- Linux-kselftest-mirror - lists.linaro.org

[PATCH net-next] selftests: net/psock_lib: Handle EINTR and EAGAIN

by Leo Stone

Make pair_udp_send_char handle EAGAIN, EINTR, and partial reads or writes. Signed-off-by: Leo Stone <leocstone(a)gmail.com> --- tools/testing/selftests/net/psock_lib.h | 39 +++++++++++++++++++------ 1 file changed, 30 insertions(+), 9 deletions(-) diff --git a/tools/testing/selftests/net/psock_lib.h b/tools/testing/selftests/net/psock_lib.h index 6e4fef560873..e28bff95c8e2 100644 --- a/tools/testing/selftests/net/psock_lib.h +++ b/tools/testing/selftests/net/psock_lib.h @@ -13,6 +13,7 @@ #include <string.h> #include <arpa/inet.h> #include <unistd.h> +#include <stdbool.h> #include "kselftest.h" @@ -110,21 +111,41 @@ static __maybe_unused void pair_udp_open(int fds[], uint16_t port) } } +static void read_write_checked(int fd, char *buf, size_t sz, bool is_write) +{ + int bytes_processed = 0; + int ret; + + do { + if (is_write) + ret = write(fd, buf + bytes_processed, + sz - bytes_processed); + else + ret = read(fd, buf + bytes_processed, + sz - bytes_processed); + if (ret == -1) { + if (errno == EAGAIN || errno == EINTR) { + continue; + } else { + fprintf(stderr, "ERROR: %s failed, bytes left=%lu\n", + is_write ? "send" : "recv", + sz - bytes_processed); + exit(1); + } + } + bytes_processed += ret; + } while (bytes_processed < sz); +} + static __maybe_unused void pair_udp_send_char(int fds[], int num, char payload) { char buf[DATA_LEN], rbuf[DATA_LEN]; memset(buf, payload, sizeof(buf)); while (num--) { - /* Should really handle EINTR and EAGAIN */ - if (write(fds[0], buf, sizeof(buf)) != sizeof(buf)) { - fprintf(stderr, "ERROR: send failed left=%d\n", num); - exit(1); - } - if (read(fds[1], rbuf, sizeof(rbuf)) != sizeof(rbuf)) { - fprintf(stderr, "ERROR: recv failed left=%d\n", num); - exit(1); - } + read_write_checked(fds[0], buf, sizeof(buf), true); + read_write_checked(fds[1], rbuf, sizeof(rbuf), false); + if (memcmp(buf, rbuf, sizeof(buf))) { fprintf(stderr, "ERROR: data failed left=%d\n", num); exit(1); -- 2.39.5

7 months, 1 week

2
2
0 0

[PATCH] kunit: tool: add ability to parse test metadata

by Rae Moar

Add ability for kunit parser to parse test metadata introduced in KTAPv2. Example of test metadata: KTAP version 2 #:ktap_test: test_name_example #:ktap_speed: slow #:ktap_test_file: /sys/kernel/... 1..1 ok 1 test Also add tests for this feature. Note this patch would no longer allow the case where the main test is missing a test plan and the subtest does not use a KTAP version line in the header. However, this is also not an accepted KTAP format. Example: KTAP version 2 // missing test plan // missing KTAP version line # Subtest: test_suite 1..1 ok 1 test ok 1 test_suite Signed-off-by: Rae Moar <rmoar(a)google.com> --- lib/kunit/attributes.c | 23 ++++-- lib/kunit/debugfs.c | 2 +- lib/kunit/test.c | 9 +-- tools/testing/kunit/kunit_parser.py | 79 +++++++++++++------ tools/testing/kunit/kunit_tool_test.py | 12 ++- .../test_is_test_passed-missing_plan.log | 2 + .../kunit/test_data/test_parse_attributes.log | 6 +- .../kunit/test_data/test_parse_metadata.log | 11 +++ 8 files changed, 106 insertions(+), 38 deletions(-) create mode 100644 tools/testing/kunit/test_data/test_parse_metadata.log diff --git a/lib/kunit/attributes.c b/lib/kunit/attributes.c index 2cf04cc09372..85db4555d332 100644 --- a/lib/kunit/attributes.c +++ b/lib/kunit/attributes.c @@ -286,11 +286,17 @@ void kunit_print_attr(void *test_or_suite, bool is_test, unsigned int test_level { int i; bool to_free = false; + bool printed = false; void *attr; const char *attr_name, *attr_str; struct kunit_suite *suite = is_test ? NULL : test_or_suite; struct kunit_case *test = is_test ? test_or_suite : NULL; + if (suite) { + kunit_log(KERN_INFO, suite, "%*s#:ktap_test: %s", + KUNIT_INDENT_LEN * test_level, "", suite->name); + } + for (i = 0; i < ARRAY_SIZE(kunit_attr_list); i++) { if (kunit_attr_list[i].print == PRINT_NEVER || (test && kunit_attr_list[i].print == PRINT_SUITE)) @@ -300,12 +306,19 @@ void kunit_print_attr(void *test_or_suite, bool is_test, unsigned int test_level attr_name = kunit_attr_list[i].name; attr_str = kunit_attr_list[i].to_string(attr, &to_free); if (test) { - kunit_log(KERN_INFO, test, "%*s# %s.%s: %s", - KUNIT_INDENT_LEN * test_level, "", test->name, - attr_name, attr_str); + if (!printed) { + kunit_log(KERN_INFO, test, "%*s#:ktap_test: %s", + KUNIT_INDENT_LEN * test_level, "", + test->name); + printed = true; + } + kunit_log(KERN_INFO, test, "%*s#:ktap_%s: %s", + KUNIT_INDENT_LEN * test_level, "", + attr_name, attr_str); } else { - kunit_log(KERN_INFO, suite, "%*s# %s: %s", - KUNIT_INDENT_LEN * test_level, "", attr_name, attr_str); + kunit_log(KERN_INFO, suite, "%*s#:ktap_%s: %s", + KUNIT_INDENT_LEN * test_level, "", + attr_name, attr_str); } /* Free to_string of attribute if needed */ diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index af71911f4a07..035cdae9d8b8 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -78,7 +78,7 @@ static int debugfs_print_results(struct seq_file *seq, void *v) /* Print suite header because it is not stored in the test logs. */ seq_puts(seq, KUNIT_SUBTEST_INDENT "KTAP version 1\n"); - seq_printf(seq, KUNIT_SUBTEST_INDENT "# Subtest: %s\n", suite->name); + seq_printf(seq, KUNIT_SUBTEST_INDENT "#:ktap_test: %s\n", suite->name); seq_printf(seq, KUNIT_SUBTEST_INDENT "1..%zd\n", kunit_suite_num_test_cases(suite)); kunit_suite_for_each_test_case(suite, test_case) diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 089c832e3cdb..4fcc39e87983 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -158,8 +158,6 @@ static void kunit_print_suite_start(struct kunit_suite *suite) * representation. */ pr_info(KUNIT_SUBTEST_INDENT "KTAP version 1\n"); - pr_info(KUNIT_SUBTEST_INDENT "# Subtest: %s\n", - suite->name); kunit_print_attr((void *)suite, false, KUNIT_LEVEL_CASE); pr_info(KUNIT_SUBTEST_INDENT "1..%zd\n", kunit_suite_num_test_cases(suite)); @@ -627,9 +625,11 @@ int kunit_run_tests(struct kunit_suite *suite) if (test_case->status == KUNIT_SKIPPED) { /* Test marked as skip */ test.status = KUNIT_SKIPPED; + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); kunit_update_stats(&param_stats, test.status); } else if (!test_case->generate_params) { /* Non-parameterised test. */ + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); test_case->status = KUNIT_SKIPPED; kunit_run_case_catch_errors(suite, test_case, &test); kunit_update_stats(&param_stats, test.status); @@ -641,7 +641,8 @@ int kunit_run_tests(struct kunit_suite *suite) kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT "KTAP version 1\n"); kunit_log(KERN_INFO, &test, KUNIT_SUBTEST_INDENT KUNIT_SUBTEST_INDENT - "# Subtest: %s", test_case->name); + "#:ktap_test: %s", test_case->name); + kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); while (test.param_value) { kunit_run_case_catch_errors(suite, test_case, &test); @@ -669,8 +670,6 @@ int kunit_run_tests(struct kunit_suite *suite) } } - kunit_print_attr((void *)test_case, true, KUNIT_LEVEL_CASE); - kunit_print_test_stats(&test, param_stats); kunit_print_ok_not_ok(&test, KUNIT_LEVEL_CASE, test_case->status, diff --git a/tools/testing/kunit/kunit_parser.py b/tools/testing/kunit/kunit_parser.py index 29fc27e8949b..52dcbad52ade 100644 --- a/tools/testing/kunit/kunit_parser.py +++ b/tools/testing/kunit/kunit_parser.py @@ -247,7 +247,7 @@ def extract_tap_lines(kernel_output: Iterable[str]) -> LineStream: yield line_num, line return LineStream(lines=isolate_ktap_output(kernel_output)) -KTAP_VERSIONS = [1] +KTAP_VERSIONS = [1, 2] TAP_VERSIONS = [13, 14] def check_version(version_num: int, accepted_versions: List[int], @@ -324,6 +324,39 @@ def parse_test_header(lines: LineStream, test: Test) -> bool: lines.pop() return True +TEST_METADATA_HEADER = re.compile(r'^\s*#:ktap_test: (.*)$') +TEST_METADATA = re.compile(r'^\s*#:(ktap_.*): (.*)$') + +def parse_test_metadata(lines: LineStream, test: Test) -> bool: + """ + Parses test metadata and stores test information in test object. + Returns False if fails to parse test metadata lines + + Accepted format: + - '# [metadata_category]: [metadata]' + + Recognized metadata categories: + - 'ktap_test' to indicate test name + + Parameters: + lines - LineStream of KTAP output to parse + test - Test object for current test being parsed + + Return: + True if successfully parsed test metadata + """ + match = TEST_METADATA_HEADER.match(lines.peek()) + if not match: + return False + test.name = match.group(1) + test.log.append(lines.pop()) + non_metadata_lines = [TEST_PLAN, TEST_RESULT, KTAP_START] + while lines and not any(re.match(lines.peek()) + for re in non_metadata_lines): + # Add checks for metadata cateories here: Attributes, Files, Other... + test.log.append(lines.pop()) + return True + TEST_PLAN = re.compile(r'^\s*1\.\.([0-9]+)') def parse_test_plan(lines: LineStream, test: Test) -> bool: @@ -442,6 +475,7 @@ def parse_diagnostic(lines: LineStream) -> List[str]: Line formats that are not parsed: - '# Subtest: [test name]' + - '#:ktap_test: [test name]' - '[ok|not ok] [test number] [-] [test name] [optional skip directive]' - 'KTAP version [version number]' @@ -453,7 +487,8 @@ def parse_diagnostic(lines: LineStream) -> List[str]: Log of diagnostic lines """ log = [] # type: List[str] - non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START, TEST_PLAN] + non_diagnostic_lines = [TEST_RESULT, TEST_HEADER, KTAP_START, TAP_START, + TEST_PLAN, TEST_METADATA_HEADER] while lines and not any(re.match(lines.peek()) for re in non_diagnostic_lines): log.append(lines.pop()) @@ -504,7 +539,7 @@ def print_test_header(test: Test, printer: Printer) -> None: message = test.name if message != "": # Add a leading space before the subtest counts only if a test name - # is provided using a "# Subtest" header line. + # is provided using a "#:ktap_test" or "# Subtest" header line. message += " " if test.expected_count: if test.expected_count == 1: @@ -702,6 +737,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: Example: KTAP version 1 + [test metadata] 1..4 [subtests] @@ -709,10 +745,11 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: "# Subtest" header line) Example (preferred format with both KTAP version line and - "# Subtest" line): + "#:ktap_test" line): KTAP version 1 - # Subtest: name + #:ktap_test: name + [test metadata] 1..3 [subtests] ok 1 name @@ -727,6 +764,7 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: Example (only KTAP version line, compliant with KTAP v1 spec): KTAP version 1 + [test metadata] 1..3 [subtests] ok 1 name @@ -755,26 +793,23 @@ def parse_test(lines: LineStream, expected_num: int, log: List[str], is_subtest: err_log = parse_diagnostic(lines) test.log.extend(err_log) - if not is_subtest: - # If parsing the main/top-level test, parse KTAP version line and - # test plan - test.name = "main" - ktap_line = parse_ktap_header(lines, test, printer) - test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) - parent_test = True - else: - # If not the main test, attempt to parse a test header containing - # the KTAP version line and/or subtest header line - ktap_line = parse_ktap_header(lines, test, printer) - subtest_line = parse_test_header(lines, test) + # If parsing the main/top-level test, parse KTAP version line, any + # test metadata, and test plan + ktap_line = parse_ktap_header(lines, test, printer) + subtest_line = parse_test_header(lines, test) + parse_test_metadata(lines, test) + parse_test_plan(lines, test) + + # Determine if the test is a parent test + if is_subtest: parent_test = (ktap_line or subtest_line) if parent_test: - # If KTAP version line and/or subtest header is found, attempt - # to parse test plan and print test header - test.log.extend(parse_diagnostic(lines)) - parse_test_plan(lines, test) print_test_header(test, printer) + else: + parent_test = True + if test.name == "": + test.name = "main" + expected_count = test.expected_count subtests = [] test_num = 1 diff --git a/tools/testing/kunit/kunit_tool_test.py b/tools/testing/kunit/kunit_tool_test.py index 0bcb0cc002f8..6ff422399130 100755 --- a/tools/testing/kunit/kunit_tool_test.py +++ b/tools/testing/kunit/kunit_tool_test.py @@ -345,8 +345,8 @@ class KUnitParserTest(unittest.TestCase): self.print_mock.assert_any_call(StrContains('suite (1 subtest)')) # Ensure attributes in correct test log - self.assertContains('# module: example', result.subtests[0].log) - self.assertContains('# test.speed: slow', result.subtests[0].subtests[0].log) + self.assertContains('#:ktap_module: example', result.subtests[0].log) + self.assertContains('#:ktap_speed: slow', result.subtests[0].subtests[0].log) def test_show_test_output_on_failure(self): output = """ @@ -363,6 +363,14 @@ class KUnitParserTest(unittest.TestCase): self.print_mock.assert_any_call(StrContains(' Indented more.')) self.noPrintCallContains('not ok 1 test1') + def test_metadata(self): + name_log = test_data_path('test_parse_metadata.log') + with open(name_log) as file: + result = kunit_parser.parse_run_tests(file.readlines(), stdout) + self.assertEqual(kunit_parser.TestStatus.SUCCESS, result.status) + self.assertEqual("main_test", result.name) + self.assertContains("#:ktap_speed: slow", result.subtests[0].log) + def line_stream_from_strs(strs: Iterable[str]) -> kunit_parser.LineStream: return kunit_parser.LineStream(enumerate(strs, start=1)) diff --git a/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log b/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log index 5cd17b7f818a..1e952b0430e1 100644 --- a/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log +++ b/tools/testing/kunit/test_data/test_is_test_passed-missing_plan.log @@ -1,4 +1,5 @@ KTAP version 1 + KTAP version 1 # Subtest: sysctl_test # sysctl_test_dointvec_null_tbl_data: sysctl_test_dointvec_null_tbl_data passed ok 1 - sysctl_test_dointvec_null_tbl_data @@ -18,6 +19,7 @@ KTAP version 1 ok 8 - sysctl_test_dointvec_single_greater_int_max kunit sysctl_test: all tests passed ok 1 - sysctl_test + KTAP version 1 # Subtest: example 1..2 init_suite diff --git a/tools/testing/kunit/test_data/test_parse_attributes.log b/tools/testing/kunit/test_data/test_parse_attributes.log index 1a13c371fe9d..d7961422c66f 100644 --- a/tools/testing/kunit/test_data/test_parse_attributes.log +++ b/tools/testing/kunit/test_data/test_parse_attributes.log @@ -1,9 +1,9 @@ KTAP version 1 1..1 KTAP version 1 - # Subtest: suite - # module: example + #:ktap_test: suite + #:ktap_module: example 1..1 - # test.speed: slow + #:ktap_speed: slow ok 1 test ok 1 suite \ No newline at end of file diff --git a/tools/testing/kunit/test_data/test_parse_metadata.log b/tools/testing/kunit/test_data/test_parse_metadata.log new file mode 100644 index 000000000000..2094867110e5 --- /dev/null +++ b/tools/testing/kunit/test_data/test_parse_metadata.log @@ -0,0 +1,11 @@ +KTAP version 2 +#:ktap_test: main_test +#:ktap_module: example +1..2 + KTAP version 2 + #:ktap_test: test_1 + #:ktap_speed: slow + 1..1 + ok 1 subtest_1 +ok 1 test_1 +ok 2 test_2 \ No newline at end of file base-commit: 62adcae479fe5bc04fa3b6c3f93bd340441f8b25 -- 2.47.0.338.g60cca15819-goog

