static void test_vcpu_ftr_id_regs(struct kvm_vcpu *vcpu) test_clidr(vcpu); test_ctr(vcpu); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1)); val++; vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_MPIDR_EL1), val); @@ -629,7 +629,7 @@ static void test_assert_id_reg_unchanged(struct kvm_vcpu *vcpu, uint32_t encodin size_t idx = encoding_to_range_idx(encoding); uint64_t observed; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding), &observed); + observed = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(encoding)); TEST_ASSERT_EQ(test_reg_vals[idx], observed); } @@ -664,9 +664,9 @@ int main(void) vm = vm_create_with_one_vcpu(&vcpu, guest_code); /* Check for AARCH64 only system */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1), &val); + val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64PFR0_EL1)); el0 = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), val); - aarch64_only = (el0 == ID_AA64PFR0_EL1_ELx_64BIT_ONLY); + aarch64_only = (el0 == ID_AA64PFR0_EL1_EL0_IMP); ksft_print_header(); diff --git a/tools/testing/selftests/kvm/aarch64/smccc_filter.c b/tools/testing/selftests/kvm/arm64/smccc_filter.c index 2d189f3da228..2d189f3da228 100644 --- a/tools/testing/selftests/kvm/aarch64/smccc_filter.c +++ b/tools/testing/selftests/kvm/arm64/smccc_filter.c diff --git a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c b/tools/testing/selftests/kvm/arm64/vcpu_width_config.c index 80b74c6f152b..80b74c6f152b 100644 --- a/tools/testing/selftests/kvm/aarch64/vcpu_width_config.c +++ b/tools/testing/selftests/kvm/arm64/vcpu_width_config.c diff --git a/tools/testing/selftests/kvm/aarch64/vgic_init.c b/tools/testing/selftests/kvm/arm64/vgic_init.c index b3b5fb0ff0a9..b3b5fb0ff0a9 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_init.c +++ b/tools/testing/selftests/kvm/arm64/vgic_init.c diff --git a/tools/testing/selftests/kvm/aarch64/vgic_irq.c b/tools/testing/selftests/kvm/arm64/vgic_irq.c index f4ac28d53747..f4ac28d53747 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_irq.c +++ b/tools/testing/selftests/kvm/arm64/vgic_irq.c diff --git a/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c index fc4fe52fb6f8..fc4fe52fb6f8 100644 --- a/tools/testing/selftests/kvm/aarch64/vgic_lpi_stress.c +++ b/tools/testing/selftests/kvm/arm64/vgic_lpi_stress.c diff --git a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c index f9c0c86d7e85..f16b3b27e32e 100644 --- a/tools/testing/selftests/kvm/aarch64/vpmu_counter_access.c +++ b/tools/testing/selftests/kvm/arm64/vpmu_counter_access.c @@ -440,8 +440,7 @@ static void create_vpmu_vm(void *guest_code) "Failed to create vgic-v3, skipping"); /* Make sure that PMUv3 support is indicated in the ID register */ - vcpu_get_reg(vpmu_vm.vcpu, - KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1), &dfr0); + dfr0 = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_ID_AA64DFR0_EL1)); pmuver = FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), dfr0); TEST_ASSERT(pmuver != ID_AA64DFR0_EL1_PMUVer_IMP_DEF && pmuver >= ID_AA64DFR0_EL1_PMUVer_IMP, @@ -484,7 +483,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) create_vpmu_vm(guest_code); vcpu = vpmu_vm.vcpu; - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr_orig); + pmcr_orig = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); pmcr = pmcr_orig; /* @@ -493,7 +492,7 @@ static void test_create_vpmu_vm_with_pmcr_n(uint64_t pmcr_n, bool expect_fail) */ set_pmcr_n(&pmcr, pmcr_n); vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), pmcr); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr); + pmcr = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); if (expect_fail) TEST_ASSERT(pmcr_orig == pmcr, @@ -521,7 +520,7 @@ static void run_access_test(uint64_t pmcr_n) vcpu = vpmu_vm.vcpu; /* Save the initial sp to restore them later to run the guest again */ - vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1), &sp); + sp = vcpu_get_reg(vcpu, ARM64_CORE_REG(sp_el1)); run_vcpu(vcpu, pmcr_n); @@ -572,12 +571,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) * Test if the 'set' and 'clr' variants of the registers * are initialized based on the number of valid counters. */ - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Initial read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(set_reg_id), reg_val); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Initial read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(clr_reg_id), reg_val); @@ -589,12 +588,12 @@ static void run_pmregs_validity_test(uint64_t pmcr_n) */ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), max_counters_mask); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(set_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Read of set_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(set_reg_id), reg_val); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id), ®_val); + reg_val = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(clr_reg_id)); TEST_ASSERT((reg_val & (~valid_counters_mask)) == 0, "Read of clr_reg: 0x%llx has unimplemented counters enabled: 0x%lx", KVM_ARM64_SYS_REG(clr_reg_id), reg_val); @@ -625,7 +624,7 @@ static uint64_t get_pmcr_n_limit(void) uint64_t pmcr; create_vpmu_vm(guest_code); - vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0), &pmcr); + pmcr = vcpu_get_reg(vpmu_vm.vcpu, KVM_ARM64_SYS_REG(SYS_PMCR_EL0)); destroy_vpmu_vm(); return get_pmcr_n(pmcr); } diff --git a/tools/testing/selftests/kvm/dirty_log_perf_test.c b/tools/testing/selftests/kvm/dirty_log_perf_test.c index 9f24303acb8c..e79817bd0e29 100644 --- a/tools/testing/selftests/kvm/dirty_log_perf_test.c +++ b/tools/testing/selftests/kvm/dirty_log_perf_test.c @@ -21,7 +21,7 @@ #include "ucall_common.h" #ifdef __aarch64__ -#include "aarch64/vgic.h" +#include "arm64/vgic.h" static int gic_fd; diff --git a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h b/tools/testing/selftests/kvm/include/arm64/arch_timer.h index bf461de34785..bf461de34785 100644 --- a/tools/testing/selftests/kvm/include/aarch64/arch_timer.h +++ b/tools/testing/selftests/kvm/include/arm64/arch_timer.h diff --git a/tools/testing/selftests/kvm/include/aarch64/delay.h b/tools/testing/selftests/kvm/include/arm64/delay.h index 329e4f5079ea..329e4f5079ea 100644 --- a/tools/testing/selftests/kvm/include/aarch64/delay.h +++ b/tools/testing/selftests/kvm/include/arm64/delay.h diff --git a/tools/testing/selftests/kvm/include/aarch64/gic.h b/tools/testing/selftests/kvm/include/arm64/gic.h index baeb3c859389..baeb3c859389 100644 --- a/tools/testing/selftests/kvm/include/aarch64/gic.h +++ b/tools/testing/selftests/kvm/include/arm64/gic.h diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h b/tools/testing/selftests/kvm/include/arm64/gic_v3.h index a76615fa39a1..a76615fa39a1 100644 --- a/tools/testing/selftests/kvm/include/aarch64/gic_v3.h +++ b/tools/testing/selftests/kvm/include/arm64/gic_v3.h diff --git a/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h index 3722ed9c8f96..3722ed9c8f96 100644 --- a/tools/testing/selftests/kvm/include/aarch64/gic_v3_its.h +++ b/tools/testing/selftests/kvm/include/arm64/gic_v3_its.h diff --git a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h index e43a57d99b56..e43a57d99b56 100644 --- a/tools/testing/selftests/kvm/include/aarch64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/arm64/kvm_util_arch.h diff --git a/tools/testing/selftests/kvm/include/aarch64/processor.h b/tools/testing/selftests/kvm/include/arm64/processor.h index 1e8d0d531fbd..1e8d0d531fbd 100644 --- a/tools/testing/selftests/kvm/include/aarch64/processor.h +++ b/tools/testing/selftests/kvm/include/arm64/processor.h diff --git a/tools/testing/selftests/kvm/include/aarch64/spinlock.h b/tools/testing/selftests/kvm/include/arm64/spinlock.h index cf0984106d14..cf0984106d14 100644 --- a/tools/testing/selftests/kvm/include/aarch64/spinlock.h +++ b/tools/testing/selftests/kvm/include/arm64/spinlock.h diff --git a/tools/testing/selftests/kvm/include/aarch64/ucall.h b/tools/testing/selftests/kvm/include/arm64/ucall.h index 4ec801f37f00..4ec801f37f00 100644 --- a/tools/testing/selftests/kvm/include/aarch64/ucall.h +++ b/tools/testing/selftests/kvm/include/arm64/ucall.h diff --git a/tools/testing/selftests/kvm/include/aarch64/vgic.h b/tools/testing/selftests/kvm/include/arm64/vgic.h index c481d0c00a5d..c481d0c00a5d 100644 --- a/tools/testing/selftests/kvm/include/aarch64/vgic.h +++ b/tools/testing/selftests/kvm/include/arm64/vgic.h diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index bc7c242480d6..4c4e5a847f67 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -702,16 +702,22 @@ static inline int __vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t va return __vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } -static inline void vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id, void *addr) +static inline uint64_t vcpu_get_reg(struct kvm_vcpu *vcpu, uint64_t id) { - struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)addr }; + uint64_t val; + struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + + TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); vcpu_ioctl(vcpu, KVM_GET_ONE_REG, ®); + return val; } static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t val) { struct kvm_one_reg reg = { .id = id, .addr = (uint64_t)&val }; + TEST_ASSERT(KVM_REG_SIZE(id) <= sizeof(val), "Reg %lx too big", id); + vcpu_ioctl(vcpu, KVM_SET_ONE_REG, ®); } diff --git a/tools/testing/selftests/kvm/include/s390x/debug_print.h b/tools/testing/selftests/kvm/include/s390/debug_print.h index 1bf275631cc6..1bf275631cc6 100644 --- a/tools/testing/selftests/kvm/include/s390x/debug_print.h +++ b/tools/testing/selftests/kvm/include/s390/debug_print.h diff --git a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h index b0ed71302722..b0ed71302722 100644 --- a/tools/testing/selftests/kvm/include/s390x/diag318_test_handler.h +++ b/tools/testing/selftests/kvm/include/s390/diag318_test_handler.h diff --git a/tools/testing/selftests/kvm/include/s390x/facility.h b/tools/testing/selftests/kvm/include/s390/facility.h index 00a1ced6538b..00a1ced6538b 100644 --- a/tools/testing/selftests/kvm/include/s390x/facility.h +++ b/tools/testing/selftests/kvm/include/s390/facility.h diff --git a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h index e43a57d99b56..e43a57d99b56 100644 --- a/tools/testing/selftests/kvm/include/s390x/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/s390/kvm_util_arch.h diff --git a/tools/testing/selftests/kvm/include/s390x/processor.h b/tools/testing/selftests/kvm/include/s390/processor.h index 33fef6fd9617..33fef6fd9617 100644 --- a/tools/testing/selftests/kvm/include/s390x/processor.h +++ b/tools/testing/selftests/kvm/include/s390/processor.h diff --git a/tools/testing/selftests/kvm/include/s390x/sie.h b/tools/testing/selftests/kvm/include/s390/sie.h index 160acd4a1db9..160acd4a1db9 100644 --- a/tools/testing/selftests/kvm/include/s390x/sie.h +++ b/tools/testing/selftests/kvm/include/s390/sie.h diff --git a/tools/testing/selftests/kvm/include/s390x/ucall.h b/tools/testing/selftests/kvm/include/s390/ucall.h index 8035a872a351..8035a872a351 100644 --- a/tools/testing/selftests/kvm/include/s390x/ucall.h +++ b/tools/testing/selftests/kvm/include/s390/ucall.h diff --git a/tools/testing/selftests/kvm/include/x86_64/apic.h b/tools/testing/selftests/kvm/include/x86/apic.h index 51990094effd..80fe9f69b38d 100644 --- a/tools/testing/selftests/kvm/include/x86_64/apic.h +++ b/tools/testing/selftests/kvm/include/x86/apic.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/apic.h - * * Copyright (C) 2021, Google LLC. */ diff --git a/tools/testing/selftests/kvm/include/x86_64/evmcs.h b/tools/testing/selftests/kvm/include/x86/evmcs.h index 901caf0e0939..5a74bb30e2f8 100644 --- a/tools/testing/selftests/kvm/include/x86_64/evmcs.h +++ b/tools/testing/selftests/kvm/include/x86/evmcs.h @@ -1,9 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * tools/testing/selftests/kvm/include/x86_64/evmcs.h - * * Copyright (C) 2018, Red Hat, Inc. - * */ #ifndef SELFTEST_KVM_EVMCS_H diff --git a/tools/testing/selftests/kvm/include/x86_64/hyperv.h b/tools/testing/selftests/kvm/include/x86/hyperv.h index 6849e2552f1b..f13e532be240 100644 --- a/tools/testing/selftests/kvm/include/x86_64/hyperv.h +++ b/tools/testing/selftests/kvm/include/x86/hyperv.h @@ -1,9 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* - * tools/testing/selftests/kvm/include/x86_64/hyperv.h - * * Copyright (C) 2021, Red Hat, Inc. - * */ #ifndef SELFTEST_KVM_HYPERV_H diff --git a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h index 972bb1c4ab4c..972bb1c4ab4c 100644 --- a/tools/testing/selftests/kvm/include/x86_64/kvm_util_arch.h +++ b/tools/testing/selftests/kvm/include/x86/kvm_util_arch.h diff --git a/tools/testing/selftests/kvm/include/x86_64/mce.h b/tools/testing/selftests/kvm/include/x86/mce.h index 6119321f3f5d..295f2d554754 100644 --- a/tools/testing/selftests/kvm/include/x86_64/mce.h +++ b/tools/testing/selftests/kvm/include/x86/mce.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/mce.h - * * Copyright (C) 2022, Google LLC. */ diff --git a/tools/testing/selftests/kvm/include/x86_64/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h index 3c10c4dc0ae8..3c10c4dc0ae8 100644 --- a/tools/testing/selftests/kvm/include/x86_64/pmu.h +++ b/tools/testing/selftests/kvm/include/x86/pmu.h diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h index 645200e95f89..d60da8966772 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86/processor.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/processor.h - * * Copyright (C) 2018, Google LLC. */ @@ -29,6 +27,8 @@ extern uint64_t guest_tsc_khz; #define MAX_NR_CPUID_ENTRIES 100 #endif +#define NONCANONICAL 0xaaaaaaaaaaaaaaaaull + /* Forced emulation prefix, used to invoke the emulator unconditionally. */ #define KVM_FEP "ud2; .byte 'k', 'v', 'm';" @@ -571,6 +571,11 @@ static inline void set_cr4(uint64_t val) __asm__ __volatile__("mov %0, %%cr4" : : "r" (val) : "memory"); } +static inline void set_idt(const struct desc_ptr *idt_desc) +{ + __asm__ __volatile__("lidt %0"::"m"(*idt_desc)); +} + static inline u64 xgetbv(u32 index) { u32 eax, edx; @@ -1012,10 +1017,19 @@ static inline struct kvm_cpuid2 *allocate_kvm_cpuid2(int nr_entries) void vcpu_init_cpuid(struct kvm_vcpu *vcpu, const struct kvm_cpuid2 *cpuid); +static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu) +{ + vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); +} + static inline struct kvm_cpuid_entry2 *__vcpu_get_cpuid_entry(struct kvm_vcpu *vcpu, uint32_t function, uint32_t index) { + TEST_ASSERT(vcpu->cpuid, "Must do vcpu_init_cpuid() first (or equivalent)"); + + vcpu_get_cpuid(vcpu); + return (struct kvm_cpuid_entry2 *)get_cpuid_entry(vcpu->cpuid, function, index); } @@ -1036,7 +1050,7 @@ static inline int __vcpu_set_cpuid(struct kvm_vcpu *vcpu) return r; /* On success, refresh the cache to pick up adjustments made by KVM. */ - vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); + vcpu_get_cpuid(vcpu); return 0; } @@ -1046,12 +1060,7 @@ static inline void vcpu_set_cpuid(struct kvm_vcpu *vcpu) vcpu_ioctl(vcpu, KVM_SET_CPUID2, vcpu->cpuid); /* Refresh the cache to pick up adjustments made by KVM. */ - vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); -} - -static inline void vcpu_get_cpuid(struct kvm_vcpu *vcpu) -{ - vcpu_ioctl(vcpu, KVM_GET_CPUID2, vcpu->cpuid); + vcpu_get_cpuid(vcpu); } void vcpu_set_cpuid_property(struct kvm_vcpu *vcpu, diff --git a/tools/testing/selftests/kvm/include/x86_64/sev.h b/tools/testing/selftests/kvm/include/x86/sev.h index 82c11c81a956..82c11c81a956 100644 --- a/tools/testing/selftests/kvm/include/x86_64/sev.h +++ b/tools/testing/selftests/kvm/include/x86/sev.h diff --git a/tools/testing/selftests/kvm/include/x86_64/svm.h b/tools/testing/selftests/kvm/include/x86/svm.h index 4803e1056055..29cffd0a9181 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm.h +++ b/tools/testing/selftests/kvm/include/x86/svm.h @@ -1,10 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* - * tools/testing/selftests/kvm/include/x86_64/svm.h - * This is a copy of arch/x86/include/asm/svm.h - * - */ - #ifndef SELFTEST_KVM_SVM_H #define SELFTEST_KVM_SVM_H diff --git a/tools/testing/selftests/kvm/include/x86_64/svm_util.h b/tools/testing/selftests/kvm/include/x86/svm_util.h index 044f0f872ba9..b74c6dcddcbd 100644 --- a/tools/testing/selftests/kvm/include/x86_64/svm_util.h +++ b/tools/testing/selftests/kvm/include/x86/svm_util.h @@ -1,8 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/svm_utils.h - * Header for nested SVM testing - * * Copyright (C) 2020, Red Hat, Inc. */ diff --git a/tools/testing/selftests/kvm/include/x86_64/ucall.h b/tools/testing/selftests/kvm/include/x86/ucall.h index d3825dcc3cd9..d3825dcc3cd9 100644 --- a/tools/testing/selftests/kvm/include/x86_64/ucall.h +++ b/tools/testing/selftests/kvm/include/x86/ucall.h diff --git a/tools/testing/selftests/kvm/include/x86_64/vmx.h b/tools/testing/selftests/kvm/include/x86/vmx.h index 5f0c0a29c556..edb3c391b982 100644 --- a/tools/testing/selftests/kvm/include/x86_64/vmx.h +++ b/tools/testing/selftests/kvm/include/x86/vmx.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/x86_64/vmx.h - * * Copyright (C) 2018, Google LLC. */ diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic.c b/tools/testing/selftests/kvm/lib/arm64/gic.c index 7abbf8866512..7abbf8866512 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h b/tools/testing/selftests/kvm/lib/arm64/gic_private.h index d24e9ecc96c6..d24e9ecc96c6 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_private.h +++ b/tools/testing/selftests/kvm/lib/arm64/gic_private.h diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c index 66d05506f78b..66d05506f78b 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c index 09f270545646..09f270545646 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/gic_v3_its.c +++ b/tools/testing/selftests/kvm/lib/arm64/gic_v3_its.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/handlers.S b/tools/testing/selftests/kvm/lib/arm64/handlers.S index 0e443eadfac6..0e443eadfac6 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/handlers.S +++ b/tools/testing/selftests/kvm/lib/arm64/handlers.S diff --git a/tools/testing/selftests/kvm/lib/aarch64/processor.c b/tools/testing/selftests/kvm/lib/arm64/processor.c index 698e34f39241..7ba3aa3755f3 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/processor.c +++ b/tools/testing/selftests/kvm/lib/arm64/processor.c @@ -281,8 +281,8 @@ void aarch64_vcpu_setup(struct kvm_vcpu *vcpu, struct kvm_vcpu_init *init) */ vcpu_set_reg(vcpu, KVM_ARM64_SYS_REG(SYS_CPACR_EL1), 3 << 20); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1), &sctlr_el1); - vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1), &tcr_el1); + sctlr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_SCTLR_EL1)); + tcr_el1 = vcpu_get_reg(vcpu, KVM_ARM64_SYS_REG(SYS_TCR_EL1)); /* Configure base granule size */ switch (vm->mode) { @@ -360,8 +360,8 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { uint64_t pstate, pc; - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate), &pstate); - vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc), &pc); + pstate = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pstate)); + pc = vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)); fprintf(stream, "%*spstate: 0x%.16lx pc: 0x%.16lx\n", indent, "", pstate, pc); diff --git a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c b/tools/testing/selftests/kvm/lib/arm64/spinlock.c index a076e780be5d..a076e780be5d 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/spinlock.c +++ b/tools/testing/selftests/kvm/lib/arm64/spinlock.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/ucall.c b/tools/testing/selftests/kvm/lib/arm64/ucall.c index ddab0ce89d4d..ddab0ce89d4d 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/ucall.c +++ b/tools/testing/selftests/kvm/lib/arm64/ucall.c diff --git a/tools/testing/selftests/kvm/lib/aarch64/vgic.c b/tools/testing/selftests/kvm/lib/arm64/vgic.c index 4427f43f73ea..4427f43f73ea 100644 --- a/tools/testing/selftests/kvm/lib/aarch64/vgic.c +++ b/tools/testing/selftests/kvm/lib/arm64/vgic.c diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 480e3a40d197..33fefeb3ca44 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1648,7 +1648,8 @@ int _vcpu_run(struct kvm_vcpu *vcpu) rc = __vcpu_run(vcpu); } while (rc == -1 && errno == EINTR); - assert_on_unhandled_exception(vcpu); + if (!rc) + assert_on_unhandled_exception(vcpu); return rc; } diff --git a/tools/testing/selftests/kvm/lib/riscv/processor.c b/tools/testing/selftests/kvm/lib/riscv/processor.c index 6ae47b3d6b25..dd663bcf0cc0 100644 --- a/tools/testing/selftests/kvm/lib/riscv/processor.c +++ b/tools/testing/selftests/kvm/lib/riscv/processor.c @@ -221,39 +221,39 @@ void vcpu_arch_dump(FILE *stream, struct kvm_vcpu *vcpu, uint8_t indent) { struct kvm_riscv_core core; - vcpu_get_reg(vcpu, RISCV_CORE_REG(mode), &core.mode); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &core.regs.pc); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra), &core.regs.ra); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp), &core.regs.sp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp), &core.regs.gp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp), &core.regs.tp); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0), &core.regs.t0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1), &core.regs.t1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2), &core.regs.t2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0), &core.regs.s0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1), &core.regs.s1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0), &core.regs.a0); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1), &core.regs.a1); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2), &core.regs.a2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3), &core.regs.a3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4), &core.regs.a4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5), &core.regs.a5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6), &core.regs.a6); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7), &core.regs.a7); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2), &core.regs.s2); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3), &core.regs.s3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4), &core.regs.s4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5), &core.regs.s5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6), &core.regs.s6); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7), &core.regs.s7); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8), &core.regs.s8); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9), &core.regs.s9); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10), &core.regs.s10); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11), &core.regs.s11); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3), &core.regs.t3); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4), &core.regs.t4); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5), &core.regs.t5); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6), &core.regs.t6); + core.mode = vcpu_get_reg(vcpu, RISCV_CORE_REG(mode)); + core.regs.pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc)); + core.regs.ra = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.ra)); + core.regs.sp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.sp)); + core.regs.gp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.gp)); + core.regs.tp = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.tp)); + core.regs.t0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t0)); + core.regs.t1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t1)); + core.regs.t2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t2)); + core.regs.s0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s0)); + core.regs.s1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s1)); + core.regs.a0 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a0)); + core.regs.a1 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a1)); + core.regs.a2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a2)); + core.regs.a3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a3)); + core.regs.a4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a4)); + core.regs.a5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a5)); + core.regs.a6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a6)); + core.regs.a7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.a7)); + core.regs.s2 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s2)); + core.regs.s3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s3)); + core.regs.s4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s4)); + core.regs.s5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s5)); + core.regs.s6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s6)); + core.regs.s7 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s7)); + core.regs.s8 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s8)); + core.regs.s9 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s9)); + core.regs.s10 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s10)); + core.regs.s11 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.s11)); + core.regs.t3 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t3)); + core.regs.t4 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t4)); + core.regs.t5 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t5)); + core.regs.t6 = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.t6)); fprintf(stream, " MODE: 0x%lx\n", core.mode); diff --git a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c index 2c432fa164f1..2c432fa164f1 100644 --- a/tools/testing/selftests/kvm/lib/s390x/diag318_test_handler.c +++ b/tools/testing/selftests/kvm/lib/s390/diag318_test_handler.c diff --git a/tools/testing/selftests/kvm/lib/s390x/facility.c b/tools/testing/selftests/kvm/lib/s390/facility.c index d540812d911a..d540812d911a 100644 --- a/tools/testing/selftests/kvm/lib/s390x/facility.c +++ b/tools/testing/selftests/kvm/lib/s390/facility.c diff --git a/tools/testing/selftests/kvm/lib/s390x/processor.c b/tools/testing/selftests/kvm/lib/s390/processor.c index 20cfe970e3e3..20cfe970e3e3 100644 --- a/tools/testing/selftests/kvm/lib/s390x/processor.c +++ b/tools/testing/selftests/kvm/lib/s390/processor.c diff --git a/tools/testing/selftests/kvm/lib/s390x/ucall.c b/tools/testing/selftests/kvm/lib/s390/ucall.c index cca98734653d..cca98734653d 100644 --- a/tools/testing/selftests/kvm/lib/s390x/ucall.c +++ b/tools/testing/selftests/kvm/lib/s390/ucall.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86/apic.c index 89153a333e83..89153a333e83 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/apic.c +++ b/tools/testing/selftests/kvm/lib/x86/apic.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/handlers.S b/tools/testing/selftests/kvm/lib/x86/handlers.S index 7629819734af..7629819734af 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/handlers.S +++ b/tools/testing/selftests/kvm/lib/x86/handlers.S diff --git a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c b/tools/testing/selftests/kvm/lib/x86/hyperv.c index 15bc8cd583aa..15bc8cd583aa 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/hyperv.c +++ b/tools/testing/selftests/kvm/lib/x86/hyperv.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/memstress.c b/tools/testing/selftests/kvm/lib/x86/memstress.c index d61e623afc8c..7f5d62a65c68 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/memstress.c +++ b/tools/testing/selftests/kvm/lib/x86/memstress.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * x86_64-specific extensions to memstress.c. + * x86-specific extensions to memstress.c. * * Copyright (C) 2022, Google, Inc. */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c index f31f0427c17c..f31f0427c17c 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/pmu.c +++ b/tools/testing/selftests/kvm/lib/x86/pmu.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/processor.c b/tools/testing/selftests/kvm/lib/x86/processor.c index 636b29ba8985..bd5a802fa7a5 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/processor.c +++ b/tools/testing/selftests/kvm/lib/x86/processor.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/processor.c - * * Copyright (C) 2018, Google LLC. */ diff --git a/tools/testing/selftests/kvm/lib/x86_64/sev.c b/tools/testing/selftests/kvm/lib/x86/sev.c index e9535ee20b7f..e9535ee20b7f 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/sev.c +++ b/tools/testing/selftests/kvm/lib/x86/sev.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/svm.c b/tools/testing/selftests/kvm/lib/x86/svm.c index 5495a92dfd5a..d239c2097391 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/svm.c +++ b/tools/testing/selftests/kvm/lib/x86/svm.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/svm.c * Helpers used for nested SVM testing * Largely inspired from KVM unit test svm.c * diff --git a/tools/testing/selftests/kvm/lib/x86_64/ucall.c b/tools/testing/selftests/kvm/lib/x86/ucall.c index 1265cecc7dd1..1265cecc7dd1 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/ucall.c +++ b/tools/testing/selftests/kvm/lib/x86/ucall.c diff --git a/tools/testing/selftests/kvm/lib/x86_64/vmx.c b/tools/testing/selftests/kvm/lib/x86/vmx.c index d7ac122820bf..d4d1208dd023 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/vmx.c +++ b/tools/testing/selftests/kvm/lib/x86/vmx.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/vmx.c - * * Copyright (C) 2018, Google LLC. */ diff --git a/tools/testing/selftests/kvm/max_guest_memory_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c index 0b9678858b6d..d9c76b4c0d88 100644 --- a/tools/testing/selftests/kvm/max_guest_memory_test.c +++ b/tools/testing/selftests/kvm/mmu_stress_test.c @@ -15,16 +15,62 @@ #include "test_util.h" #include "guest_modes.h" #include "processor.h" +#include "ucall_common.h" + +static bool mprotect_ro_done; static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride) { uint64_t gpa; + int i; - for (;;) { + for (i = 0; i < 2; i++) { for (gpa = start_gpa; gpa < end_gpa; gpa += stride) - *((volatile uint64_t *)gpa) = gpa; - GUEST_SYNC(0); + vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + GUEST_SYNC(i); } + + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + *((volatile uint64_t *)gpa); + GUEST_SYNC(2); + + /* + * Write to the region while mprotect(PROT_READ) is underway. Keep + * looping until the memory is guaranteed to be read-only, otherwise + * vCPUs may complete their writes and advance to the next stage + * prematurely. + * + * For architectures that support skipping the faulting instruction, + * generate the store via inline assembly to ensure the exact length + * of the instruction is known and stable (vcpu_arch_put_guest() on + * fixed-length architectures should work, but the cost of paranoia + * is low in this case). For x86, hand-code the exact opcode so that + * there is no room for variability in the generated instruction. + */ + do { + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) +#ifdef __x86_64__ + asm volatile(".byte 0x48,0x89,0x00" :: "a"(gpa) : "memory"); /* mov %rax, (%rax) */ +#elif defined(__aarch64__) + asm volatile("str %0, [%0]" :: "r" (gpa) : "memory"); +#else + vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); +#endif + } while (!READ_ONCE(mprotect_ro_done)); + + /* + * Only architectures that write the entire range can explicitly sync, + * as other architectures will be stuck on the write fault. + */ +#if defined(__x86_64__) || defined(__aarch64__) + GUEST_SYNC(3); +#endif + + for (gpa = start_gpa; gpa < end_gpa; gpa += stride) + vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa); + GUEST_SYNC(4); + + GUEST_ASSERT(0); } struct vcpu_info { @@ -51,34 +97,100 @@ static void rendezvous_with_boss(void) } } -static void run_vcpu(struct kvm_vcpu *vcpu) +static void assert_sync_stage(struct kvm_vcpu *vcpu, int stage) +{ + struct ucall uc; + + TEST_ASSERT_EQ(get_ucall(vcpu, &uc), UCALL_SYNC); + TEST_ASSERT_EQ(uc.args[1], stage); +} + +static void run_vcpu(struct kvm_vcpu *vcpu, int stage) { vcpu_run(vcpu); - TEST_ASSERT_EQ(get_ucall(vcpu, NULL), UCALL_SYNC); + assert_sync_stage(vcpu, stage); } static void *vcpu_worker(void *data) { + struct kvm_sregs __maybe_unused sregs; struct vcpu_info *info = data; struct kvm_vcpu *vcpu = info->vcpu; struct kvm_vm *vm = vcpu->vm; - struct kvm_sregs sregs; + int r; vcpu_args_set(vcpu, 3, info->start_gpa, info->end_gpa, vm->page_size); rendezvous_with_boss(); - run_vcpu(vcpu); + /* Stage 0, write all of guest memory. */ + run_vcpu(vcpu, 0); rendezvous_with_boss(); - vcpu_sregs_get(vcpu, &sregs); #ifdef __x86_64__ + vcpu_sregs_get(vcpu, &sregs); /* Toggle CR0.WP to trigger a MMU context reset. */ sregs.cr0 ^= X86_CR0_WP; -#endif vcpu_sregs_set(vcpu, &sregs); +#endif rendezvous_with_boss(); - run_vcpu(vcpu); + /* Stage 1, re-write all of guest memory. */ + run_vcpu(vcpu, 1); + rendezvous_with_boss(); + + /* Stage 2, read all of guest memory, which is now read-only. */ + run_vcpu(vcpu, 2); + + /* + * Stage 3, write guest memory and verify KVM returns -EFAULT for once + * the mprotect(PROT_READ) lands. Only architectures that support + * validating *all* of guest memory sync for this stage, as vCPUs will + * be stuck on the faulting instruction for other architectures. Go to + * stage 3 without a rendezvous + */ + do { + r = _vcpu_run(vcpu); + } while (!r); + TEST_ASSERT(r == -1 && errno == EFAULT, + "Expected EFAULT on write to RO memory, got r = %d, errno = %d", r, errno); + +#if defined(__x86_64__) || defined(__aarch64__) + /* + * Verify *all* writes from the guest hit EFAULT due to the VMA now + * being read-only. x86 and arm64 only at this time as skipping the + * instruction that hits the EFAULT requires advancing the program + * counter, which is arch specific and relies on inline assembly. + */ +#ifdef __x86_64__ + vcpu->run->kvm_valid_regs = KVM_SYNC_X86_REGS; +#endif + for (;;) { + r = _vcpu_run(vcpu); + if (!r) + break; + TEST_ASSERT_EQ(errno, EFAULT); +#if defined(__x86_64__) + WRITE_ONCE(vcpu->run->kvm_dirty_regs, KVM_SYNC_X86_REGS); + vcpu->run->s.regs.regs.rip += 3; +#elif defined(__aarch64__) + vcpu_set_reg(vcpu, ARM64_CORE_REG(regs.pc), + vcpu_get_reg(vcpu, ARM64_CORE_REG(regs.pc)) + 4); +#endif + + } + assert_sync_stage(vcpu, 3); +#endif /* __x86_64__ || __aarch64__ */ + rendezvous_with_boss(); + + /* + * Stage 4. Run to completion, waiting for mprotect(PROT_WRITE) to + * make the memory writable again. + */ + do { + r = _vcpu_run(vcpu); + } while (r && errno == EFAULT); + TEST_ASSERT_EQ(r, 0); + assert_sync_stage(vcpu, 4); rendezvous_with_boss(); return NULL; @@ -161,7 +273,7 @@ int main(int argc, char *argv[]) const uint64_t start_gpa = SZ_4G; const int first_slot = 1; - struct timespec time_start, time_run1, time_reset, time_run2; + struct timespec time_start, time_run1, time_reset, time_run2, time_ro, time_rw; uint64_t max_gpa, gpa, slot_size, max_mem, i; int max_slots, slot, opt, fd; bool hugepages = false; @@ -209,7 +321,13 @@ int main(int argc, char *argv[]) vcpus = malloc(nr_vcpus * sizeof(*vcpus)); TEST_ASSERT(vcpus, "Failed to allocate vCPU array"); - vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus); + vm = __vm_create_with_vcpus(VM_SHAPE_DEFAULT, nr_vcpus, +#ifdef __x86_64__ + max_mem / SZ_1G, +#else + max_mem / vm_guest_mode_params[VM_MODE_DEFAULT].page_size, +#endif + guest_code, vcpus); max_gpa = vm->max_gfn << vm->page_shift; TEST_ASSERT(max_gpa > (4 * slot_size), "MAXPHYADDR <4gb "); @@ -259,14 +377,28 @@ int main(int argc, char *argv[]) rendezvous_with_vcpus(&time_reset, "reset"); rendezvous_with_vcpus(&time_run2, "run 2"); + mprotect(mem, slot_size, PROT_READ); + usleep(10); + mprotect_ro_done = true; + sync_global_to_guest(vm, mprotect_ro_done); + + rendezvous_with_vcpus(&time_ro, "mprotect RO"); + mprotect(mem, slot_size, PROT_READ | PROT_WRITE); + rendezvous_with_vcpus(&time_rw, "mprotect RW"); + + time_rw = timespec_sub(time_rw, time_ro); + time_ro = timespec_sub(time_ro, time_run2); time_run2 = timespec_sub(time_run2, time_reset); - time_reset = timespec_sub(time_reset, time_run1); + time_reset = timespec_sub(time_reset, time_run1); time_run1 = timespec_sub(time_run1, time_start); - pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds\n", + pr_info("run1 = %ld.