7 months, 1 week

1
0
0 0

[GIT PULL] Kselftest update for Linux 6.13-rc1

by Shuah Khan

Hi Linus, Please pull the following kselftest fixes update for Linux 6.13-rc1. kselftest update for Linux 6.13-rc1 -- timers test - removes duplicates defines -- timers test - fixes to improve error reporting -- rtc test - adds check rtc alarm status to alarm test -- resctrl test - adds array overrun checks during iMC config parsing code -- resctrl test - adds array overflow checks when reading strings -- resctrl test - fixes and reorganizing code Looks like I forgot to mention signal test changes in my tag message. :( diff is attached. Tests passed on my kselftest next branch: - Individual test runs of signal, timers, rtc, and resctrl thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 8e929cb546ee42c9a61d24fae60605e9e3192354: Linux 6.12-rc3 (2024-10-13 14:33:32 -0700) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-next-6.13-rc1 for you to fetch changes up to a44c26d7fa74a5f4d2795a5c55a2d6ec1ebf1e38: selftests/resctrl: Replace magic constants used as array size (2024-11-04 17:02:03 -0700) ---------------------------------------------------------------- linux_kselftest-next-6.13-rc1 kselftest update for Linux 6.13-rc1 -- timers test - removes duplicates defines -- timers test - fixes to improve error reporting -- rtc test - adds check rtc alarm status to alarm test -- resctrl test - adds array overrun checks during iMC config parsing code -- resctrl test - adds array overflow checks when reading strings -- resctrl test - fixes and reorganizing code ---------------------------------------------------------------- Chen Ni (1): selftests: timers: Remove unneeded semicolon Dev Jain (2): selftests: Rename sigaltstack to generic signal selftests: Add a test mangling with uc_sigmask Gianfranco Trad (1): selftests: timers: improve timer_create failure message Joseph Jang (1): selftest: rtc: Add to check rtc alarm status for alarm related test Nícolas F. R. A. Prado (1): docs: dev-tools: Add documentation for the device focused kselftests Reinette Chatre (15): selftests/resctrl: Make functions only used in same file static selftests/resctrl: Print accurate buffer size as part of MBM results selftests/resctrl: Fix memory overflow due to unhandled wraparound selftests/resctrl: Protect against array overrun during iMC config parsing selftests/resctrl: Protect against array overflow when reading strings selftests/resctrl: Make wraparound handling obvious selftests/resctrl: Remove "once" parameter required to be false selftests/resctrl: Only support measured read operation selftests/resctrl: Remove unused measurement code selftests/resctrl: Make benchmark parameter passing robust selftests/resctrl: Ensure measurements skip initialization of default benchmark selftests/resctrl: Use cache size to determine "fill_buf" buffer size selftests/resctrl: Do not compare performance counters and resctrl at low bandwidth selftests/resctrl: Keep results from first test run selftests/resctrl: Replace magic constants used as array size Shuah Khan (2): selftests: timers: Remove local NSEC_PER_SEC and USEC_PER_SEC defines selftests:timers: remove local CLOCKID defines Documentation/dev-tools/kselftest.rst | 9 + Documentation/dev-tools/testing-devices.rst | 47 +++ tools/testing/selftests/Makefile | 2 +- tools/testing/selftests/resctrl/cmt_test.c | 37 +- tools/testing/selftests/resctrl/fill_buf.c | 45 +-- tools/testing/selftests/resctrl/mba_test.c | 54 ++- tools/testing/selftests/resctrl/mbm_test.c | 37 +- tools/testing/selftests/resctrl/resctrl.h | 79 +++- tools/testing/selftests/resctrl/resctrl_tests.c | 95 ++++- tools/testing/selftests/resctrl/resctrl_val.c | 447 ++++++--------------- tools/testing/selftests/resctrl/resctrlfs.c | 19 +- tools/testing/selftests/rtc/Makefile | 2 +- tools/testing/selftests/rtc/rtctest.c | 64 +++ .../selftests/{sigaltstack => signal}/.gitignore | 1 + .../selftests/{sigaltstack => signal}/Makefile | 3 +- .../current_stack_pointer.h | 0 tools/testing/selftests/signal/mangle_uc_sigmask.c | 184 +++++++++ .../selftests/{sigaltstack => signal}/sas.c | 0 tools/testing/selftests/timers/Makefile | 2 +- tools/testing/selftests/timers/adjtick.c | 6 +- .../testing/selftests/timers/alarmtimer-suspend.c | 22 +- .../testing/selftests/timers/inconsistency-check.c | 21 +- tools/testing/selftests/timers/leap-a-day.c | 2 +- tools/testing/selftests/timers/mqueue-lat.c | 2 +- tools/testing/selftests/timers/nanosleep.c | 21 +- tools/testing/selftests/timers/nsleep-lat.c | 22 +- tools/testing/selftests/timers/posix_timers.c | 15 +- tools/testing/selftests/timers/raw_skew.c | 4 +- tools/testing/selftests/timers/set-2038.c | 3 +- tools/testing/selftests/timers/set-timer-lat.c | 21 +- tools/testing/selftests/timers/valid-adjtimex.c | 4 +- 31 files changed, 701 insertions(+), 569 deletions(-) create mode 100644 Documentation/dev-tools/testing-devices.rst rename tools/testing/selftests/{sigaltstack => signal}/.gitignore (70%) rename tools/testing/selftests/{sigaltstack => signal}/Makefile (56%) rename tools/testing/selftests/{sigaltstack => signal}/current_stack_pointer.h (100%) create mode 100644 tools/testing/selftests/signal/mangle_uc_sigmask.c rename tools/testing/selftests/{sigaltstack => signal}/sas.c (100%) ----------------------------------------------------------------

7 months, 1 week

2
1
0 0

[RFCv1 0/6] Page Detective

by Pasha Tatashin

Page Detective is a new kernel debugging tool that provides detailed information about the usage and mapping of physical memory pages. It is often known that a particular page is corrupted, but it is hard to extract more information about such a page from live system. Examples are: - Checksum failure during live migration - Filesystem journal failure - dump_page warnings on the console log - Unexcpected segfaults Page Detective helps to extract more information from the kernel, so it can be used by developers to root cause the associated problem. It operates through the Linux debugfs interface, with two files: "virt" and "phys". The "virt" file takes a virtual address and PID and outputs information about the corresponding page. The "phys" file takes a physical address and outputs information about that page. The output is presented via kernel log messages (can be accessed with dmesg), and includes information such as the page's reference count, mapping, flags, and memory cgroup. It also shows whether the page is mapped in the kernel page table, and if so, how many times. Pasha Tatashin (6): mm: Make get_vma_name() function public pagewalk: Add a page table walker for init_mm page table mm: Add a dump_page variant that accept log level argument misc/page_detective: Introduce Page Detective misc/page_detective: enable loadable module selftests/page_detective: Introduce self tests for Page Detective Documentation/misc-devices/index.rst | 1 + Documentation/misc-devices/page_detective.rst | 78 ++ MAINTAINERS | 8 + drivers/misc/Kconfig | 11 + drivers/misc/Makefile | 1 + drivers/misc/page_detective.c | 808 ++++++++++++++++++ fs/inode.c | 18 +- fs/kernfs/dir.c | 1 + fs/proc/task_mmu.c | 61 -- include/linux/fs.h | 5 +- include/linux/mmdebug.h | 1 + include/linux/pagewalk.h | 2 + kernel/pid.c | 1 + mm/debug.c | 53 +- mm/memcontrol.c | 1 + mm/oom_kill.c | 1 + mm/pagewalk.c | 32 + mm/vma.c | 60 ++ tools/testing/selftests/Makefile | 1 + .../selftests/page_detective/.gitignore | 1 + .../testing/selftests/page_detective/Makefile | 7 + tools/testing/selftests/page_detective/config | 4 + .../page_detective/page_detective_test.c | 727 ++++++++++++++++ 23 files changed, 1787 insertions(+), 96 deletions(-) create mode 100644 Documentation/misc-devices/page_detective.rst create mode 100644 drivers/misc/page_detective.c create mode 100644 tools/testing/selftests/page_detective/.gitignore create mode 100644 tools/testing/selftests/page_detective/Makefile create mode 100644 tools/testing/selftests/page_detective/config create mode 100644 tools/testing/selftests/page_detective/page_detective_test.c -- 2.47.0.338.g60cca15819-goog

7 months, 1 week

11
42
0 0

KUnit expectations in atomic context

by Brendan Jackman

Hi all, Another rather vague question from me - does anyone know any reasons why we couldn't support KUNIT_EXPECT in atomic contexts? For Address Space Isolation we have some tests that want to disable preemption. I guess this is not a totally insane thing to want to do - am I missing anything there? You can see some examples here: https://github.com/googleprodkernel/linux-kvm/blob/asi-lpc-24/arch/x86/mm/a… (Actually, looks like in that code we just started doing KUNIT_EXPECT in preempt-disabled regions anyway, and I never suffered any consequences until recently. Probably we just never had those assertions fail under DEBUG_ATOMIC_SLEEP). From a very quick look, it seems like the only reason you can't KUNIT_EXPECT from atomic right now is the GFP_KERNEL allocations. So... what if we just made them GFP_ATOMIC? In general I think that's a pretty ropey approach, but maybe fine in the context of unit tests? Or, we could have variants of the assertions, or a test attribute, to just use GFP_ATOMIC in the cases where it's needed. Is there anything else missing that would need to be done? Alternatively, we could expose the whole context concern to the user in such a way that KUNIT_ASSERT can be used too, something like: struct kunit_defer defer = KUNIT_INIT_DEFER(test); preempt_disable(); KUNIT_EXPECT_DEFERRED_TRUE(&defer, ...); KUNIT_ASSERT_DEFERRED_EQ(&defer, ...); preempt_enable(); // Prints failures from above, aborts if the ASSERT failed: kunit_defer_finish(&defer); I hope that wouldn't be necessary though, it seems like a lot of API surface.

7 months, 1 week

1
0
0 0

[PATCH] selftests/mount_setattr: Fix failures on 64K PAGE_SIZE kernels

by Michael Ellerman

Currently the mount_setattr_test fails on machines with a 64K PAGE_SIZE, with errors such as: # RUN mount_setattr_idmapped.invalid_fd_negative ... mkfs.ext4: No space left on device while writing out and closing file system # mount_setattr_test.c:1055:invalid_fd_negative:Expected system("mkfs.ext4 -q /mnt/C/ext4.img") (256) == 0 (0) # invalid_fd_negative: Test terminated by assertion # FAIL mount_setattr_idmapped.invalid_fd_negative not ok 12 mount_setattr_idmapped.invalid_fd_negative The code creates a 100,000 byte tmpfs: ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV, "size=100000,mode=700"), 0); And then a little later creates a 2MB ext4 filesystem in that tmpfs: ASSERT_EQ(ftruncate(img_fd, 1024 * 2048), 0); ASSERT_EQ(system("mkfs.ext4 -q /mnt/C/ext4.img"), 0); At first glance it seems like that should never work, after all 2MB is larger than 100,000 bytes. However the filesystem image doesn't actually occupy 2MB on "disk" (actually RAM, due to tmpfs). On 4K kernels the ext4.img uses ~84KB of actual space (according to du), which just fits. However on 64K PAGE_SIZE kernels the ext4.img takes at least 256KB, which is too large to fit in the tmpfs, hence the errors. It seems fraught to rely on the ext4.img taking less space on disk than the allocated size, so instead create the tmpfs with a size of 2MB. With that all 21 tests pass on 64K PAGE_SIZE kernels. Fixes: 01eadc8dd96d ("tests: add mount_setattr() selftests") Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> --- tools/testing/selftests/mount_setattr/mount_setattr_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/mount_setattr/mount_setattr_test.c b/tools/testing/selftests/mount_setattr/mount_setattr_test.c index 68801e1a9ec2..70f65eb320a7 100644 --- a/tools/testing/selftests/mount_setattr/mount_setattr_test.c +++ b/tools/testing/selftests/mount_setattr/mount_setattr_test.c @@ -1026,7 +1026,7 @@ FIXTURE_SETUP(mount_setattr_idmapped) "size=100000,mode=700"), 0); ASSERT_EQ(mount("testing", "/mnt", "tmpfs", MS_NOATIME | MS_NODEV, - "size=100000,mode=700"), 0); + "size=2m,mode=700"), 0); ASSERT_EQ(mkdir("/mnt/A", 0777), 0); -- 2.47.0

7 months, 1 week

3
2
0 0

[GIT PULL] KUnit update for Linux 6.13-rc1

by Shuah Khan

Hi Linus, Please pull the following kunit update for Linux 6.13-rc1. kunit update for Linux 6.13-rc1 -- fixes user-after-free (UAF) bug in kunit_init_suite() -- adds option to kunit tool to print just the summary of test results -- adds option to kunit tool to print just the failed test results -- fixes kunit_zalloc_skb() to use user passed in gfp value instead of hardcoding GFP_KERNEL -- fixes kunit_zalloc_skb() kernel doc to include allocation flags variable diff is attached. Tests passed on my kunit repo: - Build make allmodconfig ./tools/testing/kunit/kunit.py run ./tools/testing/kunit/kunit.py run --alltests ./tools/testing/kunit/kunit.py run --arch x86_64 ./tools/testing/kunit/kunit.py run --alltests --arch x86_64 thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 2d5404caa8c7bb5c4e0435f94b28834ae5456623: Linux 6.12-rc7 (2024-11-10 14:19:35 -0800) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-kunit-6.13-rc1 for you to fetch changes up to 67b6d342fb6d5abfbeb71e0f23141b9b96cf7bb1: kunit: tool: print failed tests only (2024-11-14 09:38:19 -0700) ---------------------------------------------------------------- linux_kselftest-kunit-6.13-rc1 kunit update for Linux 6.13-rc1 -- fixes user-after-free (UAF) bug in kunit_init_suite() -- adds option to kunit tool to print just the summary of test results -- adds option to kunit tool to print just the failed test results -- fixes kunit_zalloc_skb() to use user passed in gfp value instead of hardcoding GFP_KERNEL -- fixes kunit_zalloc_skb() kernel doc to include allocation flags variable ---------------------------------------------------------------- Dan Carpenter (2): kunit: skb: use "gfp" variable instead of hardcoding GFP_KERNEL kunit: skb: add gfp to kernel doc for kunit_zalloc_skb() David Gow (1): kunit: tool: Only print the summary Jinjie Ruan (1): kunit: string-stream: Fix a UAF bug in kunit_init_suite() Rae Moar (1): kunit: tool: print failed tests only include/kunit/skbuff.h | 5 +- lib/kunit/string-stream.c | 1 + tools/testing/kunit/kunit.py | 28 ++++++- tools/testing/kunit/kunit_parser.py | 134 +++++++++++++++++++++------------ tools/testing/kunit/kunit_printer.py | 14 +++- tools/testing/kunit/kunit_tool_test.py | 55 +++++++------- 6 files changed, 151 insertions(+), 86 deletions(-) ----------------------------------------------------------------

7 months, 1 week

2
3
0 0

[PATCHv2 net-next] selftests: wireguards: use nft by default

by Hangbin Liu

Use nft by default if it's supported, as nft is the replacement for iptables, which is used by default in some releases. Additionally, iptables is dropped in some releases. Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- v2: use one nft table for testing (Phil Sutter) --- tools/testing/selftests/wireguard/netns.sh | 63 ++++++++++++++++++---- 1 file changed, 53 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93..be4e3b13ed22 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -44,6 +44,7 @@ sleep() { read -t "$1" -N 1 || true; } waitiperf() { pretty "${1//*-}" "wait for iperf:${3:-5201} pid $2"; while [[ $(ss -N "$1" -tlpH "sport = ${3:-5201}") != *\"iperf3\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitncatudp() { pretty "${1//*-}" "wait for udp:1111 pid $2"; while [[ $(ss -N "$1" -ulpH 'sport = 1111') != *\"ncat\",pid=$2,fd=* ]]; do sleep 0.1; done; } waitiface() { pretty "${1//*-}" "wait for $2 to come up"; ip netns exec "$1" bash -c "while [[ \$(< \"/sys/class/net/$2/operstate\") != up ]]; do read -t .1 -N 0 || true; done;"; } +use_nft() { nft --version &> /dev/null; } cleanup() { set +e @@ -75,6 +76,12 @@ pp ip netns add $netns1 pp ip netns add $netns2 ip0 link set up dev lo +if use_nft; then + n0 nft add table ip wgtest + n1 nft add table ip wgtest + n2 nft add table ip wgtest +fi + ip0 link add dev wg0 type wireguard ip0 link set wg0 netns $netns1 ip0 link add dev wg0 type wireguard @@ -196,13 +203,22 @@ ip1 link set wg0 mtu 1300 ip2 link set wg0 mtu 1300 n1 wg set wg0 peer "$pub2" endpoint 127.0.0.1:2 n2 wg set wg0 peer "$pub1" endpoint 127.0.0.1:1 -n0 iptables -A INPUT -m length --length 1360 -j DROP +if use_nft; then + n0 nft add chain ip wgtest INPUT { type filter hook input priority filter \; policy accept \; } + n0 nft add rule ip wgtest INPUT meta length 1360 counter drop +else + n0 iptables -A INPUT -m length --length 1360 -j DROP +fi n1 ip route add 192.168.241.2/32 dev wg0 mtu 1299 n2 ip route add 192.168.241.1/32 dev wg0 mtu 1299 n2 ping -c 1 -W 1 -s 1269 192.168.241.1 n2 ip route delete 192.168.241.1/32 dev wg0 mtu 1299 n1 ip route delete 192.168.241.2/32 dev wg0 mtu 1299 -n0 iptables -F INPUT +if use_nft; then + n0 nft flush table ip wgtest +else + n0 iptables -F INPUT +fi ip1 link set wg0 mtu $orig_mtu ip2 link set wg0 mtu $orig_mtu @@ -334,7 +350,12 @@ waitiface $netns2 veths n0 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout' n0 bash -c 'printf 2 > /proc/sys/net/netfilter/nf_conntrack_udp_timeout_stream' -n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 +if use_nft; then + n0 nft add chain ip wgtest POSTROUTING { type nat hook postrouting priority srcnat\; policy accept \; } + n0 nft add rule ip wgtest POSTROUTING ip saddr 192.168.1.0/24 ip daddr 10.0.0.0/24 counter snat to 10.0.0.1 +else + n0 iptables -t nat -A POSTROUTING -s 192.168.1.0/24 -d 10.0.0.0/24 -j SNAT --to 10.0.0.1 +fi n1 wg set wg0 peer "$pub2" endpoint 10.0.0.100:2 persistent-keepalive 1 n1 ping -W 1 -c 1 192.168.241.2 @@ -348,10 +369,19 @@ n1 wg set wg0 peer "$pub2" persistent-keepalive 0 # Test that sk_bound_dev_if works n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # What about when the mark changes and the packet must be rerouted? -n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +if use_nft; then + n1 nft add chain ip wgtest OUTPUT { type route hook output priority mangle\; policy accept \; } + n1 nft add rule ip wgtest OUTPUT counter meta mark set 0x1 +else + n1 iptables -t mangle -I OUTPUT -j MARK --set-xmark 1 +fi n1 ping -c 1 -W 1 192.168.241.2 # First the boring case n1 ping -I wg0 -c 1 -W 1 192.168.241.2 # Then the sk_bound_dev_if case -n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 +if use_nft; then + n1 nft flush table ip wgtest +else + n1 iptables -t mangle -D OUTPUT -j MARK --set-xmark 1 +fi # Test that onion routing works, even when it loops n1 wg set wg0 peer "$pub3" allowed-ips 192.168.242.2/32 endpoint 192.168.241.2:5 @@ -385,16 +415,29 @@ n1 ping -W 1 -c 100 -f 192.168.99.7 n1 ping -W 1 -c 100 -f abab::1111 # Have ns2 NAT into wg0 packets from ns0, but return an icmp error along the right route. -n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 -n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +if use_nft; then + n2 nft add chain ip wgtest POSTROUTING { type nat hook postrouting priority srcnat\; policy accept \; } + n2 nft add rule ip wgtest POSTROUTING ip saddr 10.0.0.0/24 ip daddr 192.168.241.0/24 counter snat to 192.168.241.2 + + n0 nft add chain ip wgtest INPUT { type filter hook input priority filter \; policy accept \; } + n0 nft add rule ip wgtest INPUT iifname "vethrs" ip saddr != 10.0.0.0/24 counter drop +else + n2 iptables -t nat -A POSTROUTING -s 10.0.0.0/24 -d 192.168.241.0/24 -j SNAT --to 192.168.241.2 + n0 iptables -t filter -A INPUT \! -s 10.0.0.0/24 -i vethrs -j DROP # Manual rpfilter just to be explicit. +fi n2 bash -c 'printf 1 > /proc/sys/net/ipv4/ip_forward' ip0 -4 route add 192.168.241.1 via 10.0.0.100 n2 wg set wg0 peer "$pub1" remove [[ $(! n0 ping -W 1 -c 1 192.168.241.1 || false) == *"From 10.0.0.100 icmp_seq=1 Destination Host Unreachable"* ]] -n0 iptables -t nat -F -n0 iptables -t filter -F -n2 iptables -t nat -F +if use_nft; then + n0 nft flush table ip wgtest + n2 nft flush table ip wgtest +else + n0 iptables -t nat -F + n0 iptables -t filter -F + n2 iptables -t nat -F +fi ip0 link del vethrc ip0 link del vethrs ip1 link del wg0 -- 2.39.5 (Apple Git-154)

7 months, 1 week

3
4
0 0

[PATCH net-next v2] mm: page_frag: fix a compile error when kernel is not compiled

by Yunsheng Lin

page_frag test module is an out of tree module, but built using KDIR as the main kernel tree, the mm test suite is just getting skipped if newly added page_frag test module fails to compile due to kernel not yet compiled. Fix the above problem by ensuring both kernel is built first and a newer kernel which has page_frag_cache.h is used. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexanderduyck(a)fb.com> CC: Linux-MM <linux-mm(a)kvack.org> Fixes: 7fef0dec415c ("mm: page_frag: add a test module for page_frag") Fixes: 65941f10caf2 ("mm: move the page fragment allocator from page_alloc into its own file") Reported-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Tested-by: Mark Brown <broonie(a)kernel.org> --- V2: Repost by adding net-next ML. Note, page_frag test module is only in the net-next tree for now, so target the net-next tree. --- tools/testing/selftests/mm/Makefile | 18 ++++++++++++++++++ tools/testing/selftests/mm/page_frag/Makefile | 2 +- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index acec529baaca..04e04733fc8a 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,7 +36,16 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +KDIR ?= /lib/modules/$(shell uname -r)/build +ifneq (,$(wildcard $(KDIR)/Module.symvers)) +ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) TEST_GEN_MODS_DIR := page_frag +else +PAGE_FRAG_WARNING = "missing page_frag_cache.h, please use a newer kernel" +endif +else +PAGE_FRAG_WARNING = "missing Module.symvers, please have the kernel built first" +endif TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test @@ -214,3 +223,12 @@ warn_missing_liburing: echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif + +ifneq ($(PAGE_FRAG_WARNING),) +all: warn_missing_page_frag + +warn_missing_page_frag: + @echo ; \ + echo "Warning: $(PAGE_FRAG_WARNING). page_frag test will be skipped." ; \ + echo +endif diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile index 58dda74d50a3..8c8bb39ffa28 100644 --- a/tools/testing/selftests/mm/page_frag/Makefile +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -1,5 +1,5 @@ PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) +KDIR ?= /lib/modules/$(shell uname -r)/build ifeq ($(V),1) Q = -- 2.33.0