%.9lds, reset = %ld.%.9lds, run2 = %ld.%.9lds, " + "ro = %ld.%.9lds, rw = %ld.%.9lds\n", time_run1.tv_sec, time_run1.tv_nsec, time_reset.tv_sec, time_reset.tv_nsec, - time_run2.tv_sec, time_run2.tv_nsec); + time_run2.tv_sec, time_run2.tv_nsec, + time_ro.tv_sec, time_ro.tv_nsec, + time_rw.tv_sec, time_rw.tv_nsec); /* * Delete even numbered slots (arbitrary) and unmap the first half of diff --git a/tools/testing/selftests/kvm/riscv/arch_timer.c b/tools/testing/selftests/kvm/riscv/arch_timer.c index 2c792228ac0b..9e370800a6a2 100644 --- a/tools/testing/selftests/kvm/riscv/arch_timer.c +++ b/tools/testing/selftests/kvm/riscv/arch_timer.c @@ -93,7 +93,7 @@ struct kvm_vm *test_vm_create(void) vcpu_init_vector_tables(vcpus[i]); /* Initialize guest timer frequency. */ - vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency), &timer_freq); + timer_freq = vcpu_get_reg(vcpus[0], RISCV_TIMER_REG(frequency)); sync_global_to_guest(vm, timer_freq); pr_debug("timer_freq: %lu\n", timer_freq); diff --git a/tools/testing/selftests/kvm/riscv/ebreak_test.c b/tools/testing/selftests/kvm/riscv/ebreak_test.c index 0e0712854953..cfed6c727bfc 100644 --- a/tools/testing/selftests/kvm/riscv/ebreak_test.c +++ b/tools/testing/selftests/kvm/riscv/ebreak_test.c @@ -60,7 +60,7 @@ int main(void) TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_DEBUG); - vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc), &pc); + pc = vcpu_get_reg(vcpu, RISCV_CORE_REG(regs.pc)); TEST_ASSERT_EQ(pc, LABEL_ADDRESS(sw_bp_1)); /* skip sw_bp_1 */ diff --git a/tools/testing/selftests/kvm/riscv/get-reg-list.c b/tools/testing/selftests/kvm/riscv/get-reg-list.c index 4bc1051848e5..8515921dfdbf 100644 --- a/tools/testing/selftests/kvm/riscv/get-reg-list.c +++ b/tools/testing/selftests/kvm/riscv/get-reg-list.c @@ -52,6 +52,8 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVINVAL: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVNAPOT: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVPBMT: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_SVVPTC: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZABHA: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZACAS: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZAWRS: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZBA: @@ -71,6 +73,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZFHMIN: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOM: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICBOZ: + case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICCRSE: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICNTR: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICOND: case KVM_REG_RISCV_ISA_EXT | KVM_REG_RISCV_ISA_SINGLE | KVM_RISCV_ISA_EXT_ZICSR: @@ -112,6 +115,7 @@ bool filter_reg(__u64 reg) case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN: + case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SUSP: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL: case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR: @@ -429,6 +433,8 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(SVINVAL), KVM_ISA_EXT_ARR(SVNAPOT), KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(SVVPTC), + KVM_ISA_EXT_ARR(ZABHA), KVM_ISA_EXT_ARR(ZACAS), KVM_ISA_EXT_ARR(ZAWRS), KVM_ISA_EXT_ARR(ZBA), @@ -448,6 +454,7 @@ static const char *isa_ext_single_id_to_str(__u64 reg_off) KVM_ISA_EXT_ARR(ZFHMIN), KVM_ISA_EXT_ARR(ZICBOM), KVM_ISA_EXT_ARR(ZICBOZ), + KVM_ISA_EXT_ARR(ZICCRSE), KVM_ISA_EXT_ARR(ZICNTR), KVM_ISA_EXT_ARR(ZICOND), KVM_ISA_EXT_ARR(ZICSR), @@ -535,10 +542,11 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off) KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SRST), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_HSM), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_PMU), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), + KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SUSP), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL), KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR), - KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN), }; if (reg_off >= ARRAY_SIZE(kvm_sbi_ext_reg_name)) @@ -949,6 +957,7 @@ KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE); KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA); KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU); KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN); +KVM_SBI_EXT_SIMPLE_CONFIG(susp, SUSP); KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA); KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F); @@ -964,6 +973,8 @@ KVM_ISA_EXT_SIMPLE_CONFIG(svadu, SVADU); KVM_ISA_EXT_SIMPLE_CONFIG(svinval, SVINVAL); KVM_ISA_EXT_SIMPLE_CONFIG(svnapot, SVNAPOT); KVM_ISA_EXT_SIMPLE_CONFIG(svpbmt, SVPBMT); +KVM_ISA_EXT_SIMPLE_CONFIG(svvptc, SVVPTC); +KVM_ISA_EXT_SIMPLE_CONFIG(zabha, ZABHA); KVM_ISA_EXT_SIMPLE_CONFIG(zacas, ZACAS); KVM_ISA_EXT_SIMPLE_CONFIG(zawrs, ZAWRS); KVM_ISA_EXT_SIMPLE_CONFIG(zba, ZBA); @@ -983,6 +994,7 @@ KVM_ISA_EXT_SIMPLE_CONFIG(zfh, ZFH); KVM_ISA_EXT_SIMPLE_CONFIG(zfhmin, ZFHMIN); KVM_ISA_EXT_SUBLIST_CONFIG(zicbom, ZICBOM); KVM_ISA_EXT_SUBLIST_CONFIG(zicboz, ZICBOZ); +KVM_ISA_EXT_SIMPLE_CONFIG(ziccrse, ZICCRSE); KVM_ISA_EXT_SIMPLE_CONFIG(zicntr, ZICNTR); KVM_ISA_EXT_SIMPLE_CONFIG(zicond, ZICOND); KVM_ISA_EXT_SIMPLE_CONFIG(zicsr, ZICSR); @@ -1017,6 +1029,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_sbi_sta, &config_sbi_pmu, &config_sbi_dbcn, + &config_sbi_susp, &config_aia, &config_fp_f, &config_fp_d, @@ -1031,6 +1044,8 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_svinval, &config_svnapot, &config_svpbmt, + &config_svvptc, + &config_zabha, &config_zacas, &config_zawrs, &config_zba, @@ -1050,6 +1065,7 @@ struct vcpu_reg_list *vcpu_configs[] = { &config_zfhmin, &config_zicbom, &config_zicboz, + &config_ziccrse, &config_zicntr, &config_zicond, &config_zicsr, diff --git a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c index f299cbfd23ca..f45c0ecc902d 100644 --- a/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c +++ b/tools/testing/selftests/kvm/riscv/sbi_pmu_test.c @@ -608,7 +608,7 @@ static void test_vm_events_overflow(void *guest_code) vcpu_init_vector_tables(vcpu); /* Initialize guest timer frequency. */ - vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency), &timer_freq); + timer_freq = vcpu_get_reg(vcpu, RISCV_TIMER_REG(frequency)); sync_global_to_guest(vm, timer_freq); run_vcpu(vcpu); diff --git a/tools/testing/selftests/kvm/s390x/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c index e32dd59703a0..85cc8c18d6e7 100644 --- a/tools/testing/selftests/kvm/s390x/cmma_test.c +++ b/tools/testing/selftests/kvm/s390/cmma_test.c @@ -444,7 +444,7 @@ static void assert_no_pages_cmma_dirty(struct kvm_vm *vm) ); } -static void test_get_inital_dirty(void) +static void test_get_initial_dirty(void) { struct kvm_vm *vm = create_vm_two_memslots(); struct kvm_vcpu *vcpu; @@ -651,7 +651,7 @@ struct testdef { } testlist[] = { { "migration mode and dirty tracking", test_migration_mode }, { "GET_CMMA_BITS: basic calls", test_get_cmma_basic }, - { "GET_CMMA_BITS: all pages are dirty initally", test_get_inital_dirty }, + { "GET_CMMA_BITS: all pages are dirty initially", test_get_initial_dirty }, { "GET_CMMA_BITS: holes are skipped", test_get_skip_holes }, }; diff --git a/tools/testing/selftests/kvm/s390x/config b/tools/testing/selftests/kvm/s390/config index 23270f2d679f..23270f2d679f 100644 --- a/tools/testing/selftests/kvm/s390x/config +++ b/tools/testing/selftests/kvm/s390/config diff --git a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c index 27255880dabd..27255880dabd 100644 --- a/tools/testing/selftests/kvm/s390x/cpumodel_subfuncs_test.c +++ b/tools/testing/selftests/kvm/s390/cpumodel_subfuncs_test.c diff --git a/tools/testing/selftests/kvm/s390x/debug_test.c b/tools/testing/selftests/kvm/s390/debug_test.c index ad8095968601..ad8095968601 100644 --- a/tools/testing/selftests/kvm/s390x/debug_test.c +++ b/tools/testing/selftests/kvm/s390/debug_test.c diff --git a/tools/testing/selftests/kvm/s390x/memop.c b/tools/testing/selftests/kvm/s390/memop.c index 4374b4cd2a80..4374b4cd2a80 100644 --- a/tools/testing/selftests/kvm/s390x/memop.c +++ b/tools/testing/selftests/kvm/s390/memop.c diff --git a/tools/testing/selftests/kvm/s390x/resets.c b/tools/testing/selftests/kvm/s390/resets.c index 357943f2bea8..b58f75b381e5 100644 --- a/tools/testing/selftests/kvm/s390x/resets.c +++ b/tools/testing/selftests/kvm/s390/resets.c @@ -61,7 +61,7 @@ static void test_one_reg(struct kvm_vcpu *vcpu, uint64_t id, uint64_t value) { uint64_t eval_reg; - vcpu_get_reg(vcpu, id, &eval_reg); + eval_reg = vcpu_get_reg(vcpu, id); TEST_ASSERT(eval_reg == value, "value == 0x%lx", value); } diff --git a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c index bba0d9a6dcc8..bba0d9a6dcc8 100644 --- a/tools/testing/selftests/kvm/s390x/shared_zeropage_test.c +++ b/tools/testing/selftests/kvm/s390/shared_zeropage_test.c diff --git a/tools/testing/selftests/kvm/s390x/sync_regs_test.c b/tools/testing/selftests/kvm/s390/sync_regs_test.c index 53def355ccba..53def355ccba 100644 --- a/tools/testing/selftests/kvm/s390x/sync_regs_test.c +++ b/tools/testing/selftests/kvm/s390/sync_regs_test.c diff --git a/tools/testing/selftests/kvm/s390x/tprot.c b/tools/testing/selftests/kvm/s390/tprot.c index 12d5e1cb62e3..12d5e1cb62e3 100644 --- a/tools/testing/selftests/kvm/s390x/tprot.c +++ b/tools/testing/selftests/kvm/s390/tprot.c diff --git a/tools/testing/selftests/kvm/s390x/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c index 135ee22856cf..d265b34c54be 100644 --- a/tools/testing/selftests/kvm/s390x/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c @@ -88,10 +88,6 @@ asm("test_skey_asm:\n" " ahi %r0,1\n" " st %r1,0(%r5,%r6)\n" - " iske %r1,%r6\n" - " ahi %r0,1\n" - " diag 0,0,0x44\n" - " sske %r1,%r6\n" " xgr %r1,%r1\n" " iske %r1,%r6\n" @@ -459,10 +455,14 @@ TEST_F(uc_kvm, uc_no_user_region) }; ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, ®ion)); - ASSERT_EQ(EINVAL, errno); + ASSERT_TRUE(errno == EEXIST || errno == EINVAL) + TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION", + strerror(errno), errno); ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION2, ®ion2)); - ASSERT_EQ(EINVAL, errno); + ASSERT_TRUE(errno == EEXIST || errno == EINVAL) + TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION2", + strerror(errno), errno); } TEST_F(uc_kvm, uc_map_unmap) @@ -596,7 +596,9 @@ TEST_F(uc_kvm, uc_skey) ASSERT_EQ(true, uc_handle_exit(self)); ASSERT_EQ(1, sync_regs->gprs[0]); - /* ISKE */ + /* SSKE + ISKE */ + sync_regs->gprs[1] = skeyvalue; + run->kvm_dirty_regs |= KVM_SYNC_GPRS; ASSERT_EQ(0, uc_run_once(self)); /* @@ -608,21 +610,11 @@ TEST_F(uc_kvm, uc_skey) TEST_ASSERT_EQ(0, sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)); TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason); TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode); - TEST_REQUIRE(sie_block->ipa != 0xb229); + TEST_REQUIRE(sie_block->ipa != 0xb22b); - /* ISKE contd. */ + /* SSKE + ISKE contd. */ ASSERT_EQ(false, uc_handle_exit(self)); ASSERT_EQ(2, sync_regs->gprs[0]); - /* assert initial skey (ACC = 0, R & C = 1) */ - ASSERT_EQ(0x06, sync_regs->gprs[1]); - uc_assert_diag44(self); - - /* SSKE + ISKE */ - sync_regs->gprs[1] = skeyvalue; - run->kvm_dirty_regs |= KVM_SYNC_GPRS; - ASSERT_EQ(0, uc_run_once(self)); - ASSERT_EQ(false, uc_handle_exit(self)); - ASSERT_EQ(3, sync_regs->gprs[0]); ASSERT_EQ(skeyvalue, sync_regs->gprs[1]); uc_assert_diag44(self); @@ -631,7 +623,7 @@ TEST_F(uc_kvm, uc_skey) run->kvm_dirty_regs |= KVM_SYNC_GPRS; ASSERT_EQ(0, uc_run_once(self)); ASSERT_EQ(false, uc_handle_exit(self)); - ASSERT_EQ(4, sync_regs->gprs[0]); + ASSERT_EQ(3, sync_regs->gprs[0]); /* assert R reset but rest of skey unchanged */ ASSERT_EQ(skeyvalue & 0xfa, sync_regs->gprs[1]); ASSERT_EQ(0, sync_regs->gprs[1] & 0x04); diff --git a/tools/testing/selftests/kvm/set_memory_region_test.c b/tools/testing/selftests/kvm/set_memory_region_test.c index a8267628e9ed..bc440d5aba57 100644 --- a/tools/testing/selftests/kvm/set_memory_region_test.c +++ b/tools/testing/selftests/kvm/set_memory_region_test.c @@ -17,9 +17,9 @@ #include <processor.h> /* - * s390x needs at least 1MB alignment, and the x86_64 MOVE/DELETE tests need a - * 2MB sized and aligned region so that the initial region corresponds to - * exactly one large page. + * s390 needs at least 1MB alignment, and the x86 MOVE/DELETE tests need a 2MB + * sized and aligned region so that the initial region corresponds to exactly + * one large page. */ #define MEM_REGION_SIZE 0x200000 @@ -235,7 +235,7 @@ static void guest_code_delete_memory_region(void) * in the guest will never succeed, and so isn't an option. */ memset(&idt, 0, sizeof(idt)); - __asm__ __volatile__("lidt %0" :: "m"(idt)); + set_idt(&idt); GUEST_SYNC(0); @@ -553,6 +553,56 @@ static void test_add_overlapping_private_memory_regions(void) close(memfd); kvm_vm_free(vm); } + +static void guest_code_mmio_during_vectoring(void) +{ + const struct desc_ptr idt_desc = { + .address = MEM_REGION_GPA, + .size = 0xFFF, + }; + + set_idt(&idt_desc); + + /* Generate a #GP by dereferencing a non-canonical address */ + *((uint8_t *)NONCANONICAL) = 0x1; + + GUEST_ASSERT(0); +} + +/* + * This test points the IDT descriptor base to an MMIO address. It should cause + * a KVM internal error when an event occurs in the guest. + */ +static void test_mmio_during_vectoring(void) +{ + struct kvm_vcpu *vcpu; + struct kvm_run *run; + struct kvm_vm *vm; + u64 expected_gpa; + + pr_info("Testing MMIO during vectoring error handling\n"); + + vm = vm_create_with_one_vcpu(&vcpu, guest_code_mmio_during_vectoring); + virt_map(vm, MEM_REGION_GPA, MEM_REGION_GPA, 1); + + run = vcpu->run; + + vcpu_run(vcpu); + TEST_ASSERT_KVM_EXIT_REASON(vcpu, KVM_EXIT_INTERNAL_ERROR); + TEST_ASSERT(run->internal.suberror == KVM_INTERNAL_ERROR_DELIVERY_EV, + "Unexpected suberror = %d", vcpu->run->internal.suberror); + TEST_ASSERT(run->internal.ndata != 4, "Unexpected internal error data array size = %d", + run->internal.ndata); + + /* The reported GPA should be IDT base + offset of the GP vector */ + expected_gpa = MEM_REGION_GPA + GP_VECTOR * sizeof(struct idt_entry); + + TEST_ASSERT(run->internal.data[3] == expected_gpa, + "Unexpected GPA = %llx (expected %lx)", + vcpu->run->internal.data[3], expected_gpa); + + kvm_vm_free(vm); +} #endif int main(int argc, char *argv[]) @@ -568,6 +618,7 @@ int main(int argc, char *argv[]) * KVM_RUN fails with ENOEXEC or EFAULT. */ test_zero_memory_regions(); + test_mmio_during_vectoring(); #endif test_invalid_memory_region_flags(); diff --git a/tools/testing/selftests/kvm/steal_time.c b/tools/testing/selftests/kvm/steal_time.c index a8d3afa0b86b..cce2520af720 100644 --- a/tools/testing/selftests/kvm/steal_time.c +++ b/tools/testing/selftests/kvm/steal_time.c @@ -269,9 +269,8 @@ static void guest_code(int cpu) static bool is_steal_time_supported(struct kvm_vcpu *vcpu) { uint64_t id = RISCV_SBI_EXT_REG(KVM_RISCV_SBI_EXT_STA); - unsigned long enabled; + unsigned long enabled = vcpu_get_reg(vcpu, id); - vcpu_get_reg(vcpu, id, &enabled); TEST_ASSERT(enabled == 0 || enabled == 1, "Expected boolean result"); return enabled; diff --git a/tools/testing/selftests/kvm/x86_64/amx_test.c b/tools/testing/selftests/kvm/x86/amx_test.c index f4ce5a185a7d..f4ce5a185a7d 100644 --- a/tools/testing/selftests/kvm/x86_64/amx_test.c +++ b/tools/testing/selftests/kvm/x86/amx_test.c diff --git a/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c index f8916bb34405..f8916bb34405 100644 --- a/tools/testing/selftests/kvm/x86_64/apic_bus_clock_test.c +++ b/tools/testing/selftests/kvm/x86/apic_bus_clock_test.c diff --git a/tools/testing/selftests/kvm/x86_64/cpuid_test.c b/tools/testing/selftests/kvm/x86/cpuid_test.c index 7b3fda6842bc..7b3fda6842bc 100644 --- a/tools/testing/selftests/kvm/x86_64/cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/cpuid_test.c diff --git a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c b/tools/testing/selftests/kvm/x86/cr4_cpuid_sync_test.c index 28cc66454601..28cc66454601 100644 --- a/tools/testing/selftests/kvm/x86_64/cr4_cpuid_sync_test.c +++ b/tools/testing/selftests/kvm/x86/cr4_cpuid_sync_test.c diff --git a/tools/testing/selftests/kvm/x86_64/debug_regs.c b/tools/testing/selftests/kvm/x86/debug_regs.c index 2d814c1d1dc4..2d814c1d1dc4 100644 --- a/tools/testing/selftests/kvm/x86_64/debug_regs.c +++ b/tools/testing/selftests/kvm/x86/debug_regs.c diff --git a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c index 2929c067c207..2929c067c207 100644 --- a/tools/testing/selftests/kvm/x86_64/dirty_log_page_splitting_test.c +++ b/tools/testing/selftests/kvm/x86/dirty_log_page_splitting_test.c diff --git a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c b/tools/testing/selftests/kvm/x86/exit_on_emulation_failure_test.c index 81055476d394..81055476d394 100644 --- a/tools/testing/selftests/kvm/x86_64/exit_on_emulation_failure_test.c +++ b/tools/testing/selftests/kvm/x86/exit_on_emulation_failure_test.c diff --git a/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c b/tools/testing/selftests/kvm/x86/feature_msrs_test.c index a72f13ae2edb..a72f13ae2edb 100644 --- a/tools/testing/selftests/kvm/x86_64/feature_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/feature_msrs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c index 762628f7d4ba..762628f7d4ba 100644 --- a/tools/testing/selftests/kvm/x86_64/fix_hypercall_test.c +++ b/tools/testing/selftests/kvm/x86/fix_hypercall_test.c diff --git a/tools/testing/selftests/kvm/x86_64/flds_emulation.h b/tools/testing/selftests/kvm/x86/flds_emulation.h index 37b1a9f52864..37b1a9f52864 100644 --- a/tools/testing/selftests/kvm/x86_64/flds_emulation.h +++ b/tools/testing/selftests/kvm/x86/flds_emulation.h diff --git a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c index 10b1b0ba374e..10b1b0ba374e 100644 --- a/tools/testing/selftests/kvm/x86_64/hwcr_msr_test.c +++ b/tools/testing/selftests/kvm/x86/hwcr_msr_test.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c b/tools/testing/selftests/kvm/x86/hyperv_clock.c index e058bc676cd6..e058bc676cd6 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_clock.c +++ b/tools/testing/selftests/kvm/x86/hyperv_clock.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c index 4f5881d4ef66..4e920705681a 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c @@ -41,13 +41,19 @@ static bool smt_possible(void) return res; } -static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, - bool evmcs_expected) +static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) { + const bool has_irqchip = !vcpu || vcpu->vm->has_irqchip; + const struct kvm_cpuid2 *hv_cpuid_entries; int i; int nent_expected = 10; u32 test_val; + if (vcpu) + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); + else + hv_cpuid_entries = kvm_get_supported_hv_cpuid(); + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" " (returned %d)", @@ -80,12 +86,19 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, entry->eax, evmcs_expected ); break; + case 0x40000003: + TEST_ASSERT(has_irqchip || !(entry->edx & BIT(19)), + "\"Direct\" Synthetic Timers should require in-kernel APIC"); + break; case 0x40000004: test_val = entry->eax & (1UL << 18); TEST_ASSERT(!!test_val == !smt_possible(), "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); + + TEST_ASSERT(has_irqchip || !(entry->eax & BIT(10)), + "Cluster IPI (i.e. SEND_IPI) should require in-kernel APIC"); break; case 0x4000000A: TEST_ASSERT(entry->eax & (1UL << 19), @@ -109,9 +122,16 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } + + /* + * Note, the CPUID array returned by the system-scoped helper is a one- + * time allocation, i.e. must not be freed. + */ + if (vcpu) + free((void *)hv_cpuid_entries); } -void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; @@ -129,19 +149,20 @@ void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) int main(int argc, char *argv[]) { struct kvm_vm *vm; - const struct kvm_cpuid2 *hv_cpuid_entries; struct kvm_vcpu *vcpu; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); + /* Test the vCPU ioctl without an in-kernel local APIC. */ + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); + test_hv_cpuid(vcpu, false); + kvm_vm_free(vm); /* Test vCPU ioctl version */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); test_hv_cpuid_e2big(vm, vcpu); - - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, false); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, false); if (!kvm_cpu_has(X86_FEATURE_VMX) || !kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { @@ -149,9 +170,7 @@ int main(int argc, char *argv[]) goto do_sys; } vcpu_enable_evmcs(vcpu); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, true); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, true); do_sys: /* Test system ioctl version */ @@ -161,9 +180,7 @@ do_sys: } test_hv_cpuid_e2big(vm, NULL); - - hv_cpuid_entries = kvm_get_supported_hv_cpuid(); - test_hv_cpuid(hv_cpuid_entries, kvm_cpu_has(X86_FEATURE_VMX)); + test_hv_cpuid(NULL, kvm_cpu_has(X86_FEATURE_VMX)); out: kvm_vm_free(vm); diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c index 74cf19661309..74cf19661309 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_evmcs.c +++ b/tools/testing/selftests/kvm/x86/hyperv_evmcs.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c index 949e08e98f31..949e08e98f31 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_extended_hypercalls.c +++ b/tools/testing/selftests/kvm/x86/hyperv_extended_hypercalls.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_features.c b/tools/testing/selftests/kvm/x86/hyperv_features.c index 068e9c69710d..068e9c69710d 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_features.c +++ b/tools/testing/selftests/kvm/x86/hyperv_features.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c b/tools/testing/selftests/kvm/x86/hyperv_ipi.c index 22c0c124582f..22c0c124582f 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_ipi.c +++ b/tools/testing/selftests/kvm/x86/hyperv_ipi.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c index 0ddb63229bcb..0ddb63229bcb 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86/hyperv_svm_test.c diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c index 077cd0ec3040..077cd0ec3040 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_tlb_flush.c +++ b/tools/testing/selftests/kvm/x86/hyperv_tlb_flush.c diff --git a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c b/tools/testing/selftests/kvm/x86/kvm_clock_test.c index 5bc12222d87a..5bc12222d87a 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_clock_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_clock_test.c diff --git a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c b/tools/testing/selftests/kvm/x86/kvm_pv_test.c index 78878b3a2725..1b805cbdb47b 100644 --- a/tools/testing/selftests/kvm/x86_64/kvm_pv_test.c +++ b/tools/testing/selftests/kvm/x86/kvm_pv_test.c @@ -139,10 +139,12 @@ static void test_pv_unhalt(void) struct kvm_vm *vm; struct kvm_cpuid_entry2 *ent; u32 kvm_sig_old; + int r; - pr_info("testing KVM_FEATURE_PV_UNHALT\n"); + if (!(kvm_check_cap(KVM_CAP_X86_DISABLE_EXITS) & KVM_X86_DISABLE_EXITS_HLT)) + return; - TEST_REQUIRE(KVM_CAP_X86_DISABLE_EXITS); + pr_info("testing KVM_FEATURE_PV_UNHALT\n"); /* KVM_PV_UNHALT test */ vm = vm_create_with_one_vcpu(&vcpu, guest_main); @@ -151,19 +153,45 @@ static void test_pv_unhalt(void) TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), "Enabling X86_FEATURE_KVM_PV_UNHALT had no effect"); - /* Make sure KVM clears vcpu->arch.kvm_cpuid */ + /* Verify KVM disallows disabling exits after vCPU creation. */ + r = __vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + TEST_ASSERT(r && errno == EINVAL, + "Disabling exits after vCPU creation didn't fail as expected"); + + kvm_vm_free(vm); + + /* Verify that KVM clear PV_UNHALT from guest CPUID. */ + vm = vm_create(1); + vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + + vcpu = vm_vcpu_add(vm, 0, NULL); + TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "vCPU created with PV_UNHALT set by default"); + + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); + TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "PV_UNHALT set in guest CPUID when HLT-exiting is disabled"); + + /* + * Clobber the KVM PV signature and verify KVM does NOT clear PV_UNHALT + * when KVM PV is not present, and DOES clear PV_UNHALT when switching + * back to the correct signature.. + */ ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); kvm_sig_old = ent->ebx; ent->ebx = 0xdeadbeef; vcpu_set_cpuid(vcpu); - vm_enable_cap(vm, KVM_CAP_X86_DISABLE_EXITS, KVM_X86_DISABLE_EXITS_HLT); + vcpu_set_cpuid_feature(vcpu, X86_FEATURE_KVM_PV_UNHALT); + TEST_ASSERT(vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), + "PV_UNHALT cleared when using bogus KVM PV signature"); + ent = vcpu_get_cpuid_entry(vcpu, KVM_CPUID_SIGNATURE); ent->ebx = kvm_sig_old; vcpu_set_cpuid(vcpu); TEST_ASSERT(!vcpu_cpuid_has(vcpu, X86_FEATURE_KVM_PV_UNHALT), - "KVM_FEATURE_PV_UNHALT is set with KVM_CAP_X86_DISABLE_EXITS"); + "PV_UNHALT set in guest CPUID when HLT-exiting is disabled"); /* FIXME: actually test KVM_FEATURE_PV_UNHALT feature */ diff --git a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c b/tools/testing/selftests/kvm/x86/max_vcpuid_cap_test.c index 7e2bfb3c3f3b..7e2bfb3c3f3b 100644 --- a/tools/testing/selftests/kvm/x86_64/max_vcpuid_cap_test.c +++ b/tools/testing/selftests/kvm/x86/max_vcpuid_cap_test.c diff --git a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c index 2b550eff35f1..2b550eff35f1 100644 --- a/tools/testing/selftests/kvm/x86_64/monitor_mwait_test.c +++ b/tools/testing/selftests/kvm/x86/monitor_mwait_test.c diff --git a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c index 3eb0313ffa39..3eb0313ffa39 100644 --- a/tools/testing/selftests/kvm/x86_64/nested_exceptions_test.c +++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c index e7efb2b35f8b..e7efb2b35f8b 100644 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.c diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.sh index caad084b8bfd..caad084b8bfd 100755 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh +++ b/tools/testing/selftests/kvm/x86/nx_huge_pages_test.sh diff --git a/tools/testing/selftests/kvm/x86_64/platform_info_test.c b/tools/testing/selftests/kvm/x86/platform_info_test.c index 9cbf283ebc55..9cbf283ebc55 100644 --- a/tools/testing/selftests/kvm/x86_64/platform_info_test.c +++ b/tools/testing/selftests/kvm/x86/platform_info_test.c diff --git a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c index 698cb36989db..698cb36989db 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c diff --git a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c index c15513cd74d1..c15513cd74d1 100644 --- a/tools/testing/selftests/kvm/x86_64/pmu_event_filter_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c index 82a8d88b5338..82a8d88b5338 100644 --- a/tools/testing/selftests/kvm/x86_64/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c diff --git a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c index 13e72fcec8dd..13e72fcec8dd 100644 --- a/tools/testing/selftests/kvm/x86_64/private_mem_kvm_exits_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c diff --git a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c b/tools/testing/selftests/kvm/x86/recalc_apic_map_test.c index cbc92a862ea9..cbc92a862ea9 100644 --- a/tools/testing/selftests/kvm/x86_64/recalc_apic_map_test.c +++ b/tools/testing/selftests/kvm/x86/recalc_apic_map_test.c diff --git a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c index 49913784bc82..49913784bc82 100644 --- a/tools/testing/selftests/kvm/x86_64/set_boot_cpu_id.c +++ b/tools/testing/selftests/kvm/x86/set_boot_cpu_id.c diff --git a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c b/tools/testing/selftests/kvm/x86/set_sregs_test.c index c021c0795a96..f4095a3d1278 100644 --- a/tools/testing/selftests/kvm/x86_64/set_sregs_test.c +++ b/tools/testing/selftests/kvm/x86/set_sregs_test.c @@ -41,13 +41,15 @@ do { \ TEST_ASSERT(!memcmp(&new, &orig, sizeof(new)), "KVM modified sregs"); \ } while (0) +#define KVM_ALWAYS_ALLOWED_CR4 (X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | \ + X86_CR4_DE | X86_CR4_PSE | X86_CR4_PAE | \ + X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | \ + X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT) + static uint64_t calc_supported_cr4_feature_bits(void) { - uint64_t cr4; + uint64_t cr4 = KVM_ALWAYS_ALLOWED_CR4; - cr4 = X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE | - X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE | X86_CR4_PGE | - X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT; if (kvm_cpu_has(X86_FEATURE_UMIP)) cr4 |= X86_CR4_UMIP; if (kvm_cpu_has(X86_FEATURE_LA57)) @@ -72,36 +74,31 @@ static uint64_t calc_supported_cr4_feature_bits(void) return cr4; } -int main(int argc, char *argv[]) +static void test_cr_bits(struct kvm_vcpu *vcpu, uint64_t cr4) { struct kvm_sregs sregs; - struct kvm_vcpu *vcpu; - struct kvm_vm *vm; - uint64_t cr4; int rc, i; - /* - * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and - * use it to verify all supported CR4 bits can be set prior to defining - * the vCPU model, i.e. without doing KVM_SET_CPUID2. - */ - vm = vm_create_barebones(); - vcpu = __vm_vcpu_add(vm, 0); - vcpu_sregs_get(vcpu, &sregs); - - sregs.cr0 = 0; - sregs.cr4 |= calc_supported_cr4_feature_bits(); - cr4 = sregs.cr4; - + sregs.cr0 &= ~(X86_CR0_CD | X86_CR0_NW); + sregs.cr4 |= cr4; rc = _vcpu_sregs_set(vcpu, &sregs); TEST_ASSERT(!rc, "Failed to set supported CR4 bits (0x%lx)", cr4); + TEST_ASSERT(!!(sregs.cr4 & X86_CR4_OSXSAVE) == + (vcpu->cpuid && vcpu_cpuid_has(vcpu, X86_FEATURE_OSXSAVE)), + "KVM didn't %s OSXSAVE in CPUID as expected", + (sregs.cr4 & X86_CR4_OSXSAVE) ? "set" : "clear"); + + TEST_ASSERT(!!(sregs.cr4 & X86_CR4_PKE) == + (vcpu->cpuid && vcpu_cpuid_has(vcpu, X86_FEATURE_OSPKE)), + "KVM didn't %s OSPKE in CPUID as expected", + (sregs.cr4 & X86_CR4_PKE) ? "set" : "clear"); + vcpu_sregs_get(vcpu, &sregs); TEST_ASSERT(sregs.cr4 == cr4, "sregs.CR4 (0x%llx) != CR4 (0x%lx)", sregs.cr4, cr4); - /* Verify all unsupported features are rejected by KVM. */ TEST_INVALID_CR_BIT(vcpu, cr4, sregs, X86_CR4_UMIP); TEST_INVALID_CR_BIT(vcpu, cr4, sregs, X86_CR4_LA57); TEST_INVALID_CR_BIT(vcpu, cr4, sregs, X86_CR4_VMXE); @@ -119,10 +116,28 @@ int main(int argc, char *argv[]) /* NW without CD is illegal, as is PG without PE. */ TEST_INVALID_CR_BIT(vcpu, cr0, sregs, X86_CR0_NW); TEST_INVALID_CR_BIT(vcpu, cr0, sregs, X86_CR0_PG); +} + +int main(int argc, char *argv[]) +{ + struct kvm_sregs sregs; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int rc; + /* + * Create a dummy VM, specifically to avoid doing KVM_SET_CPUID2, and + * use it to verify KVM enforces guest CPUID even if *userspace* never + * sets CPUID. + */ + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); + test_cr_bits(vcpu, KVM_ALWAYS_ALLOWED_CR4); kvm_vm_free(vm); - /* Create a "real" VM and verify APIC_BASE can be set. */ + /* Create a "real" VM with a fully populated guest CPUID and verify + * APIC_BASE and all supported CR4 can be set. + */ vm = vm_create_with_one_vcpu(&vcpu, NULL); vcpu_sregs_get(vcpu, &sregs); @@ -135,6 +150,8 @@ int main(int argc, char *argv[]) TEST_ASSERT(!rc, "Couldn't set IA32_APIC_BASE to %llx (valid)", sregs.apic_base); + test_cr_bits(vcpu, calc_supported_cr4_feature_bits()); + kvm_vm_free(vm); return 0; diff --git a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c b/tools/testing/selftests/kvm/x86/sev_init2_tests.c index 3fb967f40c6a..3fb967f40c6a 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_init2_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_init2_tests.c diff --git a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c index 0a6dfba3905b..0a6dfba3905b 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_migrate_tests.c +++ b/tools/testing/selftests/kvm/x86/sev_migrate_tests.c diff --git a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c index ae77698e6e97..a1a688e75266 100644 --- a/tools/testing/selftests/kvm/x86_64/sev_smoke_test.c +++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c @@ -155,7 +155,7 @@ static void guest_shutdown_code(void) /* Clobber the IDT so that #UD is guaranteed to trigger SHUTDOWN. */ memset(&idt, 0, sizeof(idt)); - __asm__ __volatile__("lidt %0" :: "m"(idt)); + set_idt(&idt); __asm__ __volatile__("ud2"); } diff --git a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c index fabeeaddfb3a..fabeeaddfb3a 100644 --- a/tools/testing/selftests/kvm/x86_64/smaller_maxphyaddr_emulation_test.c +++ b/tools/testing/selftests/kvm/x86/smaller_maxphyaddr_emulation_test.c diff --git a/tools/testing/selftests/kvm/x86_64/smm_test.c b/tools/testing/selftests/kvm/x86/smm_test.c index 55c88d664a94..55c88d664a94 100644 --- a/tools/testing/selftests/kvm/x86_64/smm_test.c +++ b/tools/testing/selftests/kvm/x86/smm_test.c diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86/state_test.c index 141b7fc0c965..141b7fc0c965 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86/state_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c index 916e04248fbb..916e04248fbb 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_int_ctl_test.c +++ b/tools/testing/selftests/kvm/x86/svm_int_ctl_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c index 00135cbba35e..00135cbba35e 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_shutdown_test.