7 months, 1 week

3
2
0 0

[PATCH v2] net/unix: pass pidfd flags via SCM_PIDFD cmsg

by Stas Sergeev

Currently SCM_PIDFD cmsg cannot be sent via unix socket (returns -EINVAL) and SO_PASSPIDFD doesn't support flags. The created pidfd always has flags set to 0. This patch implements SCM_PIDFD cmsg in AF_UNIX socket, which can be used to send flags to SO_PASSPIDFD-enabled recipient. Self-test is added for the propagation of PIDFD_NONBLOCK flag. This is mainly needed for the future extensions, like eg this one: https://lore.kernel.org/lkml/8288a08e-448b-43c2-82dc-59f87d0d9072@yandex.ru… where it was suggested to try solving the supplementary groups problem with pidfd. Changes in v2: remove flags validation in scm_pidfd_recv(), as suggested by Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: Stas Sergeev <stsp2(a)yandex.ru> CC: "David S. Miller" <davem(a)davemloft.net> CC: Eric Dumazet <edumazet(a)google.com> CC: Jakub Kicinski <kuba(a)kernel.org> CC: Paolo Abeni <pabeni(a)redhat.com> CC: Simon Horman <horms(a)kernel.org> CC: Shuah Khan <shuah(a)kernel.org> CC: Christian Brauner <brauner(a)kernel.org> CC: Jens Axboe <axboe(a)kernel.dk> CC: Willem de Bruijn <willemb(a)google.com> CC: Pavel Begunkov <asml.silence(a)gmail.com> CC: Gabriel Krisman Bertazi <krisman(a)suse.de> CC: Mina Almasry <almasrymina(a)google.com> CC: Oleg Nesterov <oleg(a)redhat.com> CC: Tycho Andersen <tandersen(a)netflix.com> CC: Al Viro <viro(a)zeniv.linux.org.uk> CC: Kuniyuki Iwashima <kuniyu(a)amazon.com> CC: Gou Hao <gouhao(a)uniontech.com> CC: Abhishek Chauhan <quic_abchauha(a)quicinc.com> CC: Michal Luczaj <mhal(a)rbox.co> CC: Kees Cook <kees(a)kernel.org> CC: Aleksa Sarai <cyphar(a)cyphar.com> CC: linux-kernel(a)vger.kernel.org CC: netdev(a)vger.kernel.org CC: linux-kselftest(a)vger.kernel.org --- include/linux/pidfs.h | 9 +++ include/linux/socket.h | 2 +- include/net/af_unix.h | 1 + include/net/scm.h | 3 +- kernel/pid.c | 6 +- net/core/scm.c | 14 ++++ net/core/sock.c | 1 + net/unix/af_unix.c | 3 + .../testing/selftests/net/af_unix/scm_pidfd.c | 70 +++++++++++++++++-- 9 files changed, 99 insertions(+), 10 deletions(-) diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..c4c5c1a0c2ad 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,7 +2,16 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +#include <uapi/linux/pidfd.h> + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +static inline int pidfd_validate_flags(unsigned int flags) +{ + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) + return -EINVAL; + return 0; +} + #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..ee27d391e5aa 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -178,7 +178,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ -#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_PIDFD 0x04 /* r: pidfd, w: pidfd_flags (int) */ struct ucred { __u32 pid; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 63129c79b8cb..4bc197548c2f 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_skb_parms { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ #endif + u32 pidfd_flags; u32 consumed; } __randomize_layout; diff --git a/include/net/scm.h b/include/net/scm.h index 0d35c7c77a74..1326edcacacb 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -48,6 +48,7 @@ struct scm_cookie { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Passed security ID */ #endif + u32 pidfd_flags; }; void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm); @@ -154,7 +155,7 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm if (!scm->pid) return; - pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + pidfd = pidfd_prepare(scm->pid, scm->pidfd_flags, &pidfd_file); if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { if (pidfd_file) { diff --git a/kernel/pid.c b/kernel/pid.c index 2715afb77eab..b1100ae8ea63 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -629,10 +629,12 @@ static int pidfd_create(struct pid *pid, unsigned int flags) SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; + int err; struct pid *p; - if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) - return -EINVAL; + err = pidfd_validate_flags(flags); + if (err) + return err; if (pid <= 0) return -EINVAL; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..3bcdecdacd7e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -23,6 +23,7 @@ #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> @@ -210,6 +211,19 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->creds.gid = gid; break; } + case SCM_PIDFD: + { + unsigned int flags; + + if (cmsg->cmsg_len != CMSG_LEN(sizeof(flags))) + goto error; + memcpy(&flags, CMSG_DATA(cmsg), sizeof(flags)); + err = pidfd_validate_flags(flags); + if (err) + goto error; + p->pidfd_flags = flags; + break; + } default: goto error; } diff --git a/net/core/sock.c b/net/core/sock.c index 039be95c40cf..d1fce437c035 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2930,6 +2930,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: + case SCM_PIDFD: break; default: return -EINVAL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..8b19dfec0221 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1892,6 +1892,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen UNIXCB(skb).uid = scm->creds.uid; UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; + UNIXCB(skb).pidfd_flags = scm->pidfd_flags; unix_get_secdata(scm, skb); if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@ -2486,6 +2487,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, memset(&scm, 0, sizeof(scm)); scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); if (!(flags & MSG_PEEK)) { @@ -2873,6 +2875,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); check_creds = true; } diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..1e70ff253a1d 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -5,6 +5,7 @@ #include <stddef.h> #include <stdio.h> #include <stdlib.h> +#include <fcntl.h> #include <sys/socket.h> #include <linux/socket.h> #include <unistd.h> @@ -15,6 +16,11 @@ #include <sys/types.h> #include <sys/wait.h> +/* There are problems including linux/pidfd.h, so define. */ +#ifndef PIDFD_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#endif + #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -126,7 +132,7 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } -static int cmsg_check(int fd) +static int cmsg_check(int fd, unsigned int pidfd_flags) { struct msghdr msg = { 0 }; struct cmsghdr *cmsg; @@ -136,6 +142,7 @@ static int cmsg_check(int fd) char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; int *pidfd = NULL; + unsigned int flags; pid_t parent_pid; int err; @@ -197,6 +204,13 @@ static int cmsg_check(int fd) return 1; } + flags = fcntl(*pidfd, F_GETFL, 0); + flags &= ~O_ACCMODE; + if (flags != pidfd_flags) { + log_err("SCM_PIDFD flags mismatch: %x != %x", flags, pidfd_flags); + return 1; + } + /* pidfd from SCM_PIDFD should point to the parent process PID */ parent_pid = get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); @@ -227,30 +241,49 @@ FIXTURE_VARIANT(scm_pidfd) { int type; bool abstract; + unsigned int flags; }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) { .type = SOCK_STREAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) { .type = SOCK_STREAM, .abstract = 1, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) { .type = SOCK_DGRAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) { .type = SOCK_DGRAM, .abstract = 1, + .flags = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_nonblock) +{ + .type = SOCK_STREAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_nonblock) +{ + .type = SOCK_DGRAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, }; FIXTURE_SETUP(scm_pidfd) @@ -335,7 +368,7 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, close(self->startup_pipe[1]); - if (cmsg_check(cfd)) { + if (cmsg_check(cfd, variant->flags)) { log_err("cmsg_check failed"); child_die(); } @@ -375,6 +408,27 @@ TEST_F(scm_pidfd, test) int err; int pfd; int child_status = 0; + char iobuf; + unsigned int pidfd_flags; + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec io = { + .iov_base = &iobuf, + .iov_len = sizeof(iobuf) + }; + union { + char buf[CMSG_SPACE(sizeof(pidfd_flags))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_PIDFD; + cmsg->cmsg_len = CMSG_LEN(sizeof(pidfd_flags)); self->server = socket(AF_UNIX, variant->type, 0); ASSERT_NE(-1, self->server); @@ -414,12 +468,16 @@ TEST_F(scm_pidfd, test) close(self->startup_pipe[0]); if (variant->type == SOCK_DGRAM) { - err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen); - ASSERT_NE(-1, err); - } else { - err = send(pfd, "x", sizeof(char), 0); + err = connect(pfd, + (struct sockaddr *)&self->client_addr->listen_addr, + self->client_addr->addrlen); ASSERT_NE(-1, err); } + iobuf = 'x'; + pidfd_flags = variant->flags; + memcpy(CMSG_DATA(cmsg), &pidfd_flags, sizeof(pidfd_flags)); + err = sendmsg(pfd, &msg, 0); + ASSERT_NE(-1, err); close(pfd); waitpid(self->client_pid, &child_status, 0); -- 2.47.0

7 months, 2 weeks

3
4
0 0

[PATCH net-next v4 0/3] selftests: Add selftest for link layer and performance testing

by Mohan Prasad J

The series of patches are for doing basic tests of NIC driver. Test comprises checks for auto-negotiation, speed, duplex state and throughput between local NIC and partner. Tools such as ethtool, iperf3 are used. Signed-off-by: Mohan Prasad J <mohan.prasad(a)microchip.com> --- Changes in v4: - Type hints are added for arguments and return types. - Test values can be modified through command line. - Minor code improvements. - GenerateTraffic class extended for throughput test. - Protocol testcases separated. Changes in v3: Link to v3: https://patchwork.kernel.org/project/netdevbpf/cover/20241016215014.401476-… - LinkConfig class is included in the hw library. This contains generic APIs for doing link layer operations. - Auto-negotiation checks involve changing the auto-neg state both in local and partner NIC. - Link layer test and performance test are separated to different selftest files. - Resetting of NIC driver done after test completion. Changes in v2: Link to v2: https://patchwork.kernel.org/project/netdevbpf/cover/20240917023525.2571082… - Changed the hardcoded implementation of speed, duplex states, throughput to generic values, in order to support all type of NIC drivers. - Test executes based on the supported link modes between local NIC driver and partner. - Instead of lan743x directory, selftest file is now relocated to /selftests/drivers/net/hw. Link to v1: https://patchwork.kernel.org/project/netdevbpf/cover/20240903221549.1215842… --- Mohan Prasad J (3): selftests: nic_link_layer: Add link layer selftest for NIC driver selftests: nic_link_layer: Add selftest case for speed and duplex states selftests: nic_performance: Add selftest for performance of NIC driver .../testing/selftests/drivers/net/hw/Makefile | 6 +- .../drivers/net/hw/lib/py/__init__.py | 1 + .../drivers/net/hw/lib/py/linkconfig.py | 222 ++++++++++++++++++ .../drivers/net/hw/nic_link_layer.py | 113 +++++++++ .../drivers/net/hw/nic_performance.py | 137 +++++++++++ .../selftests/drivers/net/lib/py/load.py | 20 +- 6 files changed, 496 insertions(+), 3 deletions(-) create mode 100644 tools/testing/selftests/drivers/net/hw/lib/py/linkconfig.py create mode 100644 tools/testing/selftests/drivers/net/hw/nic_link_layer.py create mode 100644 tools/testing/selftests/drivers/net/hw/nic_performance.py -- 2.43.0

7 months, 2 weeks

3
5
0 0

[PATCH bpf-next v2 00/13] selftests/bpf: migrate test_flow_dissector.sh to test_progs

by Alexis Lothoré (eBPF Foundation)

Hello, this new series aims to migrate test_flow_dissector.sh into test_progs. There are 2 "main" parts in test_flow_dissector.sh: - a set of tests checking flow_dissector programs attachment to either root namespace or non-root namespace - dissection test The first set is integrated in flow_dissector.c, which already contains some existing tests for flow_dissector programs. This series uses the opportunity to update a bit this file (use new assert, re-split tests, etc) The second part is migrated into a new file under test_progs, flow_dissector_classification.c. It uses the same eBPF programs as flow_dissector.c, but the difference is rather about how those program are executed: - flow_dissector.c manually runs programs with BPF_PROG_RUN - flow_dissector_classification.c sends real packets to be dissected, and so it also executes kernel code related to eBPF flow dissector (eg: __skb_flow_bpf_to_target) --- Changes in v2: - allow tests to run in parallel - move some generic helpers to network_helpers.h - define proper function for ASSERT_MEMEQ - fetch acked-by tags - Link to v1: https://lore.kernel.org/r/20241113-flow_dissector-v1-0-27c4df0592dc@bootlin… --- Alexis Lothoré (eBPF Foundation) (13): selftests/bpf: add a macro to compare raw memory selftests/bpf: use ASSERT_MEMEQ to compare bpf flow keys selftests/bpf: replace CHECK calls with ASSERT macros in flow_dissector test selftests/bpf: re-split main function into dedicated tests selftests/bpf: expose all subtests from flow_dissector selftests/bpf: add gre packets testing to flow_dissector selftests/bpf: migrate flow_dissector namespace exclusivity test selftests/bpf: Enable generic tc actions in selftests config selftests/bpf: move ip checksum helper to network helpers selftests/bpf: rename pseudo headers checksum computation selftests/bpf: add network helpers to generate udp checksums selftests/bpf: migrate bpf flow dissectors tests to test_progs selftests/bpf: remove test_flow_dissector.sh tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 3 +- tools/testing/selftests/bpf/config | 1 + tools/testing/selftests/bpf/network_helpers.h | 64 +- .../selftests/bpf/prog_tests/flow_dissector.c | 323 +++++++-- .../bpf/prog_tests/flow_dissector_classification.c | 807 +++++++++++++++++++++ .../selftests/bpf/prog_tests/xdp_metadata.c | 24 +- tools/testing/selftests/bpf/test_flow_dissector.c | 780 -------------------- tools/testing/selftests/bpf/test_flow_dissector.sh | 178 ----- tools/testing/selftests/bpf/test_progs.c | 15 + tools/testing/selftests/bpf/test_progs.h | 15 + tools/testing/selftests/bpf/xdp_hw_metadata.c | 12 +- 12 files changed, 1153 insertions(+), 1070 deletions(-) --- base-commit: 9e71d50d3befb93a6394b0979f8ebd0dc9bd8d0f change-id: 20241019-flow_dissector-3eb0c07fc163 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

7 months, 2 weeks

3
24
0 0

[PATCH net 0/2] ipv6: fix temporary address not removed correctly

by Hangbin Liu

Currently the temporary address is not removed when mngtmpaddr is deleted or becomes unmanaged. The patch set fixed this issue and add a related test. Hangbin Liu (2): net/ipv6: delete temporary address if mngtmpaddr is removed or un-mngtmpaddr selftests/rtnetlink.sh: add mngtempaddr test net/ipv6/addrconf.c | 5 ++ tools/testing/selftests/net/rtnetlink.sh | 89 ++++++++++++++++++++++++ 2 files changed, 94 insertions(+) -- 2.46.0

7 months, 2 weeks

4
17
0 0

[PATCH v2] kunit: string-stream: Fix a UAF bug in kunit_init_suite()

by Jinjie Ruan

In kunit_debugfs_create_suite(), if alloc_string_stream() fails in the kunit_suite_for_each_test_case() loop, the "suite->log = stream" has assigned before, and the error path only free the suite->log's stream memory but not set it to NULL, so the later string_stream_clear() of suite->log in kunit_init_suite() will cause below UAF bug. Set stream pointer to NULL after free to fix it. Unable to handle kernel paging request at virtual address 006440150000030d Mem abort info: ESR = 0x0000000096000004 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x04: level 0 translation fault Data abort info: ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [006440150000030d] address between user and kernel address ranges Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: iio_test_gts industrialio_gts_helper cfg80211 rfkill ipv6 [last unloaded: iio_test_gts] CPU: 5 UID: 0 PID: 6253 Comm: modprobe Tainted: G B W N 6.12.0-rc4+ #458 Tainted: [B]=BAD_PAGE, [W]=WARN, [N]=TEST Hardware name: linux,dummy-virt (DT) pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : string_stream_clear+0x54/0x1ac lr : string_stream_clear+0x1a8/0x1ac sp : ffffffc080b47410 x29: ffffffc080b47410 x28: 006440550000030d x27: ffffff80c96b5e98 x26: ffffff80c96b5e80 x25: ffffffe461b3f6c0 x24: 0000000000000003 x23: ffffff80c96b5e88 x22: 1ffffff019cdf4fc x21: dfffffc000000000 x20: ffffff80ce6fa7e0 x19: 032202a80000186d x18: 0000000000001840 x17: 0000000000000000 x16: 0000000000000000 x15: ffffffe45c355cb4 x14: ffffffe45c35589c x13: ffffffe45c03da78 x12: ffffffb810168e75 x11: 1ffffff810168e74 x10: ffffffb810168e74 x9 : dfffffc000000000 x8 : 0000000000000004 x7 : 0000000000000003 x6 : 0000000000000001 x5 : ffffffc080b473a0 x4 : 0000000000000000 x3 : 0000000000000000 x2 : 0000000000000001 x1 : ffffffe462fbf620 x0 : dfffffc000000000 Call trace: string_stream_clear+0x54/0x1ac __kunit_test_suites_init+0x108/0x1d8 kunit_exec_run_tests+0xb8/0x100 kunit_module_notify+0x400/0x55c notifier_call_chain+0xfc/0x3b4 blocking_notifier_call_chain+0x68/0x9c do_init_module+0x24c/0x5c8 load_module+0x4acc/0x4e90 init_module_from_file+0xd4/0x128 idempotent_init_module+0x2d4/0x57c __arm64_sys_finit_module+0xac/0x100 invoke_syscall+0x6c/0x258 el0_svc_common.constprop.0+0x160/0x22c do_el0_svc+0x44/0x5c el0_svc+0x48/0xb8 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194 Code: f9400753 d2dff800 f2fbffe0 d343fe7c (38e06b80) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception Cc: stable(a)vger.kernel.org Fixes: a3fdf784780c ("kunit: string-stream: Decouple string_stream from kunit") Suggested-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> Signed-off-by: Jinjie Ruan <ruanjinjie(a)huawei.com> --- v2: - Correct the fix way. - Add Suggested-by. --- lib/kunit/debugfs.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..b25d214b93e1 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -212,8 +212,11 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) err: string_stream_destroy(suite->log); - kunit_suite_for_each_test_case(suite, test_case) + suite->log = NULL; + kunit_suite_for_each_test_case(suite, test_case) { string_stream_destroy(test_case->log); + test_case->log = NULL; + } } void kunit_debugfs_destroy_suite(struct kunit_suite *suite) -- 2.34.1

7 months, 2 weeks

3
3
0 0

[PATCH bpf v4 0/2] bpf: fix recursive lock and add test

by Jiayuan Chen

1. fix recursive lock when ebpf prog return SK_PASS. 2. add selftest to reproduce recursive lock. Note that the test code can reproduce the 'dead-lock' and if just the selftest merged without first patch, the test case will definitely fail, because the issue of deadlock is inevitable. --- v2->v4: fix line length reported by patchwork and remove unused code. (max_line_length is set to 80 in patchwork but default is 100 in kernel tree) v1->v2: 1.inspired by martin.lau to add selftest to reproduce the issue. 2. follow the community rules for patch. v1: https://lore.kernel.org/bpf/55fc6114-7e64-4b65-86d2-92cfd1e9e92f@linux.dev/… --- Jiayuan Chen (2): bpf: fix recursive lock when verdict program return SK_PASS selftests/bpf: Add some tests with sockmap SK_PASS net/core/skmsg.c | 4 +- .../selftests/bpf/prog_tests/sockmap_basic.c | 54 +++++++++++++++++++ 2 files changed, 56 insertions(+), 2 deletions(-) -- 2.43.5

7 months, 2 weeks

3
4
0 0

[PATCH v1] selftests/bpf: fix application of sizeof to pointer

by guanjing

sizeof when applied to a pointer typed expression gives the size of the pointer. tools/testing/selftests/bpf/progs/test_tunnel_kern.c:678:41-47: ERROR: application of sizeof to pointer The proper fix in this particular case is to code sizeof(*gopt) instead of sizeof(gopt). This issue was detected with the help of Coccinelle. Fixes: 5ddafcc377f9 ("selftests/bpf: Fix a few tests for GCC related warnings.") Signed-off-by: guanjing <guanjing(a)cmss.chinamobile.com> --- tools/testing/selftests/bpf/progs/test_tunnel_kern.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c index 32127f1cd687..3a437cdc5c15 100644 --- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c @@ -675,7 +675,7 @@ int ip6geneve_set_tunnel(struct __sk_buff *skb) gopt->length = 2; /* 4-byte multiple */ *(int *) &gopt->opt_data = bpf_htonl(0xfeedbeef); - ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(gopt)); + ret = bpf_skb_set_tunnel_opt(skb, gopt, sizeof(*gopt)); if (ret < 0) { log_err(ret); return TC_ACT_SHOT; -- 2.33.0

7 months, 2 weeks

2
1
0 0

[PATCH net-next] selftests: net: netlink-dumps: validation checks

by Jakub Kicinski

The sanity checks are going to get silently cast to unsigned and always pass. Cast the sizeof to signed size. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/netlink-dumps.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 195febbf6a61..07423f256f96 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -185,10 +185,10 @@ TEST(test_sanity) ASSERT_EQ(n, sizeof(dump_policies)); n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); - ASSERT_GE(n, sizeof(struct nlmsghdr)); + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); - ASSERT_GE(n, sizeof(struct nlmsghdr)); + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); close(netlink_sock); } -- 2.47.0

7 months, 2 weeks

3
2
0 0

[PATCH net-next] mm: page_frag: fix a compile error when kernel is not compiled

by Yunsheng Lin

page_frag test module is an out of tree module, but built using KDIR as the main kernel tree, the mm test suite is just getting skipped if newly added page_frag test module fails to compile due to kernel not yet compiled. Fix the above problem by ensuring both kernel is built first and a newer kernel which has page_frag_cache.h is used. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexanderduyck(a)fb.com> CC: Linux-MM <linux-mm(a)kvack.org> Fixes: 7fef0dec415c ("mm: page_frag: add a test module for page_frag") Fixes: 65941f10caf2 ("mm: move the page fragment allocator from page_alloc into its own file") Reported-by: Mark Brown <broonie(a)kernel.org> Signed-off-by: Yunsheng Lin <yunshenglin0825(a)gmail.com> --- Mote, page_frag test module is only in the net-next tree for now, so target the net-next tree. --- tools/testing/selftests/mm/Makefile | 18 ++++++++++++++++++ tools/testing/selftests/mm/page_frag/Makefile | 2 +- 2 files changed, 19 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index acec529baaca..04e04733fc8a 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,7 +36,16 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +KDIR ?= /lib/modules/$(shell uname -r)/build +ifneq (,$(wildcard $(KDIR)/Module.symvers)) +ifneq (,$(wildcard $(KDIR)/include/linux/page_frag_cache.h)) TEST_GEN_MODS_DIR := page_frag +else +PAGE_FRAG_WARNING = "missing page_frag_cache.h, please use a newer kernel" +endif +else +PAGE_FRAG_WARNING = "missing Module.symvers, please have the kernel built first" +endif TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test @@ -214,3 +223,12 @@ warn_missing_liburing: echo "Warning: missing liburing support. Some tests will be skipped." ; \ echo endif + +ifneq ($(PAGE_FRAG_WARNING),) +all: warn_missing_page_frag + +warn_missing_page_frag: + @echo ; \ + echo "Warning: $(PAGE_FRAG_WARNING). page_frag test will be skipped." ; \ + echo +endif diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile index 58dda74d50a3..8c8bb39ffa28 100644 --- a/tools/testing/selftests/mm/page_frag/Makefile +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -1,5 +1,5 @@ PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) -KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) +KDIR ?= /lib/modules/$(shell uname -r)/build ifeq ($(V),1) Q = -- 2.34.1

7 months, 2 weeks

3
3
0 0

[RFC PATCH net-next 11/11] selftests: forwarding: Add a selftest for the new reserved_bits UAPI