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_shutdown_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c index 7b6481d6c0d3..7b6481d6c0d3 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_nested_soft_inject_test.c +++ b/tools/testing/selftests/kvm/x86/svm_nested_soft_inject_test.c diff --git a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c index 8a62cca28cfb..8a62cca28cfb 100644 --- a/tools/testing/selftests/kvm/x86_64/svm_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86/svm_vmcall_test.c diff --git a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c b/tools/testing/selftests/kvm/x86/sync_regs_test.c index 8fa3948b0170..8fa3948b0170 100644 --- a/tools/testing/selftests/kvm/x86_64/sync_regs_test.c +++ b/tools/testing/selftests/kvm/x86/sync_regs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c index 56306a19144a..56306a19144a 100644 --- a/tools/testing/selftests/kvm/x86_64/triple_fault_event_test.c +++ b/tools/testing/selftests/kvm/x86/triple_fault_event_test.c diff --git a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c index 12b0964f4f13..12b0964f4f13 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/tsc_msrs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c index 59c7304f805e..59c7304f805e 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c +++ b/tools/testing/selftests/kvm/x86/tsc_scaling_sync.c diff --git a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c b/tools/testing/selftests/kvm/x86/ucna_injection_test.c index 57f157c06b39..57f157c06b39 100644 --- a/tools/testing/selftests/kvm/x86_64/ucna_injection_test.c +++ b/tools/testing/selftests/kvm/x86/ucna_injection_test.c diff --git a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c b/tools/testing/selftests/kvm/x86/userspace_io_test.c index 9481cbcf284f..9481cbcf284f 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_io_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_io_test.c diff --git a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c index 32b2794b78fe..32b2794b78fe 100644 --- a/tools/testing/selftests/kvm/x86_64/userspace_msr_exit_test.c +++ b/tools/testing/selftests/kvm/x86/userspace_msr_exit_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c index a81a24761aac..a81a24761aac 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_apic_access_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_apic_access_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c b/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c index dad988351493..dad988351493 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_close_while_nested_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c index fa512d033205..fa512d033205 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_dirty_log_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c index 3fd6eceab46f..3fd6eceab46f 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_exception_with_invalid_guest_state.c +++ b/tools/testing/selftests/kvm/x86/vmx_exception_with_invalid_guest_state.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c index a100ee5f0009..a100ee5f0009 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_invalid_nested_guest_state.c +++ b/tools/testing/selftests/kvm/x86/vmx_invalid_nested_guest_state.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c index 90720b6205f4..90720b6205f4 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_msrs_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_msrs_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c b/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c index 1759fa5cb3f2..1759fa5cb3f2 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_nested_tsc_scaling_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_nested_tsc_scaling_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c index a1f5ff45d518..a1f5ff45d518 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_pmu_caps_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_pmu_caps_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c index 00dd2ac07a61..00dd2ac07a61 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_preemption_timer_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_preemption_timer_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c b/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c index 67a62a5a8895..67a62a5a8895 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_set_nested_state_test.c diff --git a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c index 2ceb5c78c442..2ceb5c78c442 100644 --- a/tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c +++ b/tools/testing/selftests/kvm/x86/vmx_tsc_adjust_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c index a76078a08ff8..a76078a08ff8 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_ipi_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_ipi_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c b/tools/testing/selftests/kvm/x86/xapic_state_test.c index 88bcca188799..88bcca188799 100644 --- a/tools/testing/selftests/kvm/x86_64/xapic_state_test.c +++ b/tools/testing/selftests/kvm/x86/xapic_state_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c index c8a5c5e51661..c8a5c5e51661 100644 --- a/tools/testing/selftests/kvm/x86_64/xcr0_cpuid_test.c +++ b/tools/testing/selftests/kvm/x86/xcr0_cpuid_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c index a59b3c799bb2..a59b3c799bb2 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86/xen_shinfo_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86/xen_vmcall_test.c index 2585087cdf5c..2585087cdf5c 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c +++ b/tools/testing/selftests/kvm/x86/xen_vmcall_test.c diff --git a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c b/tools/testing/selftests/kvm/x86/xss_msr_test.c index f331a4e9bae3..f331a4e9bae3 100644 --- a/tools/testing/selftests/kvm/x86_64/xss_msr_test.c +++ b/tools/testing/selftests/kvm/x86/xss_msr_test.c diff --git a/tools/testing/selftests/landlock/.gitignore b/tools/testing/selftests/landlock/.gitignore index 470203a7cd73..335b2b1a3463 100644 --- a/tools/testing/selftests/landlock/.gitignore +++ b/tools/testing/selftests/landlock/.gitignore @@ -1,2 +1,4 @@ /*_test +/sandbox-and-launch /true +/wait-pipe diff --git a/tools/testing/selftests/landlock/Makefile b/tools/testing/selftests/landlock/Makefile index 348e2dbdb4e0..5cb0828f0514 100644 --- a/tools/testing/selftests/landlock/Makefile +++ b/tools/testing/selftests/landlock/Makefile @@ -10,14 +10,14 @@ src_test := $(wildcard *_test.c) TEST_GEN_PROGS := $(src_test:.c=) -TEST_GEN_PROGS_EXTENDED := true +TEST_GEN_PROGS_EXTENDED := true sandbox-and-launch wait-pipe # Short targets: -$(TEST_GEN_PROGS): LDLIBS += -lcap +$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static include ../lib.mk # Targets with $(OUTPUT)/ prefix: -$(TEST_GEN_PROGS): LDLIBS += -lcap +$(TEST_GEN_PROGS): LDLIBS += -lcap -lpthread $(TEST_GEN_PROGS_EXTENDED): LDFLAGS += -static diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h index 61056fa074bb..6064c9ac0532 100644 --- a/tools/testing/selftests/landlock/common.h +++ b/tools/testing/selftests/landlock/common.h @@ -9,17 +9,15 @@ #include <arpa/inet.h> #include <errno.h> -#include <linux/landlock.h> #include <linux/securebits.h> #include <sys/capability.h> #include <sys/socket.h> -#include <sys/syscall.h> -#include <sys/types.h> #include <sys/un.h> #include <sys/wait.h> #include <unistd.h> #include "../kselftest_harness.h" +#include "wrappers.h" #define TMP_DIR "tmp" @@ -30,33 +28,8 @@ /* TEST_F_FORK() should not be used for new tests. */ #define TEST_F_FORK(fixture_name, test_name) TEST_F(fixture_name, test_name) -#ifndef landlock_create_ruleset -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); -} -#endif - -#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) -{ - 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) -{ - return syscall(__NR_landlock_restrict_self, ruleset_fd, flags); -} -#endif +static const char bin_sandbox_and_launch[] = "./sandbox-and-launch"; +static const char bin_wait_pipe[] = "./wait-pipe"; static void _init_caps(struct __test_metadata *const _metadata, bool drop_all) { @@ -234,6 +207,7 @@ enforce_ruleset(struct __test_metadata *const _metadata, const int ruleset_fd) struct protocol_variant { int domain; int type; + int protocol; }; struct service_fixture { @@ -250,11 +224,6 @@ struct service_fixture { }; }; -static pid_t __maybe_unused sys_gettid(void) -{ - return syscall(__NR_gettid); -} - static void __maybe_unused set_unix_address(struct service_fixture *const srv, const unsigned short index) { diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config index 29af19c4e9f9..425de4c20271 100644 --- a/tools/testing/selftests/landlock/config +++ b/tools/testing/selftests/landlock/config @@ -1,8 +1,11 @@ +CONFIG_AF_UNIX_OOB=y CONFIG_CGROUPS=y CONFIG_CGROUP_SCHED=y CONFIG_INET=y CONFIG_IPV6=y CONFIG_KEYS=y +CONFIG_MPTCP=y +CONFIG_MPTCP_IPV6=y CONFIG_NET=y CONFIG_NET_NS=y CONFIG_OVERLAY_FS=y diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 6788762188fe..aa6f2c1cbec7 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -37,6 +37,10 @@ #include <linux/fs.h> #include <linux/mount.h> +/* Defines AT_EXECVE_CHECK without type conflicts. */ +#define _ASM_GENERIC_FCNTL_H +#include <linux/fcntl.h> + #include "common.h" #ifndef renameat2 @@ -55,11 +59,17 @@ int open_tree(int dfd, const char *filename, unsigned int flags) } #endif +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + #ifndef RENAME_EXCHANGE #define RENAME_EXCHANGE (1 << 1) #endif -#define BINARY_PATH "./true" +static const char bin_true[] = "./true"; /* Paths (sibling number and depth) */ static const char dir_s1d1[] = TMP_DIR "/s1d1"; @@ -85,6 +95,9 @@ static const char file1_s3d1[] = TMP_DIR "/s3d1/f1"; /* dir_s3d2 is a mount point. */ static const char dir_s3d2[] = TMP_DIR "/s3d1/s3d2"; static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3"; +static const char file1_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3/f1"; +static const char dir_s3d4[] = TMP_DIR "/s3d1/s3d2/s3d4"; +static const char file1_s3d4[] = TMP_DIR "/s3d1/s3d2/s3d4/f1"; /* * layout1 hierarchy: @@ -108,8 +121,11 @@ static const char dir_s3d3[] = TMP_DIR "/s3d1/s3d2/s3d3"; * │  └── f2 * └── s3d1 *   ├── f1 - * └── s3d2 - * └── s3d3 + * └── s3d2 [mount point] + *   ├── s3d3 + *   │ └── f1 + *   └── s3d4 + *   └── f1 */ static bool fgrep(FILE *const inf, const char *const str) @@ -358,7 +374,8 @@ static void create_layout1(struct __test_metadata *const _metadata) ASSERT_EQ(0, mount_opt(&mnt_tmp, dir_s3d2)); clear_cap(_metadata, CAP_SYS_ADMIN); - ASSERT_EQ(0, mkdir(dir_s3d3, 0700)); + create_file(_metadata, file1_s3d3); + create_file(_metadata, file1_s3d4); } static void remove_layout1(struct __test_metadata *const _metadata) @@ -378,7 +395,8 @@ static void remove_layout1(struct __test_metadata *const _metadata) EXPECT_EQ(0, remove_path(dir_s2d2)); EXPECT_EQ(0, remove_path(file1_s3d1)); - EXPECT_EQ(0, remove_path(dir_s3d3)); + EXPECT_EQ(0, remove_path(file1_s3d3)); + EXPECT_EQ(0, remove_path(file1_s3d4)); set_cap(_metadata, CAP_SYS_ADMIN); umount(dir_s3d2); clear_cap(_metadata, CAP_SYS_ADMIN); @@ -1957,8 +1975,8 @@ TEST_F_FORK(layout1, relative_chroot_chdir) test_relative_path(_metadata, REL_CHROOT_CHDIR); } -static void copy_binary(struct __test_metadata *const _metadata, - const char *const dst_path) +static void copy_file(struct __test_metadata *const _metadata, + const char *const src_path, const char *const dst_path) { int dst_fd, src_fd; struct stat statbuf; @@ -1968,11 +1986,10 @@ static void copy_binary(struct __test_metadata *const _metadata, { TH_LOG("Failed to open \"%s\": %s", dst_path, strerror(errno)); } - src_fd = open(BINARY_PATH, O_RDONLY | O_CLOEXEC); + src_fd = open(src_path, O_RDONLY | O_CLOEXEC); ASSERT_LE(0, src_fd) { - TH_LOG("Failed to open \"" BINARY_PATH "\": %s", - strerror(errno)); + TH_LOG("Failed to open \"%s\": %s", src_path, strerror(errno)); } ASSERT_EQ(0, fstat(src_fd, &statbuf)); ASSERT_EQ(statbuf.st_size, @@ -2003,11 +2020,26 @@ static void test_execute(struct __test_metadata *const _metadata, const int err, ASSERT_EQ(1, WIFEXITED(status)); ASSERT_EQ(err ? 2 : 0, WEXITSTATUS(status)) { - TH_LOG("Unexpected return code for \"%s\": %s", path, - strerror(errno)); + TH_LOG("Unexpected return code for \"%s\"", path); }; } +static void test_check_exec(struct __test_metadata *const _metadata, + const int err, const char *const path) +{ + int ret; + char *const argv[] = { (char *)path, NULL }; + + ret = sys_execveat(AT_FDCWD, path, argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); + if (err) { + EXPECT_EQ(-1, ret); + EXPECT_EQ(errno, err); + } else { + EXPECT_EQ(0, ret); + } +} + TEST_F_FORK(layout1, execute) { const struct rule rules[] = { @@ -2021,9 +2053,13 @@ TEST_F_FORK(layout1, execute) create_ruleset(_metadata, rules[0].access, rules); ASSERT_LE(0, ruleset_fd); - copy_binary(_metadata, file1_s1d1); - copy_binary(_metadata, file1_s1d2); - copy_binary(_metadata, file1_s1d3); + copy_file(_metadata, bin_true, file1_s1d1); + copy_file(_metadata, bin_true, file1_s1d2); + copy_file(_metadata, bin_true, file1_s1d3); + + /* Checks before file1_s1d1 being denied. */ + test_execute(_metadata, 0, file1_s1d1); + test_check_exec(_metadata, 0, file1_s1d1); enforce_ruleset(_metadata, ruleset_fd); ASSERT_EQ(0, close(ruleset_fd)); @@ -2031,14 +2067,94 @@ TEST_F_FORK(layout1, execute) ASSERT_EQ(0, test_open(dir_s1d1, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d1, O_RDONLY)); test_execute(_metadata, EACCES, file1_s1d1); + test_check_exec(_metadata, EACCES, file1_s1d1); ASSERT_EQ(0, test_open(dir_s1d2, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d2, O_RDONLY)); test_execute(_metadata, 0, file1_s1d2); + test_check_exec(_metadata, 0, file1_s1d2); ASSERT_EQ(0, test_open(dir_s1d3, O_RDONLY)); ASSERT_EQ(0, test_open(file1_s1d3, O_RDONLY)); test_execute(_metadata, 0, file1_s1d3); + test_check_exec(_metadata, 0, file1_s1d3); +} + +TEST_F_FORK(layout1, umount_sandboxer) +{ + int pipe_child[2], pipe_parent[2]; + char buf_parent; + pid_t child; + int status; + + copy_file(_metadata, bin_sandbox_and_launch, file1_s3d3); + ASSERT_EQ(0, pipe2(pipe_child, 0)); + ASSERT_EQ(0, pipe2(pipe_parent, 0)); + + child = fork(); + ASSERT_LE(0, child); + if (child == 0) { + char pipe_child_str[12], pipe_parent_str[12]; + char *const argv[] = { (char *)file1_s3d3, + (char *)bin_wait_pipe, pipe_child_str, + pipe_parent_str, NULL }; + + /* Passes the pipe FDs to the executed binary and its child. */ + EXPECT_EQ(0, close(pipe_child[0])); + EXPECT_EQ(0, close(pipe_parent[1])); + snprintf(pipe_child_str, sizeof(pipe_child_str), "%d", + pipe_child[1]); + snprintf(pipe_parent_str, sizeof(pipe_parent_str), "%d", + pipe_parent[0]); + + /* + * We need bin_sandbox_and_launch (copied inside the mount as + * file1_s3d3) to execute bin_wait_pipe (outside the mount) to + * make sure the mount point will not be EBUSY because of + * file1_s3d3 being in use. This avoids a potential race + * condition between the following read() and umount() calls. + */ + ASSERT_EQ(0, execve(argv[0], argv, NULL)) + { + TH_LOG("Failed to execute \"%s\": %s", argv[0], + strerror(errno)); + }; + _exit(1); + return; + } + + EXPECT_EQ(0, close(pipe_child[1])); + EXPECT_EQ(0, close(pipe_parent[0])); + + /* Waits for the child to sandbox itself. */ + EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1)); + + /* Tests that the sandboxer is tied to its mount point. */ + set_cap(_metadata, CAP_SYS_ADMIN); + EXPECT_EQ(-1, umount(dir_s3d2)); + EXPECT_EQ(EBUSY, errno); + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Signals the child to launch a grandchild. */ + EXPECT_EQ(1, write(pipe_parent[1], ".", 1)); + + /* Waits for the grandchild. */ + EXPECT_EQ(1, read(pipe_child[0], &buf_parent, 1)); + + /* Tests that the domain's sandboxer is not tied to its mount point. */ + set_cap(_metadata, CAP_SYS_ADMIN); + EXPECT_EQ(0, umount(dir_s3d2)) + { + TH_LOG("Failed to umount \"%s\": %s", dir_s3d2, + strerror(errno)); + }; + clear_cap(_metadata, CAP_SYS_ADMIN); + + /* Signals the grandchild to terminate. */ + EXPECT_EQ(1, write(pipe_parent[1], ".", 1)); + ASSERT_EQ(child, waitpid(child, &status, 0)); + ASSERT_EQ(1, WIFEXITED(status)); + ASSERT_EQ(0, WEXITSTATUS(status)); } TEST_F_FORK(layout1, link) @@ -2444,6 +2560,44 @@ TEST_F_FORK(layout1, refer_mount_root_deny) EXPECT_EQ(0, close(root_fd)); } +TEST_F_FORK(layout1, refer_part_mount_tree_is_allowed) +{ + const struct rule layer1[] = { + { + /* Parent mount point. */ + .path = dir_s3d1, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_MAKE_REG, + }, + { + /* + * Removing the source file is allowed because its + * access rights are already a superset of the + * destination. + */ + .path = dir_s3d4, + .access = LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_MAKE_REG | + LANDLOCK_ACCESS_FS_REMOVE_FILE, + }, + {}, + }; + int ruleset_fd; + + ASSERT_EQ(0, unlink(file1_s3d3)); + ruleset_fd = create_ruleset(_metadata, + LANDLOCK_ACCESS_FS_REFER | + LANDLOCK_ACCESS_FS_MAKE_REG | + LANDLOCK_ACCESS_FS_REMOVE_FILE, + layer1); + + ASSERT_LE(0, ruleset_fd); + enforce_ruleset(_metadata, ruleset_fd); + ASSERT_EQ(0, close(ruleset_fd)); + + ASSERT_EQ(0, rename(file1_s3d4, file1_s3d3)); +} + TEST_F_FORK(layout1, reparent_link) { const struct rule layer1[] = { diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c index 4e0aeb53b225..d9de0ee49ebc 100644 --- a/tools/testing/selftests/landlock/net_test.c +++ b/tools/testing/selftests/landlock/net_test.c @@ -85,18 +85,18 @@ static void setup_loopback(struct __test_metadata *const _metadata) clear_ambient_cap(_metadata, CAP_NET_ADMIN); } +static bool prot_is_tcp(const struct protocol_variant *const prot) +{ + return (prot->domain == AF_INET || prot->domain == AF_INET6) && + prot->type == SOCK_STREAM && + (prot->protocol == IPPROTO_TCP || prot->protocol == IPPROTO_IP); +} + static bool is_restricted(const struct protocol_variant *const prot, const enum sandbox_type sandbox) { - switch (prot->domain) { - case AF_INET: - case AF_INET6: - switch (prot->type) { - case SOCK_STREAM: - return sandbox == TCP_SANDBOX; - } - break; - } + if (sandbox == TCP_SANDBOX) + return prot_is_tcp(prot); return false; } @@ -105,7 +105,7 @@ static int socket_variant(const struct service_fixture *const srv) int ret; ret = socket(srv->protocol.domain, srv->protocol.type | SOCK_CLOEXEC, - 0); + srv->protocol.protocol); if (ret < 0) return -errno; return ret; @@ -290,22 +290,70 @@ FIXTURE_TEARDOWN(protocol) } /* clang-format off */ -FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp) { +FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp1) { /* clang-format on */ .sandbox = NO_SANDBOX, .prot = { .domain = AF_INET, .type = SOCK_STREAM, + /* IPPROTO_IP == 0 */ + .protocol = IPPROTO_IP, }, }; /* clang-format off */ -FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp) { +FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp2) { + /* clang-format on */ + .sandbox = NO_SANDBOX, + .prot = { + .domain = AF_INET, + .type = SOCK_STREAM, + .protocol = IPPROTO_TCP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_mptcp) { + /* clang-format on */ + .sandbox = NO_SANDBOX, + .prot = { + .domain = AF_INET, + .type = SOCK_STREAM, + .protocol = IPPROTO_MPTCP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp1) { + /* clang-format on */ + .sandbox = NO_SANDBOX, + .prot = { + .domain = AF_INET6, + .type = SOCK_STREAM, + /* IPPROTO_IP == 0 */ + .protocol = IPPROTO_IP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp2) { /* clang-format on */ .sandbox = NO_SANDBOX, .prot = { .domain = AF_INET6, .type = SOCK_STREAM, + .protocol = IPPROTO_TCP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_mptcp) { + /* clang-format on */ + .sandbox = NO_SANDBOX, + .prot = { + .domain = AF_INET6, + .type = SOCK_STREAM, + .protocol = IPPROTO_MPTCP, }, }; @@ -350,22 +398,70 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_unix_datagram) { }; /* clang-format off */ -FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp) { +FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp1) { + /* clang-format on */ + .sandbox = TCP_SANDBOX, + .prot = { + .domain = AF_INET, + .type = SOCK_STREAM, + /* IPPROTO_IP == 0 */ + .protocol = IPPROTO_IP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp2) { + /* clang-format on */ + .sandbox = TCP_SANDBOX, + .prot = { + .domain = AF_INET, + .type = SOCK_STREAM, + .protocol = IPPROTO_TCP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_mptcp) { /* clang-format on */ .sandbox = TCP_SANDBOX, .prot = { .domain = AF_INET, .type = SOCK_STREAM, + .protocol = IPPROTO_MPTCP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp1) { + /* clang-format on */ + .sandbox = TCP_SANDBOX, + .prot = { + .domain = AF_INET6, + .type = SOCK_STREAM, + /* IPPROTO_IP == 0 */ + .protocol = IPPROTO_IP, + }, +}; + +/* clang-format off */ +FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp2) { + /* clang-format on */ + .sandbox = TCP_SANDBOX, + .prot = { + .domain = AF_INET6, + .type = SOCK_STREAM, + .protocol = IPPROTO_TCP, }, }; /* clang-format off */ -FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp) { +FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_mptcp) { /* clang-format on */ .sandbox = TCP_SANDBOX, .prot = { .domain = AF_INET6, .type = SOCK_STREAM, + .protocol = IPPROTO_MPTCP, }, }; diff --git a/tools/testing/selftests/landlock/ptrace_test.c b/tools/testing/selftests/landlock/ptrace_test.c index a19db4d0b3bd..8f31b673ff2d 100644 --- a/tools/testing/selftests/landlock/ptrace_test.c +++ b/tools/testing/selftests/landlock/ptrace_test.c @@ -22,8 +22,6 @@ /* Copied from security/yama/yama_lsm.c */ #define YAMA_SCOPE_DISABLED 0 #define YAMA_SCOPE_RELATIONAL 1 -#define YAMA_SCOPE_CAPABILITY 2 -#define YAMA_SCOPE_NO_ATTACH 3 static void create_domain(struct __test_metadata *const _metadata) { diff --git a/tools/testing/selftests/landlock/sandbox-and-launch.c b/tools/testing/selftests/landlock/sandbox-and-launch.c new file mode 100644 index 000000000000..3e32e1a51ac5 --- /dev/null +++ b/tools/testing/selftests/landlock/sandbox-and-launch.c @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sandbox itself and execute another program (in a different mount point). + * + * Used by layout1.umount_sandboxer from fs_test.c + * + * Copyright © 2024-2025 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include <errno.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/prctl.h> +#include <unistd.h> + +#include "wrappers.h" + +int main(int argc, char *argv[]) +{ + struct landlock_ruleset_attr ruleset_attr = { + .scoped = LANDLOCK_SCOPE_SIGNAL, + }; + int pipe_child, pipe_parent, ruleset_fd; + char buf; + + /* + * The first argument must be the file descriptor number of a pipe. + * The second argument must be the program to execute. + */ + if (argc != 4) { + fprintf(stderr, "Wrong number of arguments (not three)\n"); + return 1; + } + + pipe_child = atoi(argv[2]); + pipe_parent = atoi(argv[3]); + + ruleset_fd = + landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0); + if (ruleset_fd < 0) { + perror("Failed to create ruleset"); + return 1; + } + + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0)) { + perror("Failed to call prctl()"); + return 1; + } + + if (landlock_restrict_self(ruleset_fd, 0)) { + perror("Failed to restrict self"); + return 1; + } + + if (close(ruleset_fd)) { + perror("Failed to close ruleset"); + return 1; + } + + /* Signals that we are sandboxed. */ + errno = 0; + if (write(pipe_child, ".", 1) != 1) { + perror("Failed to write to the second argument"); + return 1; + } + + /* Waits for the parent to try to umount. */ + if (read(pipe_parent, &buf, 1) != 1) { + perror("Failed to write to the third argument"); + return 1; + } + + /* Shifts arguments. */ + argv[0] = argv[1]; + argv[1] = argv[2]; + argv[2] = argv[3]; + argv[3] = NULL; + execve(argv[0], argv, NULL); + perror("Failed to execute the provided binary"); + return 1; +} diff --git a/tools/testing/selftests/landlock/wait-pipe.c b/tools/testing/selftests/landlock/wait-pipe.c new file mode 100644 index 000000000000..0dbcd260a0fa --- /dev/null +++ b/tools/testing/selftests/landlock/wait-pipe.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Write in a pipe and wait. + * + * Used by layout1.umount_sandboxer from fs_test.c + * + * Copyright © 2024-2025 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> + +int main(int argc, char *argv[]) +{ + int pipe_child, pipe_parent; + char buf; + + /* The first argument must be the file descriptor number of a pipe. */ + if (argc != 3) { + fprintf(stderr, "Wrong number of arguments (not two)\n"); + return 1; + } + + pipe_child = atoi(argv[1]); + pipe_parent = atoi(argv[2]); + + /* Signals that we are waiting. */ + if (write(pipe_child, ".", 1) != 1) { + perror("Failed to write to first argument"); + return 1; + } + + /* Waits for the parent do its test. */ + if (read(pipe_parent, &buf, 1) != 1) { + perror("Failed to write to the second argument"); + return 1; + } + + return 0; +} diff --git a/tools/testing/selftests/landlock/wrappers.h b/tools/testing/selftests/landlock/wrappers.h new file mode 100644 index 000000000000..65548323e45d --- /dev/null +++ b/tools/testing/selftests/landlock/wrappers.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Syscall wrappers + * + * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> + * Copyright © 2019-2020 ANSSI + * Copyright © 2021-2025 Microsoft Corporation + */ + +#define _GNU_SOURCE +#include <linux/landlock.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef landlock_create_ruleset +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); +} +#endif + +#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) +{ + 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) +{ + return syscall(__NR_landlock_restrict_self, ruleset_fd, flags); +} +#endif + +static inline pid_t sys_gettid(void) +{ + return syscall(__NR_gettid); +} diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index e5d06fb40233..15601402dee6 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -306,7 +306,8 @@ function check_result { result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \ grep -e 'livepatch:' -e 'test_klp' | \ grep -v '\(tainting\|taints\) kernel' | \ - sed 's/^\[[ 0-9.]*\] //') + sed 's/^\[[ 0-9.]*\] //' | \ + sed 's/^\[[ ]*[CT][0-9]*\] //') if [[ "$expect" == "$result" ]] ; then echo "ok" diff --git a/tools/testing/selftests/media_tests/regression_test.txt b/tools/testing/selftests/media_tests/regression_test.txt index 2627367681f7..9d0fcd98c085 100644 --- a/tools/testing/selftests/media_tests/regression_test.txt +++ b/tools/testing/selftests/media_tests/regression_test.txt @@ -1,5 +1,5 @@ Testing for regressions in Media Controller API register, ioctl, syscall, -and unregister paths. There have a few problems that result in user-after +and unregister paths. There have a few problems that result in use-after free on media_device, media_devnode, and cdev pointers when the driver is unbound while ioctl is in progress. @@ -15,11 +15,11 @@ Build media_device_test cd tools/testing/selftests/media_tests make -Regressions test for cdev user-after free error on /dev/mediaX when driver +Regressions test for cdev use-after-free error on /dev/mediaX when driver is unbound: Start media_device_test to regression test media devnode dynamic alloc -and cdev user-after-free fixes. This opens media dev files and sits in +and cdev use-after-free fixes. This opens media dev files and sits in a loop running media ioctl MEDIA_IOC_DEVICE_INFO command once every 10 seconds. The idea is when device file goes away, media devnode and cdev should stick around until this test exits. @@ -40,4 +40,4 @@ keep ioctls going while bind/unbind runs. Copy bind_unbind_sample.txt and make changes to specify the driver name and number to run bind and unbind. Start the bind_unbind.sh -Run dmesg looking for any user-after free errors or mutex lock errors. +Run dmesg looking for any use-after-free errors or mutex lock errors. diff --git a/tools/testing/selftests/memfd/memfd_test.c b/tools/testing/selftests/memfd/memfd_test.c index c0c53451a16d..5b993924cc3f 100644 --- a/tools/testing/selftests/memfd/memfd_test.c +++ b/tools/testing/selftests/memfd/memfd_test.c @@ -171,7 +171,7 @@ static void mfd_fail_new(const char *name, unsigned int flags) r = sys_memfd_create(name, flags); if (r >= 0) { printf("memfd_create(\"%s\", %u) succeeded, but failure expected\n", - name, flags); + name ? name : "NULL", flags); close(r); abort(); } diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8f01f4da1c0d..121000c28c10 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -27,6 +27,7 @@ protection_keys_64 madv_populate uffd-stress uffd-unit-tests +uffd-wp-mremap mlock-intersect-test mlock-random-test virtual_address_range @@ -36,6 +37,9 @@ map_fixed_noreplace write_to_hugetlbfs hmm-tests memfd_secret +hugetlb_dio +pkey_sighandler_tests_32 +pkey_sighandler_tests_64 soft-dirty split_huge_page_test ksm_tests @@ -49,7 +53,6 @@ va_high_addr_switch hugetlb_fault_after_madv hugetlb_madv_vs_map mseal_test -seal_elf droppable hugetlb_dio pkey_sighandler_tests_32 diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 3de23ea4663f..63ce39d024bb 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -33,9 +33,16 @@ endif # LDLIBS. MAKEFLAGS += --no-builtin-rules -CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) +CFLAGS = -Wall -O2 -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +# Some distributions (such as Ubuntu) configure GCC so that _FORTIFY_SOURCE is +# automatically enabled at -O1 or above. This triggers various unused-result +# warnings where functions such as read() or write() are called and their +# return value is not checked. Disable _FORTIFY_SOURCE to silence those +# warnings. +CFLAGS += -U_FORTIFY_SOURCE + KDIR ?= /lib/modules/$(shell uname -r)/build ifneq (,$(wildcard $(KDIR)/Module.symvers)) ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) @@ -75,13 +82,13 @@ TEST_GEN_FILES += mrelease_test TEST_GEN_FILES += mremap_dontunmap TEST_GEN_FILES += mremap_test TEST_GEN_FILES += mseal_test -TEST_GEN_FILES += seal_elf TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress TEST_GEN_FILES += uffd-unit-tests +TEST_GEN_FILES += uffd-wp-mremap TEST_GEN_FILES += split_huge_page_test TEST_GEN_FILES += ksm_tests TEST_GEN_FILES += ksm_functional_tests @@ -152,11 +159,16 @@ $(TEST_GEN_FILES): vm_util.c thp_settings.c $(OUTPUT)/uffd-stress: uffd-common.c $(OUTPUT)/uffd-unit-tests: uffd-common.c +$(OUTPUT)/uffd-wp-mremap: uffd-common.c +$(OUTPUT)/protection_keys: pkey_util.c +$(OUTPUT)/pkey_sighandler_tests: pkey_util.c ifeq ($(ARCH),x86_64) BINARIES_32 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_32)) BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64)) +$(BINARIES_32) $(BINARIES_64): pkey_util.c + define gen-target-rule-32 $(1) $(1)_32: $(OUTPUT)/$(1)_32 .PHONY: $(1) $(1)_32 diff --git a/tools/testing/selftests/mm/config b/tools/testing/selftests/mm/config index 4309916f629e..a28baa536332 100644 --- a/tools/testing/selftests/mm/config +++ b/tools/testing/selftests/mm/config @@ -7,3 +7,4 @@ CONFIG_TEST_HMM=m CONFIG_GUP_TEST=y CONFIG_TRANSPARENT_HUGEPAGE=y CONFIG_MEM_SOFT_DIRTY=y +CONFIG_ANON_VMA_NAME=y diff --git a/tools/testing/selftests/mm/cow.c b/tools/testing/selftests/mm/cow.c index 1238e1c5aae1..9446673645eb 100644 --- a/tools/testing/selftests/mm/cow.c +++ b/tools/testing/selftests/mm/cow.c @@ -1482,7 +1482,7 @@ static void run_with_zeropage(non_anon_test_fn fn, const char *desc) } smem = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANON, -1, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1583,7 +1583,7 @@ static void run_with_memfd(non_anon_test_fn fn, const char *desc) goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1634,7 +1634,7 @@ static void run_with_tmpfile(non_anon_test_fn fn, const char *desc) goto close; } smem = mmap(NULL, pagesize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1684,7 +1684,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, goto close; } smem = mmap(NULL, hugetlbsize, PROT_READ, MAP_SHARED, fd, 0); - if (mem == MAP_FAILED) { + if (smem == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); goto munmap; } @@ -1696,7 +1696,7 @@ static void run_with_memfd_hugetlb(non_anon_test_fn fn, const char *desc, fn(mem, smem, hugetlbsize); munmap: munmap(mem, hugetlbsize); - if (mem != MAP_FAILED) + if (smem != MAP_FAILED) munmap(smem, hugetlbsize); close: close(fd); diff --git a/tools/testing/selftests/mm/guard-pages.c b/tools/testing/selftests/mm/guard-pages.c index 7cdf815d0d63..ece37212a8a2 100644 --- a/tools/testing/selftests/mm/guard-pages.c +++ b/tools/testing/selftests/mm/guard-pages.c @@ -55,6 +55,12 @@ static int pidfd_open(pid_t pid, unsigned int flags) return syscall(SYS_pidfd_open, pid, flags); } +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t n, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, n, advice, flags); +} + /* * Enable our signal catcher and try to read/write the specified buffer. The * return value indicates whether the read/write succeeds without a fatal @@ -419,7 +425,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_EQ(munmap(&ptr_region[99 * page_size], page_size), 0); /* Now guard in one step. */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_INSTALL, 0); /* OK we don't have permission to do this, skip. */ if (count == -1 && errno == EPERM) @@ -440,7 +446,7 @@ TEST_F(guard_pages, process_madvise) ASSERT_FALSE(try_read_write_buf(&ptr3[19 * page_size])); /* Now do the same with unguard... */ - count = process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); + count = sys_process_madvise(pidfd, vec, 6, MADV_GUARD_REMOVE, 0); /* ...and everything should now succeed. */ @@ -990,7 +996,7 @@ TEST_F(guard_pages, fork) MAP_ANON | MAP_PRIVATE, -1, 0); ASSERT_NE(ptr, MAP_FAILED); - /* Establish guard apges in the first 5 pages. */ + /* Establish guard pages in the first 5 pages. */ ASSERT_EQ(madvise(ptr, 5 * page_size, MADV_GUARD_INSTALL), 0); pid = fork(); @@ -1030,6 +1036,77 @@ TEST_F(guard_pages, fork) } /* + * Assert expected behaviour after we fork populated ranges of anonymous memory + * and then guard and unguard the range. + */ +TEST_F(guard_pages, fork_cow) +{ + const unsigned long page_size = self->page_size; + char *ptr; + pid_t pid; + int i; + + /* Map 10 pages. */ + ptr = mmap(NULL, 10 * page_size, PROT_READ | PROT_WRITE, + MAP_ANON | MAP_PRIVATE, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + /* Populate range. */ + for (i = 0; i < 10 * page_size; i++) { + char chr = 'a' + (i % 26); + + ptr[i] = chr; + } + + pid = fork(); + ASSERT_NE(pid, -1); + if (!pid) { + /* This is the child process now. */ + + /* Ensure the range is as expected. */ + for (i = 0; i < 10 * page_size; i++) { + char expected = 'a' + (i % 26); + char actual = ptr[i]; + + ASSERT_EQ(actual, expected); + } + + /* Establish guard pages across the whole range. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_INSTALL), 0); + /* Remove it. */ + ASSERT_EQ(madvise(ptr, 10 * page_size, MADV_GUARD_REMOVE), 0); + + /* + * By removing the guard pages, the page tables will be + * cleared. Assert that we are looking at the zero page now. + */ + for (i = 0; i < 10 * page_size; i++) { + char actual = ptr[i]; + + ASSERT_EQ(actual, '\0'); + } + + exit(0); + } + + /* Parent process. */ + + /* Parent simply waits on child. */ + waitpid(pid, NULL, 0); + + /* Ensure the range is unchanged in parent anon range. */ + for (i = 0; i < 10 * page_size; i++) { + char expected = 'a' + (i % 26); + char actual = ptr[i]; + + ASSERT_EQ(actual, expected); + } + + /* Cleanup. */ + ASSERT_EQ(munmap(ptr, 10 * page_size), 0); +} + +/* * Assert that forking a process with VMAs that do have VM_WIPEONFORK set * behave as expected. */ diff --git a/tools/testing/selftests/mm/ksm_tests.c b/tools/testing/selftests/mm/ksm_tests.c index b748c48908d9..dcdd5bb20f3d 100644 --- a/tools/testing/selftests/mm/ksm_tests.c +++ b/tools/testing/selftests/mm/ksm_tests.c @@ -776,7 +776,7 @@ err_out: int main(int argc, char *argv[]) { - int ret, opt; + int ret = 0, opt; int prot = 0; int ksm_scan_limit_sec = KSM_SCAN_LIMIT_SEC_DEFAULT; int merge_type = KSM_MERGE_TYPE_DEFAULT; diff --git a/tools/testing/selftests/mm/migration.c b/tools/testing/selftests/mm/migration.c index 64bcbb7151cf..1e3a595fbf01 100644 --- a/tools/testing/selftests/mm/migration.c +++ b/tools/testing/selftests/mm/migration.c @@ -204,4 +204,103 @@ TEST_F_TIMEOUT(migration, private_anon_thp, 2*RUNTIME) ASSERT_EQ(pthread_cancel(self->threads[i]), 0); } +/* + * migration test with shared anon THP page + */ + +TEST_F_TIMEOUT(migration, shared_anon_thp, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, 2 * TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + ptr = (uint64_t *) ALIGN((uintptr_t) ptr, TWOMEG); + ASSERT_EQ(madvise(ptr, TWOMEG, MADV_HUGEPAGE), 0); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); + access_mem(ptr); + } else { + self->pids[i] = pid; + } + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + +/* + * migration test with private anon hugetlb page + */ +TEST_F_TIMEOUT(migration, private_anon_htlb, 2*RUNTIME) +{ + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) + if (pthread_create(&self->threads[i], NULL, access_mem, ptr)) + perror("Couldn't create thread"); + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(pthread_cancel(self->threads[i]), 0); +} + +/* + * migration test with shared anon hugetlb page + */ +TEST_F_TIMEOUT(migration, shared_anon_htlb, 2*RUNTIME) +{ + pid_t pid; + uint64_t *ptr; + int i; + + if (self->nthreads < 2 || self->n1 < 0 || self->n2 < 0) + SKIP(return, "Not enough threads or NUMA nodes available"); + + ptr = mmap(NULL, TWOMEG, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); + ASSERT_NE(ptr, MAP_FAILED); + + memset(ptr, 0xde, TWOMEG); + for (i = 0; i < self->nthreads - 1; i++) { + pid = fork(); + if (!pid) { + prctl(PR_SET_PDEATHSIG, SIGHUP); + /* Parent may have died before prctl so check now. */ + if (getppid() == 1) + kill(getpid(), SIGHUP); + access_mem(ptr); + } else { + self->pids[i] = pid; + } + } + + ASSERT_EQ(migrate(ptr, self->n1, self->n2), 0); + for (i = 0; i < self->nthreads - 1; i++) + ASSERT_EQ(kill(self->pids[i], SIGTERM), 0); +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index 1db134063c38..af2fce496912 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -280,6 +280,7 @@ static void test_uffdio_copy(void) dst = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE|MAP_ANON, -1, 0); if (dst == MAP_FAILED) { ksft_test_result_fail("mmap() failed\n"); + free(src); return; } diff --git a/tools/testing/selftests/mm/mremap_test.c b/tools/testing/selftests/mm/mremap_test.c index 5a3a9bcba640..bb84476a177f 100644 --- a/tools/testing/selftests/mm/mremap_test.c +++ b/tools/testing/selftests/mm/mremap_test.c @@ -34,7 +34,7 @@ struct config { unsigned long long dest_alignment; unsigned long long region_size; int overlapping; - int dest_preamble_size; + unsigned int dest_preamble_size; }; struct test { @@ -328,7 +328,7 @@ static void mremap_move_within_range(unsigned int pattern_seed, char *rand_addr) { char *test_name = "mremap mremap move within range"; void *src, *dest; - int i, success = 1; + unsigned int i, success = 1; size_t size = SIZE_MB(20); void *ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, @@ -384,7 +384,7 @@ out: static long long remap_region(struct config c, unsigned int threshold_mb, char *rand_addr) { - void *addr, *src_addr, *dest_addr, *dest_preamble_addr; + void *addr, *src_addr, *dest_addr, *dest_preamble_addr = NULL; unsigned long long t, d; struct timespec t_start = {0, 0}, t_end = {0, 0}; long long start_ns, end_ns, align_mask, ret, offset; @@ -569,7 +569,7 @@ static void mremap_move_1mb_from_start(unsigned int pattern_seed, { char *test_name = "mremap move 1mb from start at 1MB+256KB aligned src"; void *src = NULL, *dest = NULL; - int i, success = 1; + unsigned int i, success = 1; /* Config to reuse get_source_mapping() to do an aligned mmap. */ struct config c = { @@ -636,7 +636,7 @@ out: static void run_mremap_test_case(struct test test_case, int *failures, unsigned int threshold_mb, - unsigned int pattern_seed, char *rand_addr) + char *rand_addr) { long long remap_time = remap_region(test_case.config, threshold_mb, rand_addr); @@ -708,7 +708,8 @@ static int parse_args(int argc, char **argv, unsigned int *threshold_mb, int main(int argc, char **argv) { int failures = 0; - int i, run_perf_tests; + unsigned int i; + int run_perf_tests; unsigned int threshold_mb = VALIDATION_DEFAULT_THRESHOLD; /* hard-coded test configs */ @@ -831,7 +832,7 @@ int main(int argc, char **argv) for (i = 0; i < ARRAY_SIZE(test_cases); i++) run_mremap_test_case(test_cases[i], &failures, threshold_mb, - pattern_seed, rand_addr); + rand_addr); maps_fp = fopen("/proc/self/maps", "r"); @@ -853,7 +854,7 @@ int main(int argc, char **argv) "mremap HAVE_MOVE_PMD/PUD optimization time comparison for 1GB region:"); for (i = 0; i < ARRAY_SIZE(perf_test_cases); i++) run_mremap_test_case(perf_test_cases[i], &failures, - threshold_mb, pattern_seed, + threshold_mb, rand_addr); } diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c index 01675c412b2a..ad17005521a8 100644 --- a/tools/testing/selftests/mm/mseal_test.c +++ b/tools/testing/selftests/mm/mseal_test.c @@ -802,7 +802,7 @@ static void test_seal_mprotect_partial_mprotect_tail(bool seal) } -static void test_seal_mprotect_two_vma_with_gap(bool seal) +static void test_seal_mprotect_two_vma_with_gap(void) { void *ptr; unsigned long page_size = getpagesize(); @@ -1864,7 +1864,7 @@ static void test_seal_madvise_nodiscard(bool seal) REPORT_TEST_PASS(); } -int main(int argc, char **argv) +int main(void) { bool test_seal = seal_support(); @@ -1913,8 +1913,8 @@ int main(int argc, char **argv) test_seal_mprotect_partial_mprotect(false); test_seal_mprotect_partial_mprotect(true); - test_seal_mprotect_two_vma_with_gap(false); - test_seal_mprotect_two_vma_with_gap(true); + test_seal_mprotect_two_vma_with_gap(); + test_seal_mprotect_two_vma_with_gap(); test_seal_mprotect_merge(false); test_seal_mprotect_merge(true); diff --git a/tools/testing/selftests/mm/pagemap_ioctl.c b/tools/testing/selftests/mm/pagemap_ioctl.c index bcc73b4e805c..57b4bba2b45f 100644 --- a/tools/testing/selftests/mm/pagemap_ioctl.c +++ b/tools/testing/selftests/mm/pagemap_ioctl.c @@ -34,8 +34,8 @@ #define PAGEMAP "/proc/self/pagemap" int pagemap_fd; int uffd; -int page_size; -int hpage_size; +unsigned int page_size; +unsigned int hpage_size; const char *progname; #define LEN(region) ((region.end - region.start)/page_size) @@ -235,7 +235,9 @@ int get_reads(struct page_region *vec, int vec_size) int sanity_tests_sd(void) { - int mem_size, vec_size, ret, ret2, ret3, i, num_pages = 1000, total_pages = 0; + unsigned long long mem_size, vec_size, i, total_pages = 0; + long ret, ret2, ret3; + int num_pages = 1000; int total_writes, total_reads, reads, count; struct page_region *vec, *vec2; char *mem, *m[2]; @@ -321,9 +323,9 @@ int sanity_tests_sd(void) ret = pagemap_ioctl(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == mem_size/(page_size * 2), + ksft_test_result((unsigned long long)ret == mem_size/(page_size * 2), "%s Repeated pattern of written and non-written pages\n", __func__); /* 4. Repeated pattern of written and non-written pages in parts */ @@ -331,21 +333,21 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, num_pages/2 - 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec, 2, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ret3 = pagemap_ioctl(mem, mem_size, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret3 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret3, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret3, errno, strerror(errno)); ksft_test_result((ret + ret3) == num_pages/2 && ret2 == 2, - "%s Repeated pattern of written and non-written pages in parts %d %d %d\n", + "%s Repeated pattern of written and non-written pages in parts %ld %ld %ld\n", __func__, ret, ret3, ret2); /* 5. Repeated pattern of written and non-written pages max_pages */ @@ -357,13 +359,13 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, num_pages/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ksft_test_result(ret == num_pages/2 && ret2 == 1, "%s Repeated pattern of written and non-written pages max_pages\n", @@ -378,12 +380,12 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ret2 = pagemap_ioctl(mem, mem_size, vec2, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret2 < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret2, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret2, errno, strerror(errno)); ksft_test_result(ret == 1 && LEN(vec[0]) == 2 && vec[0].start == (uintptr_t)(mem + page_size) && @@ -416,7 +418,7 @@ int sanity_tests_sd(void) ret = pagemap_ioctl(m[1], mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && LEN(vec[0]) == mem_size/page_size, "%s Two regions\n", __func__); @@ -448,7 +450,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); for (i = 0; i < mem_size/page_size; i += 2) mem[i * page_size]++; @@ -457,7 +459,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -465,7 +467,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -473,7 +475,7 @@ int sanity_tests_sd(void) PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, mem_size/(page_size*5), PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); total_pages += ret; @@ -515,9 +517,9 @@ int sanity_tests_sd(void) vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); - if (ret > vec_size) + if ((unsigned long)ret > vec_size) break; reads = get_reads(vec, ret); @@ -554,63 +556,63 @@ int sanity_tests_sd(void) ret = pagemap_ioc(mem, 0, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end address\n"); ret = pagemap_ioc(mem, 0, vec, vec_size, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end with WP\n"); ret = pagemap_ioc(mem, 0, vec, 0, PM_SCAN_WP_MATCHING | PM_SCAN_CHECK_WPASYNC, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 0 && walk_end == (long)mem, "Walk_end: Same start and end with 0 output buffer\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: Big vec\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: vec of minimum length\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size/2), "Walk_end: Half max pages\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size), "Walk_end: 1 max page\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, -1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + mem_size), "Walk_end: max pages\n"); @@ -621,49 +623,49 @@ int sanity_tests_sd(void) ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Big vec\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, 0, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end sparse: vec of minimum length\n"); ret = pagemap_ioc(mem, mem_size, vec, 1, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size/2, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_end sparse: Max pages specified\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, vec_size/2, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); - ksft_test_result(ret == vec_size/2 && walk_end == (long)(mem + mem_size), + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); + ksft_test_result((unsigned long)ret == vec_size/2 && walk_end == (long)(mem + mem_size), "Walk_endsparse : Half max pages\n"); ret = pagemap_ioc(mem, mem_size, vec, vec_size, 0, 1, PAGE_IS_WRITTEN, 0, 0, PAGE_IS_WRITTEN, &walk_end); if (ret < 0) - ksft_exit_fail_msg("error %d %d %s\n", ret, errno, strerror(errno)); + ksft_exit_fail_msg("error %ld %d %s\n", ret, errno, strerror(errno)); ksft_test_result(ret == 1 && walk_end == (long)(mem + page_size * 2), "Walk_end: 1 max page\n"); @@ -674,9 +676,10 @@ int sanity_tests_sd(void) return 0; } -int base_tests(char *prefix, char *mem, int mem_size, int skip) +int base_tests(char *prefix, char *mem, unsigned long long mem_size, int skip) { - int vec_size, written; + unsigned long long vec_size; + int written; struct page_region *vec, *vec2; if (skip) { @@ -799,8 +802,8 @@ int hpage_unit_tests(void) char *map; int ret, ret2; size_t num_pages = 10; - int map_size = hpage_size * num_pages; - int vec_size = map_size/page_size; + unsigned long long map_size = hpage_size * num_pages; + unsigned long long vec_size = map_size/page_size; struct page_region *vec, *vec2; vec = malloc(sizeof(struct page_region) * vec_size); @@ -1047,7 +1050,8 @@ static void test_simple(void) int sanity_tests(void) { - int mem_size, vec_size, ret, fd, i, buf_size; + unsigned long long mem_size, vec_size; + int ret, fd, i, buf_size; struct page_region *vec; char *mem, *fmem; struct stat sbuf; @@ -1312,7 +1316,9 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, { struct pm_scan_arg arg = {0}; struct page_region rgns[256]; - int i, j, cnt, ret; + unsigned long long i, j; + long ret; + int cnt; arg.size = sizeof(struct pm_scan_arg); arg.start = (uintptr_t)mem; @@ -1330,7 +1336,7 @@ static ssize_t get_dirty_pages_reset(char *mem, unsigned int count, ksft_exit_fail_msg("ioctl failed\n"); cnt = 0; - for (i = 0; i < ret; ++i) { + for (i = 0; i < (unsigned long)ret; ++i) { if (rgns[i].categories != PAGE_IS_WRITTEN) ksft_exit_fail_msg("wrong flags\n"); @@ -1384,9 +1390,10 @@ void *thread_proc(void *mem) static void transact_test(int page_size) { unsigned int i, count, extra_pages; + unsigned int c; pthread_t th; char *mem; - int ret, c; + int ret; if (pthread_barrier_init(&start_barrier, NULL, nthreads + 1)) ksft_exit_fail_msg("pthread_barrier_init\n"); @@ -1405,9 +1412,9 @@ static void transact_test(int page_size) memset(mem, 0, 0x1000 * nthreads * pages_per_thread); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count > 0, "%s count %d\n", __func__, count); + ksft_test_result(count > 0, "%s count %u\n", __func__, count); count = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); - ksft_test_result(count == 0, "%s count %d\n", __func__, count); + ksft_test_result(count == 0, "%s count %u\n", __func__, count); finish = 0; for (i = 0; i < nthreads; ++i) @@ -1429,7 +1436,7 @@ static void transact_test(int page_size) ksft_exit_fail_msg("pthread_barrier_wait\n"); if (count > nthreads * access_per_thread) - ksft_exit_fail_msg("Too big count %d expected %d, iter %d\n", + ksft_exit_fail_msg("Too big count %u expected %u, iter %u\n", count, nthreads * access_per_thread, i); c = get_dirty_pages_reset(mem, nthreads * pages_per_thread, 1, page_size); @@ -1454,7 +1461,7 @@ static void transact_test(int page_size) * access and application gets page fault again for the same write. */ if (count < nthreads * access_per_thread) { - ksft_test_result_fail("Lost update, iter %d, %d vs %d.\n", i, count, + ksft_test_result_fail("Lost update, iter %u, %u vs %u.\n", i, count, nthreads * access_per_thread); return; } @@ -1467,15 +1474,16 @@ static void transact_test(int page_size) finish = 1; pthread_barrier_wait(&end_barrier); - ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %d.\n", __func__, + ksft_test_result_pass("%s Extra pages %u (%.1lf%%), extra thread faults %u.\n", __func__, extra_pages, 100.0 * extra_pages / (iter_count * nthreads * access_per_thread), extra_thread_faults); } -int main(int argc, char *argv[]) +int main(int __attribute__((unused)) argc, char *argv[]) { - int mem_size, shmid, buf_size, fd, i, ret; + int shmid, buf_size, fd, i, ret; + unsigned long long mem_size; char *mem, *map, *fmem; struct stat sbuf; diff --git a/tools/testing/selftests/mm/pkey-arm64.h b/tools/testing/selftests/mm/pkey-arm64.h index d9d2100eafc0..8e9685e03c44 100644 --- a/tools/testing/selftests/mm/pkey-arm64.h +++ b/tools/testing/selftests/mm/pkey-arm64.h @@ -30,7 +30,7 @@ #define NR_PKEYS 8 #define NR_RESERVED_PKEYS 1 /* pkey-0 */ -#define PKEY_ALLOW_ALL 0x77777777 +#define PKEY_REG_ALLOW_ALL 0x77777777 #define PKEY_REG_ALLOW_NONE 0x0 #define PKEY_BITS_PER_PKEY 4 @@ -81,11 +81,11 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { } -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { return PTR_ERR_ENOTSUP; } diff --git a/tools/testing/selftests/mm/pkey-helpers.h b/tools/testing/selftests/mm/pkey-helpers.h index f7cfe163b0ff..f080e97b39be 100644 --- a/tools/testing/selftests/mm/pkey-helpers.h +++ b/tools/testing/selftests/mm/pkey-helpers.h @@ -13,22 +13,22 @@ #include <ucontext.h> #include <sys/mman.h> +#include <linux/types.h> + #include "../kselftest.h" /* Define some kernel-like types */ -#define u8 __u8 -#define u16 __u16 -#define u32 __u32 -#define u64 __u64 +typedef __u8 u8; +typedef __u16 u16; +typedef __u32 u32; +typedef __u64 u64; #define PTR_ERR_ENOTSUP ((void *)-ENOTSUP) #ifndef DEBUG_LEVEL #define DEBUG_LEVEL 0 #endif -#define DPRINT_IN_SIGNAL_BUF_SIZE 4096 extern int dprint_in_signal; -extern char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; extern int test_nr; extern int iteration_nr; @@ -83,17 +83,18 @@ extern void abort_hooks(void); #ifndef noinline # define noinline __attribute__((noinline)) #endif +#ifndef __maybe_unused +# define __maybe_unused __attribute__((__unused__)) +#endif -noinline int read_ptr(int *ptr) -{ - /* Keep GCC from optimizing this away somehow */ - barrier(); - return *ptr; -} - -void expected_pkey_fault(int pkey); int sys_pkey_alloc(unsigned long flags, unsigned long init_val); int sys_pkey_free(unsigned long pkey); +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey); + +/* For functions called from protection_keys.c only */ +noinline int read_ptr(int *ptr); +void expected_pkey_fault(int pkey); int mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, unsigned long pkey); void record_pkey_malloc(void *ptr, long size, int prot); @@ -171,38 +172,6 @@ static inline void write_pkey_reg(u64 pkey_reg) pkey_reg, __read_pkey_reg()); } -/* - * These are technically racy. since something could - * change PKEY register between the read and the write. - */ -static inline void __pkey_access_allow(int pkey, int do_allow) -{ - u64 pkey_reg = read_pkey_reg(); - int bit = pkey * 2; - - if (do_allow) - pkey_reg &= (1<<bit); - else - pkey_reg |= (1<<bit); - - dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); - write_pkey_reg(pkey_reg); -} - -static inline void __pkey_write_allow(int pkey, int do_allow_write) -{ - u64 pkey_reg = read_pkey_reg(); - int bit = pkey * 2 + 1; - - if (do_allow_write) - pkey_reg &= (1<<bit); - else - pkey_reg |= (1<<bit); - - write_pkey_reg(pkey_reg); - dprintf4("pkey_reg now: %016llx\n", read_pkey_reg()); -} - #define ALIGN_UP(x, align_to) (((x) + ((align_to)-1)) & ~((align_to)-1)) #define ALIGN_DOWN(x, align_to) ((x) & ~((align_to)-1)) #define ALIGN_PTR_UP(p, ptr_align_to) \ diff --git a/tools/testing/selftests/mm/pkey-powerpc.h b/tools/testing/selftests/mm/pkey-powerpc.h index 3d0c0bdae5bc..1bad310d282a 100644 --- a/tools/testing/selftests/mm/pkey-powerpc.h +++ b/tools/testing/selftests/mm/pkey-powerpc.h @@ -91,7 +91,7 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS_64K_3KEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { /* * powerpc does not allow userspace to change permissions of exec-only @@ -105,7 +105,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) /* 4-byte instructions * 16384 = 64K page */ #define __page_o_noops() asm(".rept 16384 ; nop; .endr") -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { void *ptr; int ret; diff --git a/tools/testing/selftests/mm/pkey-x86.h b/tools/testing/selftests/mm/pkey-x86.h index ac91777c8917..f7ecd335df1e 100644 --- a/tools/testing/selftests/mm/pkey-x86.h +++ b/tools/testing/selftests/mm/pkey-x86.h @@ -113,7 +113,7 @@ static inline u32 pkey_bit_position(int pkey) #define XSTATE_PKEY 0x200 #define XSTATE_BV_OFFSET 512 -int pkey_reg_xstate_offset(void) +static inline int pkey_reg_xstate_offset(void) { unsigned int eax; unsigned int ebx; @@ -148,7 +148,7 @@ static inline int get_arch_reserved_keys(void) return NR_RESERVED_PKEYS; } -void expect_fault_on_read_execonly_key(void *p1, int pkey) +static inline void expect_fault_on_read_execonly_key(void *p1, int pkey) { int ptr_contents; @@ -157,7 +157,7 @@ void expect_fault_on_read_execonly_key(void *p1, int pkey) expected_pkey_fault(pkey); } -void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) +static inline void *malloc_pkey_with_mprotect_subpage(long size, int prot, u16 pkey) { return PTR_ERR_ENOTSUP; } diff --git a/tools/testing/selftests/mm/pkey_sighandler_tests.c b/tools/testing/selftests/mm/pkey_sighandler_tests.c index c593a426341c..1ac8c8809880 100644 --- a/tools/testing/selftests/mm/pkey_sighandler_tests.c +++ b/tools/testing/selftests/mm/pkey_sighandler_tests.c @@ -32,11 +32,9 @@ #define STACK_SIZE PTHREAD_STACK_MIN -void expected_pkey_fault(int pkey) {} - -pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; -pthread_cond_t cond = PTHREAD_COND_INITIALIZER; -siginfo_t siginfo = {0}; +static pthread_mutex_t mutex = PTHREAD_MUTEX_INITIALIZER; +static pthread_cond_t cond = PTHREAD_COND_INITIALIZER; +static siginfo_t siginfo = {0}; /* * We need to use inline assembly instead of glibc's syscall because glibc's @@ -163,7 +161,7 @@ static void *thread_segv_with_pkey0_disabled(void *ptr) __write_pkey_reg(pkey_reg_restrictive_default()); /* Segfault (with SEGV_MAPERR) */ - *(int *) (0x1) = 1; + *(volatile int *)NULL = 1; return NULL; } @@ -179,7 +177,6 @@ static void *thread_segv_pkuerr_stack(void *ptr) static void *thread_segv_maperr_ptr(void *ptr) { stack_t *stack = ptr; - int *bad = (int *)1; u64 pkey_reg; /* @@ -195,7 +192,7 @@ static void *thread_segv_maperr_ptr(void *ptr) __write_pkey_reg(pkey_reg); /* Segfault */ - *bad = 1; + *(volatile int *)NULL = 1; syscall_raw(SYS_exit, 0, 0, 0, 0, 0, 0); return NULL; } @@ -234,7 +231,7 @@ static void test_sigsegv_handler_with_pkey0_disabled(void) ksft_test_result(siginfo.si_signo == SIGSEGV && siginfo.si_code == SEGV_MAPERR && - siginfo.si_addr == (void *)1, + siginfo.si_addr == NULL, "%s\n", __func__); } @@ -314,11 +311,11 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) __write_pkey_reg(pkey_reg); /* Protect the new stack with MPK 1 */ - pkey = pkey_alloc(0, 0); - pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + pkey = sys_pkey_alloc(0, 0); + sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); /* Set up alternate signal stack that will use the default MPK */ - sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); sigstack.ss_flags = 0; sigstack.ss_size = STACK_SIZE; @@ -349,7 +346,7 @@ static void test_sigsegv_handler_with_different_pkey_for_stack(void) ksft_test_result(siginfo.si_signo == SIGSEGV && siginfo.si_code == SEGV_MAPERR && - siginfo.si_addr == (void *)1, + siginfo.si_addr == NULL, "%s\n", __func__); } @@ -487,11 +484,11 @@ static void test_pkru_sigreturn(void) __write_pkey_reg(pkey_reg); /* Protect the stack with MPK 2 */ - pkey = pkey_alloc(0, 0); - pkey_mprotect(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); + pkey = sys_pkey_alloc(0, 0); + sys_mprotect_pkey(stack, STACK_SIZE, PROT_READ | PROT_WRITE, pkey); /* Set up alternate signal stack that will use the default MPK */ - sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE | PROT_EXEC, + sigstack.ss_sp = mmap(0, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); sigstack.ss_flags = 0; sigstack.ss_size = STACK_SIZE; @@ -538,6 +535,9 @@ int main(int argc, char *argv[]) ksft_print_header(); ksft_set_plan(ARRAY_SIZE(pkey_tests)); + if (!is_pkeys_supported()) + ksft_exit_skip("pkeys not supported\n"); + for (i = 0; i < ARRAY_SIZE(pkey_tests); i++) (*pkey_tests[i])(); diff --git a/tools/testing/selftests/mm/pkey_util.c b/tools/testing/selftests/mm/pkey_util.c new file mode 100644 index 000000000000..ca4ad0d44ab2 --- /dev/null +++ b/tools/testing/selftests/mm/pkey_util.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <sys/syscall.h> +#include <unistd.h> + +#include "pkey-helpers.h" + +int sys_pkey_alloc(unsigned long flags, unsigned long init_val) +{ + int ret = syscall(SYS_pkey_alloc, flags, init_val); + dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", + __func__, flags, init_val, ret, errno); + return ret; +} + +int sys_pkey_free(unsigned long pkey) +{ + int ret = syscall(SYS_pkey_free, pkey); + dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); + return ret; +} + +int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, + unsigned long pkey) +{ + int sret; + + dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, + ptr, size, orig_prot, pkey); + + errno = 0; + sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); + if (errno) { + dprintf2("SYS_mprotect_key sret: %d\n", sret); + dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); + dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); + if (DEBUG_LEVEL >= 2) + perror("SYS_mprotect_pkey"); + } + return sret; +} diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c index 4990f7ab4cb7..a4683f2476f2 100644 --- a/tools/testing/selftests/mm/protection_keys.c +++ b/tools/testing/selftests/mm/protection_keys.c @@ -53,9 +53,15 @@ int test_nr; u64 shadow_pkey_reg; int dprint_in_signal; -char dprint_in_signal_buffer[DPRINT_IN_SIGNAL_BUF_SIZE]; -void cat_into_file(char *str, char *file) +noinline int read_ptr(int *ptr) +{ + /* Keep GCC from optimizing this away somehow */ + barrier(); + return *ptr; +} + +static void cat_into_file(char *str, char *file) { int fd = open(file, O_RDWR); int ret; @@ -82,7 +88,7 @@ void cat_into_file(char *str, char *file) #if CONTROL_TRACING > 0 static int warned_tracing; -int tracing_root_ok(void) +static int tracing_root_ok(void) { if (geteuid() != 0) { if (!warned_tracing) @@ -95,7 +101,7 @@ int tracing_root_ok(void) } #endif -void tracing_on(void) +static void tracing_on(void) { #if CONTROL_TRACING > 0 #define TRACEDIR "/sys/kernel/tracing" @@ -119,7 +125,7 @@ void tracing_on(void) #endif } -void tracing_off(void) +static void tracing_off(void) { #if CONTROL_TRACING > 0 if (!tracing_root_ok()) @@ -153,7 +159,7 @@ __attribute__((__aligned__(65536))) #else __attribute__((__aligned__(PAGE_SIZE))) #endif -void lots_o_noops_around_write(int *write_to_me) +static void lots_o_noops_around_write(int *write_to_me) { dprintf3("running %s()\n", __func__); __page_o_noops(); @@ -164,7 +170,7 @@ void lots_o_noops_around_write(int *write_to_me) dprintf3("%s() done\n", __func__); } -void dump_mem(void *dumpme, int len_bytes) +static void dump_mem(void *dumpme, int len_bytes) { char *c = (void *)dumpme; int i; @@ -207,7 +213,7 @@ static int hw_pkey_set(int pkey, unsigned long rights, unsigned long flags) return 0; } -void pkey_disable_set(int pkey, int flags) +static void pkey_disable_set(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; @@ -245,7 +251,7 @@ void pkey_disable_set(int pkey, int flags) pkey, flags); } -void pkey_disable_clear(int pkey, int flags) +static void pkey_disable_clear(int pkey, int flags) { unsigned long syscall_flags = 0; int ret; @@ -271,19 +277,19 @@ void pkey_disable_clear(int pkey, int flags) pkey, read_pkey_reg()); } -void pkey_write_allow(int pkey) +__maybe_unused static void pkey_write_allow(int pkey) { pkey_disable_clear(pkey, PKEY_DISABLE_WRITE); } -void pkey_write_deny(int pkey) +__maybe_unused static void pkey_write_deny(int pkey) { pkey_disable_set(pkey, PKEY_DISABLE_WRITE); } -void pkey_access_allow(int pkey) +__maybe_unused static void pkey_access_allow(int pkey) { pkey_disable_clear(pkey, PKEY_DISABLE_ACCESS); } -void pkey_access_deny(int pkey) +__maybe_unused static void pkey_access_deny(int pkey) { pkey_disable_set(pkey, PKEY_DISABLE_ACCESS); } @@ -301,9 +307,9 @@ static char *si_code_str(int si_code) return "UNKNOWN"; } -int pkey_faults; -int last_si_pkey = -1; -void signal_handler(int signum, siginfo_t *si, void *vucontext) +static int pkey_faults; +static int last_si_pkey = -1; +static void signal_handler(int signum, siginfo_t *si, void *vucontext) { ucontext_t *uctxt = vucontext; int trapno; @@ -390,27 +396,21 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext) /* restore access and let the faulting instruction continue */ pkey_access_allow(siginfo_pkey); #elif defined(__aarch64__) - aarch64_write_signal_pkey(uctxt, PKEY_ALLOW_ALL); + aarch64_write_signal_pkey(uctxt, PKEY_REG_ALLOW_ALL); #endif /* arch */ pkey_faults++; dprintf1("<<<<==================================================\n"); dprint_in_signal = 0; } -int wait_all_children(void) -{ - int status; - return waitpid(-1, &status, 0); -} - -void sig_chld(int x) +static void sig_chld(int x) { dprint_in_signal = 1; dprintf2("[%d] SIGCHLD: %d\n", getpid(), x); dprint_in_signal = 0; } -void setup_sigsegv_handler(void) +static void setup_sigsegv_handler(void) { int r, rs; struct sigaction newact; @@ -436,13 +436,13 @@ void setup_sigsegv_handler(void) pkey_assert(r == 0); } -void setup_handlers(void) +static void setup_handlers(void) { signal(SIGCHLD, &sig_chld); setup_sigsegv_handler(); } -pid_t fork_lazy_child(void) +static pid_t fork_lazy_child(void) { pid_t forkret; @@ -460,35 +460,7 @@ pid_t fork_lazy_child(void) return forkret; } -int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot, - unsigned long pkey) -{ - int sret; - - dprintf2("%s(0x%p, %zx, prot=%lx, pkey=%lx)\n", __func__, - ptr, size, orig_prot, pkey); - - errno = 0; - sret = syscall(__NR_pkey_mprotect, ptr, size, orig_prot, pkey); - if (errno) { - dprintf2("SYS_mprotect_key sret: %d\n", sret); - dprintf2("SYS_mprotect_key prot: 0x%lx\n", orig_prot); - dprintf2("SYS_mprotect_key failed, errno: %d\n", errno); - if (DEBUG_LEVEL >= 2) - perror("SYS_mprotect_pkey"); - } - return sret; -} - -int sys_pkey_alloc(unsigned long flags, unsigned long init_val) -{ - int ret = syscall(SYS_pkey_alloc, flags, init_val); - dprintf1("%s(flags=%lx, init_val=%lx) syscall ret: %d errno: %d\n", - __func__, flags, init_val, ret, errno); - return ret; -} - -int alloc_pkey(void) +static int alloc_pkey(void) { int ret; unsigned long init_val = 0x0; @@ -534,19 +506,12 @@ int alloc_pkey(void) return ret; } -int sys_pkey_free(unsigned long pkey) -{ - int ret = syscall(SYS_pkey_free, pkey); - dprintf1("%s(pkey=%ld) syscall ret: %d\n", __func__, pkey, ret); - return ret; -} - /* * I had a bug where pkey bits could be set by mprotect() but * not cleared. This ensures we get lots of random bit sets * and clears on the vma and pte pkey bits. */ -int alloc_random_pkey(void) +static int alloc_random_pkey(void) { int max_nr_pkey_allocs; int ret; @@ -629,7 +594,7 @@ struct pkey_malloc_record { }; struct pkey_malloc_record *pkey_malloc_records; struct pkey_malloc_record *pkey_last_malloc_record; -long nr_pkey_malloc_records; +static long nr_pkey_malloc_records; void record_pkey_malloc(void *ptr, long size, int prot) { long i; @@ -667,7 +632,7 @@ void record_pkey_malloc(void *ptr, long size, int prot) nr_pkey_malloc_records++; } -void free_pkey_malloc(void *ptr) +static void free_pkey_malloc(void *ptr) { long i; int ret; @@ -694,8 +659,7 @@ void free_pkey_malloc(void *ptr) pkey_assert(false); } - -void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) +static void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) { void *ptr; int ret; @@ -715,7 +679,7 @@ void *malloc_pkey_with_mprotect(long size, int prot, u16 pkey) return ptr; } -void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) +static void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) { int ret; void *ptr; @@ -745,10 +709,10 @@ void *malloc_pkey_anon_huge(long size, int prot, u16 pkey) return ptr; } -int hugetlb_setup_ok; +static int hugetlb_setup_ok; #define SYSFS_FMT_NR_HUGE_PAGES "/sys/kernel/mm/hugepages/hugepages-%ldkB/nr_hugepages" #define GET_NR_HUGE_PAGES 10 -void setup_hugetlbfs(void) +static void setup_hugetlbfs(void) { int err; int fd; @@ -796,7 +760,7 @@ void setup_hugetlbfs(void) hugetlb_setup_ok = 1; } -void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) +static void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) { void *ptr; int flags = MAP_ANONYMOUS|MAP_PRIVATE|MAP_HUGETLB; @@ -817,42 +781,15 @@ void *malloc_pkey_hugetlb(long size, int prot, u16 pkey) return ptr; } -void *malloc_pkey_mmap_dax(long size, int prot, u16 pkey) -{ - void *ptr; - int fd; - - dprintf1("doing %s(size=%ld, prot=0x%x, pkey=%d)\n", __func__, - size, prot, pkey); - pkey_assert(pkey < NR_PKEYS); - fd = open("/dax/foo", O_RDWR); - pkey_assert(fd >= 0); - - ptr = mmap(0, size, prot, MAP_SHARED, fd, 0); - pkey_assert(ptr != (void *)-1); - - mprotect_pkey(ptr, size, prot, pkey); - - record_pkey_malloc(ptr, size, prot); - - dprintf1("mmap()'d for pkey %d @ %p\n", pkey, ptr); - close(fd); - return ptr; -} - -void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { +static void *(*pkey_malloc[])(long size, int prot, u16 pkey) = { malloc_pkey_with_mprotect, malloc_pkey_with_mprotect_subpage, malloc_pkey_anon_huge, malloc_pkey_hugetlb -/* can not do direct with the pkey_mprotect() API: - malloc_pkey_mmap_direct, - malloc_pkey_mmap_dax, -*/ }; -void *malloc_pkey(long size, int prot, u16 pkey) +static void *malloc_pkey(long size, int prot, u16 pkey) { void *ret; static int malloc_type; @@ -882,7 +819,7 @@ void *malloc_pkey(long size, int prot, u16 pkey) return ret; } -int last_pkey_faults; +static int last_pkey_faults; #define UNKNOWN_PKEY -2 void expected_pkey_fault(int pkey) { @@ -905,7 +842,7 @@ void expected_pkey_fault(int pkey) */ if (__read_pkey_reg() != 0) #elif defined(__aarch64__) - if (__read_pkey_reg() != PKEY_ALLOW_ALL) + if (__read_pkey_reg() != PKEY_REG_ALLOW_ALL) #else if (__read_pkey_reg() != shadow_pkey_reg) #endif /* arch */ @@ -924,9 +861,9 @@ void expected_pkey_fault(int pkey) pkey_assert(last_pkey_faults == pkey_faults); \ } while (0) -int test_fds[10] = { -1 }; -int nr_test_fds; -void __save_test_fd(int fd) +static int test_fds[10] = { -1 }; +static int nr_test_fds; +static void __save_test_fd(int fd) { pkey_assert(fd >= 0); pkey_assert(nr_test_fds < ARRAY_SIZE(test_fds)); @@ -934,14 +871,14 @@ void __save_test_fd(int fd) nr_test_fds++; } -int get_test_read_fd(void) +static int get_test_read_fd(void) { int test_fd = open("/etc/passwd", O_RDONLY); __save_test_fd(test_fd); return test_fd; } -void close_test_fds(void) +static void close_test_fds(void) { int i; @@ -954,7 +891,7 @@ void close_test_fds(void) nr_test_fds = 0; } -void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) +static void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) { int i, err; int max_nr_pkey_allocs; @@ -1006,7 +943,7 @@ void test_pkey_alloc_free_attach_pkey0(int *ptr, u16 pkey) pkey_assert(!err); } -void test_read_of_write_disabled_region(int *ptr, u16 pkey) +static void test_read_of_write_disabled_region(int *ptr, u16 pkey) { int ptr_contents; @@ -1016,7 +953,7 @@ void test_read_of_write_disabled_region(int *ptr, u16 pkey) dprintf1("*ptr: %d\n", ptr_contents); dprintf1("\n"); } -void test_read_of_access_disabled_region(int *ptr, u16 pkey) +static void test_read_of_access_disabled_region(int *ptr, u16 pkey) { int ptr_contents; @@ -1028,7 +965,7 @@ void test_read_of_access_disabled_region(int *ptr, u16 pkey) expected_pkey_fault(pkey); } -void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, +static void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { int ptr_contents; @@ -1045,7 +982,7 @@ void test_read_of_access_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, +static void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { *ptr = __LINE__; @@ -1056,14 +993,14 @@ void test_write_of_write_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_write_of_write_disabled_region(int *ptr, u16 pkey) +static void test_write_of_write_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling write access to PKEY[%02d], doing write\n", pkey); pkey_write_deny(pkey); *ptr = __LINE__; expected_pkey_fault(pkey); } -void test_write_of_access_disabled_region(int *ptr, u16 pkey) +static void test_write_of_access_disabled_region(int *ptr, u16 pkey) { dprintf1("disabling access to PKEY[%02d], doing write\n", pkey); pkey_access_deny(pkey); @@ -1071,7 +1008,7 @@ void test_write_of_access_disabled_region(int *ptr, u16 pkey) expected_pkey_fault(pkey); } -void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, +static void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, u16 pkey) { *ptr = __LINE__; @@ -1082,7 +1019,7 @@ void test_write_of_access_disabled_region_with_page_already_mapped(int *ptr, expected_pkey_fault(pkey); } -void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) +static void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) { int ret; int test_fd = get_test_read_fd(); @@ -1094,7 +1031,8 @@ void test_kernel_write_of_access_disabled_region(int *ptr, u16 pkey) dprintf1("read ret: %d\n", ret); pkey_assert(ret); } -void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) + +static void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) { int ret; int test_fd = get_test_read_fd(); @@ -1107,7 +1045,7 @@ void test_kernel_write_of_write_disabled_region(int *ptr, u16 pkey) pkey_assert(ret); } -void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) +static void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) { int pipe_ret, vmsplice_ret; struct iovec iov; @@ -1129,7 +1067,7 @@ void test_kernel_gup_of_access_disabled_region(int *ptr, u16 pkey) close(pipe_fds[1]); } -void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) +static void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) { int ignored = 0xdada; int futex_ret; @@ -1147,7 +1085,7 @@ void test_kernel_gup_write_to_write_disabled_region(int *ptr, u16 pkey) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) +static void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) { int err; int i; @@ -1170,7 +1108,7 @@ void test_pkey_syscalls_on_non_allocated_pkey(int *ptr, u16 pkey) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) +static void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) { int err; int bad_pkey = NR_PKEYS+99; @@ -1180,7 +1118,7 @@ void test_pkey_syscalls_bad_args(int *ptr, u16 pkey) pkey_assert(err); } -void become_child(void) +static void become_child(void) { pid_t forkret; @@ -1196,7 +1134,7 @@ void become_child(void) } /* Assumes that all pkeys other than 'pkey' are unallocated */ -void test_pkey_alloc_exhaust(int *ptr, u16 pkey) +static void test_pkey_alloc_exhaust(int *ptr, u16 pkey) { int err; int allocated_pkeys[NR_PKEYS] = {0}; @@ -1263,7 +1201,7 @@ void test_pkey_alloc_exhaust(int *ptr, u16 pkey) } } -void arch_force_pkey_reg_init(void) +static void arch_force_pkey_reg_init(void) { #if defined(__i386__) || defined(__x86_64__) /* arch */ u64 *buf; @@ -1302,7 +1240,7 @@ void arch_force_pkey_reg_init(void) * a long-running test that continually checks the pkey * register. */ -void test_pkey_init_state(int *ptr, u16 pkey) +static void test_pkey_init_state(int *ptr, u16 pkey) { int err; int allocated_pkeys[NR_PKEYS] = {0}; @@ -1340,7 +1278,7 @@ void test_pkey_init_state(int *ptr, u16 pkey) * have to call pkey_alloc() to use it first. Make sure that it * is usable. */ -void test_mprotect_with_pkey_0(int *ptr, u16 pkey) +static void test_mprotect_with_pkey_0(int *ptr, u16 pkey) { long size; int prot; @@ -1364,7 +1302,7 @@ void test_mprotect_with_pkey_0(int *ptr, u16 pkey) mprotect_pkey(ptr, size, prot, pkey); } -void test_ptrace_of_child(int *ptr, u16 pkey) +static void test_ptrace_of_child(int *ptr, u16 pkey) { __attribute__((__unused__)) int peek_result; pid_t child_pid; @@ -1440,7 +1378,7 @@ void test_ptrace_of_child(int *ptr, u16 pkey) free(plain_ptr_unaligned); } -void *get_pointer_to_instructions(void) +static void *get_pointer_to_instructions(void) { void *p1; @@ -1461,7 +1399,7 @@ void *get_pointer_to_instructions(void) return p1; } -void test_executing_on_unreadable_memory(int *ptr, u16 pkey) +static void test_executing_on_unreadable_memory(int *ptr, u16 pkey) { void *p1; int scratch; @@ -1493,7 +1431,7 @@ void test_executing_on_unreadable_memory(int *ptr, u16 pkey) pkey_assert(!ret); } -void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) +static void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) { void *p1; int scratch; @@ -1542,7 +1480,7 @@ void test_implicit_mprotect_exec_only_memory(int *ptr, u16 pkey) } #if defined(__i386__) || defined(__x86_64__) -void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) { u32 new_pkru; pid_t child; @@ -1665,7 +1603,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) #endif #if defined(__aarch64__) -void test_ptrace_modifies_pkru(int *ptr, u16 pkey) +static void test_ptrace_modifies_pkru(int *ptr, u16 pkey) { pid_t child; int status, ret; @@ -1742,7 +1680,7 @@ void test_ptrace_modifies_pkru(int *ptr, u16 pkey) } #endif -void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) +static void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) { int size = PAGE_SIZE; int sret; @@ -1756,7 +1694,7 @@ void test_mprotect_pkey_on_unsupported_cpu(int *ptr, u16 pkey) pkey_assert(sret < 0); } -void (*pkey_tests[])(int *ptr, u16 pkey) = { +static void (*pkey_tests[])(int *ptr, u16 pkey) = { test_read_of_write_disabled_region, test_read_of_access_disabled_region, test_read_of_access_disabled_region_with_page_already_mapped, @@ -1782,7 +1720,7 @@ void (*pkey_tests[])(int *ptr, u16 pkey) = { #endif }; -void run_tests_once(void) +static void run_tests_once(void) { int *ptr; int prot = PROT_READ|PROT_WRITE; @@ -1816,7 +1754,7 @@ void run_tests_once(void) iteration_nr++; } -void pkey_setup_shadow(void) +static void pkey_setup_shadow(void) { shadow_pkey_reg = __read_pkey_reg(); } diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2fc290d9430c..da7e26668103 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -45,6 +45,8 @@ separated by spaces: vmalloc smoke tests - hmm hmm smoke tests +- madv_guard + test madvise(2) MADV_GUARD_INSTALL and MADV_GUARD_REMOVE options - madv_populate test memadvise(2) MADV_POPULATE_{READ,WRITE} options - memfd_secret @@ -218,7 +220,7 @@ run_test() { if test_selected ${CATEGORY}; then # On memory constrainted systems some tests can fail to allocate hugepages. # perform some cleanup before the test for a higher success rate. - if [ ${CATEGORY} == "thp" ] | [ ${CATEGORY} == "hugetlb" ]; then + if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then echo 3 > /proc/sys/vm/drop_caches sleep 2 echo 1 > /proc/sys/vm/compact_memory @@ -307,6 +309,7 @@ CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 3 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem-private 20 16 +CATEGORY="userfaultfd" run_test ./uffd-wp-mremap #cleanup echo "$nr_hugepgs" > /proc/sys/vm/nr_hugepages @@ -375,6 +378,9 @@ CATEGORY="mremap" run_test ./mremap_dontunmap CATEGORY="hmm" run_test bash ./test_hmm.sh smoke +# MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests +CATEGORY="madv_guard" run_test ./guard-pages + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c deleted file mode 100644 index d9f8ba8d5050..000000000000 --- a/tools/testing/selftests/mm/seal_elf.c +++ /dev/null @@ -1,137 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE -#include <sys/mman.h> -#include <stdint.h> -#include <asm-generic/unistd.h> -#include <string.h> -#include <sys/time.h> -#include <sys/resource.h> -#include <stdbool.h> -#include "../kselftest.h" -#include <syscall.h> -#include <errno.h> -#include <stdio.h> -#include <stdlib.h> -#include <fcntl.h> -#include <sys/ioctl.h> -#include <sys/vfs.h> -#include <sys/stat.h> -#include "mseal_helpers.h" - -/* - * define sys_xyx to call syscall directly. - */ -static int sys_mseal(void *start, size_t len) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mseal, start, len, 0); - return sret; -} - -static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot) -{ - int sret; - - errno = 0; - sret = syscall(__NR_mprotect, ptr, size, prot); - return sret; -} - -static bool seal_support(void) -{ - int ret; - void *ptr; - unsigned long page_size = getpagesize(); - - ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0); - if (ptr == (void *) -1) - return false; - - ret = sys_mseal(ptr, page_size); - if (ret < 0) - return false; - - return true; -} - -const char somestr[4096] = {"READONLY"}; - -static void test_seal_elf(void) -{ - int ret; - FILE *maps; - char line[512]; - uintptr_t addr_start, addr_end; - char prot[5]; - char filename[256]; - unsigned long page_size = getpagesize(); - unsigned long long ptr = (unsigned long long) somestr; - char *somestr2 = (char *)somestr; - - /* - * Modify the protection of readonly somestr - */ - if (((unsigned long long)ptr % page_size) != 0) - ptr = (unsigned long long)ptr & ~(page_size - 1); - - ksft_print_msg("somestr = %s\n", somestr); - ksft_print_msg("change protection to rw\n"); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ|PROT_WRITE); - FAIL_TEST_IF_FALSE(!ret); - *somestr2 = 'A'; - ksft_print_msg("somestr is modified to: %s\n", somestr); - ret = sys_mprotect((void *)ptr, page_size, PROT_READ); - FAIL_TEST_IF_FALSE(!ret); - - maps = fopen("/proc/self/maps", "r"); - FAIL_TEST_IF_FALSE(maps); - - /* - * apply sealing to elf binary - */ - while (fgets(line, sizeof(line), maps)) { - if (sscanf(line, "%lx-%lx %4s %*x %*x:%*x %*u %255[^\n]", - &addr_start, &addr_end, prot, filename) == 4) { - if (strlen(filename)) { - /* - * seal the mapping if read only. - */ - if (strstr(prot, "r-")) { - ret = sys_mseal((void *)addr_start, addr_end - addr_start); - FAIL_TEST_IF_FALSE(!ret); - ksft_print_msg("sealed: %lx-%lx %s %s\n", - addr_start, addr_end, prot, filename); - if ((uintptr_t) somestr >= addr_start && - (uintptr_t) somestr <= addr_end) - ksft_print_msg("mapping for somestr found\n"); - } - } - } - } - fclose(maps); - - ret = sys_mprotect((void *)ptr, page_size, PROT_READ | PROT_WRITE); - FAIL_TEST_IF_FALSE(ret < 0); - ksft_print_msg("somestr is sealed, mprotect is rejected\n"); - - REPORT_TEST_PASS(); -} - -int main(int argc, char **argv) -{ - bool test_seal = seal_support(); - - ksft_print_header(); - ksft_print_msg("pid=%d\n", getpid()); - - if (!test_seal) - ksft_exit_skip("sealing not supported, check CONFIG_64BIT\n"); - - ksft_set_plan(1); - - test_seal_elf(); - - ksft_finished(); -} diff --git a/tools/testing/selftests/mm/soft-dirty.c b/tools/testing/selftests/mm/soft-dirty.c index bdfa5d085f00..8e1462ce0532 100644 --- a/tools/testing/selftests/mm/soft-dirty.c +++ b/tools/testing/selftests/mm/soft-dirty.c @@ -128,7 +128,7 @@ static void test_mprotect(int pagemap_fd, int pagesize, bool anon) { const char *type[] = {"file", "anon"}; const char *fname = "./soft-dirty-test-file"; - int test_fd; + int test_fd = 0; char *map; if (anon) { diff --git a/tools/testing/selftests/mm/split_huge_page_test.c b/tools/testing/selftests/mm/split_huge_page_test.c index eb6d1b9fc362..3f353f3d070f 100644 --- a/tools/testing/selftests/mm/split_huge_page_test.c +++ b/tools/testing/selftests/mm/split_huge_page_test.c @@ -108,38 +108,28 @@ static void verify_rss_anon_split_huge_page_all_zeroes(char *one_page, int nr_hp unsigned long rss_anon_before, rss_anon_after; size_t i; - if (!check_huge_anon(one_page, 4, pmd_pagesize)) { - printf("No THP is allocated\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 4, pmd_pagesize)) + ksft_exit_fail_msg("No THP is allocated\n"); rss_anon_before = rss_anon(); - if (!rss_anon_before) { - printf("No RssAnon is allocated before split\n"); - exit(EXIT_FAILURE); - } + if (!rss_anon_before) + ksft_exit_fail_msg("No RssAnon is allocated before split\n"); /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, (uint64_t)one_page + len, 0); for (i = 0; i < len; i++) - if (one_page[i] != (char)0) { - printf("%ld byte corrupted\n", i); - exit(EXIT_FAILURE); - } + if (one_page[i] != (char)0) + ksft_exit_fail_msg("%ld byte corrupted\n", i); - if (!check_huge_anon(one_page, 0, pmd_pagesize)) { - printf("Still AnonHugePages not split\n"); - exit(EXIT_FAILURE); - } + if (!check_huge_anon(one_page, 0, pmd_pagesize)) + ksft_exit_fail_msg("Still AnonHugePages not split\n"); rss_anon_after = rss_anon(); - if (rss_anon_after >= rss_anon_before) { - printf("Incorrect RssAnon value. Before: %ld After: %ld\n", + if (rss_anon_after >= rss_anon_before) + ksft_exit_fail_msg("Incorrect RssAnon value. Before: %ld After: %ld\n", rss_anon_before, rss_anon_after); - exit(EXIT_FAILURE); - } } void split_pmd_zero_pages(void) @@ -150,11 +140,11 @@ void split_pmd_zero_pages(void) one_page = allocate_zero_filled_hugepage(len); verify_rss_anon_split_huge_page_all_zeroes(one_page, nr_hpages, len); - printf("Split zero filled huge pages successful\n"); + ksft_test_result_pass("Split zero filled huge pages successful\n"); free(one_page); } -void split_pmd_thp(void) +void split_pmd_thp_to_order(int order) { char *one_page; size_t len = 4 * pmd_pagesize; @@ -174,7 +164,7 @@ void split_pmd_thp(void) /* split all THPs */ write_debugfs(PID_FMT, getpid(), (uint64_t)one_page, - (uint64_t)one_page + len, 0); + (uint64_t)one_page + len, order); for (i = 0; i < len; i++) if (one_page[i] != (char)i) @@ -184,7 +174,7 @@ void split_pmd_thp(void) if (!check_huge_anon(one_page, 0, pmd_pagesize)) ksft_exit_fail_msg("Still AnonHugePages not split\n"); - ksft_test_result_pass("Split huge pages successful\n"); + ksft_test_result_pass("Split huge pages to order %d successful\n", order); free(one_page); } @@ -491,7 +481,7 @@ int main(int argc, char **argv) if (argc > 1) optional_xfs_path = argv[1]; - ksft_set_plan(3+9); + ksft_set_plan(1+8+2+9); pagesize = getpagesize(); pageshift = ffs(pagesize) - 1; @@ -502,7 +492,11 @@ int main(int argc, char **argv) fd_size = 2 * pmd_pagesize; split_pmd_zero_pages(); - split_pmd_thp(); + + for (i = 0; i < 9; i++) + if (i != 1) + split_pmd_thp_to_order(i); + split_pte_mapped_thp(); split_file_backed_thp(); diff --git a/tools/testing/selftests/mm/thp_settings.c b/tools/testing/selftests/mm/thp_settings.c index 577eaab6266f..ad872af1c81a 100644 --- a/tools/testing/selftests/mm/thp_settings.c +++ b/tools/testing/selftests/mm/thp_settings.c @@ -87,7 +87,7 @@ int write_file(const char *path, const char *buf, size_t buflen) return (unsigned int) numwritten; } -const unsigned long read_num(const char *path) +unsigned long read_num(const char *path) { char buf[21]; @@ -172,7 +172,7 @@ void thp_write_string(const char *name, const char *val) } } -const unsigned long thp_read_num(const char *name) +unsigned long thp_read_num(const char *name) { char path[PATH_MAX]; int ret; diff --git a/tools/testing/selftests/mm/thp_settings.h b/tools/testing/selftests/mm/thp_settings.h index 876235a23460..fc131d23d593 100644 --- a/tools/testing/selftests/mm/thp_settings.h +++ b/tools/testing/selftests/mm/thp_settings.h @@ -64,12 +64,12 @@ struct thp_settings { int read_file(const char *path, char *buf, size_t buflen); int write_file(const char *path, const char *buf, size_t buflen); -const unsigned long read_num(const char *path); +unsigned long read_num(const char *path); void write_num(const char *path, unsigned long num); int thp_read_string(const char *name, const char * const strings[]); void thp_write_string(const char *name, const char *val); -const unsigned long thp_read_num(const char *name); +unsigned long thp_read_num(const char *name); void thp_write_num(const char *name, unsigned long num); void thp_write_settings(struct thp_settings *settings); diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c index a2e71b1636e7..9ff71fa1f9bf 100644 --- a/tools/testing/selftests/mm/uffd-unit-tests.c +++ b/tools/testing/selftests/mm/uffd-unit-tests.c @@ -1122,7 +1122,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, char c; unsigned long long count; struct uffd_args args = { 0 }; - char *orig_area_src, *orig_area_dst; + char *orig_area_src = NULL, *orig_area_dst = NULL; unsigned long step_size, step_count; unsigned long src_offs = 0; unsigned long dst_offs = 0; @@ -1190,7 +1190,7 @@ uffd_move_test_common(uffd_test_args_t *targs, unsigned long chunk_size, nr, count, count_verify[src_offs + nr + i]); } } - if (step_size > page_size) { + if (chunk_size > page_size) { area_src = orig_area_src; area_dst = orig_area_dst; } diff --git a/tools/testing/selftests/mm/uffd-wp-mremap.c b/tools/testing/selftests/mm/uffd-wp-mremap.c new file mode 100644 index 000000000000..2c4f984bd73c --- /dev/null +++ b/tools/testing/selftests/mm/uffd-wp-mremap.c @@ -0,0 +1,380 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define _GNU_SOURCE +#include <stdbool.h> +#include <stdint.h> +#include <fcntl.h> +#include <assert.h> +#include <linux/mman.h> +#include <sys/mman.h> +#include "../kselftest.h" +#include "thp_settings.h" +#include "uffd-common.h" + +static int pagemap_fd; +static size_t pagesize; +static int nr_pagesizes = 1; +static int nr_thpsizes; +static size_t thpsizes[20]; +static int nr_hugetlbsizes; +static size_t hugetlbsizes[10]; + +static int sz2ord(size_t size) +{ + return __builtin_ctzll(size / pagesize); +} + +static int detect_thp_sizes(size_t sizes[], int max) +{ + int count = 0; + unsigned long orders; + size_t kb; + int i; + + /* thp not supported at all. */ + if (!read_pmd_pagesize()) + return 0; + + orders = thp_supported_orders(); + + for (i = 0; orders && count < max; i++) { + if (!(orders & (1UL << i))) + continue; + orders &= ~(1UL << i); + kb = (pagesize >> 10) << i; + sizes[count++] = kb * 1024; + ksft_print_msg("[INFO] detected THP size: %zu KiB\n", kb); + } + + return count; +} + +static void *mmap_aligned(size_t size, int prot, int flags) +{ + size_t mmap_size = size * 2; + char *mmap_mem, *mem; + + mmap_mem = mmap(NULL, mmap_size, prot, flags, -1, 0); + if (mmap_mem == MAP_FAILED) + return mmap_mem; + + mem = (char *)(((uintptr_t)mmap_mem + size - 1) & ~(size - 1)); + munmap(mmap_mem, mem - mmap_mem); + munmap(mem + size, mmap_mem + mmap_size - mem - size); + + return mem; +} + +static void *alloc_one_folio(size_t size, bool private, bool hugetlb) +{ + bool thp = !hugetlb && size > pagesize; + int flags = MAP_ANONYMOUS; + int prot = PROT_READ | PROT_WRITE; + char *mem, *addr; + + assert((size & (size - 1)) == 0); + + if (private) + flags |= MAP_PRIVATE; + else + flags |= MAP_SHARED; + + /* + * For THP, we must explicitly enable the THP size, allocate twice the + * required space then manually align. + */ + if (thp) { + struct thp_settings settings = *thp_current_settings(); + + if (private) + settings.hugepages[sz2ord(size)].enabled = THP_ALWAYS; + else + settings.shmem_hugepages[sz2ord(size)].enabled = SHMEM_ALWAYS; + + thp_push_settings(&settings); + + mem = mmap_aligned(size, prot, flags); + } else { + if (hugetlb) { + flags |= MAP_HUGETLB; + flags |= __builtin_ctzll(size) << MAP_HUGE_SHIFT; + } + + mem = mmap(NULL, size, prot, flags, -1, 0); + } + + if (mem == MAP_FAILED) { + mem = NULL; + goto out; + } + + assert(((uintptr_t)mem & (size - 1)) == 0); + + /* + * Populate the folio by writing the first byte and check that all pages + * are populated. Finally set the whole thing to non-zero data to avoid + * kernel from mapping it back to the zero page. + */ + mem[0] = 1; + for (addr = mem; addr < mem + size; addr += pagesize) { + if (!pagemap_is_populated(pagemap_fd, addr)) { + munmap(mem, size); + mem = NULL; + goto out; + } + } + memset(mem, 1, size); +out: + if (thp) + thp_pop_settings(); + + return mem; +} + +static bool check_uffd_wp_state(void *mem, size_t size, bool expect) +{ + uint64_t pte; + void *addr; + + for (addr = mem; addr < mem + size; addr += pagesize) { + pte = pagemap_get_entry(pagemap_fd, addr); + if (!!(pte & PM_UFFD_WP) != expect) { + ksft_test_result_fail("uffd-wp not %s for pte %lu!\n", + expect ? "set" : "clear", + (addr - mem) / pagesize); + return false; + } + } + + return true; +} + +static bool range_is_swapped(void *addr, size_t size) +{ + for (; size; addr += pagesize, size -= pagesize) + if (!pagemap_is_swapped(pagemap_fd, addr)) + return false; + return true; +} + +static void test_one_folio(size_t size, bool private, bool swapout, bool hugetlb) +{ + struct uffdio_writeprotect wp_prms; + uint64_t features = 0; + void *addr = NULL; + void *mem = NULL; + + assert(!(hugetlb && swapout)); + + ksft_print_msg("[RUN] %s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n", + __func__, + size, + private ? "true" : "false", + swapout ? "true" : "false", + hugetlb ? "true" : "false"); + + /* Allocate a folio of required size and type. */ + mem = alloc_one_folio(size, private, hugetlb); + if (!mem) { + ksft_test_result_fail("alloc_one_folio() failed\n"); + goto out; + } + + /* Register range for uffd-wp. */ + if (userfaultfd_open(&features)) { + ksft_test_result_fail("userfaultfd_open() failed\n"); + goto out; + } + if (uffd_register(uffd, mem, size, false, true, false)) { + ksft_test_result_fail("uffd_register() failed\n"); + goto out; + } + wp_prms.mode = UFFDIO_WRITEPROTECT_MODE_WP; + wp_prms.range.start = (uintptr_t)mem; + wp_prms.range.len = size; + if (ioctl(uffd, UFFDIO_WRITEPROTECT, &wp_prms)) { + ksft_test_result_fail("ioctl(UFFDIO_WRITEPROTECT) failed\n"); + goto out; + } + + if (swapout) { + madvise(mem, size, MADV_PAGEOUT); + if (!range_is_swapped(mem, size)) { + ksft_test_result_skip("MADV_PAGEOUT did not work, is swap enabled?\n"); + goto out; + } + } + + /* Check that uffd-wp is set for all PTEs in range. */ + if (!check_uffd_wp_state(mem, size, true)) + goto out; + + /* + * Move the mapping to a new, aligned location. Since + * UFFD_FEATURE_EVENT_REMAP is not set, we expect the uffd-wp bit for + * each PTE to be cleared in the new mapping. + */ + addr = mmap_aligned(size, PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS); + if (addr == MAP_FAILED) { + ksft_test_result_fail("mmap_aligned() failed\n"); + goto out; + } + if (mremap(mem, size, size, MREMAP_FIXED | MREMAP_MAYMOVE, addr) == MAP_FAILED) { + ksft_test_result_fail("mremap() failed\n"); + munmap(addr, size); + goto out; + } + mem = addr; + + /* Check that uffd-wp is cleared for all PTEs in range. */ + if (!check_uffd_wp_state(mem, size, false)) + goto out; + + ksft_test_result_pass("%s(size=%zu, private=%s, swapout=%s, hugetlb=%s)\n", + __func__, + size, + private ? "true" : "false", + swapout ? "true" : "false", + hugetlb ? "true" : "false"); +out: + if (mem) + munmap(mem, size); + if (uffd >= 0) { + close(uffd); + uffd = -1; + } +} + +struct testcase { + size_t *sizes; + int *nr_sizes; + bool private; + bool swapout; + bool hugetlb; +}; + +static const struct testcase testcases[] = { + /* base pages. */ + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = false, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = true, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = false, + .swapout = true, + .hugetlb = false, + }, + { + .sizes = &pagesize, + .nr_sizes = &nr_pagesizes, + .private = true, + .swapout = true, + .hugetlb = false, + }, + + /* thp. */ + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = false, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = true, + .swapout = false, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = false, + .swapout = true, + .hugetlb = false, + }, + { + .sizes = thpsizes, + .nr_sizes = &nr_thpsizes, + .private = true, + .swapout = true, + .hugetlb = false, + }, + + /* hugetlb. */ + { + .sizes = hugetlbsizes, + .nr_sizes = &nr_hugetlbsizes, + .private = false, + .swapout = false, + .hugetlb = true, + }, + { + .sizes = hugetlbsizes, + .nr_sizes = &nr_hugetlbsizes, + .private = true, + .swapout = false, + .hugetlb = true, + }, +}; + +int main(int argc, char **argv) +{ + struct thp_settings settings; + int i, j, plan = 0; + + pagesize = getpagesize(); + nr_thpsizes = detect_thp_sizes(thpsizes, ARRAY_SIZE(thpsizes)); + nr_hugetlbsizes = detect_hugetlb_page_sizes(hugetlbsizes, + ARRAY_SIZE(hugetlbsizes)); + + /* If THP is supported, save THP settings and initially disable THP. */ + if (nr_thpsizes) { + thp_save_settings(); + thp_read_settings(&settings); + for (i = 0; i < NR_ORDERS; i++) { + settings.hugepages[i].enabled = THP_NEVER; + settings.shmem_hugepages[i].enabled = SHMEM_NEVER; + } + thp_push_settings(&settings); + } + + for (i = 0; i < ARRAY_SIZE(testcases); i++) + plan += *testcases[i].nr_sizes; + ksft_set_plan(plan); + + pagemap_fd = open("/proc/self/pagemap", O_RDONLY); + if (pagemap_fd < 0) + ksft_exit_fail_msg("opening pagemap failed\n"); + + for (i = 0; i < ARRAY_SIZE(testcases); i++) { + const struct testcase *tc = &testcases[i]; + + for (j = 0; j < *tc->nr_sizes; j++) + test_one_folio(tc->sizes[j], tc->private, tc->swapout, + tc->hugetlb); + } + + /* If THP is supported, restore original THP settings. */ + if (nr_thpsizes) + thp_restore_settings(); + + i = ksft_get_fail_cnt(); + if (i) + ksft_exit_fail_msg("%d out of %d tests failed\n", + i, ksft_test_num()); + ksft_exit_pass(); +} diff --git a/tools/testing/selftests/mm/virtual_address_range.c b/tools/testing/selftests/mm/virtual_address_range.c index 2a2b69e91950..b380e102b22f 100644 --- a/tools/testing/selftests/mm/virtual_address_range.c +++ b/tools/testing/selftests/mm/virtual_address_range.c @@ -10,10 +10,12 @@ #include <string.h> #include <unistd.h> #include <errno.h> +#include <sys/prctl.h> #include <sys/mman.h> #include <sys/time.h> #include <fcntl.h> +#include "vm_util.h" #include "../kselftest.h" /* @@ -82,6 +84,24 @@ static void validate_addr(char *ptr, int high_addr) ksft_exit_fail_msg("Bad address %lx\n", addr); } +static void mark_range(char *ptr, size_t size) +{ + if (prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, ptr, size, "virtual_address_range") == -1) { + if (errno == EINVAL) { + /* Depends on CONFIG_ANON_VMA_NAME */ + ksft_test_result_skip("prctl(PR_SET_VMA_ANON_NAME) not supported\n"); + ksft_finished(); + } else { + ksft_exit_fail_perror("prctl(PR_SET_VMA_ANON_NAME) failed\n"); + } + } +} + +static int is_marked_vma(const char *vma_name) +{ + return vma_name && !strcmp(vma_name, "[anon:virtual_address_range]\n"); +} + static int validate_lower_address_hint(void) { char *ptr; @@ -116,12 +136,17 @@ static int validate_complete_va_space(void) prev_end_addr = 0; while (fgets(line, sizeof(line), file)) { + const char *vma_name = NULL; + int vma_name_start = 0; unsigned long hop; - if (sscanf(line, "%lx-%lx %s[rwxp-]", - &start_addr, &end_addr, prot) != 3) + if (sscanf(line, "%lx-%lx %4s %*s %*s %*s %n", + &start_addr, &end_addr, prot, &vma_name_start) != 3) ksft_exit_fail_msg("cannot parse /proc/self/maps\n"); + if (vma_name_start) + vma_name = line + vma_name_start; + /* end of userspace mappings; ignore vsyscall mapping */ if (start_addr & (1UL << 63)) return 0; @@ -135,6 +160,9 @@ static int validate_complete_va_space(void) if (prot[0] != 'r') continue; + if (check_vmflag_io((void *)start_addr)) + continue; + /* * Confirm whether MAP_CHUNK_SIZE chunk can be found or not. * If write succeeds, no need to check MAP_CHUNK_SIZE - 1 @@ -149,6 +177,9 @@ static int validate_complete_va_space(void) return 1; lseek(fd, 0, SEEK_SET); + if (is_marked_vma(vma_name)) + munmap((char *)(start_addr + hop), MAP_CHUNK_SIZE); + hop += MAP_CHUNK_SIZE; } } @@ -166,7 +197,7 @@ int main(int argc, char *argv[]) ksft_set_plan(1); for (i = 0; i < NR_CHUNKS_LOW; i++) { - ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + ptr[i] = mmap(NULL, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (ptr[i] == MAP_FAILED) { @@ -175,6 +206,7 @@ int main(int argc, char *argv[]) break; } + mark_range(ptr[i], MAP_CHUNK_SIZE); validate_addr(ptr[i], 0); } lchunks = i; @@ -186,12 +218,13 @@ int main(int argc, char *argv[]) for (i = 0; i < NR_CHUNKS_HIGH; i++) { hint = hint_addr(); - hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ | PROT_WRITE, + hptr[i] = mmap(hint, MAP_CHUNK_SIZE, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); if (hptr[i] == MAP_FAILED) break; + mark_range(ptr[i], MAP_CHUNK_SIZE); validate_addr(hptr[i], 1); } hchunks = i; diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index d8d0cf04bb57..a36734fb62f3 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -2,6 +2,7 @@ #include <string.h> #include <fcntl.h> #include <dirent.h> +#include <inttypes.h> #include <sys/ioctl.h> #include <linux/userfaultfd.h> #include <linux/fs.h> @@ -138,7 +139,7 @@ void clear_softdirty(void) ksft_exit_fail_msg("opening clear_refs failed\n"); ret = write(fd, ctrl, strlen(ctrl)); close(fd); - if (ret != strlen(ctrl)) + if (ret != (signed int)strlen(ctrl)) ksft_exit_fail_msg("writing clear_refs failed\n"); } @@ -193,13 +194,11 @@ err_out: return rss_anon; } -bool __check_huge(void *addr, char *pattern, int nr_hpages, - uint64_t hpage_size) +char *__get_smap_entry(void *addr, const char *pattern, char *buf, size_t len) { - uint64_t thp = -1; int ret; FILE *fp; - char buffer[MAX_LINE_LENGTH]; + char *entry = NULL; char addr_pattern[MAX_LINE_LENGTH]; ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-", @@ -211,23 +210,40 @@ bool __check_huge(void *addr, char *pattern, int nr_hpages, if (!fp) ksft_exit_fail_msg("%s: Failed to open file %s\n", __func__, SMAP_FILE_PATH); - if (!check_for_pattern(fp, addr_pattern, buffer, sizeof(buffer))) + if (!check_for_pattern(fp, addr_pattern, buf, len)) goto err_out; - /* - * Fetch the pattern in the same block and check the number of - * hugepages. - */ - if (!check_for_pattern(fp, pattern, buffer, sizeof(buffer))) + /* Fetch the pattern in the same block */ + if (!check_for_pattern(fp, pattern, buf, len)) goto err_out; - snprintf(addr_pattern, MAX_LINE_LENGTH, "%s%%9ld kB", pattern); + /* Trim trailing newline */ + entry = strchr(buf, '\n'); + if (entry) + *entry = '\0'; - if (sscanf(buffer, addr_pattern, &thp) != 1) - ksft_exit_fail_msg("Reading smap error\n"); + entry = buf + strlen(pattern); err_out: fclose(fp); + return entry; +} + +bool __check_huge(void *addr, char *pattern, int nr_hpages, + uint64_t hpage_size) +{ + char buffer[MAX_LINE_LENGTH]; + uint64_t thp = -1; + char *entry; + + entry = __get_smap_entry(addr, pattern, buffer, sizeof(buffer)); + if (!entry) + goto err_out; + + if (sscanf(entry, "%9" SCNu64 " kB", &thp) != 1) + ksft_exit_fail_msg("Reading smap error\n"); + +err_out: return thp == (nr_hpages * (hpage_size >> 10)); } @@ -384,3 +400,27 @@ unsigned long get_free_hugepages(void) fclose(f); return fhp; } + +bool check_vmflag_io(void *addr) +{ + char buffer[MAX_LINE_LENGTH]; + const char *flags; + size_t flaglen; + + flags = __get_smap_entry(addr, "VmFlags:", buffer, sizeof(buffer)); + if (!flags) + ksft_exit_fail_msg("%s: No VmFlags for %p\n", __func__, addr); + + while (true) { + flags += strspn(flags, " "); + + flaglen = strcspn(flags, " "); + if (!flaglen) + return false; + + if (flaglen == strlen("io") && !memcmp(flags, "io", flaglen)) + return true; + + flags += flaglen; + } +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index 2eaed8209925..b60ac68a9dc8 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -53,6 +53,7 @@ int uffd_unregister(int uffd, void *addr, uint64_t len); int uffd_register_with_ioctls(int uffd, void *addr, uint64_t len, bool miss, bool wp, bool minor, uint64_t *ioctls); unsigned long get_free_hugepages(void); +bool check_vmflag_io(void *addr); /* * On ppc64 this will only work with radix 2M hugepage size diff --git a/tools/testing/selftests/mm/write_to_hugetlbfs.c b/tools/testing/selftests/mm/write_to_hugetlbfs.c index 1289d311efd7..34c91f7e6128 100644 --- a/tools/testing/selftests/mm/write_to_hugetlbfs.c +++ b/tools/testing/selftests/mm/write_to_hugetlbfs.c @@ -89,7 +89,7 @@ int main(int argc, char **argv) size = atoi(optarg); break; case 'p': - strncpy(path, optarg, sizeof(path)); + strncpy(path, optarg, sizeof(path) - 1); break; case 'm': if (atoi(optarg) >= MAX_METHOD) { diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py index d10f420e4ef6..fd0d959914e4 100755 --- a/tools/testing/selftests/net/bpf_offload.py +++ b/tools/testing/selftests/net/bpf_offload.py @@ -215,12 +215,14 @@ def bpftool_map_list_wait(expected=0, n_retry=20, ns=""): raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None, - fail=True, include_stderr=False): + fail=True, include_stderr=False, dev_bind=None): args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name) if prog_type is not None: args += " type " + prog_type if dev is not None: args += " dev " + dev + elif dev_bind is not None: + args += " xdpmeta_dev " + dev_bind if len(maps): args += " map " + " map ".join(maps) @@ -980,6 +982,16 @@ try: rm("/sys/fs/bpf/offload") sim.wait_for_flush() + bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/devbound", + dev_bind=sim['ifname']) + devbound = bpf_pinned("/sys/fs/bpf/devbound") + start_test("Test dev-bound program in generic mode...") + ret, _, err = sim.set_xdp(devbound, "generic", fail=False, include_stderr=True) + fail(ret == 0, "devbound program in generic mode allowed") + check_extack(err, "Can't attach device-bound programs in generic mode.", args) + rm("/sys/fs/bpf/devbound") + sim.wait_for_flush() + start_test("Test XDP load failure...") sim.dfs["dev/bpf_bind_verifier_accept"] = 0 ret, _, err = bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/offload", diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh index 3885a2a91f7d..baed5e380dae 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh @@ -20,6 +20,7 @@ ALL_TESTS=" test_port_range_ipv4_tcp test_port_range_ipv6_udp test_port_range_ipv6_tcp + test_port_range_ipv4_udp_drop " NUM_NETIFS=4 @@ -194,6 +195,51 @@ test_port_range_ipv6_tcp() __test_port_range $proto $ip_proto $sip $dip $mode "$name" } +test_port_range_ipv4_udp_drop() +{ + local proto=ipv4 + local ip_proto=udp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 UDP Drop" + local dmac=$(mac_get $h2) + local smac=$(mac_get $h1) + local sport_min=2000 + local sport_max=3000 + local sport_mid=$((sport_min + (sport_max - sport_min) / 2)) + local dport=5000 + + RET=0 + + tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport \ + action drop + + # Test ports outside range - should pass + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_min - 1)),dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$dport" + + # Test ports inside range - should be dropped + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_mid,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_max,dp=$dport" + + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Filter did not drop the expected number of packets" + + tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower + + log_test "Port range matching - $name" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index 18b9443454a9..c22623b9a2a5 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../../ @@ -9,7 +9,10 @@ TEST_FILES := ../../../../../Documentation/netlink/specs TEST_FILES += ../../../../net/ynl TEST_GEN_FILES += csum +TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c)) TEST_INCLUDES := $(wildcard py/*.py sh/*.sh) include ../../lib.mk + +include ../bpf.mk diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c new file mode 100644 index 000000000000..d988b2e0cee8 --- /dev/null +++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define KBUILD_MODNAME "xdp_dummy" +#include <linux/bpf.h> +#include <bpf/bpf_helpers.h> + +SEC("xdp") +int xdp_dummy_prog(struct xdp_md *ctx) +{ + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 8e3fc05a5397..c76525fe2b84 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 414addef9a45..d240d02fa443 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1302,7 +1302,7 @@ again: return ret; if (cfg_truncate > 0) { - xdisconnect(fd); + shutdown(fd, SHUT_WR); } else if (--cfg_repeat > 0) { xdisconnect(fd); diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile index 2f1508abc826..3fd1da2ec07d 100644 --- a/tools/testing/selftests/net/openvswitch/Makefile +++ b/tools/testing/selftests/net/openvswitch/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := openvswitch.sh diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index e15c43b7359b..ef8b25a606d8 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -39,11 +39,13 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then # xfail tests that are known flaky with dbg config, not fixable. # still run them for coverage (and expect 100% pass without dbg). declare -ar xfail_list=( + "tcp_eor_no-coalesce-retrans.pkt" "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_slow_start_slow-start-after-win-update.pkt" "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" "tcp_zerocopy_epoll_.*.pkt" - "tcp_tcp_info_tcp-info-*-limited.pkt" + "tcp_tcp_info_tcp-info-.*-limited.pkt" ) readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3f2fca02fec5..36ff28af4b19 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -103,6 +103,19 @@ struct testcase testcases_v4[] = { .r_num_mss = 1, }, { + /* datalen <= MSS < gso_len: will fall back to no GSO */ + .tlen = CONST_MSS_V4, + .gso_len = CONST_MSS_V4 + 1, + .r_num_mss = 0, + .r_len_last = CONST_MSS_V4, + }, + { + /* MSS < datalen < gso_len: fail */ + .tlen = CONST_MSS_V4 + 1, + .gso_len = CONST_MSS_V4 + 2, + .tfail = true, + }, + { /* send a single MSS + 1B */ .tlen = CONST_MSS_V4 + 1, .gso_len = CONST_MSS_V4, @@ -206,6 +219,19 @@ struct testcase testcases_v6[] = { .r_num_mss = 1, }, { + /* datalen <= MSS < gso_len: will fall back to no GSO */ + .tlen = CONST_MSS_V6, + .gso_len = CONST_MSS_V6 + 1, + .r_num_mss = 0, + .r_len_last = CONST_MSS_V6, + }, + { + /* MSS < datalen < gso_len: fail */ + .tlen = CONST_MSS_V6 + 1, + .gso_len = CONST_MSS_V6 + 2, + .tfail = true + }, + { /* send a single MSS + 1B */ .tlen = CONST_MSS_V6 + 1, .gso_len = CONST_MSS_V6, diff --git a/tools/testing/selftests/nolibc/Makefile b/tools/testing/selftests/nolibc/Makefile index e92e0b885861..7d14a7c0cb62 100644 --- a/tools/testing/selftests/nolibc/Makefile +++ b/tools/testing/selftests/nolibc/Makefile @@ -43,6 +43,7 @@ cc-option = $(call __cc-option, $(CC),$(CLANG_CROSS_FLAGS),$(1),$(2)) # configure default variants for target kernel supported architectures XARCH_powerpc = ppc XARCH_mips = mips32le +XARCH_riscv = riscv64 XARCH = $(or $(XARCH_$(ARCH)),$(ARCH)) # map from user input variants to their kernel supported architectures @@ -51,6 +52,8 @@ ARCH_ppc64 = powerpc ARCH_ppc64le = powerpc ARCH_mips32le = mips ARCH_mips32be = mips +ARCH_riscv32 = riscv +ARCH_riscv64 = riscv ARCH := $(or $(ARCH_$(XARCH)),$(XARCH)) # kernel image names by architecture @@ -65,6 +68,8 @@ IMAGE_ppc = vmlinux IMAGE_ppc64 = vmlinux IMAGE_ppc64le = arch/powerpc/boot/zImage IMAGE_riscv = arch/riscv/boot/Image +IMAGE_riscv32 = arch/riscv/boot/Image +IMAGE_riscv64 = arch/riscv/boot/Image IMAGE_s390 = arch/s390/boot/bzImage IMAGE_loongarch = arch/loongarch/boot/vmlinuz.efi IMAGE = $(objtree)/$(IMAGE_$(XARCH)) @@ -82,6 +87,8 @@ DEFCONFIG_ppc = pmac32_defconfig DEFCONFIG_ppc64 = powernv_be_defconfig DEFCONFIG_ppc64le = powernv_defconfig DEFCONFIG_riscv = defconfig +DEFCONFIG_riscv32 = rv32_defconfig +DEFCONFIG_riscv64 = defconfig DEFCONFIG_s390 = defconfig DEFCONFIG_loongarch = defconfig DEFCONFIG = $(DEFCONFIG_$(XARCH)) @@ -104,6 +111,8 @@ QEMU_ARCH_ppc = ppc QEMU_ARCH_ppc64 = ppc64 QEMU_ARCH_ppc64le = ppc64 QEMU_ARCH_riscv = riscv64 +QEMU_ARCH_riscv32 = riscv32 +QEMU_ARCH_riscv64 = riscv64 QEMU_ARCH_s390 = s390x QEMU_ARCH_loongarch = loongarch64 QEMU_ARCH = $(QEMU_ARCH_$(XARCH)) @@ -130,6 +139,8 @@ QEMU_ARGS_ppc = -M g3beige -append "console=ttyS0 panic=-1 $(TEST:%=NOLIB QEMU_ARGS_ppc64 = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_ppc64le = -M powernv -append "console=hvc0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_riscv = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv32 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" +QEMU_ARGS_riscv64 = -M virt -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_s390 = -M s390-ccw-virtio -append "console=ttyS0 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS_loongarch = -M virt -append "console=ttyS0,115200 panic=-1 $(TEST:%=NOLIBC_TEST=%)" QEMU_ARGS = -m 1G $(QEMU_ARGS_$(XARCH)) $(QEMU_ARGS_BIOS) $(QEMU_ARGS_EXTRA) diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c index 6fba7025c5e3..0e0e3b48a8c3 100644 --- a/tools/testing/selftests/nolibc/nolibc-test.c +++ b/tools/testing/selftests/nolibc/nolibc-test.c @@ -302,7 +302,10 @@ int expect_syszr(int expr, int llen) { int ret = 0; - if (expr) { + if (errno == ENOSYS) { + llen += printf(" = ENOSYS"); + result(llen, SKIPPED); + } else if (expr) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); result(llen, FAIL); @@ -342,7 +345,10 @@ int expect_sysne(int expr, int llen, int val) { int ret = 0; - if (expr == val) { + if (errno == ENOSYS) { + llen += printf(" = ENOSYS"); + result(llen, SKIPPED); + } else if (expr == val) { ret = 1; llen += printf(" = %d %s ", expr, errorname(errno)); result(llen, FAIL); @@ -367,7 +373,9 @@ int expect_syserr2(int expr, int expret, int experr1, int experr2, int llen) int _errno = errno; llen += printf(" = %d %s ", expr, errorname(_errno)); - if (expr != expret || (_errno != experr1 && _errno != experr2)) { + if (errno == ENOSYS) { + result(llen, SKIPPED); + } else if (expr != expret || (_errno != experr1 && _errno != experr2)) { ret = 1; if (experr2 == 0) llen += printf(" != (%d %s) ", expret, errorname(experr1)); @@ -1229,19 +1237,20 @@ int run_stdlib(int min, int max) static int expect_vfprintf(int llen, int c, const char *expected, const char *fmt, ...) { - int ret, fd; + int ret, pipefd[2]; ssize_t w, r; char buf[100]; FILE *memfile; va_list args; - fd = open("/tmp", O_TMPFILE | O_EXCL | O_RDWR, 0600); - if (fd == -1) { - result(llen, SKIPPED); - return 0; + ret = pipe(pipefd); + if (ret == -1) { + llen += printf(" pipe() != %s", strerror(errno)); + result(llen, FAIL); + return 1; } - memfile = fdopen(fd, "w+"); + memfile = fdopen(pipefd[1], "w"); if (!memfile) { result(llen, FAIL); return 1; @@ -1257,13 +1266,10 @@ static int expect_vfprintf(int llen, int c, const char *expected, const char *fm return 1; } - fflush(memfile); - lseek(fd, 0, SEEK_SET); - - r = read(fd, buf, sizeof(buf) - 1); - fclose(memfile); + r = read(pipefd[0], buf, sizeof(buf) - 1); + if (r != w) { llen += printf(" written(%d) != read(%d)", (int)w, (int)r); result(llen, FAIL); @@ -1323,7 +1329,8 @@ static int run_protection(int min __attribute__((unused)), int max __attribute__((unused))) { pid_t pid; - int llen = 0, status; + int llen = 0, ret; + siginfo_t siginfo = {}; struct rlimit rlimit = { 0, 0 }; llen += printf("0 -fstackprotector "); @@ -1361,10 +1368,11 @@ static int run_protection(int min __attribute__((unused)), return 1; default: - pid = waitpid(pid, &status, 0); + ret = waitid(P_PID, pid, &siginfo, WEXITED); - if (pid == -1 || !WIFSIGNALED(status) || WTERMSIG(status) != SIGABRT) { - llen += printf("waitpid()"); + if (ret != 0 || siginfo.si_signo != SIGCHLD || + siginfo.si_code != CLD_KILLED || siginfo.si_status != SIGABRT) { + llen += printf("waitid()"); result(llen, FAIL); return 1; } diff --git a/tools/testing/selftests/nolibc/run-tests.sh b/tools/testing/selftests/nolibc/run-tests.sh index e7ecda4ae796..9c5160c53881 100755 --- a/tools/testing/selftests/nolibc/run-tests.sh +++ b/tools/testing/selftests/nolibc/run-tests.sh @@ -17,7 +17,7 @@ perform_download=0 test_mode=system werror=1 llvm= -archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv s390 loongarch" +archs="i386 x86_64 arm64 arm mips32le mips32be ppc ppc64 ppc64le riscv32 riscv64 s390 loongarch" TEMP=$(getopt -o 'j:d:c:b:a:m:pelh' -n "$0" -- "$@") @@ -143,6 +143,13 @@ test_arch() { arch=$1 ct_arch=$(crosstool_arch "$arch") ct_abi=$(crosstool_abi "$1") + + if [ ! -d "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/." ]; then + echo "No toolchain found in ${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}." + echo "Did you install the toolchains or set the correct arch ? Rerun with -h for help." + return 1 + fi + cross_compile=$(realpath "${download_location}gcc-${crosstool_version}-nolibc/${ct_arch}-${ct_abi}/bin/${ct_arch}-${ct_abi}-") build_dir="${build_location}/${arch}" if [ "$werror" -ne 0 ]; then diff --git a/tools/testing/selftests/pci_endpoint/.gitignore b/tools/testing/selftests/pci_endpoint/.gitignore new file mode 100644 index 000000000000..6a4837a3e034 --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +pci_endpoint_test diff --git a/tools/testing/selftests/pci_endpoint/Makefile b/tools/testing/selftests/pci_endpoint/Makefile new file mode 100644 index 000000000000..bf21ebf20b4a --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +CFLAGS += -O2 -Wl,-no-as-needed -Wall $(KHDR_INCLUDES) +LDFLAGS += -lrt -lpthread -lm + +TEST_GEN_PROGS = pci_endpoint_test + +include ../lib.mk diff --git a/tools/testing/selftests/pci_endpoint/config b/tools/testing/selftests/pci_endpoint/config new file mode 100644 index 000000000000..7cdcf117db8d --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/config @@ -0,0 +1,4 @@ +CONFIG_PCI_ENDPOINT=y +CONFIG_PCI_ENDPOINT_CONFIGFS=y +CONFIG_PCI_EPF_TEST=m +CONFIG_PCI_ENDPOINT_TEST=m diff --git a/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c new file mode 100644 index 000000000000..c267b822c108 --- /dev/null +++ b/tools/testing/selftests/pci_endpoint/pci_endpoint_test.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Kselftest for PCI Endpoint Subsystem + * + * Copyright (c) 2022 Samsung Electronics Co., Ltd. + * https://www.samsung.com + * Author: Aman Gupta <aman1.gupta@samsung.com> + * + * Copyright (c) 2024, Linaro Ltd. + * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> + */ + +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/ioctl.h> +#include <unistd.h> + +#include "../../../../include/uapi/linux/pcitest.h" + +#include "../kselftest_harness.h" + +#define pci_ep_ioctl(cmd, arg) \ +({ \ + ret = ioctl(self->fd, cmd, arg); \ + ret = ret < 0 ? -errno : 0; \ +}) + +static const char *test_device = "/dev/pci-endpoint-test.0"; +static const unsigned long test_size[5] = { 1, 1024, 1025, 1024000, 1024001 }; + +FIXTURE(pci_ep_bar) +{ + int fd; +}; + +FIXTURE_SETUP(pci_ep_bar) +{ + self->fd = open(test_device, O_RDWR); + + ASSERT_NE(-1, self->fd) TH_LOG("Can't open PCI Endpoint Test device"); +} + +FIXTURE_TEARDOWN(pci_ep_bar) +{ + close(self->fd); +} + +FIXTURE_VARIANT(pci_ep_bar) +{ + int barno; +}; + +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR0) { .barno = 0 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR1) { .barno = 1 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR2) { .barno = 2 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR3) { .barno = 3 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR4) { .barno = 4 }; +FIXTURE_VARIANT_ADD(pci_ep_bar, BAR5) { .barno = 5 }; + +TEST_F(pci_ep_bar, BAR_TEST) +{ + int ret; + + pci_ep_ioctl(PCITEST_BAR, variant->barno); + EXPECT_FALSE(ret) TH_LOG("Test failed for BAR%d", variant->barno); +} + +FIXTURE(pci_ep_basic) +{ + int fd; +}; + +FIXTURE_SETUP(pci_ep_basic) +{ + self->fd = open(test_device, O_RDWR); + + ASSERT_NE(-1, self->fd) TH_LOG("Can't open PCI Endpoint Test device"); +} + +FIXTURE_TEARDOWN(pci_ep_basic) +{ + close(self->fd); +} + +TEST_F(pci_ep_basic, CONSECUTIVE_BAR_TEST) +{ + int ret; + + pci_ep_ioctl(PCITEST_BARS, 0); + EXPECT_FALSE(ret) TH_LOG("Consecutive BAR test failed"); +} + +TEST_F(pci_ep_basic, LEGACY_IRQ_TEST) +{ + int ret; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 0); + ASSERT_EQ(0, ret) TH_LOG("Can't set Legacy IRQ type"); + + pci_ep_ioctl(PCITEST_LEGACY_IRQ, 0); + EXPECT_FALSE(ret) TH_LOG("Test failed for Legacy IRQ"); +} + +TEST_F(pci_ep_basic, MSI_TEST) +{ + int ret, i; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 1; i <= 32; i++) { + pci_ep_ioctl(PCITEST_MSI, i); + EXPECT_FALSE(ret) TH_LOG("Test failed for MSI%d", i); + } +} + +TEST_F(pci_ep_basic, MSIX_TEST) +{ + int ret, i; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 2); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI-X IRQ type"); + + for (i = 1; i <= 2048; i++) { + pci_ep_ioctl(PCITEST_MSIX, i); + EXPECT_FALSE(ret) TH_LOG("Test failed for MSI-X%d", i); + } +} + +FIXTURE(pci_ep_data_transfer) +{ + int fd; +}; + +FIXTURE_SETUP(pci_ep_data_transfer) +{ + self->fd = open(test_device, O_RDWR); + + ASSERT_NE(-1, self->fd) TH_LOG("Can't open PCI Endpoint Test device"); +} + +FIXTURE_TEARDOWN(pci_ep_data_transfer) +{ + close(self->fd); +} + +FIXTURE_VARIANT(pci_ep_data_transfer) +{ + bool use_dma; +}; + +FIXTURE_VARIANT_ADD(pci_ep_data_transfer, memcpy) +{ + .use_dma = false, +}; + +FIXTURE_VARIANT_ADD(pci_ep_data_transfer, dma) +{ + .use_dma = true, +}; + +TEST_F(pci_ep_data_transfer, READ_TEST) +{ + struct pci_endpoint_test_xfer_param param = {}; + int ret, i; + + if (variant->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 0; i < ARRAY_SIZE(test_size); i++) { + param.size = test_size[i]; + pci_ep_ioctl(PCITEST_READ, ¶m); + EXPECT_FALSE(ret) TH_LOG("Test failed for size (%ld)", + test_size[i]); + } +} + +TEST_F(pci_ep_data_transfer, WRITE_TEST) +{ + struct pci_endpoint_test_xfer_param param = {}; + int ret, i; + + if (variant->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 0; i < ARRAY_SIZE(test_size); i++) { + param.size = test_size[i]; + pci_ep_ioctl(PCITEST_WRITE, ¶m); + EXPECT_FALSE(ret) TH_LOG("Test failed for size (%ld)", + test_size[i]); + } +} + +TEST_F(pci_ep_data_transfer, COPY_TEST) +{ + struct pci_endpoint_test_xfer_param param = {}; + int ret, i; + + if (variant->use_dma) + param.flags = PCITEST_FLAGS_USE_DMA; + + pci_ep_ioctl(PCITEST_SET_IRQTYPE, 1); + ASSERT_EQ(0, ret) TH_LOG("Can't set MSI IRQ type"); + + for (i = 0; i < ARRAY_SIZE(test_size); i++) { + param.size = test_size[i]; + pci_ep_ioctl(PCITEST_COPY, ¶m); + EXPECT_FALSE(ret) TH_LOG("Test failed for size (%ld)", + test_size[i]); + } +} +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index 9faa686f90e4..e9728e86b4f2 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -497,7 +497,7 @@ static int child_poll_leader_exit_test(void *args) pthread_create(&t2, NULL, test_pidfd_poll_leader_exit_thread, NULL); /* - * glibc exit calls exit_group syscall, so explicity call exit only + * glibc exit calls exit_group syscall, so explicitly call exit only * so that only the group leader exits, leaving the threads alone. */ *child_exit_secs = time(NULL); diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index f408bd6bfc3d..984534cfbf1b 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -8,5 +8,6 @@ TEST_GEN_PROGS := resctrl_tests LOCAL_HDRS += $(wildcard *.h) include ../lib.mk +CFLAGS += -I$(top_srcdir)/tools/include $(OUTPUT)/resctrl_tests: $(wildcard *.c) diff --git a/tools/testing/selftests/resctrl/cmt_test.c b/tools/testing/selftests/resctrl/cmt_test.c index 3bbf3042fb06..d09e693dc739 100644 --- a/tools/testing/selftests/resctrl/cmt_test.c +++ b/tools/testing/selftests/resctrl/cmt_test.c @@ -169,8 +169,8 @@ static int cmt_run_test(const struct resctrl_test *test, const struct user_param return ret; ret = check_results(¶m, span, n); - if (ret && (get_vendor() == ARCH_INTEL)) - ksft_print_msg("Intel CMT may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } diff --git a/tools/testing/selftests/resctrl/mba_test.c b/tools/testing/selftests/resctrl/mba_test.c index 536d9089d2f6..c7e9adc0368f 100644 --- a/tools/testing/selftests/resctrl/mba_test.c +++ b/tools/testing/selftests/resctrl/mba_test.c @@ -201,6 +201,8 @@ static int mba_run_test(const struct resctrl_test *test, const struct user_param return ret; ret = check_results(); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } diff --git a/tools/testing/selftests/resctrl/mbm_test.c b/tools/testing/selftests/resctrl/mbm_test.c index 315b2ef3b3bc..84d8bc250539 100644 --- a/tools/testing/selftests/resctrl/mbm_test.c +++ b/tools/testing/selftests/resctrl/mbm_test.c @@ -160,8 +160,8 @@ static int mbm_run_test(const struct resctrl_test *test, const struct user_param return ret; ret = check_results(param.fill_buf ? param.fill_buf->buf_size : 0); - if (ret && (get_vendor() == ARCH_INTEL)) - ksft_print_msg("Intel MBM may be inaccurate when Sub-NUMA Clustering is enabled. Check BIOS configuration.\n"); + if (ret && (get_vendor() == ARCH_INTEL) && !snc_kernel_support()) + ksft_print_msg("Kernel doesn't support Sub-NUMA Clustering but it is enabled on the system.\n"); return ret; } diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index dab1953fc7a0..cd3adfc14969 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -11,6 +11,7 @@ #include <signal.h> #include <dirent.h> #include <stdbool.h> +#include <ctype.h> #include <sys/stat.h> #include <sys/ioctl.h> #include <sys/mount.h> @@ -21,6 +22,7 @@ #include <sys/eventfd.h> #include <asm/unistd.h> #include <linux/perf_event.h> +#include <linux/compiler.h> #include "../kselftest.h" #define MB (1024 * 1024) @@ -156,8 +158,11 @@ struct perf_event_read { */ extern volatile int *value_sink; +extern int snc_unreliable; + extern char llc_occup_path[1024]; +int snc_nodes_per_l3_cache(void); int get_vendor(void); bool check_resctrlfs_support(void); int filter_dmesg(void); @@ -198,6 +203,7 @@ void ctrlc_handler(int signum, siginfo_t *info, void *ptr); int signal_handler_register(const struct resctrl_test *test); void signal_handler_unregister(void); unsigned int count_bits(unsigned long n); +int snc_kernel_support(void); void perf_event_attr_initialize(struct perf_event_attr *pea, __u64 config); void perf_event_initialize_read_format(struct perf_event_read *pe_read); diff --git a/tools/testing/selftests/resctrl/resctrl_tests.c b/tools/testing/selftests/resctrl/resctrl_tests.c index 3335af815b21..5154ffd821c4 100644 --- a/tools/testing/selftests/resctrl/resctrl_tests.c +++ b/tools/testing/selftests/resctrl/resctrl_tests.c @@ -118,7 +118,7 @@ static bool test_vendor_specific_check(const struct resctrl_test *test) static void run_single_test(const struct resctrl_test *test, const struct user_params *uparams) { - int ret; + int ret, snc_mode; if (test->disabled) return; @@ -128,8 +128,15 @@ static void run_single_test(const struct resctrl_test *test, const struct user_p return; } + snc_mode = snc_nodes_per_l3_cache(); + ksft_print_msg("Starting %s test ...\n", test->name); + if (snc_mode == 1 && snc_unreliable && get_vendor() == ARCH_INTEL) { + ksft_test_result_skip("SNC detection unreliable due to offline CPUs. Test results may not be accurate if SNC enabled.\n"); + return; + } + if (test_prepare(test)) { ksft_exit_fail_msg("Abnormal failure when preparing for the test\n"); return; diff --git a/tools/testing/selftests/resctrl/resctrlfs.c b/tools/testing/selftests/resctrl/resctrlfs.c index d38d6dd90be4..195f04c4d158 100644 --- a/tools/testing/selftests/resctrl/resctrlfs.c +++ b/tools/testing/selftests/resctrl/resctrlfs.c @@ -13,6 +13,8 @@ #include "resctrl.h" +int snc_unreliable; + static int find_resctrl_mount(char *buffer) { FILE *mounts; @@ -157,6 +159,98 @@ int get_domain_id(const char *resource, int cpu_no, int *domain_id) } /* + * Count number of CPUs in a /sys bitmap + */ +static unsigned int count_sys_bitmap_bits(char *name) +{ + FILE *fp = fopen(name, "r"); + int count = 0, c; + + if (!fp) + return 0; + + while ((c = fgetc(fp)) != EOF) { + if (!isxdigit(c)) + continue; + switch (c) { + case 'f': + count++; + fallthrough; + case '7': case 'b': case 'd': case 'e': + count++; + fallthrough; + case '3': case '5': case '6': case '9': case 'a': case 'c': + count++; + fallthrough; + case '1': case '2': case '4': case '8': + count++; + break; + } + } + fclose(fp); + + return count; +} + +static bool cpus_offline_empty(void) +{ + char offline_cpus_str[64]; + FILE *fp; + + fp = fopen("/sys/devices/system/cpu/offline", "r"); + if (!fp) { + ksft_perror("Could not open /sys/devices/system/cpu/offline"); + return 0; + } + + if (fscanf(fp, "%63s", offline_cpus_str) < 0) { + if (!errno) { + fclose(fp); + return 1; + } + ksft_perror("Could not read /sys/devices/system/cpu/offline"); + } + + fclose(fp); + + return 0; +} + +/* + * Detect SNC by comparing #CPUs in node0 with #CPUs sharing LLC with CPU0. + * If any CPUs are offline declare the detection as unreliable. + */ +int snc_nodes_per_l3_cache(void) +{ + int node_cpus, cache_cpus; + static int snc_mode; + + if (!snc_mode) { + snc_mode = 1; + if (!cpus_offline_empty()) { + ksft_print_msg("Runtime SNC detection unreliable due to offline CPUs.\n"); + ksft_print_msg("Setting SNC mode to disabled.\n"); + snc_unreliable = 1; + return snc_mode; + } + node_cpus = count_sys_bitmap_bits("/sys/devices/system/node/node0/cpumap"); + cache_cpus = count_sys_bitmap_bits("/sys/devices/system/cpu/cpu0/cache/index3/shared_cpu_map"); + + if (!node_cpus || !cache_cpus) { + ksft_print_msg("Could not determine Sub-NUMA Cluster mode.\n"); + snc_unreliable = 1; + return snc_mode; + } + snc_mode = cache_cpus / node_cpus; + + if (snc_mode > 1) + ksft_print_msg("SNC-%d mode discovered.\n", snc_mode); + } + + return snc_mode; +} + +/* * get_cache_size - Get cache size for a specified CPU * @cpu_no: CPU number * @cache_type: Cache level L2/L3 @@ -211,6 +305,17 @@ int get_cache_size(int cpu_no, const char *cache_type, unsigned long *cache_size break; } + /* + * The amount of cache represented by each bit in the masks + * in the schemata file is reduced by a factor equal to SNC + * nodes per L3 cache. + * E.g. on a SNC-2 system with a 100MB L3 cache a test that + * allocates memory from its local SNC node (default behavior + * without using libnuma) will only see 50 MB llc_occupancy + * with a fully populated L3 mask in the schemata file. + */ + if (cache_num == 3) + *cache_size /= snc_nodes_per_l3_cache(); return 0; } @@ -852,3 +957,35 @@ unsigned int count_bits(unsigned long n) return count; } + +/** + * snc_kernel_support - Check for existence of mon_sub_L3_00 file that indicates + * SNC resctrl support on the kernel side. + * + * Return: 0 if not supported, 1 if SNC is disabled or SNC discovery is + * unreliable or SNC is both enabled and supported. + */ +int snc_kernel_support(void) +{ + char node_path[PATH_MAX]; + struct stat statbuf; + int ret; + + ret = snc_nodes_per_l3_cache(); + /* + * If SNC is disabled then its kernel support isn't important. If SNC + * got disabled because the discovery process was unreliable the + * snc_unreliable variable was set. It can be used to verify the SNC + * discovery reliability elsewhere in the selftest. + */ + if (ret == 1) + return ret; + + snprintf(node_path, sizeof(node_path), "%s/%s", RESCTRL_PATH, + "mon_data/mon_L3_00/mon_sub_L3_00"); + + if (!stat(node_path, &statbuf)) + return 1; + + return 0; +} diff --git a/tools/testing/selftests/ring-buffer/map_test.c b/tools/testing/selftests/ring-buffer/map_test.c index d10a847130fb..a58f520f2f41 100644 --- a/tools/testing/selftests/ring-buffer/map_test.c +++ b/tools/testing/selftests/ring-buffer/map_test.c @@ -233,12 +233,18 @@ TEST_F(map, data_mmap) ASSERT_NE(data, MAP_FAILED); munmap(data, data_len); - /* Overflow the available subbufs by 1 */ + /* Offset within ring-buffer bounds, mapping size overflow */ meta_len += desc->meta->subbuf_size * 2; data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, desc->cpu_fd, meta_len); ASSERT_EQ(data, MAP_FAILED); + /* Offset outside ring-buffer bounds */ + data_len = desc->meta->subbuf_size * desc->meta->nr_subbufs; + data = mmap(NULL, data_len, PROT_READ, MAP_SHARED, + desc->cpu_fd, data_len + (desc->meta->subbuf_size * 2)); + ASSERT_EQ(data, MAP_FAILED); + /* Verify meta-page padding */ if (desc->meta->meta_page_size > getpagesize()) { data_len = desc->meta->meta_page_size; diff --git a/tools/testing/selftests/riscv/vector/.gitignore b/tools/testing/selftests/riscv/vector/.gitignore index 9ae7964491d5..7d9c87cd0649 100644 --- a/tools/testing/selftests/riscv/vector/.gitignore +++ b/tools/testing/selftests/riscv/vector/.gitignore @@ -1,3 +1,4 @@ vstate_exec_nolibc vstate_prctl -v_initval_nolibc +v_initval +v_exec_initval_nolibc diff --git a/tools/testing/selftests/riscv/vector/Makefile b/tools/testing/selftests/riscv/vector/Makefile index bfff0ff4f3be..6f7497f4e7b3 100644 --- a/tools/testing/selftests/riscv/vector/Makefile +++ b/tools/testing/selftests/riscv/vector/Makefile @@ -2,18 +2,27 @@ # Copyright (C) 2021 ARM Limited # Originally tools/testing/arm64/abi/Makefile -TEST_GEN_PROGS := vstate_prctl v_initval_nolibc -TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc +TEST_GEN_PROGS := v_initval vstate_prctl +TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc v_exec_initval_nolibc include ../../lib.mk -$(OUTPUT)/vstate_prctl: vstate_prctl.c ../hwprobe/sys_hwprobe.S +$(OUTPUT)/sys_hwprobe.o: ../hwprobe/sys_hwprobe.S + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/v_helpers.o: v_helpers.c + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/vstate_prctl: vstate_prctl.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ $(OUTPUT)/vstate_exec_nolibc: vstate_exec_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc -$(OUTPUT)/v_initval_nolibc: v_initval_nolibc.c +$(OUTPUT)/v_initval: v_initval.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ + +$(OUTPUT)/v_exec_initval_nolibc: v_exec_initval_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c new file mode 100644 index 000000000000..35c0812e32de --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Get values of vector registers as soon as the program starts to test if + * is properly cleaning the values before starting a new program. Vector + * registers are caller saved, so no function calls may happen before reading + * the values. To further ensure consistency, this file is compiled without + * libc and without auto-vectorization. + * + * To be "clean" all values must be either all ones or all zeroes. + */ + +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) + +int main(int argc, char **argv) +{ + char prev_value = 0, value; + unsigned long vl; + int first = 1; + + if (argc > 2 && strcmp(argv[2], "x")) + asm volatile ( + // 0 | zimm[10:0] | rs1 | 1 1 1 | rd |1010111| vsetvli + // vsetvli t4, x0, e8, m1, d1 + ".4byte 0b00000000000000000111111011010111\n\t" + "mv %[vl], t4\n\t" + : [vl] "=r" (vl) : : "t4" + ); + else + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvli %[vl], x0, e8, m1, ta, ma\n\t" + ".option pop\n\t" + : [vl] "=r" (vl) + ); + +#define CHECK_VECTOR_REGISTER(register) ({ \ + for (int i = 0; i < vl; i++) { \ + asm volatile ( \ + ".option push\n\t" \ + ".option arch, +v\n\t" \ + "vmv.x.s %0, " __stringify(register) "\n\t" \ + "vsrl.vi " __stringify(register) ", " __stringify(register) ", 8\n\t" \ + ".option pop\n\t" \ + : "=r" (value)); \ + if (first) { \ + first = 0; \ + } else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \ + printf("Register " __stringify(register) \ + " values not clean! value: %u\n", value); \ + exit(-1); \ + } \ + prev_value = value; \ + } \ +}) + + CHECK_VECTOR_REGISTER(v0); + CHECK_VECTOR_REGISTER(v1); + CHECK_VECTOR_REGISTER(v2); + CHECK_VECTOR_REGISTER(v3); + CHECK_VECTOR_REGISTER(v4); + CHECK_VECTOR_REGISTER(v5); + CHECK_VECTOR_REGISTER(v6); + CHECK_VECTOR_REGISTER(v7); + CHECK_VECTOR_REGISTER(v8); + CHECK_VECTOR_REGISTER(v9); + CHECK_VECTOR_REGISTER(v10); + CHECK_VECTOR_REGISTER(v11); + CHECK_VECTOR_REGISTER(v12); + CHECK_VECTOR_REGISTER(v13); + CHECK_VECTOR_REGISTER(v14); + CHECK_VECTOR_REGISTER(v15); + CHECK_VECTOR_REGISTER(v16); + CHECK_VECTOR_REGISTER(v17); + CHECK_VECTOR_REGISTER(v18); + CHECK_VECTOR_REGISTER(v19); + CHECK_VECTOR_REGISTER(v20); + CHECK_VECTOR_REGISTER(v21); + CHECK_VECTOR_REGISTER(v22); + CHECK_VECTOR_REGISTER(v23); + CHECK_VECTOR_REGISTER(v24); + CHECK_VECTOR_REGISTER(v25); + CHECK_VECTOR_REGISTER(v26); + CHECK_VECTOR_REGISTER(v27); + CHECK_VECTOR_REGISTER(v28); + CHECK_VECTOR_REGISTER(v29); + CHECK_VECTOR_REGISTER(v30); + CHECK_VECTOR_REGISTER(v31); + +#undef CHECK_VECTOR_REGISTER + + return 0; +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.c b/tools/testing/selftests/riscv/vector/v_helpers.c new file mode 100644 index 000000000000..01a8799dcb78 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../hwprobe/hwprobe.h" +#include <asm/vendor/thead.