by Petr Machata

Run VXLAN packets through a gateway. Flip individual bits of the packet and/or reserved bits of the gateway, and check that the gateway treats the packets as expected. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: Vladimir Oltean <vladimir.oltean(a)nxp.com> CC: linux-kselftest(a)vger.kernel.org .../net/forwarding/vxlan_reserved.sh | 352 ++++++++++++++++++ 1 file changed, 352 insertions(+) create mode 100755 tools/testing/selftests/net/forwarding/vxlan_reserved.sh diff --git a/tools/testing/selftests/net/forwarding/vxlan_reserved.sh b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh new file mode 100755 index 000000000000..46c31794b91b --- /dev/null +++ b/tools/testing/selftests/net/forwarding/vxlan_reserved.sh @@ -0,0 +1,352 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +--------------------+ +# | H1 (vrf) | +# | + $h1 | +# | | 192.0.2.1/28 | +# +----|---------------+ +# | +# +----|--------------------------------+ +# | SW | | +# | +--|------------------------------+ | +# | | + $swp1 BR1 (802.1d) | | +# | | | | +# | | + vx1 (vxlan) | | +# | | local 192.0.2.17 | | +# | | id 1000 dstport $VXPORT | | +# | +---------------------------------+ | +# | | +# | 192.0.2.32/28 via 192.0.2.18 | +# | | +# | + $rp1 | +# | | 192.0.2.17/28 | +# +--|----------------------------------+ +# | +# +--|----------------------------------+ +# | | | +# | + $rp2 | +# | 192.0.2.18/28 | +# | | +# | VRP2 (vrf) | +# +-------------------------------------+ + +: ${VXPORT:=4789} +: ${ALL_TESTS:=" + default_test + plain_test + reserved_0_test + reserved_10_test + reserved_31_test + reserved_56_test + reserved_63_test + "} + +NUM_NETIFS=4 +source lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 + defer simple_if_fini $h1 192.0.2.1/28 + + tc qdisc add dev $h1 clsact + defer tc qdisc del dev $h1 clsact + + tc filter add dev $h1 ingress pref 77 \ + prot ip flower skip_hw ip_proto icmp action drop + defer tc filter del dev $h1 ingress pref 77 +} + +switch_create() +{ + ip_link_add br1 type bridge vlan_filtering 0 mcast_snooping 0 + # Make sure the bridge uses the MAC address of the local port and not + # that of the VxLAN's device. + ip_link_set_addr br1 $(mac_get $swp1) + ip_link_set_up br1 + + ip_link_set_up $rp1 + ip_addr_add $rp1 192.0.2.17/28 + ip_route_add 192.0.2.32/28 nexthop via 192.0.2.18 + + ip_link_set_master $swp1 br1 + ip_link_set_up $swp1 +} + +vrp2_create() +{ + simple_if_init $rp2 192.0.2.18/28 + defer simple_if_fini $rp2 192.0.2.18/28 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + rp1=${NETIFS[p3]} + rp2=${NETIFS[p4]} + + vrf_prepare + defer vrf_cleanup + + forwarding_enable + defer forwarding_restore + + h1_create + switch_create + + vrp2_create +} + +vxlan_header_bytes() +{ + local vni=$1; shift + local -a extra_bits=("$@") + local -a bits + local i + + for ((i=0; i < 64; i++)); do + bits[i]=0 + done + + # Bit 4 is the I flag and is always on. + bits[4]=1 + + for i in ${extra_bits[@]}; do + bits[i]=1 + done + + # Bits 32..55 carry the VNI + local mask=0x800000 + for ((i=0; i < 24; i++)); do + bits[$((i + 32))]=$(((vni & mask) != 0)) + ((mask >>= 1)) + done + + local bytes + for ((i=0; i < 8; i++)); do + local byte=0 + local j + for ((j=0; j < 8; j++)); do + local bit=${bits[8 * i + j]} + ((byte += bit << (7 - j))) + done + bytes+=$(printf %02x $byte): + done + + echo ${bytes%:} +} + +neg_bytes() +{ + local bytes=$1; shift + + local -A neg=([0]=f [1]=e [2]=d [3]=c [4]=b [5]=a [6]=9 [7]=8 + [8]=7 [9]=6 [a]=5 [b]=4 [c]=3 [d]=2 [e]=1 [f]=0 [:]=:) + local out + local i + + for ((i=0; i < ${#bytes}; i++)); do + local c=${bytes:$i:1} + out+=${neg[$c]} + done + echo $out +} + +vxlan_ping_do() +{ + local count=$1; shift + local dev=$1; shift + local next_hop_mac=$1; shift + local dest_ip=$1; shift + local dest_mac=$1; shift + local vni=$1; shift + local reserved_bits=$1; shift + + local vxlan_header=$(vxlan_header_bytes $vni $reserved_bits) + + $MZ $dev -c $count -d 100msec -q \ + -b $next_hop_mac -B $dest_ip \ + -t udp sp=23456,dp=$VXPORT,p=$(: + )"$vxlan_header:"$( : VXLAN + )"$dest_mac:"$( : ETH daddr + )"00:11:22:33:44:55:"$( : ETH saddr + )"08:00:"$( : ETH type + )"45:"$( : IP version + IHL + )"00:"$( : IP TOS + )"00:54:"$( : IP total length + )"99:83:"$( : IP identification + )"40:00:"$( : IP flags + frag off + )"40:"$( : IP TTL + )"01:"$( : IP proto + )"00:00:"$( : IP header csum + )"$(ipv4_to_bytes 192.0.2.3):"$( : IP saddr + )"$(ipv4_to_bytes 192.0.2.1):"$( : IP daddr + )"08:"$( : ICMP type + )"00:"$( : ICMP code + )"8b:f2:"$( : ICMP csum + )"1f:6a:"$( : ICMP request identifier + )"00:01:"$( : ICMP request seq. number + )"4f:ff:c5:5b:00:00:00:00:"$( : ICMP payload + )"6d:74:0b:00:00:00:00:00:"$( : + )"10:11:12:13:14:15:16:17:"$( : + )"18:19:1a:1b:1c:1d:1e:1f:"$( : + )"20:21:22:23:24:25:26:27:"$( : + )"28:29:2a:2b:2c:2d:2e:2f:"$( : + )"30:31:32:33:34:35:36:37" +} + +vxlan_device_add() +{ + ip_link_add vx1 up type vxlan id 1000 \ + local 192.0.2.17 dstport "$VXPORT" \ + nolearning noudpcsum tos inherit ttl 100 "$@" + ip_link_set_master vx1 br1 +} + +vxlan_all_reserved_bits() +{ + local i + + for ((i=0; i < 64; i++)); do + if ((i == 4 || i >= 32 && i < 56)); then + continue + fi + echo $i + done +} + +vxlan_ping_vanilla() +{ + vxlan_ping_do 10 $rp2 $(mac_get $rp1) 192.0.2.17 $(mac_get $h1) 1000 +} + +vxlan_ping_reserved() +{ + for bit in $(vxlan_all_reserved_bits); do + vxlan_ping_do 1 $rp2 $(mac_get $rp1) \ + 192.0.2.17 $(mac_get $h1) 1000 "$bit" + ((n++)) + done +} + +vxlan_ping_test() +{ + local what=$1; shift + local get_stat=$1; shift + local expect=$1; shift + + RET=0 + + local t0=$($get_stat) + + "$@" + check_err $? "Failure when running $@" + + local t1=$($get_stat) + local delta=$((t1 - t0)) + + ((expect == delta)) + check_err $? "Expected to capture $expect packets, got $delta." + + log_test "$what" +} + +__default_test_do() +{ + local n_allowed_bits=$1; shift + local what=$1; shift + + vxlan_ping_test "$what: clean packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + 10 vxlan_ping_vanilla + + local t0=$(link_stats_get vx1 rx errors) + vxlan_ping_test "$what: mangled packets" \ + "tc_rule_stats_get $h1 77 ingress" \ + $n_allowed_bits vxlan_ping_reserved + local t1=$(link_stats_get vx1 rx errors) + + RET=0 + local expect=$((39 - n_allowed_bits)) + local delta=$((t1 - t0)) + ((expect == delta)) + check_err $? "Expected $expect error packets, got $delta." + log_test "$what: drops reported" +} + +default_test_do() +{ + vxlan_device_add + __default_test_do 0 "Default" +} + +default_test() +{ + in_defer_scope \ + default_test_do +} + +plain_test_do() +{ + vxlan_device_add reserved_bits 0xf7ffffff000000ff + __default_test_do 0 "reserved_bits 0xf7ffffff000000ff" +} + +plain_test() +{ + in_defer_scope \ + plain_test_do +} + +reserved_test() +{ + local bit=$1; shift + + local allowed_bytes=$(vxlan_header_bytes 0xffffff $bit) + local reserved_bytes=$(neg_bytes $allowed_bytes) + local reserved_bits=${reserved_bytes//:/} + + vxlan_device_add reserved_bits 0x$reserved_bits + __default_test_do 1 "reserved_bits 0x$reserved_bits" +} + +reserved_0_test() +{ + in_defer_scope \ + reserved_test 0 +} + +reserved_10_test() +{ + in_defer_scope \ + reserved_test 10 +} + +reserved_31_test() +{ + in_defer_scope \ + reserved_test 31 +} + +reserved_56_test() +{ + in_defer_scope \ + reserved_test 56 +} + +reserved_63_test() +{ + in_defer_scope \ + reserved_test 63 +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS -- 2.47.0

7 months, 2 weeks

1
0
0 0

[RFC PATCH net-next 10/11] selftests: net: lib: Add several autodefer helpers

by Petr Machata

Add ip_link_set_addr(), ip_link_set_up(), ip_addr_add() and ip_route_add() to the suite of helpers that automatically schedule a corresponding cleanup. When setting a new MAC, one needs to remember the old address first. Move mac_get() from forwarding/ to that end. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: Vladimir Oltean <vladimir.oltean(a)nxp.com> CC: linux-kselftest(a)vger.kernel.org tools/testing/selftests/net/forwarding/lib.sh | 7 ---- tools/testing/selftests/net/lib.sh | 39 +++++++++++++++++++ 2 files changed, 39 insertions(+), 7 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 7337f398f9cc..1fd40bada694 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -932,13 +932,6 @@ packets_rate() echo $(((t1 - t0) / interval)) } -mac_get() -{ - local if_name=$1 - - ip -j link show dev $if_name | jq -r '.[]["address"]' -} - ether_addr_to_u64() { local addr="$1" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 5ea6537acd2b..2cd5c743b2d9 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -435,6 +435,13 @@ xfail_on_veth() fi } +mac_get() +{ + local if_name=$1 + + ip -j link show dev $if_name | jq -r '.[]["address"]' +} + kill_process() { local pid=$1; shift @@ -459,3 +466,35 @@ ip_link_set_master() ip link set dev "$member" master "$master" defer ip link set dev "$member" nomaster } + +ip_link_set_addr() +{ + local name=$1; shift + local addr=$1; shift + + local old_addr=$(mac_get "$name") + ip link set dev "$name" address "$addr" + defer ip link set dev "$name" address "$old_addr" +} + +ip_link_set_up() +{ + local name=$1; shift + + ip link set dev "$name" up + defer ip link set dev "$name" down +} + +ip_addr_add() +{ + local name=$1; shift + + ip addr add dev "$name" "$@" + defer ip addr del dev "$name" "$@" +} + +ip_route_add() +{ + ip route add "$@" + defer ip route del "$@" +} -- 2.47.0

7 months, 2 weeks

1
0
0 0

[RFC PATCH net-next 09/11] selftests: net: lib: Rename ip_link_master() to ip_link_set_master()

by Petr Machata

Let's have a verb in that function name to make it clearer what's going on. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Ido Schimmel <idosch(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: Vladimir Oltean <vladimir.oltean(a)nxp.com> CC: linux-kselftest(a)vger.kernel.org tools/testing/selftests/net/fdb_notify.sh | 6 +++--- tools/testing/selftests/net/lib.sh | 2 +- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh index c03151e7791c..c159230c9b62 100755 --- a/tools/testing/selftests/net/fdb_notify.sh +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -49,7 +49,7 @@ test_dup_vxlan_self() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan" dev vx self dst 192.0.2.1 do_test_dup del "vxlan" dev vx self dst 192.0.2.1 @@ -59,7 +59,7 @@ test_dup_vxlan_master() { ip_link_add br up type bridge vlan_filtering 1 ip_link_add vx up type vxlan id 2000 dstport 4789 - ip_link_master vx br + ip_link_set_master vx br do_test_dup add "vxlan master" dev vx master do_test_dup del "vxlan master" dev vx master @@ -79,7 +79,7 @@ test_dup_macvlan_master() ip_link_add br up type bridge vlan_filtering 1 ip_link_add dd up type dummy ip_link_add mv up link dd type macvlan mode passthru - ip_link_master mv br + ip_link_set_master mv br do_test_dup add "macvlan master" dev mv self do_test_dup del "macvlan master" dev mv self diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 8994fec1c38f..5ea6537acd2b 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -451,7 +451,7 @@ ip_link_add() defer ip link del dev "$name" } -ip_link_master() +ip_link_set_master() { local member=$1; shift local master=$1; shift -- 2.47.0

7 months, 2 weeks

1
0
0 0

[PATCH] selftests/bpf: Remove unused variable

by Zhu Jun

the variable is never referenced in the code, just remove them. Signed-off-by: Zhu Jun <zhujun2(a)cmss.chinamobile.com> --- tools/testing/selftests/bpf/prog_tests/log_buf.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/log_buf.c b/tools/testing/selftests/bpf/prog_tests/log_buf.c index 27676a04d0b6..5d1678b15d8b 100644 --- a/tools/testing/selftests/bpf/prog_tests/log_buf.c +++ b/tools/testing/selftests/bpf/prog_tests/log_buf.c @@ -191,7 +191,6 @@ static void bpf_prog_load_log_buf(void) ASSERT_LT(fd, 0, "bad_fd"); if (fd >= 0) close(fd); - fd = -1; free(log_buf); } @@ -259,7 +258,6 @@ static void bpf_btf_load_log_buf(void) ASSERT_LT(fd, 0, "bad_fd"); if (fd >= 0) close(fd); - fd = -1; cleanup: free(log_buf); -- 2.17.1

7 months, 2 weeks

2
1
0 0

[PATCH] kvm: hardware_disable_test: remove unused macro

by Ba Jing

After reviewing the code, it was found that the macro GUEST_CODE_PIO_PORT is never referenced in the code. Just remove it. Signed-off-by: Ba Jing <bajing(a)cmss.chinamobile.com> --- tools/testing/selftests/kvm/hardware_disable_test.c | 1 - 1 file changed, 1 deletion(-) diff --git a/tools/testing/selftests/kvm/hardware_disable_test.c b/tools/testing/selftests/kvm/hardware_disable_test.c index bce73bcb973c..94bd6ed24cf3 100644 --- a/tools/testing/selftests/kvm/hardware_disable_test.c +++ b/tools/testing/selftests/kvm/hardware_disable_test.c @@ -20,7 +20,6 @@ #define SLEEPING_THREAD_NUM (1 << 4) #define FORK_NUM (1ULL << 9) #define DELAY_US_MAX 2000 -#define GUEST_CODE_PIO_PORT 4 sem_t *sem; -- 2.33.0