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/wait.h> + +bool is_xtheadvector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR; +} + +bool is_vector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_EXT_ZVE32X; +} + +int launch_test(char *next_program, int test_inherit, int xtheadvector) +{ + char *exec_argv[4], *exec_envp[1]; + int rc, pid, status; + + pid = fork(); + if (pid < 0) { + printf("fork failed %d", pid); + return -1; + } + + if (!pid) { + exec_argv[0] = next_program; + exec_argv[1] = test_inherit != 0 ? "x" : NULL; + exec_argv[2] = xtheadvector != 0 ? "x" : NULL; + exec_argv[3] = NULL; + exec_envp[0] = NULL; + /* launch the program again to check inherit */ + rc = execve(next_program, exec_argv, exec_envp); + if (rc) { + perror("execve"); + printf("child execve failed %d\n", rc); + exit(-1); + } + } + + rc = waitpid(-1, &status, 0); + if (rc < 0) { + printf("waitpid failed\n"); + return -3; + } + + if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || + WIFSIGNALED(status)) { + printf("child exited abnormally\n"); + return -4; + } + + return WEXITSTATUS(status); +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.h b/tools/testing/selftests/riscv/vector/v_helpers.h new file mode 100644 index 000000000000..763cddfe26da --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include <stdbool.h> + +bool is_xtheadvector_supported(void); + +bool is_vector_supported(void); + +int launch_test(char *next_program, int test_inherit, int xtheadvector); diff --git a/tools/testing/selftests/riscv/vector/v_initval.c b/tools/testing/selftests/riscv/vector/v_initval.c new file mode 100644 index 000000000000..be9e1d18ad29 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_initval.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest_harness.h" +#include "v_helpers.h" + +#define NEXT_PROGRAM "./v_exec_initval_nolibc" + +TEST(v_initval) +{ + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + ASSERT_EQ(0, launch_test(NEXT_PROGRAM, 0, xtheadvector)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c deleted file mode 100644 index 6174ffe016dc..000000000000 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include "../../kselftest.h" -#define MAX_VSIZE (8192 * 32) - -void dump(char *ptr, int size) -{ - int i = 0; - - for (i = 0; i < size; i++) { - if (i != 0) { - if (i % 16 == 0) - printf("\n"); - else if (i % 8 == 0) - printf(" "); - } - printf("%02x ", ptr[i]); - } - printf("\n"); -} - -int main(void) -{ - int i; - unsigned long vl; - char *datap, *tmp; - - ksft_set_plan(1); - - datap = malloc(MAX_VSIZE); - if (!datap) { - ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); - exit(-1); - } - - tmp = datap; - asm volatile ( - ".option push\n\t" - ".option arch, +v\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%2)\n\t" - "add %1, %2, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl), "=r" (tmp) : "r" (datap) : "memory"); - - ksft_print_msg("vl = %lu\n", vl); - - if (datap[0] != 0x00 && datap[0] != 0xff) { - ksft_test_result_fail("v-regesters are not properly initialized\n"); - dump(datap, vl * 4); - exit(-1); - } - - for (i = 1; i < vl * 4; i++) { - if (datap[i] != datap[0]) { - ksft_test_result_fail("detect stale values on v-regesters\n"); - dump(datap, vl * 4); - exit(-2); - } - } - - free(datap); - - ksft_test_result_pass("tests for v_initval_nolibc pass\n"); - ksft_exit_pass(); - return 0; -} diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 1f9969bed235..7b7d6f21acb4 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -6,13 +6,16 @@ int main(int argc, char **argv) { - int rc, pid, status, test_inherit = 0; + int rc, pid, status, test_inherit = 0, xtheadvector = 0; long ctrl, ctrl_c; char *exec_argv[2], *exec_envp[2]; - if (argc > 1) + if (argc > 1 && strcmp(argv[1], "x")) test_inherit = 1; + if (argc > 2 && strcmp(argv[2], "x")) + xtheadvector = 1; + ctrl = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL); if (ctrl < 0) { puts("PR_RISCV_V_GET_CONTROL is not supported\n"); @@ -53,11 +56,14 @@ int main(int argc, char **argv) puts("child's vstate_ctrl not equal to parent's\n"); exit(-1); } - asm volatile (".option push\n\t" - ".option arch, +v\n\t" - "vsetvli x0, x0, e32, m8, ta, ma\n\t" - ".option pop\n\t" - ); + if (xtheadvector) + asm volatile (".4byte 0x00007ed7"); + else + asm volatile (".option push\n\t" + ".option arch, +v\n\t" + "vsetvli x0, x0, e32, m8, ta, ma\n\t" + ".option pop\n\t" + ); exit(ctrl); } } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 40b3bffcbb40..62fbb17a0556 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -3,181 +3,244 @@ #include <unistd.h> #include <errno.h> #include <sys/wait.h> +#include <sys/types.h> +#include <stdlib.h> -#include "../hwprobe/hwprobe.h" -#include "../../kselftest.h" +#include "../../kselftest_harness.h" +#include "v_helpers.h" #define NEXT_PROGRAM "./vstate_exec_nolibc" -static int launch_test(int test_inherit) -{ - char *exec_argv[3], *exec_envp[1]; - int rc, pid, status; - - pid = fork(); - if (pid < 0) { - ksft_test_result_fail("fork failed %d", pid); - return -1; - } - if (!pid) { - exec_argv[0] = NEXT_PROGRAM; - exec_argv[1] = test_inherit != 0 ? "x" : NULL; - exec_argv[2] = NULL; - exec_envp[0] = NULL; - /* launch the program again to check inherit */ - rc = execve(NEXT_PROGRAM, exec_argv, exec_envp); - if (rc) { - perror("execve"); - ksft_test_result_fail("child execve failed %d\n", rc); - exit(-1); - } - } - - rc = waitpid(-1, &status, 0); - if (rc < 0) { - ksft_test_result_fail("waitpid failed\n"); - return -3; - } - - if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || - WIFSIGNALED(status)) { - ksft_test_result_fail("child exited abnormally\n"); - return -4; - } - - return WEXITSTATUS(status); -} - -int test_and_compare_child(long provided, long expected, int inherit) +int test_and_compare_child(long provided, long expected, int inherit, int xtheadvector) { int rc; rc = prctl(PR_RISCV_V_SET_CONTROL, provided); if (rc != 0) { - ksft_test_result_fail("prctl with provided arg %lx failed with code %d\n", - provided, rc); + printf("prctl with provided arg %lx failed with code %d\n", + provided, rc); return -1; } - rc = launch_test(inherit); + rc = launch_test(NEXT_PROGRAM, inherit, xtheadvector); if (rc != expected) { - ksft_test_result_fail("Test failed, check %d != %ld\n", rc, - expected); + printf("Test failed, check %d != %ld\n", rc, expected); return -2; } return 0; } -#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 -#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 +#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 +#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 -int main(void) +TEST(get_control_no_v) { - struct riscv_hwprobe pair; - long flag, expected; long rc; - ksft_set_plan(1); + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); - pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; - rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); - if (rc < 0) { - ksft_test_result_fail("hwprobe() failed with %ld\n", rc); - return -1; - } + rc = prctl(PR_RISCV_V_GET_CONTROL); + EXPECT_EQ(-1, rc) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); +} - if (pair.key != RISCV_HWPROBE_KEY_IMA_EXT_0) { - ksft_test_result_fail("hwprobe cannot probe RISCV_HWPROBE_KEY_IMA_EXT_0\n"); - return -2; - } +TEST(set_control_no_v) +{ + long rc; - if (!(pair.value & RISCV_HWPROBE_EXT_ZVE32X)) { - rc = prctl(PR_RISCV_V_GET_CONTROL); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -3; - } - - rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("SET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -4; - } - - ksft_test_result_skip("Vector not supported\n"); - return 0; - } + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); + + rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); + EXPECT_EQ(-1, rc) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); +} + +TEST(vstate_on_current) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_ON; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != 0) { - ksft_test_result_fail("Enabling V for current should always success\n"); - return -5; - } + EXPECT_EQ(0, rc) TH_LOG("Enabling V for current should always succeed"); +} + +TEST(vstate_off_eperm) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_OFF; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != -1 || errno != EPERM) { - ksft_test_result_fail("Disabling current's V alive must fail with EPERM(%d)\n", - errno); - return -5; + EXPECT_EQ(EPERM, errno) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); + EXPECT_EQ(-1, rc) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); +} + +TEST(vstate_on_no_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); } /* Turn on next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0)) - return -6; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0, xtheadvector)); +} + +TEST(vstate_off_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 0)) - return -7; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 1, xtheadvector)); +} + +TEST(vstate_on_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + /* Turn on next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_on_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn on next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; - if (test_and_compare_child(flag, expected, 0)) - return -8; - if (test_and_compare_child(flag, expected, 1)) - return -9; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +TEST(vstate_off_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + /* Turn off next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_off_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; - if (test_and_compare_child(flag, expected, 0)) - return -10; - if (test_and_compare_child(flag, expected, 1)) - return -11; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_1) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - /* arguments should fail with EINVAL */ rc = prctl(PR_RISCV_V_SET_CONTROL, 0xff0); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_2) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); rc = prctl(PR_RISCV_V_SET_CONTROL, 0x3); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } +/* arguments should fail with EINVAL */ +TEST(inval_set_control_3) +{ + int rc; - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - ksft_test_result_pass("tests for riscv_v_vstate_ctrl pass\n"); - ksft_exit_pass(); - return 0; + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); } + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c index 2f37961240ca..05d03e679e06 100644 --- a/tools/testing/selftests/rseq/param_test.c +++ b/tools/testing/selftests/rseq/param_test.c @@ -226,8 +226,32 @@ unsigned int yield_mod_cnt, nr_abort; "addi " INJECT_ASM_REG "," INJECT_ASM_REG ", -1\n\t" \ "bnez " INJECT_ASM_REG ", 222b\n\t" \ "333:\n\t" +#elif defined(__or1k__) +#define RSEQ_INJECT_INPUT \ + , [loop_cnt_1]"m"(loop_cnt[1]) \ + , [loop_cnt_2]"m"(loop_cnt[2]) \ + , [loop_cnt_3]"m"(loop_cnt[3]) \ + , [loop_cnt_4]"m"(loop_cnt[4]) \ + , [loop_cnt_5]"m"(loop_cnt[5]) \ + , [loop_cnt_6]"m"(loop_cnt[6]) +#define INJECT_ASM_REG "r31" + +#define RSEQ_INJECT_CLOBBER \ + , INJECT_ASM_REG + +#define RSEQ_INJECT_ASM(n) \ + "l.lwz " INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \ + "l.sfeqi " INJECT_ASM_REG ", 0\n\t" \ + "l.bf 333f\n\t" \ + " l.nop\n\t" \ + "222:\n\t" \ + "l.addi " INJECT_ASM_REG "," INJECT_ASM_REG ", -1\n\t" \ + "l.sfeqi " INJECT_ASM_REG ", 0\n\t" \ + "l.bf 222f\n\t" \ + " l.nop\n\t" \ + "333:\n\t" #else #error unsupported target #endif diff --git a/tools/testing/selftests/rseq/rseq-or1k-bits.h b/tools/testing/selftests/rseq/rseq-or1k-bits.h new file mode 100644 index 000000000000..15d0e8200cd1 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-or1k-bits.h @@ -0,0 +1,412 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ + +#include "rseq-bits-template.h" + +#if defined(RSEQ_TEMPLATE_MO_RELAXED) && \ + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_storev)(intptr_t *v, intptr_t expect, intptr_t newv, + int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [expect] "r" (expect), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpnev_storeoffp_load)(intptr_t *v, intptr_t expectnot, + off_t voffp, intptr_t *load, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPNE(v, expectnot, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPNE(v, expectnot, "%l[error2]") +#endif + RSEQ_ASM_OP_R_LOAD(v) + RSEQ_ASM_OP_R_STORE(load) + RSEQ_ASM_OP_R_LOAD_OFF(voffp) + RSEQ_ASM_OP_R_FINAL_STORE(v, 3) + RSEQ_INJECT_ASM(5) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [expectnot] "r" (expectnot), + [load] "m" (*load), + [voffp] "Ir" (voffp) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_addv)(intptr_t *v, intptr_t count, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") +#endif + RSEQ_ASM_OP_R_LOAD(v) + RSEQ_ASM_OP_R_ADD(count) + RSEQ_ASM_OP_R_FINAL_STORE(v, 3) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [count] "r" (count) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_cmpeqv_storev)(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t expect2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error3]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) + RSEQ_ASM_OP_CMPEQ(v2, expect2, "%l[cmpfail]") + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") + RSEQ_ASM_OP_CMPEQ(v2, expect2, "%l[error3]") +#endif + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [v] "m" (*v), + [expect] "r" (expect), + [v2] "m" (*v2), + [expect2] "r" (expect2), + [newv] "r" (newv) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2, error3 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +error3: + rseq_bug("2nd expected value comparison failed"); +#endif +} + +#define RSEQ_ARCH_HAS_OFFSET_DEREF_ADDV + +/* + * pval = *(ptr+off) + * *pval += inc; + */ +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, intptr_t inc, + int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") +#endif + RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, 3) + RSEQ_INJECT_ASM(4) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [ptr] "r" (ptr), + [off] "r" (off), + [inc] "r" (inc) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort +#ifdef RSEQ_COMPARE_TWICE + , error1 +#endif + ); + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +#endif +} + +#endif /* #if defined(RSEQ_TEMPLATE_MO_RELAXED) && + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */ + +#if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && \ + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trystorev_storev)(intptr_t *v, intptr_t expect, + intptr_t *v2, intptr_t newv2, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_STORE(v2, newv2) + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_TEMPLATE_MO_RELEASE + RSEQ_ASM_OP_FINAL_STORE_RELEASE(v, newv, 3) +#else + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) +#endif + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [v2] "m" (*v2), + [newv2] "r" (newv2) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +static inline __always_inline +int RSEQ_TEMPLATE_IDENTIFIER(rseq_cmpeqv_trymemcpy_storev)(intptr_t *v, intptr_t expect, + void *dst, void *src, size_t len, + intptr_t newv, int cpu) +{ + RSEQ_INJECT_C(9) + __asm__ __volatile__ goto(RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f) + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[cmpfail]") +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error1]") + RSEQ_ASM_DEFINE_EXIT_POINT(2f, "%l[error2]") +#endif + RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs) + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f) + RSEQ_INJECT_ASM(3) + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[cmpfail]") + RSEQ_INJECT_ASM(4) +#ifdef RSEQ_COMPARE_TWICE + RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") + RSEQ_ASM_OP_CMPEQ(v, expect, "%l[error2]") +#endif + RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) + RSEQ_INJECT_ASM(5) +#ifdef RSEQ_TEMPLATE_MO_RELEASE + RSEQ_ASM_OP_FINAL_STORE_RELEASE(v, newv, 3) +#else + RSEQ_ASM_OP_FINAL_STORE(v, newv, 3) +#endif + RSEQ_INJECT_ASM(6) + RSEQ_ASM_DEFINE_ABORT(4, abort) + : /* gcc asm goto does not allow outputs */ + : [cpu_id] "r" (cpu), + [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), + [expect] "r" (expect), + [v] "m" (*v), + [newv] "r" (newv), + [dst] "r" (dst), + [src] "r" (src), + [len] "r" (len) + RSEQ_INJECT_INPUT + : "memory", RSEQ_ASM_TMP_REG_1, RSEQ_ASM_TMP_REG_2, + RSEQ_ASM_TMP_REG_3, RSEQ_ASM_TMP_REG_4 + RSEQ_INJECT_CLOBBER + : abort, cmpfail +#ifdef RSEQ_COMPARE_TWICE + , error1, error2 +#endif + ); + + return 0; +abort: + RSEQ_INJECT_FAILED + return -1; +cmpfail: + return 1; +#ifdef RSEQ_COMPARE_TWICE +error1: + rseq_bug("cpu_id comparison failed"); +error2: + rseq_bug("expected value comparison failed"); +#endif +} + +#endif /* #if (defined(RSEQ_TEMPLATE_MO_RELAXED) || defined(RSEQ_TEMPLATE_MO_RELEASE)) && + (defined(RSEQ_TEMPLATE_CPU_ID) || defined(RSEQ_TEMPLATE_MM_CID)) */ + +#include "rseq-bits-reset.h" diff --git a/tools/testing/selftests/rseq/rseq-or1k-thread-pointer.h b/tools/testing/selftests/rseq/rseq-or1k-thread-pointer.h new file mode 100644 index 000000000000..cda740f7aff3 --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-or1k-thread-pointer.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: LGPL-2.1-only OR MIT */ +#ifndef _RSEQ_OR1K_THREAD_POINTER +#define _RSEQ_OR1K_THREAD_POINTER + +static inline void *rseq_thread_pointer(void) +{ + void *__thread_register; + + __asm__ ("l.or %0, r10, r0" : "=r" (__thread_register)); + return __thread_register; +} + +#endif diff --git a/tools/testing/selftests/rseq/rseq-or1k.h b/tools/testing/selftests/rseq/rseq-or1k.h new file mode 100644 index 000000000000..9e78eebdf79a --- /dev/null +++ b/tools/testing/selftests/rseq/rseq-or1k.h @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: LGPL-2.1 OR MIT */ + +/* + * Select the instruction "l.nop 0x35" as the RSEQ_SIG. + */ +#define RSEQ_SIG 0x15000035 + +#define rseq_smp_mb() __asm__ __volatile__ ("l.msync" ::: "memory") +#define rseq_smp_rmb() rseq_smp_mb() +#define rseq_smp_wmb() rseq_smp_mb() +#define RSEQ_ASM_TMP_REG_1 "r31" +#define RSEQ_ASM_TMP_REG_2 "r29" +#define RSEQ_ASM_TMP_REG_3 "r27" +#define RSEQ_ASM_TMP_REG_4 "r25" + +#define rseq_smp_load_acquire(p) \ +__extension__ ({ \ + rseq_unqual_scalar_typeof(*(p)) ____p1 = RSEQ_READ_ONCE(*(p)); \ + rseq_smp_mb(); \ + ____p1; \ +}) + +#define rseq_smp_acquire__after_ctrl_dep() rseq_smp_rmb() + +#define rseq_smp_store_release(p, v) \ +do { \ + rseq_smp_mb(); \ + RSEQ_WRITE_ONCE(*(p), v); \ +} while (0) + +#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip, \ + post_commit_offset, abort_ip) \ + ".pushsection __rseq_cs, \"aw\"\n" \ + ".balign 32\n" \ + __rseq_str(label) ":\n" \ + ".long " __rseq_str(version) ", " __rseq_str(flags) "\n" \ + ".long 0x0, " __rseq_str(start_ip) ", " \ + "0x0, " __rseq_str(post_commit_offset) ", " \ + "0x0, " __rseq_str(abort_ip) "\n" \ + ".popsection\n\t" \ + ".pushsection __rseq_cs_ptr_array, \"aw\"\n" \ + ".long 0x0, " __rseq_str(label) "b\n" \ + ".popsection\n" + +#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \ + __RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip, \ + ((post_commit_ip) - (start_ip)), abort_ip) + +/* + * Exit points of a rseq critical section consist of all instructions outside + * of the critical section where a critical section can either branch to or + * reach through the normal course of its execution. The abort IP and the + * post-commit IP are already part of the __rseq_cs section and should not be + * explicitly defined as additional exit points. Knowing all exit points is + * useful to assist debuggers stepping over the critical section. + */ +#define RSEQ_ASM_DEFINE_EXIT_POINT(start_ip, exit_ip) \ + ".pushsection __rseq_exit_point_array, \"aw\"\n" \ + ".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(exit_ip) "\n" \ + ".popsection\n" + +#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ + RSEQ_INJECT_ASM(1) \ + "l.movhi " RSEQ_ASM_TMP_REG_1 ", hi(" __rseq_str(cs_label) ")\n"\ + "l.ori " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ + ", lo(" __rseq_str(cs_label) ")\n"\ + "l.sw %[" __rseq_str(rseq_cs) "], " RSEQ_ASM_TMP_REG_1 "\n" \ + __rseq_str(label) ":\n" + +#define RSEQ_ASM_DEFINE_ABORT(label, abort_label) \ + "l.j 222f\n" \ + " l.nop\n" \ + ".balign 4\n" \ + ".long " __rseq_str(RSEQ_SIG) "\n" \ + __rseq_str(label) ":\n" \ + "l.j %l[" __rseq_str(abort_label) "]\n" \ + " l.nop\n" \ + "222:\n" + +#define RSEQ_ASM_OP_STORE(var, value) \ + "l.sw %[" __rseq_str(var) "], %[" __rseq_str(value) "]\n" + +#define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "l.sfne " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "]\n" \ + "l.bf " __rseq_str(label) "\n" \ + " l.nop\n" + +#define RSEQ_ASM_OP_CMPNE(var, expect, label) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "l.sfeq " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "]\n" \ + "l.bf " __rseq_str(label) "\n" \ + " l.nop\n" + +#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ + RSEQ_INJECT_ASM(2) \ + RSEQ_ASM_OP_CMPEQ(current_cpu_id, cpu_id, label) + +#define RSEQ_ASM_OP_R_LOAD(var) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" + +#define RSEQ_ASM_OP_R_STORE(var) \ + "l.sw %[" __rseq_str(var) "], " RSEQ_ASM_TMP_REG_1 "\n" + +#define RSEQ_ASM_OP_R_LOAD_OFF(offset) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", " \ + "%[" __rseq_str(offset) "](" RSEQ_ASM_TMP_REG_1 ")\n" + +#define RSEQ_ASM_OP_R_ADD(count) \ + "l.add " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ + ", %[" __rseq_str(count) "]\n" + +#define RSEQ_ASM_OP_FINAL_STORE(var, value, post_commit_label) \ + RSEQ_ASM_OP_STORE(var, value) \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(var, value, post_commit_label) \ + "l.msync\n" \ + RSEQ_ASM_OP_STORE(var, value) \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label) \ + "l.sw %[" __rseq_str(var) "], " RSEQ_ASM_TMP_REG_1 "\n" \ + __rseq_str(post_commit_label) ":\n" + +#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len) \ + "l.sfeq %[" __rseq_str(len) "], r0\n" \ + "l.bf 333f\n" \ + " l.nop\n" \ + "l.ori " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(len) "], 0\n" \ + "l.ori " RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(src) "], 0\n" \ + "l.ori " RSEQ_ASM_TMP_REG_3 ", %[" __rseq_str(dst) "], 0\n" \ + "222:\n" \ + "l.lbz " RSEQ_ASM_TMP_REG_4 ", 0(" RSEQ_ASM_TMP_REG_2 ")\n" \ + "l.sb 0(" RSEQ_ASM_TMP_REG_3 "), " RSEQ_ASM_TMP_REG_4 "\n" \ + "l.addi " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 ", -1\n" \ + "l.addi " RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", 1\n" \ + "l.addi " RSEQ_ASM_TMP_REG_3 ", " RSEQ_ASM_TMP_REG_3 ", 1\n" \ + "l.sfne " RSEQ_ASM_TMP_REG_1 ", r0\n" \ + "l.bf 222b\n" \ + " l.nop\n" \ + "333:\n" + +#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, post_commit_label) \ + "l.ori " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "], 0\n" \ + RSEQ_ASM_OP_R_ADD(off) \ + "l.lwz " RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n" \ + RSEQ_ASM_OP_R_ADD(inc) \ + __rseq_str(post_commit_label) ":\n" + +/* Per-cpu-id indexing. */ + +#define RSEQ_TEMPLATE_CPU_ID +#define RSEQ_TEMPLATE_MO_RELAXED +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELAXED + +#define RSEQ_TEMPLATE_MO_RELEASE +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELEASE +#undef RSEQ_TEMPLATE_CPU_ID + +/* Per-mm-cid indexing. */ + +#define RSEQ_TEMPLATE_MM_CID +#define RSEQ_TEMPLATE_MO_RELAXED +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELAXED + +#define RSEQ_TEMPLATE_MO_RELEASE +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELEASE +#undef RSEQ_TEMPLATE_MM_CID + +/* APIs which are not based on cpu ids. */ + +#define RSEQ_TEMPLATE_CPU_ID_NONE +#define RSEQ_TEMPLATE_MO_RELAXED +#include "rseq-or1k-bits.h" +#undef RSEQ_TEMPLATE_MO_RELAXED +#undef RSEQ_TEMPLATE_CPU_ID_NONE diff --git a/tools/testing/selftests/rseq/rseq-riscv-bits.h b/tools/testing/selftests/rseq/rseq-riscv-bits.h index de31a0143139..f02f411d550d 100644 --- a/tools/testing/selftests/rseq/rseq-riscv-bits.h +++ b/tools/testing/selftests/rseq/rseq-riscv-bits.h @@ -243,7 +243,7 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i #ifdef RSEQ_COMPARE_TWICE RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]") #endif - RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, 3) + RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, 3) RSEQ_INJECT_ASM(4) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ @@ -251,8 +251,8 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i [current_cpu_id] "m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD), [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [ptr] "r" (ptr), - [off] "er" (off), - [inc] "er" (inc) + [off] "r" (off), + [inc] "r" (inc) RSEQ_INJECT_INPUT : "memory", RSEQ_ASM_TMP_REG_1 RSEQ_INJECT_CLOBBER diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h index 37e598d0a365..67d544aaa9a3 100644 --- a/tools/testing/selftests/rseq/rseq-riscv.h +++ b/tools/testing/selftests/rseq/rseq-riscv.h @@ -158,7 +158,7 @@ do { \ "bnez " RSEQ_ASM_TMP_REG_1 ", 222b\n" \ "333:\n" -#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, post_commit_label) \ +#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, post_commit_label) \ "mv " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "]\n" \ RSEQ_ASM_OP_R_ADD(off) \ REG_L RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n" \ diff --git a/tools/testing/selftests/rseq/rseq-thread-pointer.h b/tools/testing/selftests/rseq/rseq-thread-pointer.h index 977c25d758b2..3d5019307a1b 100644 --- a/tools/testing/selftests/rseq/rseq-thread-pointer.h +++ b/tools/testing/selftests/rseq/rseq-thread-pointer.h @@ -12,6 +12,8 @@ #include "rseq-x86-thread-pointer.h" #elif defined(__PPC__) #include "rseq-ppc-thread-pointer.h" +#elif defined(__or1k__) +#include "rseq-or1k-thread-pointer.h" #else #include "rseq-generic-thread-pointer.h" #endif diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 5b9772cdf265..f6156790c3b4 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -61,7 +61,6 @@ unsigned int rseq_size = -1U; unsigned int rseq_flags; static int rseq_ownership; -static int rseq_reg_success; /* At least one rseq registration has succeded. */ /* Allocate a large area for the TLS. */ #define RSEQ_THREAD_AREA_ALLOC_SIZE 1024 @@ -152,14 +151,27 @@ int rseq_register_current_thread(void) } rc = sys_rseq(&__rseq_abi, get_rseq_min_alloc_size(), 0, RSEQ_SIG); if (rc) { - if (RSEQ_READ_ONCE(rseq_reg_success)) { + /* + * After at least one thread has registered successfully + * (rseq_size > 0), the registration of other threads should + * never fail. + */ + if (RSEQ_READ_ONCE(rseq_size) > 0) { /* Incoherent success/failure within process. */ abort(); } return -1; } assert(rseq_current_cpu_raw() >= 0); - RSEQ_WRITE_ONCE(rseq_reg_success, 1); + + /* + * The first thread to register sets the rseq_size to mimic the libc + * behavior. + */ + if (RSEQ_READ_ONCE(rseq_size) == 0) { + RSEQ_WRITE_ONCE(rseq_size, get_rseq_kernel_feature_size()); + } + return 0; } @@ -235,12 +247,18 @@ void rseq_init(void) return; } rseq_ownership = 1; - if (!rseq_available()) { - rseq_size = 0; - return; - } + + /* Calculate the offset of the rseq area from the thread pointer. */ rseq_offset = (void *)&__rseq_abi - rseq_thread_pointer(); + + /* rseq flags are deprecated, always set to 0. */ rseq_flags = 0; + + /* + * Set the size to 0 until at least one thread registers to mimic the + * libc behavior. + */ + rseq_size = 0; } static __attribute__((destructor)) diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h index 4e217b620e0c..ba424ce80a71 100644 --- a/tools/testing/selftests/rseq/rseq.h +++ b/tools/testing/selftests/rseq/rseq.h @@ -60,7 +60,14 @@ extern ptrdiff_t rseq_offset; /* - * Size of the registered rseq area. 0 if the registration was + * The rseq ABI is composed of extensible feature fields. The extensions + * are done by appending additional fields at the end of the structure. + * The rseq_size defines the size of the active feature set which can be + * used by the application for the current rseq registration. Features + * starting at offset >= rseq_size are inactive and should not be used. + * + * The rseq_size is the intersection between the available allocation + * size for the rseq area and the feature size supported by the kernel. * unsuccessful. */ extern unsigned int rseq_size; @@ -122,6 +129,8 @@ static inline struct rseq_abi *rseq_get_abi(void) #include <rseq-s390.h> #elif defined(__riscv) #include <rseq-riscv.h> +#elif defined(__or1k__) +#include <rseq-or1k.h> #else #error unsupported target #endif diff --git a/tools/testing/selftests/run_kselftest.sh b/tools/testing/selftests/run_kselftest.sh index a28c1416cb89..50e03eefe7ac 100755 --- a/tools/testing/selftests/run_kselftest.sh +++ b/tools/testing/selftests/run_kselftest.sh @@ -21,7 +21,7 @@ usage() cat <<EOF Usage: $0 [OPTIONS] -s | --summary Print summary with detailed log in output.log (conflict with -p) - -p | --per_test_log Print test log in /tmp with each test name (conflict with -s) + -p | --per-test-log Print test log in /tmp with each test name (conflict with -s) -t | --test COLLECTION:TEST Run TEST from COLLECTION -c | --collection COLLECTION Run all tests from COLLECTION -l | --list List the available collection:test entries diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c index fa946d9146d4..d67431f57ac6 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.c +++ b/tools/testing/selftests/sched_ext/create_dsq.c @@ -14,11 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct create_dsq *skel; - skel = create_dsq__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = create_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(create_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c index e65d22f23f3b..b6d13496b24e 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_bogus_dsq_fail *skel; - skel = ddsp_bogus_dsq_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_bogus_dsq_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_bogus_dsq_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c index abafee587cd6..af9ce4ee8baa 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_vtimelocal_fail *skel; - skel = ddsp_vtimelocal_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_vtimelocal_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_vtimelocal_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index fbda6bf54671..c02b2aa6fc64 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,7 +43,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - if (p->nr_cpus_allowed == nr_cpus) + if (p->nr_cpus_allowed == nr_cpus && !is_migration_disabled(p)) target = bpf_get_prandom_u32() % nr_cpus; else target = scx_bpf_task_cpu(p); diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 0ff27e57fe43..e1f2ce4abfe6 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -15,6 +15,7 @@ static enum scx_test_status setup(void **ctx) skel = dsp_local_on__open(); SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); skel->rodata->nr_cpus = libbpf_num_possible_cpus(); SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel"); diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c index 73e679953e27..d3387ae03679 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_last_no_enq_fails *skel; - skel = enq_last_no_enq_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_last_no_enq_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_last_no_enq_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c index dd1350e5f002..a80e3a3b3698 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_select_cpu_fails *skel; - skel = enq_select_cpu_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_select_cpu_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_select_cpu_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 31bcd06e21cd..9451782689de 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -23,6 +23,7 @@ static enum scx_test_status run(void *ctx) char buf[16]; skel = exit__open(); + SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; exit__load(skel); link = bpf_map__attach_struct_ops(skel->maps.exit_ops); diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 87bf220b1bce..1c9ceb661c43 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -49,8 +49,10 @@ static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined) SCX_ASSERT(is_cpu_online()); - skel = hotplug__open_and_load(); - SCX_ASSERT(skel); + skel = hotplug__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(hotplug__load(skel), "Failed to load skel"); /* Testing the offline -> online path, so go offline before starting */ if (onlining) diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 97d45f1e5597..eddf9e0e26e7 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -15,22 +15,6 @@ #define SCHED_EXT 7 -static struct init_enable_count * -open_load_prog(bool global) -{ - struct init_enable_count *skel; - - skel = init_enable_count__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); - - if (!global) - skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; - - SCX_BUG_ON(init_enable_count__load(skel), "Failed to load skel"); - - return skel; -} - static enum scx_test_status run_test(bool global) { struct init_enable_count *skel; @@ -40,7 +24,14 @@ static enum scx_test_status run_test(bool global) struct sched_param param = {}; pid_t pids[num_pre_forks]; - skel = open_load_prog(global); + skel = init_enable_count__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + + if (!global) + skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; + + SCX_FAIL_IF(init_enable_count__load(skel), "Failed to load skel"); /* * Fork a bunch of children before we attach the scheduler so that we @@ -159,7 +150,7 @@ static enum scx_test_status run(void *ctx) struct scx_test init_enable_count = { .name = "init_enable_count", - .description = "Verify we do the correct amount of counting of init, " + .description = "Verify we correctly count the occurrences of init, " "enable, etc callbacks.", .run = run, }; diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c index f38fc973c380..c6be50a9941d 100644 --- a/tools/testing/selftests/sched_ext/maximal.c +++ b/tools/testing/selftests/sched_ext/maximal.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct maximal *skel; - skel = maximal__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c index 31cfafb0cf65..aacf0c58ca4f 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.c +++ b/tools/testing/selftests/sched_ext/maybe_null.c @@ -43,7 +43,7 @@ static enum scx_test_status run(void *ctx) struct scx_test maybe_null = { .name = "maybe_null", - .description = "Verify if PTR_MAYBE_NULL work for .dispatch", + .description = "Verify if PTR_MAYBE_NULL works for .dispatch", .run = run, }; REGISTER_SCX_TEST(&maybe_null) diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c index 6c5db8ebbf8a..89f7261757ff 100644 --- a/tools/testing/selftests/sched_ext/minimal.c +++ b/tools/testing/selftests/sched_ext/minimal.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct minimal *skel; - skel = minimal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = minimal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(minimal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c index 3cd57ef8daaa..05974820ca69 100644 --- a/tools/testing/selftests/sched_ext/prog_run.c +++ b/tools/testing/selftests/sched_ext/prog_run.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct prog_run *skel; - skel = prog_run__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = prog_run__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(prog_run__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c index 5cfba2d6e056..308211d80436 100644 --- a/tools/testing/selftests/sched_ext/reload_loop.c +++ b/tools/testing/selftests/sched_ext/reload_loop.c @@ -18,11 +18,10 @@ bool force_exit = false; static enum scx_test_status setup(void **ctx) { - skel = maximal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); return SCX_TEST_PASS; } diff --git a/tools/testing/selftests/sched_ext/runner.c b/tools/testing/selftests/sched_ext/runner.c index eab48c7ff309..aa2d7d32dda9 100644 --- a/tools/testing/selftests/sched_ext/runner.c +++ b/tools/testing/selftests/sched_ext/runner.c @@ -22,11 +22,12 @@ const char help_fmt[] = "\n" " -t TEST Only run tests whose name includes this string\n" " -s Include print output for skipped tests\n" +" -l List all available tests\n" " -q Don't print the test descriptions during run\n" " -h Display this help and exit\n"; static volatile int exit_req; -static bool quiet, print_skipped; +static bool quiet, print_skipped, list; #define MAX_SCX_TESTS 2048 @@ -133,7 +134,7 @@ int main(int argc, char **argv) libbpf_set_strict_mode(LIBBPF_STRICT_ALL); - while ((opt = getopt(argc, argv, "qst:h")) != -1) { + while ((opt = getopt(argc, argv, "qslt:h")) != -1) { switch (opt) { case 'q': quiet = true; @@ -141,6 +142,9 @@ int main(int argc, char **argv) case 's': print_skipped = true; break; + case 'l': + list = true; + break; case 't': filter = optarg; break; @@ -154,6 +158,13 @@ int main(int argc, char **argv) enum scx_test_status status; struct scx_test *test = &__scx_tests[i]; + if (list) { + printf("%s\n", test->name); + if (i == (__scx_num_tests - 1)) + return 0; + continue; + } + if (filter && should_skip_test(test, filter)) { /* * Printing the skipped tests and their preambles can diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c index a53a40c2d2f0..5b6e045e1109 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl *skel; - skel = select_cpu_dfl__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c index 1d85bf4bf3a3..9b5d232efb7f 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl_nodispatch *skel; - skel = select_cpu_dfl_nodispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl_nodispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl_nodispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c index 0309ca8785b3..80283dbc41b7 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch *skel; - skel = select_cpu_dispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c index 47eb6ed7627d..5e72ebbc90a5 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_bad_dsq *skel; - skel = select_cpu_dispatch_bad_dsq__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_bad_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_bad_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c index 48ff028a3c46..aa85949478bc 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_dbl_dsp *skel; - skel = select_cpu_dispatch_dbl_dsp__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_dbl_dsp__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_dbl_dsp__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c index b4629c2364f5..1e9b5c9bfff1 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_vtime *skel; - skel = select_cpu_vtime__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_vtime__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_vtime__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 8c3a73461475..14ba51b52095 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -47,6 +47,7 @@ #include <linux/kcmp.h> #include <sys/resource.h> #include <sys/capability.h> +#include <linux/perf_event.h> #include <unistd.h> #include <sys/syscall.h> @@ -68,6 +69,10 @@ # define PR_SET_PTRACER 0x59616d61 #endif +#ifndef noinline +#define noinline __attribute__((noinline)) +#endif + #ifndef PR_SET_NO_NEW_PRIVS #define PR_SET_NO_NEW_PRIVS 38 #define PR_GET_NO_NEW_PRIVS 39 @@ -4888,6 +4893,200 @@ TEST(tsync_vs_dead_thread_leader) EXPECT_EQ(0, status); } +noinline int probed(void) +{ + return 1; +} + +static int parse_uint_from_file(const char *file, const char *fmt) +{ + int err = -1, ret; + FILE *f; + + f = fopen(file, "re"); + if (f) { + err = fscanf(f, fmt, &ret); + fclose(f); + } + return err == 1 ? ret : err; +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static ssize_t get_uprobe_offset(const void *addr) +{ + size_t start, base, end; + bool found = false; + char buf[256]; + FILE *f; + + f = fopen("/proc/self/maps", "r"); + if (!f) + return -1; + + while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) { + if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) { + found = true; + break; + } + } + fclose(f); + return found ? (uintptr_t)addr - start + base : -1; +} + +FIXTURE(URETPROBE) { + int fd; +}; + +FIXTURE_VARIANT(URETPROBE) { + /* + * All of the URETPROBE behaviors can be tested with either + * uretprobe attached or not + */ + bool attach; +}; + +FIXTURE_VARIANT_ADD(URETPROBE, attached) { + .attach = true, +}; + +FIXTURE_VARIANT_ADD(URETPROBE, not_attached) { + .attach = false, +}; + +FIXTURE_SETUP(URETPROBE) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + ssize_t offset; + int type, bit; + +#ifndef __NR_uretprobe + SKIP(return, "__NR_uretprobe syscall not defined"); +#endif + + if (!variant->attach) + return; + + memset(&attr, 0, attr_sz); + + type = determine_uprobe_perf_type(); + ASSERT_GE(type, 0); + bit = determine_uprobe_retprobe_bit(); + ASSERT_GE(bit, 0); + offset = get_uprobe_offset(probed); + ASSERT_GE(offset, 0); + + attr.config |= 1 << bit; + attr.size = attr_sz; + attr.type = type; + attr.config1 = ptr_to_u64("/proc/self/exe"); + attr.config2 = offset; + + self->fd = syscall(__NR_perf_event_open, &attr, + getpid() /* pid */, -1 /* cpu */, -1 /* group_fd */, + PERF_FLAG_FD_CLOEXEC); +} + +FIXTURE_TEARDOWN(URETPROBE) +{ + /* we could call close(self->fd), but we'd need extra filter for + * that and since we are calling _exit right away.. + */ +} + +static int run_probed_with_filter(struct sock_fprog *prog) +{ + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) || + seccomp(SECCOMP_SET_MODE_FILTER, 0, prog)) { + return -1; + } + + probed(); + return 0; +} + +TEST_F(URETPROBE, uretprobe_default_allow) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_default_block) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), +#ifdef __NR_uretprobe + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 0, 1), +#endif + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_default_block_with_uretprobe_syscall) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), +#ifdef __NR_uretprobe + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 2, 0), +#endif + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + /* * TODO: * - expand NNP testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index d3dd65b05b5f..9044ac054167 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -94,5 +94,37 @@ "$TC qdisc del dev $DUMMY ingress", "$IP addr del 10.10.10.10/24 dev $DUMMY" ] - } + }, + { + "id": "a4b9", + "name": "Test class qlen notification", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem", + "$TC qdisc add dev $DUMMY parent 2: handle 3: drr", + "$TC filter add dev $DUMMY parent 3: basic action drop", + "$TC class add dev $DUMMY parent 3: classid 3:1 drr", + "$TC class del dev $DUMMY classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json index ae3d286a32b2..6f20d033670d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json @@ -313,6 +313,29 @@ "matchPattern": "qdisc bfifo 1: root", "matchCount": "0", "teardown": [ + ] + }, + { + "id": "d774", + "name": "Check pfifo_head_drop qdisc enqueue behaviour when limit == 0", + "category": [ + "qdisc", + "pfifo_head_drop" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: pfifo_head_drop limit 0", + "$IP link set dev $DUMMY up || true" + ], + "cmdUnderTest": "ping -c2 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "dropped 2", + "matchCount": "1", + "teardown": [ ] } ] diff --git a/tools/testing/selftests/timers/clocksource-switch.c b/tools/testing/selftests/timers/clocksource-switch.c index c5264594064c..83faa4e354e3 100644 --- a/tools/testing/selftests/timers/clocksource-switch.c +++ b/tools/testing/selftests/timers/clocksource-switch.c @@ -156,8 +156,8 @@ int main(int argc, char **argv) /* Check everything is sane before we start switching asynchronously */ if (do_sanity_check) { for (i = 0; i < count; i++) { - printf("Validating clocksource %s\n", - clocksource_list[i]); + ksft_print_msg("Validating clocksource %s\n", + clocksource_list[i]); if (change_clocksource(clocksource_list[i])) { status = -1; goto out; @@ -169,7 +169,7 @@ int main(int argc, char **argv) } } - printf("Running Asynchronous Switching Tests...\n"); + ksft_print_msg("Running Asynchronous Switching Tests...\n"); pid = fork(); if (!pid) return run_tests(runtime); diff --git a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c index b5c3ddb90942..02ecfe687dc2 100644 --- a/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c +++ b/tools/testing/selftests/tmpfs/bug-link-o-tmpfile.c @@ -23,45 +23,56 @@ #include <sys/mount.h> #include <unistd.h> +#include "../kselftest.h" + int main(void) { int fd; + // Setting up kselftest framework + ksft_print_header(); + ksft_set_plan(1); + + // Check if test is run as root + if (geteuid()) { + ksft_exit_skip("This test needs root to run!\n"); + return 1; + } + if (unshare(CLONE_NEWNS) == -1) { if (errno == ENOSYS || errno == EPERM) { - fprintf(stderr, "error: unshare, errno %d\n", errno); - return 4; + ksft_exit_skip("unshare() error: unshare, errno %d\n", errno); + } else { + ksft_exit_fail_msg("unshare() error: unshare, errno %d\n", errno); } - fprintf(stderr, "error: unshare, errno %d\n", errno); - return 1; } + if (mount(NULL, "/", NULL, MS_PRIVATE|MS_REC, NULL) == -1) { - fprintf(stderr, "error: mount '/', errno %d\n", errno); - return 1; + ksft_exit_fail_msg("mount() error: Root filesystem private mount: Fail %d\n", errno); } /* Our heroes: 1 root inode, 1 O_TMPFILE inode, 1 permanent inode. */ if (mount(NULL, "/tmp", "tmpfs", 0, "nr_inodes=3") == -1) { - fprintf(stderr, "error: mount tmpfs, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("mount() error: Mounting tmpfs on /tmp: Fail %d\n", errno); } fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_TMPFILE, 0600); if (fd == -1) { - fprintf(stderr, "error: open 1, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("openat() error: Open first temporary file: Fail %d\n", errno); } + if (linkat(fd, "", AT_FDCWD, "/tmp/1", AT_EMPTY_PATH) == -1) { - fprintf(stderr, "error: linkat, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("linkat() error: Linking the temporary file: Fail %d\n", errno); + /* Ensure fd is closed on failure */ + close(fd); } close(fd); fd = openat(AT_FDCWD, "/tmp", O_WRONLY|O_TMPFILE, 0600); if (fd == -1) { - fprintf(stderr, "error: open 2, errno %d\n", errno); - return 1; + ksft_exit_fail_msg("openat() error: Opening the second temporary file: Fail %d\n", errno); } - + ksft_test_result_pass(" "); + ksft_exit_pass(); return 0; } diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c index 28f35620c499..2fe5e983cb22 100644 --- a/tools/testing/selftests/vDSO/parse_vdso.c +++ b/tools/testing/selftests/vDSO/parse_vdso.c @@ -53,6 +53,7 @@ static struct vdso_info /* Symbol table */ ELF(Sym) *symtab; const char *symstrings; + ELF(Word) *gnu_hash; ELF_HASH_ENTRY *bucket, *chain; ELF_HASH_ENTRY nbucket, nchain; @@ -81,6 +82,16 @@ static unsigned long elf_hash(const char *name) return h; } +static uint32_t gnu_hash(const char *name) +{ + const unsigned char *s = (void *)name; + uint32_t h = 5381; + + for (; *s; s++) + h += h * 32 + *s; + return h; +} + void vdso_init_from_sysinfo_ehdr(uintptr_t base) { size_t i; @@ -123,6 +134,7 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) */ ELF_HASH_ENTRY *hash = 0; vdso_info.symstrings = 0; + vdso_info.gnu_hash = 0; vdso_info.symtab = 0; vdso_info.versym = 0; vdso_info.verdef = 0; @@ -143,6 +155,11 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) ((uintptr_t)dyn[i].d_un.d_ptr + vdso_info.load_offset); break; + case DT_GNU_HASH: + vdso_info.gnu_hash = + (ELF(Word) *)((uintptr_t)dyn[i].d_un.d_ptr + + vdso_info.load_offset); + break; case DT_VERSYM: vdso_info.versym = (ELF(Versym) *) ((uintptr_t)dyn[i].d_un.d_ptr @@ -155,17 +172,27 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base) break; } } - if (!vdso_info.symstrings || !vdso_info.symtab || !hash) + if (!vdso_info.symstrings || !vdso_info.symtab || + (!hash && !vdso_info.gnu_hash)) return; /* Failed */ if (!vdso_info.verdef) vdso_info.versym = 0; /* Parse the hash table header. */ - vdso_info.nbucket = hash[0]; - vdso_info.nchain = hash[1]; - vdso_info.bucket = &hash[2]; - vdso_info.chain = &hash[vdso_info.nbucket + 2]; + if (vdso_info.gnu_hash) { + vdso_info.nbucket = vdso_info.gnu_hash[0]; + /* The bucket array is located after the header (4 uint32) and the bloom + * filter (size_t array of gnu_hash[2] elements). + */ + vdso_info.bucket = vdso_info.gnu_hash + 4 + + sizeof(size_t) / 4 * vdso_info.gnu_hash[2]; + } else { + vdso_info.nbucket = hash[0]; + vdso_info.nchain = hash[1]; + vdso_info.bucket = &hash[2]; + vdso_info.chain = &hash[vdso_info.nbucket + 2]; + } /* That's all we need. */ vdso_info.valid = true; @@ -209,6 +236,26 @@ static bool vdso_match_version(ELF(Versym) ver, && !strcmp(name, vdso_info.symstrings + aux->vda_name); } +static bool check_sym(ELF(Sym) *sym, ELF(Word) i, const char *name, + const char *version, unsigned long ver_hash) +{ + /* Check for a defined global or weak function w/ right name. */ + if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) + return false; + if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && + ELF64_ST_BIND(sym->st_info) != STB_WEAK) + return false; + if (strcmp(name, vdso_info.symstrings + sym->st_name)) + return false; + + /* Check symbol version. */ + if (vdso_info.versym && + !vdso_match_version(vdso_info.versym[i], version, ver_hash)) + return false; + + return true; +} + void *vdso_sym(const char *version, const char *name) { unsigned long ver_hash; @@ -216,29 +263,36 @@ void *vdso_sym(const char *version, const char *name) return 0; ver_hash = elf_hash(version); - ELF(Word) chain = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; - - for (; chain != STN_UNDEF; chain = vdso_info.chain[chain]) { - ELF(Sym) *sym = &vdso_info.symtab[chain]; - - /* Check for a defined global or weak function w/ right name. */ - if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC) - continue; - if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL && - ELF64_ST_BIND(sym->st_info) != STB_WEAK) - continue; - if (sym->st_shndx == SHN_UNDEF) - continue; - if (strcmp(name, vdso_info.symstrings + sym->st_name)) - continue; - - /* Check symbol version. */ - if (vdso_info.versym - && !vdso_match_version(vdso_info.versym[chain], - version, ver_hash)) - continue; - - return (void *)(vdso_info.load_offset + sym->st_value); + ELF(Word) i; + + if (vdso_info.gnu_hash) { + uint32_t h1 = gnu_hash(name), h2, *hashval; + + i = vdso_info.bucket[h1 % vdso_info.nbucket]; + if (i == 0) + return 0; + h1 |= 1; + hashval = vdso_info.bucket + vdso_info.nbucket + + (i - vdso_info.gnu_hash[1]); + for (;; i++) { + ELF(Sym) *sym = &vdso_info.symtab[i]; + h2 = *hashval++; + if (h1 == (h2 | 1) && + check_sym(sym, i, name, version, ver_hash)) + return (void *)(vdso_info.load_offset + + sym->st_value); + if (h2 & 1) + break; + } + } else { + i = vdso_info.bucket[elf_hash(name) % vdso_info.nbucket]; + for (; i; i = vdso_info.chain[i]) { + ELF(Sym) *sym = &vdso_info.symtab[i]; + if (sym->st_shndx != SHN_UNDEF && + check_sym(sym, i, name, version, ver_hash)) + return (void *)(vdso_info.load_offset + + sym->st_value); + } } return 0; diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..4d4a76532dc9 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -237,7 +237,7 @@ static uint64_t set_metadata(uint64_t src, unsigned long lam) * both pointers should point to the same address. * * @return: - * 0: value on the pointer with metadate and value on original are same + * 0: value on the pointer with metadata and value on original are same * 1: not same. */ static int handle_lam_test(void *src, unsigned int lam) diff --git a/tools/testing/selftests/zram/.gitignore b/tools/testing/selftests/zram/.gitignore new file mode 100644 index 000000000000..088cd9bad87a --- /dev/null +++ b/tools/testing/selftests/zram/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +err.log diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c index 9bcf1736bf18..04ab45e27fb8 100644 --- a/tools/testing/vma/vma.c +++ b/tools/testing/vma/vma.c @@ -18,6 +18,12 @@ static bool fail_prealloc; #define vma_iter_prealloc(vmi, vma) \ (fail_prealloc ? -ENOMEM : mas_preallocate(&(vmi)->mas, (vma), GFP_KERNEL)) +#define CONFIG_DEFAULT_MMAP_MIN_ADDR 65536 + +unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR; +unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT; + /* * Directly import the VMA implementation here. Our vma_internal.h wrapper * provides userland-equivalent functionality for everything vma.c uses. @@ -47,6 +53,11 @@ struct task_struct *get_current(void) return &__current; } +unsigned long rlimit(unsigned int limit) +{ + return (unsigned long)-1; +} + /* Helper function to simply allocate a VMA. */ static struct vm_area_struct *alloc_vma(struct mm_struct *mm, unsigned long start, @@ -1563,6 +1574,57 @@ static bool test_expand_only_mode(void) return true; } +static bool test_mmap_region_basic(void) +{ + struct mm_struct mm = {}; + unsigned long addr; + struct vm_area_struct *vma; + VMA_ITERATOR(vmi, &mm, 0); + + current->mm = &mm; + + /* Map at 0x300000, length 0x3000. */ + addr = __mmap_region(NULL, 0x300000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x300, NULL); + ASSERT_EQ(addr, 0x300000); + + /* Map at 0x250000, length 0x3000. */ + addr = __mmap_region(NULL, 0x250000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x250, NULL); + ASSERT_EQ(addr, 0x250000); + + /* Map at 0x303000, merging to 0x300000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x303000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x303, NULL); + ASSERT_EQ(addr, 0x303000); + + /* Map at 0x24d000, merging to 0x250000 of length 0x6000. */ + addr = __mmap_region(NULL, 0x24d000, 0x3000, + VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE, + 0x24d, NULL); + ASSERT_EQ(addr, 0x24d000); + + ASSERT_EQ(mm.map_count, 2); + + for_each_vma(vmi, vma) { + if (vma->vm_start == 0x300000) { + ASSERT_EQ(vma->vm_end, 0x306000); + ASSERT_EQ(vma->vm_pgoff, 0x300); + } else if (vma->vm_start == 0x24d000) { + ASSERT_EQ(vma->vm_end, 0x253000); + ASSERT_EQ(vma->vm_pgoff, 0x24d); + } else { + ASSERT_FALSE(true); + } + } + + cleanup_mm(&mm, &vmi); + return true; +} + int main(void) { int num_tests = 0, num_fail = 0; @@ -1596,6 +1658,8 @@ int main(void) TEST(copy_vma); TEST(expand_only_mode); + TEST(mmap_region_basic); + #undef TEST printf("%d tests run, %d passed, %d failed.\n", diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h index 1d9fc97b8e80..1eae23039854 100644 --- a/tools/testing/vma/vma_internal.h +++ b/tools/testing/vma/vma_internal.h @@ -27,11 +27,23 @@ #include <linux/rbtree.h> #include <linux/rwsem.h> +extern unsigned long stack_guard_gap; +#ifdef CONFIG_MMU +extern unsigned long mmap_min_addr; +extern unsigned long dac_mmap_min_addr; +#else +#define mmap_min_addr 0UL +#define dac_mmap_min_addr 0UL +#endif + #define VM_WARN_ON(_expr) (WARN_ON(_expr)) #define VM_WARN_ON_ONCE(_expr) (WARN_ON_ONCE(_expr)) +#define VM_WARN_ON_VMG(_expr, _vmg) (WARN_ON(_expr)) #define VM_BUG_ON(_expr) (BUG_ON(_expr)) #define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr)) +#define MMF_HAS_MDWE 28 + #define VM_NONE 0x00000000 #define VM_READ 0x00000001 #define VM_WRITE 0x00000002 @@ -39,6 +51,7 @@ #define VM_SHARED 0x00000008 #define VM_MAYREAD 0x00000010 #define VM_MAYWRITE 0x00000020 +#define VM_MAYEXEC 0x00000040 #define VM_GROWSDOWN 0x00000100 #define VM_PFNMAP 0x00000400 #define VM_LOCKED 0x00002000 @@ -51,6 +64,8 @@ #define VM_STACK VM_GROWSDOWN #define VM_SHADOW_STACK VM_NONE #define VM_SOFTDIRTY 0 +#define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ +#define VM_GROWSUP VM_NONE #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC) #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP) @@ -58,6 +73,20 @@ /* This mask represents all the VMA flag bits used by mlock */ #define VM_LOCKED_MASK (VM_LOCKED | VM_LOCKONFAULT) +#define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) + +#define VM_DATA_FLAGS_TSK_EXEC (VM_READ | VM_WRITE | TASK_EXEC | \ + VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC) + +#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC + +#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK) + +#define RLIMIT_STACK 3 /* max stack size */ +#define RLIMIT_MEMLOCK 8 /* max locked-in-memory address space */ + +#define CAP_IPC_LOCK 14 + #ifdef CONFIG_64BIT /* VM is sealed, in vm_flags */ #define VM_SEALED _BITUL(63) @@ -122,10 +151,22 @@ enum { TASK_COMM_LEN = 16, }; +/* + * Flags for bug emulation. + * + * These occupy the top three bytes. + */ +enum { + READ_IMPLIES_EXEC = 0x0400000, +}; + struct task_struct { char comm[TASK_COMM_LEN]; pid_t pid; struct mm_struct *mm; + + /* Used for emulating ABI behavior of previous Linux versions: */ + unsigned int personality; }; struct task_struct *get_current(void); @@ -186,6 +227,10 @@ struct mm_struct { unsigned long data_vm; /* VM_WRITE & ~VM_SHARED & ~VM_STACK */ unsigned long exec_vm; /* VM_EXEC & ~VM_WRITE & ~VM_STACK */ unsigned long stack_vm; /* VM_STACK */ + + unsigned long def_flags; + + unsigned long flags; /* Must use atomic bitops to access */ }; struct vma_lock { @@ -373,6 +418,17 @@ struct vm_operations_struct { unsigned long addr); }; +struct vm_unmapped_area_info { +#define VM_UNMAPPED_AREA_TOPDOWN 1 + unsigned long flags; + unsigned long length; + unsigned long low_limit; + unsigned long high_limit; + unsigned long align_mask; + unsigned long align_offset; + unsigned long start_gap; +}; + static inline void vma_iter_invalidate(struct vma_iterator *vmi) { mas_pause(&vmi->mas); @@ -432,6 +488,8 @@ static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached) extern const struct vm_operations_struct vma_dummy_vm_ops; +extern unsigned long rlimit(unsigned int limit); + static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm) { memset(vma, 0, sizeof(*vma)); @@ -853,6 +911,11 @@ static inline void mmap_write_unlock(struct mm_struct *) { } +static inline int mmap_write_lock_killable(struct mm_struct *) +{ + return 0; +} + static inline bool can_modify_mm(struct mm_struct *mm, unsigned long start, unsigned long end) @@ -938,7 +1001,7 @@ static inline bool is_file_hugepages(struct file *) static inline int security_vm_enough_memory_mm(struct mm_struct *, long) { - return true; + return 0; } static inline bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long) @@ -1033,4 +1096,159 @@ static inline int mmap_file(struct file *, struct vm_area_struct *) return 0; } +static inline unsigned long stack_guard_start_gap(struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_GROWSDOWN) + return stack_guard_gap; + + /* See reasoning around the VM_SHADOW_STACK definition */ + if (vma->vm_flags & VM_SHADOW_STACK) + return PAGE_SIZE; + + return 0; +} + +static inline unsigned long vm_start_gap(struct vm_area_struct *vma) +{ + unsigned long gap = stack_guard_start_gap(vma); + unsigned long vm_start = vma->vm_start; + + vm_start -= gap; + if (vm_start > vma->vm_start) + vm_start = 0; + return vm_start; +} + +static inline unsigned long vm_end_gap(struct vm_area_struct *vma) +{ + unsigned long vm_end = vma->vm_end; + + if (vma->vm_flags & VM_GROWSUP) { + vm_end += stack_guard_gap; + if (vm_end < vma->vm_end) + vm_end = -PAGE_SIZE; + } + return vm_end; +} + +static inline int is_hugepage_only_range(struct mm_struct *mm, + unsigned long addr, unsigned long len) +{ + return 0; +} + +static inline bool vma_is_accessible(struct vm_area_struct *vma) +{ + return vma->vm_flags & VM_ACCESS_FLAGS; +} + +static inline bool capable(int cap) +{ + return true; +} + +static inline bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, + unsigned long bytes) +{ + unsigned long locked_pages, limit_pages; + + if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK)) + return true; + + locked_pages = bytes >> PAGE_SHIFT; + locked_pages += mm->locked_vm; + + limit_pages = rlimit(RLIMIT_MEMLOCK); + limit_pages >>= PAGE_SHIFT; + + return locked_pages <= limit_pages; +} + +static inline int __anon_vma_prepare(struct vm_area_struct *vma) +{ + struct anon_vma *anon_vma = calloc(1, sizeof(struct anon_vma)); + + if (!anon_vma) + return -ENOMEM; + + anon_vma->root = anon_vma; + vma->anon_vma = anon_vma; + + return 0; +} + +static inline int anon_vma_prepare(struct vm_area_struct *vma) +{ + if (likely(vma->anon_vma)) + return 0; + + return __anon_vma_prepare(vma); +} + +static inline void userfaultfd_unmap_complete(struct mm_struct *mm, + struct list_head *uf) +{ +} + +/* + * Denies creating a writable executable mapping or gaining executable permissions. + * + * This denies the following: + * + * a) mmap(PROT_WRITE | PROT_EXEC) + * + * b) mmap(PROT_WRITE) + * mprotect(PROT_EXEC) + * + * c) mmap(PROT_WRITE) + * mprotect(PROT_READ) + * mprotect(PROT_EXEC) + * + * But allows the following: + * + * d) mmap(PROT_READ | PROT_EXEC) + * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. + */ +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) +{ + /* If MDWE is disabled, we have nothing to deny. */ + if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) + return false; + + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) + return true; + + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) + return true; + + return false; +} + +static inline int mapping_map_writable(struct address_space *mapping) +{ + int c = atomic_read(&mapping->i_mmap_writable); + + /* Derived from the raw_atomic_inc_unless_negative() implementation. */ + do { + if (c < 0) + return -EPERM; + } while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1)); + + return 0; +} + #endif /* __MM_VMA_INTERNAL_H */ diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 7058dc614c25..de25892f865f 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -96,41 +96,57 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ -int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ +int vsock_bind(unsigned int cid, unsigned int port, int type) { - struct sockaddr_vm sa_client = { - .svm_family = AF_VSOCK, - .svm_cid = VMADDR_CID_ANY, - .svm_port = bind_port, - }; - struct sockaddr_vm sa_server = { + struct sockaddr_vm sa = { .svm_family = AF_VSOCK, .svm_cid = cid, .svm_port = port, }; + int fd; - int client_fd, ret; - - client_fd = socket(AF_VSOCK, type, 0); - if (client_fd < 0) { + fd = socket(AF_VSOCK, type, 0); + if (fd < 0) { perror("socket"); exit(EXIT_FAILURE); } - if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) { + if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) { perror("bind"); exit(EXIT_FAILURE); } + return fd; +} + +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port) +{ + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = cid, + .svm_port = port, + }; + int ret; + timeout_begin(TIMEOUT); do { - ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server)); + ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa)); timeout_check("connect"); } while (ret < 0 && errno == EINTR); timeout_end(); - if (ret < 0) { + return ret; +} + +/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ +int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +{ + int client_fd; + + client_fd = vsock_bind(VMADDR_CID_ANY, bind_port, type); + + if (vsock_connect_fd(client_fd, cid, port)) { perror("connect"); exit(EXIT_FAILURE); } @@ -141,17 +157,6 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po /* Connect to <cid, port> and return the file descriptor. */ int vsock_connect(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; - int ret; int fd; control_expectln("LISTENING"); @@ -162,20 +167,14 @@ int vsock_connect(unsigned int cid, unsigned int port, int type) exit(EXIT_FAILURE); } - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + if (vsock_connect_fd(fd, cid, port)) { int old_errno = errno; close(fd); fd = -1; errno = old_errno; } + return fd; } @@ -192,28 +191,9 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port) /* Listen on <cid, port> and return the file descriptor. */ static int vsock_listen(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; int fd; - fd = socket(AF_VSOCK, type, 0); - if (fd < 0) { - perror("socket"); - exit(EXIT_FAILURE); - } - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(cid, port, type); if (listen(fd, 1) < 0) { perror("listen"); diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e62f46b2b92a..d1f765ce3eee 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -39,10 +39,12 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); unsigned int parse_port(const char *str); +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port); int vsock_connect(unsigned int cid, unsigned int port, int type); int vsock_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_bind(unsigned int cid, unsigned int port, int type); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); int vsock_seqpacket_connect(unsigned int cid, unsigned int port); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 1eebbc0d5f61..d0f6d253ac72 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -113,24 +113,9 @@ static void test_stream_bind_only_client(const struct test_opts *opts) static void test_stream_bind_only_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = opts->peer_port, - .svm_cid = VMADDR_CID_ANY, - }, - }; int fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(VMADDR_CID_ANY, opts->peer_port, SOCK_STREAM); /* Notify the client that the server is ready */ control_writeln("BIND"); @@ -1708,6 +1693,137 @@ static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) close(fd); } +#define MAX_PORT_RETRIES 24 /* net/vmw_vsock/af_vsock.c */ + +/* Test attempts to trigger a transport release for an unbound socket. This can + * lead to a reference count mishandling. + */ +static void test_stream_transport_uaf_client(const struct test_opts *opts) +{ + int sockets[MAX_PORT_RETRIES]; + struct sockaddr_vm addr; + int fd, i, alen; + + fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM); + + alen = sizeof(addr); + if (getsockname(fd, (struct sockaddr *)&addr, &alen)) { + perror("getsockname"); + exit(EXIT_FAILURE); + } + + for (i = 0; i < MAX_PORT_RETRIES; ++i) + sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port, + SOCK_STREAM); + + close(fd); + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) { + perror("Unexpected connect() #1 success"); + exit(EXIT_FAILURE); + } + + /* Vulnerable system may crash now. */ + if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) { + perror("Unexpected connect() #2 success"); + exit(EXIT_FAILURE); + } + + close(fd); + while (i--) + close(sockets[i]); + + control_writeln("DONE"); +} + +static void test_stream_transport_uaf_server(const struct test_opts *opts) +{ + control_expectln("DONE"); +} + +static void test_stream_connect_retry_client(const struct test_opts *opts) +{ + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + fprintf(stderr, "Unexpected connect() #1 success\n"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTEN"); + control_expectln("LISTENING"); + + if (vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + perror("connect() #2"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_connect_retry_server(const struct test_opts *opts) +{ + int fd; + + control_expectln("LISTEN"); + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + +static void test_stream_linger_client(const struct test_opts *opts) +{ + struct linger optval = { + .l_onoff = 1, + .l_linger = 1 + }; + int fd; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) { + perror("setsockopt(SO_LINGER)"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_linger_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1853,6 +1969,21 @@ static struct test_case test_cases[] = { .run_client = test_stream_msgzcopy_leak_zcskb_client, .run_server = test_stream_msgzcopy_leak_zcskb_server, }, + { + .name = "SOCK_STREAM transport release use-after-free", + .run_client = test_stream_transport_uaf_client, + .run_server = test_stream_transport_uaf_server, + }, + { + .name = "SOCK_STREAM retry failed connect()", + .run_client = test_stream_connect_retry_client, + .run_server = test_stream_connect_retry_server, + }, + { + .name = "SOCK_STREAM SO_LINGER null-ptr-deref", + .run_client = test_stream_linger_client, + .run_server = test_stream_linger_server, + }, {}, }; |