7 months, 2 weeks

2
1
0 0

[PATCH v2 0/5] Improve arm64 pkeys handling in signal delivery

by Kevin Brodsky

This series is a follow-up to Joey's Permission Overlay Extension (POE) series [1] that recently landed on mainline. The goal is to improve the way we handle the register that governs which pkeys/POIndex are accessible (POR_EL0) during signal delivery. As things stand, we may unexpectedly fail to write the signal frame on the stack because POR_EL0 is not reset before the uaccess operations. See patch 3 for more details and the main changes this series brings. A similar series landed recently for x86/MPK [2]; the present series aims at aligning arm64 with x86. Worth noting: once the signal frame is written, POR_EL0 is still set to POR_EL0_INIT, granting access to pkey 0 only. This means that a program that sets up an alternate signal stack with a non-zero pkey will need some assembly trampoline to set POR_EL0 before invoking the real signal handler, as discussed here [3]. This is not ideal, but it makes experimentation with pkeys in signal handlers possible while waiting for a potential interface to control the pkey state when delivering a signal. See Pierre's reply [4] for more information about use-cases and a potential interface. The x86 series also added kselftests to ensure that no spurious SIGSEGV occurs during signal delivery regardless of which pkey is accessible at the point where the signal is delivered. This series adapts those kselftests to allow running them on arm64 (patch 4-5). Finally patch 2 is a clean-up following feedback on Joey's series [5]. I have tested this series on arm64 and x86_64 (booting and running the protection_keys and pkey_sighandler_tests mm kselftests). v1..v2: * In setup_rt_frame(), ensured that POR_EL0 is reset to its original value if we fail to deliver the signal (addresses Catalin's concern [6]). * Renamed *unpriv_access* to *user_access* in patch 3 (suggestion from Dave). * Made what patch 1-2 do explicit in the commit message body (suggestion from Dave). - Kevin [1] https://lore.kernel.org/linux-arm-kernel/20240822151113.1479789-1-joey.goul… [2] https://lore.kernel.org/lkml/20240802061318.2140081-1-aruna.ramakrishna@ora… [3] https://lore.kernel.org/lkml/CABi2SkWxNkP2O7ipkP67WKz0-LV33e5brReevTTtba6oK… [4] https://lore.kernel.org/linux-arm-kernel/87plns8owh.fsf@arm.com/ [5] https://lore.kernel.org/linux-arm-kernel/20241015114116.GA19334@willie-the-… [6] https://lore.kernel.org/linux-arm-kernel/Zw6D2waVyIwYE7wd@arm.com/ Cc: akpm(a)linux-foundation.org Cc: anshuman.khandual(a)arm.com Cc: aruna.ramakrishna(a)oracle.com Cc: broonie(a)kernel.org Cc: catalin.marinas(a)arm.com Cc: dave.hansen(a)linux.intel.com Cc: dave.martin(a)arm.com Cc: jeffxu(a)chromium.org Cc: joey.gouly(a)arm.com Cc: pierre.langlois(a)arm.com Cc: shuah(a)kernel.org Cc: sroettger(a)google.com Cc: will(a)kernel.org Cc: linux-kselftest(a)vger.kernel.org Cc: x86(a)kernel.org Kevin Brodsky (5): arm64: signal: Remove unused macro arm64: signal: Remove unnecessary check when saving POE state arm64: signal: Improve POR_EL0 handling to avoid uaccess failures selftests/mm: Use generic pkey register manipulation selftests/mm: Enable pkey_sighandler_tests on arm64 arch/arm64/kernel/signal.c | 95 +++++++++++++--- tools/testing/selftests/mm/Makefile | 8 +- tools/testing/selftests/mm/pkey-arm64.h | 1 + tools/testing/selftests/mm/pkey-x86.h | 2 + .../selftests/mm/pkey_sighandler_tests.c | 101 +++++++++++++----- 5 files changed, 162 insertions(+), 45 deletions(-) -- 2.43.0

7 months, 2 weeks

4
18
0 0

[PATCH bpf-next/net 0/5] bpf: Add mptcp_subflow bpf_iter support

by Matthieu Baerts (NGI0)

Here is a series from Geliang, adding mptcp_subflow bpf_iter support. We are working on extending MPTCP with BPF, e.g. to control the path manager -- in charge of the creation, deletion, and announcements of subflows (paths) -- and the packet scheduler -- in charge of selecting which available path the next data will be sent to. These extensions need to iterate over the list of subflows attached to an MPTCP connection, and do some specific actions via some new kfunc that will be added later on. This preparation work is split in different patches: - Patch 1: register some "basic" MPTCP kfunc. - Patch 2: add mptcp_subflow bpf_iter support. Note that previous versions of this single patch have already been shared to the BPF mailing list. The changelog has been kept with a comment, but the version number has been reset to avoid confusions. - Patch 3: add kfunc to make sure the msk is valid - Patch 4: add more MPTCP endpoints in the selftests, in order to create more than 2 subflows. - Patch 5: add a very simple test validating mptcp_subflow bpf_iter support. This test could be written without the new bpf_iter, but it is there only to make sure this specific feature works as expected. Signed-off-by: Matthieu Baerts (NGI0) <matttbe(a)kernel.org> --- Geliang Tang (5): bpf: Register mptcp common kfunc set bpf: Add mptcp_subflow bpf_iter bpf: Acquire and release mptcp socket selftests/bpf: More endpoints for endpoint_init selftests/bpf: Add mptcp_subflow bpf_iter subtest net/mptcp/bpf.c | 104 ++++++++++++++++- tools/testing/selftests/bpf/bpf_experimental.h | 8 ++ tools/testing/selftests/bpf/prog_tests/mptcp.c | 129 ++++++++++++++++++++- tools/testing/selftests/bpf/progs/mptcp_bpf.h | 10 ++ .../testing/selftests/bpf/progs/mptcp_bpf_iters.c | 64 ++++++++++ 5 files changed, 308 insertions(+), 7 deletions(-) --- base-commit: 141b4d6a8049cecdc8124f87e044b83a9e80730d change-id: 20241108-bpf-next-net-mptcp-bpf_iter-subflows-027f6d87770e Best regards, -- Matthieu Baerts (NGI0) <matttbe(a)kernel.org>

7 months, 2 weeks

3
9
0 0

[PATCH v7 00/13] iommufd: Add vIOMMU infrastructure (Part-1)

by Nicolin Chen

This series introduces a new vIOMMU infrastructure and related ioctls. IOMMUFD has been using the HWPT infrastructure for all cases, including a nested IO page table support. Yet, there're limitations for an HWPT-based structure to support some advanced HW-accelerated features, such as CMDQV on NVIDIA Grace, and HW-accelerated vIOMMU on AMD. Even for a multi-IOMMU environment, it is not straightforward for nested HWPTs to share the same parent HWPT (stage-2 IO pagetable), with the HWPT infrastructure alone: a parent HWPT typically hold one stage-2 IO pagetable and tag it with only one ID in the cache entries. When sharing one large stage-2 IO pagetable across physical IOMMU instances, that one ID may not always be available across all the IOMMU instances. In other word, it's ideal for SW to have a different container for the stage-2 IO pagetable so it can hold another ID that's available. And this container will be able to hold some advanced feature too. For this "different container", add vIOMMU, an additional layer to hold extra virtualization information: _______________________________________________________________________ | iommufd (with vIOMMU) | | _____________ | | | | | | |----------------| vIOMMU | | | | ______ | | _____________ ________ | | | | | | | | | | | | | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | | | |______| |_____________| |_____________| |________| | | | | | | | | |______|________|______________|__________________|_______________|_____| | | | | | ______v_____ | ______v_____ ______v_____ ___v__ | struct | | PFN | (paging) | | (nested) | |struct| |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| |____________| storage|____________| |____________| |______| The vIOMMU object should be seen as a slice of a physical IOMMU instance that is passed to or shared with a VM. That can be some HW/SW resources: - Security namespace for guest owned ID, e.g. guest-controlled cache tags - Non-device-affiliated event reporting, e.g. invalidation queue errors - Access to a sharable nesting parent pagetable across physical IOMMUs - Virtualization of various platforms IDs, e.g. RIDs and others - Delivery of paravirtualized invalidation - Direct assigned invalidation queues - Direct assigned interrupts On a multi-IOMMU system, the vIOMMU object must be instanced to the number of the physical IOMMUs that have a slice passed to (via device) a guest VM, while being able to hold the shareable parent HWPT. Each vIOMMU then just needs to allocate its own individual ID to tag its own cache: ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested0 |--->| viommu0 ------------------ ---------------- | | IDx | ---------------------------- ---------------------------- ---------------- | | paging_hwpt0 | | hwpt_nested1 |--->| viommu1 ------------------ ---------------- | | IDy | ---------------------------- As an initial part-1, add IOMMUFD_CMD_VIOMMU_ALLOC ioctl for an allocation only. More vIOMMU-based structs and ioctls will be introduced in the follow-up series to support vDEVICE, vIRQ (vEVENT) and vQUEUE objects. Although we repurposed the vIOMMU object from an earlier RFC, just for a referece: https://lore.kernel.org/all/cover.1712978212.git.nicolinc@nvidia.com/ This series is on Github: https://github.com/nicolinc/iommufd/commits/iommufd_viommu_p1-v7 (QEMU branch for testing will be provided in Jason's nesting series) Changelog v7 * Added "Reviewed-by" from Jason * Dropped "select IOMMUFD_DRIVER_CORE" in Kconfig * Decoupled IOMMUFD_DRIVER from IOMMUFD_DRIVER_CORE * Moved vIOMMU negative tests out of FIXTURE_SETUP to a TEST_F * Dropped the "flags" check in iommufd_viommu_alloc_hwpt_nested * Added the kdoc for "flags" in iommufd_viommu_alloc_hwpt_nested v6 https://lore.kernel.org/all/cover.1730313237.git.nicolinc@nvidia.com/ * Improved comment lines * Added a TEST_F for IO page fault * Fixed indentations in iommufd.rst * Revised kdoc of the viommu_alloc op * Added "Reviewed-by" from Kevin and Jason * Passed in "flags" to ->alloc_domain_nested * Renamed "free" op to "destroy" in viommu_ops * Skipped SMMUv3 driver changes (to post in a separate series) * Fixed "flags" validation in iommufd_viommu_alloc_hwpt_nested * Added CONFIG_IOMMUFD_DRIVER_CORE for sharing between iommufd core and IOMMU dirvers * Replaced iommufd_verify_unfinalized_object with xa_cmpxchg in iommufd_object_finalize/abort functions v5 https://lore.kernel.org/all/cover.1729897352.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Kevin * Reworked iommufd_viommu_alloc helper * Revised the uAPI kdoc for vIOMMU object * Revised comments for pluggable iommu_dev * Added a couple of cleanup patches for selftest * Renamed domain_alloc_nested op to alloc_domain_nested * Updated a few commit messages to reflect the latest series * Renamed iommufd_hwpt_nested_alloc_for_viommu to iommufd_viommu_alloc_hwpt_nested, and added flag validation v4 https://lore.kernel.org/all/cover.1729553811.git.nicolinc@nvidia.com/ * Added "Reviewed-by" from Jason * Dropped IOMMU_VIOMMU_TYPE_DEFAULT support * Dropped iommufd_object_alloc_elm renamings * Renamed iommufd's viommu_api.c to driver.c * Reworked iommufd_viommu_alloc helper * Added a separate iommufd_hwpt_nested_alloc_for_viommu function for hwpt_nested allocations on a vIOMMU, and added comparison between viommu->iommu_dev->ops and dev_iommu_ops(idev->dev) * Replaced s2_parent with vsmmu in arm_smmu_nested_domain * Replaced domain_alloc_user in iommu_ops with domain_alloc_nested in viommu_ops * Replaced wait_queue_head_t with a completion, to delay the unplug of mock_iommu_dev * Corrected documentation graph that was missing struct iommu_device * Added an iommufd_verify_unfinalized_object helper to verify driver- allocated vIOMMU/vDEVICE objects * Added missing test cases for TEST_LENGTH and fail_nth v3 https://lore.kernel.org/all/cover.1728491453.git.nicolinc@nvidia.com/ * Rebased on top of Jason's nesting v3 series https://lore.kernel.org/all/0-v3-e2e16cd7467f+2a6a1-smmuv3_nesting_jgg@nvid… * Split the series into smaller parts * Added Jason's Reviewed-by * Added back viommu->iommu_dev * Added support for driver-allocated vIOMMU v.s. core-allocated * Dropped arm_smmu_cache_invalidate_user * Added an iommufd_test_wait_for_users() in selftest * Reworked test code to make viommu an individual FIXTURE * Added missing TEST_LENGTH case for the new ioctl command v2 https://lore.kernel.org/all/cover.1724776335.git.nicolinc@nvidia.com/ * Limited vdev_id to one per idev * Added a rw_sem to protect the vdev_id list * Reworked driver-level APIs with proper lockings * Added a new viommu_api file for IOMMUFD_DRIVER config * Dropped useless iommu_dev point from the viommu structure * Added missing index numnbers to new types in the uAPI header * Dropped IOMMU_VIOMMU_INVALIDATE uAPI; Instead, reuse the HWPT one * Reworked mock_viommu_cache_invalidate() using the new iommu helper * Reordered details of set/unset_vdev_id handlers for proper lockings v1 https://lore.kernel.org/all/cover.1723061377.git.nicolinc@nvidia.com/ Thanks! Nicolin Nicolin Chen (13): iommufd: Move struct iommufd_object to public iommufd header iommufd: Move _iommufd_object_alloc helper to a sharable file iommufd: Introduce IOMMUFD_OBJ_VIOMMU and its related struct iommufd: Verify object in iommufd_object_finalize/abort() iommufd/viommu: Add IOMMU_VIOMMU_ALLOC ioctl iommufd: Add alloc_domain_nested op to iommufd_viommu_ops iommufd: Allow pt_id to carry viommu_id for IOMMU_HWPT_ALLOC iommufd/selftest: Add container_of helpers iommufd/selftest: Prepare for mock_viommu_alloc_domain_nested() iommufd/selftest: Add refcount to mock_iommu_device iommufd/selftest: Add IOMMU_VIOMMU_TYPE_SELFTEST iommufd/selftest: Add IOMMU_VIOMMU_ALLOC test coverage Documentation: userspace-api: iommufd: Update vIOMMU drivers/iommu/iommufd/Kconfig | 4 + drivers/iommu/iommufd/Makefile | 4 +- drivers/iommu/iommufd/iommufd_private.h | 33 +-- drivers/iommu/iommufd/iommufd_test.h | 2 + include/linux/iommu.h | 14 + include/linux/iommufd.h | 86 ++++++ include/uapi/linux/iommufd.h | 54 +++- tools/testing/selftests/iommu/iommufd_utils.h | 28 ++ drivers/iommu/iommufd/driver.c | 40 +++ drivers/iommu/iommufd/hw_pagetable.c | 73 ++++- drivers/iommu/iommufd/main.c | 54 ++-- drivers/iommu/iommufd/selftest.c | 266 +++++++++++++----- drivers/iommu/iommufd/viommu.c | 81 ++++++ tools/testing/selftests/iommu/iommufd.c | 137 +++++++++ .../selftests/iommu/iommufd_fail_nth.c | 11 + Documentation/userspace-api/iommufd.rst | 69 ++++- 16 files changed, 804 insertions(+), 152 deletions(-) create mode 100644 drivers/iommu/iommufd/driver.c create mode 100644 drivers/iommu/iommufd/viommu.c base-commit: 0bcceb1f51c77f6b98a7aab00847ed340bf36e35 -- 2.43.0

7 months, 2 weeks

4
28
0 0

[PATCHv2 net] selftests: wireguard: load nf_conntrack if it's not present

by Hangbin Liu

Some distros may not load nf_conntrack by default, which will cause subsequent nf_conntrack settings to fail. Let's load this module if it's not loaded by default. Fixes: e7096c131e51 ("net: WireGuard secure network tunnel") Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- v2: load the mode directly in case nf_conntrack is build in (Simon Horman) --- tools/testing/selftests/wireguard/netns.sh | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/wireguard/netns.sh b/tools/testing/selftests/wireguard/netns.sh index 405ff262ca93..fa4dd7eb5918 100755 --- a/tools/testing/selftests/wireguard/netns.sh +++ b/tools/testing/selftests/wireguard/netns.sh @@ -66,6 +66,7 @@ cleanup() { orig_message_cost="$(< /proc/sys/net/core/message_cost)" trap cleanup EXIT printf 0 > /proc/sys/net/core/message_cost +modprobe nf_conntrack ip netns del $netns0 2>/dev/null || true ip netns del $netns1 2>/dev/null || true -- 2.39.5 (Apple Git-154)

7 months, 2 weeks

3
2
0 0

[PATCH] selftests/livepatch: Check if CONFIG_LIVEPATCH is enabled

by Siddharth Menon

When CONFIG_LIVEPATCH is disabled, compilation fails due to the required structs from the livepatch header file being undefined. This checks for CONFIG_LIVEPATCH in order to verify that it is enabled before compiling livepatch self-tests. Reviewed-by: Shuah Khan <skhan(a)linuxfoundation.org> Signed-off-by: Siddharth Menon <simeddon(a)gmail.com> --- tools/testing/selftests/livepatch/test_modules/Makefile | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/livepatch/test_modules/Makefile b/tools/testing/selftests/livepatch/test_modules/Makefile index e6e638c4bcba..b34b80544709 100644 --- a/tools/testing/selftests/livepatch/test_modules/Makefile +++ b/tools/testing/selftests/livepatch/test_modules/Makefile @@ -1,5 +1,6 @@ TESTMODS_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) KDIR ?= /lib/modules/$(shell uname -r)/build +CONFIG_LIVEPATCH := $(shell cd $(KDIR) && scripts/config --state CONFIG_LIVEPATCH) obj-m += test_klp_atomic_replace.o \ test_klp_callbacks_busy.o \ @@ -13,10 +14,15 @@ obj-m += test_klp_atomic_replace.o \ test_klp_shadow_vars.o \ test_klp_syscall.o -# Ensure that KDIR exists, otherwise skip the compilation + +# Ensure that KDIR exists and CONFIG_LIVEPATCH is enabled, else skip compilation modules: ifneq ("$(wildcard $(KDIR))", "") +ifneq ($(filter y m,$(CONFIG_LIVEPATCH)),) $(Q)$(MAKE) -C $(KDIR) modules KBUILD_EXTMOD=$(TESTMODS_DIR) +else + $(warning CONFIG_LIVEPATCH is not enabled in the kernel config file.) +endif endif # Ensure that KDIR exists, otherwise skip the clean target -- 2.39.5

7 months, 2 weeks

4
3
0 0

[PATCH v2] selftests/powerpc: Remove the path after initialization.

by zhangjiao2

From: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> If there were no anamolies noted, then we can simply remove the log file and return. Signed-off-by: zhang jiao <zhangjiao2(a)cmss.chinamobile.com> --- v1->v2: Remove the path after initialization. tools/testing/selftests/powerpc/mm/tlbie_test.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/powerpc/mm/tlbie_test.c b/tools/testing/selftests/powerpc/mm/tlbie_test.c index 48344a74b212..35f0098399cc 100644 --- a/tools/testing/selftests/powerpc/mm/tlbie_test.c +++ b/tools/testing/selftests/powerpc/mm/tlbie_test.c @@ -313,16 +313,16 @@ static inline void end_verification_log(unsigned int tid, unsigned nr_anamolies) fclose(f); - if (nr_anamolies == 0) { - remove(path); - return; - } - sprintf(logfile, logfilename, tid); strcpy(path, logdir); strcat(path, separator); strcat(path, logfile); + if (nr_anamolies == 0) { + remove(path); + return; + } + printf("Thread %02d chunk has %d corrupted words. For details check %s\n", tid, nr_anamolies, path); } -- 2.33.0

7 months, 2 weeks

3
2
0 0

[PATCH 1/5] selftests/powerpc: Lower run time of count_stcx_fail test

by Michael Ellerman

The count_stcx_fail test runs for close to or just over 2 minutes, which means it sometimes times out. That's overkill for a test that just demonstrates some PMU counters are working. Drop the 64 billion instruction case, to lower the runtime to ~30s. Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> --- tools/testing/selftests/powerpc/pmu/count_stcx_fail.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c index 2070a1e2b3a5..d8dd9a9c6c1b 100644 --- a/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c +++ b/tools/testing/selftests/powerpc/pmu/count_stcx_fail.c @@ -144,9 +144,6 @@ static int test_body(void) /* Run for 16Bi instructions */ FAIL_IF(do_count_loop(events, 16000000000, overhead, true)); - /* Run for 64Bi instructions */ - FAIL_IF(do_count_loop(events, 64000000000, overhead, true)); - event_close(&events[0]); event_close(&events[1]); -- 2.47.0

7 months, 2 weeks

2
5
0 0

Nov:16:24

by Van. HR

Hello, I am a private investment consultant representing the interest of a multinational conglomerate that wishes to place funds into a trust management portfolio. Please indicate your interest for additional information. Regards, Van Collin.

7 months, 2 weeks

1
0
0 0

[PATCH net-next v23 1/7] mm: page_frag: add a test module for page_frag

by Yunsheng Lin

The testing is done by ensuring that the fragment allocated from a frag_frag_cache instance is pushed into a ptr_ring instance in a kthread binded to a specified cpu, and a kthread binded to a specified cpu will pop the fragment from the ptr_ring and free the fragment. CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Alexander Duyck <alexander.duyck(a)gmail.com> CC: Linux-MM <linux-mm(a)kvack.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> Reviewed-by: Alexander Duyck <alexanderduyck(a)fb.com> --- tools/testing/selftests/mm/Makefile | 3 + tools/testing/selftests/mm/page_frag/Makefile | 18 ++ .../selftests/mm/page_frag/page_frag_test.c | 198 ++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 8 + tools/testing/selftests/mm/test_page_frag.sh | 175 ++++++++++++++++ 5 files changed, 402 insertions(+) create mode 100644 tools/testing/selftests/mm/page_frag/Makefile create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c create mode 100755 tools/testing/selftests/mm/test_page_frag.sh diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 02e1204971b0..acec529baaca 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES) LDLIBS = -lrt -lpthread -lm +TEST_GEN_MODS_DIR := page_frag + TEST_GEN_FILES = cow TEST_GEN_FILES += compaction_test TEST_GEN_FILES += gup_longterm @@ -126,6 +128,7 @@ TEST_FILES += test_hmm.sh TEST_FILES += va_high_addr_switch.sh TEST_FILES += charge_reserved_hugetlb.sh TEST_FILES += hugetlb_reparenting_test.sh +TEST_FILES += test_page_frag.sh # required by charge_reserved_hugetlb.sh TEST_FILES += write_hugetlb_memory.sh diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile new file mode 100644 index 000000000000..58dda74d50a3 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/Makefile @@ -0,0 +1,18 @@ +PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = page_frag_test.ko + +obj-m += page_frag_test.o + +all: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c new file mode 100644 index 000000000000..912d97b99107 --- /dev/null +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Test module for page_frag cache + * + * Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/cpumask.h> +#include <linux/completion.h> +#include <linux/ptr_ring.h> +#include <linux/kthread.h> + +#define TEST_FAILED_PREFIX "page_frag_test failed: " + +static struct ptr_ring ptr_ring; +static int nr_objs = 512; +static atomic_t nthreads; +static struct completion wait; +static struct page_frag_cache test_nc; +static int test_popped; +static int test_pushed; +static bool force_exit; + +static int nr_test = 2000000; +module_param(nr_test, int, 0); +MODULE_PARM_DESC(nr_test, "number of iterations to test"); + +static bool test_align; +module_param(test_align, bool, 0); +MODULE_PARM_DESC(test_align, "use align API for testing"); + +static int test_alloc_len = 2048; +module_param(test_alloc_len, int, 0); +MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); + +static int test_push_cpu; +module_param(test_push_cpu, int, 0); +MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment"); + +static int test_pop_cpu; +module_param(test_pop_cpu, int, 0); +MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment"); + +static int page_frag_pop_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag pop test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_popped < nr_test) { + void *obj = __ptr_ring_consume(ring); + + if (obj) { + test_popped++; + page_frag_free(obj); + } else { + if (force_exit) + break; + + cond_resched(); + } + } + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + pr_info("page_frag pop test thread exits on cpu %d\n", + smp_processor_id()); + + return 0; +} + +static int page_frag_push_thread(void *arg) +{ + struct ptr_ring *ring = arg; + + pr_info("page_frag push test thread begins on cpu %d\n", + smp_processor_id()); + + while (test_pushed < nr_test && !force_exit) { + void *va; + int ret; + + if (test_align) { + va = page_frag_alloc_align(&test_nc, test_alloc_len, + GFP_KERNEL, SMP_CACHE_BYTES); + + if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); + } + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } + + if (!va) + continue; + + ret = __ptr_ring_produce(ring, va); + if (ret) { + page_frag_free(va); + cond_resched(); + } else { + test_pushed++; + } + } + + pr_info("page_frag push test thread exits on cpu %d\n", + smp_processor_id()); + + if (atomic_dec_and_test(&nthreads)) + complete(&wait); + + return 0; +} + +static int __init page_frag_test_init(void) +{ + struct task_struct *tsk_push, *tsk_pop; + int last_pushed = 0, last_popped = 0; + ktime_t start; + u64 duration; + int ret; + + test_nc.va = NULL; + atomic_set(&nthreads, 2); + init_completion(&wait); + + if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 || + !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu)) + return -EINVAL; + + ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL); + if (ret) + return ret; + + tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring, + test_push_cpu, "page_frag_push"); + if (IS_ERR(tsk_push)) + return PTR_ERR(tsk_push); + + tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring, + test_pop_cpu, "page_frag_pop"); + if (IS_ERR(tsk_pop)) { + kthread_stop(tsk_push); + return PTR_ERR(tsk_pop); + } + + start = ktime_get(); + wake_up_process(tsk_push); + wake_up_process(tsk_pop); + + pr_info("waiting for test to complete\n"); + + while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000))) { + /* exit if there is no progress for push or pop size */ + if (last_pushed == test_pushed || last_popped == test_popped) { + WARN_ONCE(true, TEST_FAILED_PREFIX "no progress\n"); + force_exit = true; + continue; + } + + last_pushed = test_pushed; + last_popped = test_popped; + pr_info("page_frag_test progress: pushed = %d, popped = %d\n", + test_pushed, test_popped); + } + + if (force_exit) { + pr_err(TEST_FAILED_PREFIX "exit with error\n"); + goto out; + } + + duration = (u64)ktime_us_delta(ktime_get(), start); + pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", duration); + +out: + ptr_ring_cleanup(&ptr_ring, NULL); + page_frag_cache_drain(&test_nc); + + return -EAGAIN; +} + +static void __exit page_frag_test_exit(void) +{ +} + +module_init(page_frag_test_init); +module_exit(page_frag_test_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Yunsheng Lin <linyunsheng(a)huawei.com>"); +MODULE_DESCRIPTION("Test module for page_frag"); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index c5797ad1d37b..2c5394584af4 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -75,6 +75,8 @@ separated by spaces: read-only VMAs - mdwe test prctl(PR_SET_MDWE, ...) +- page_frag + test handling of page fragment allocation and freeing example: ./run_vmtests.sh -t "hmm mmap ksm" EOF @@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty CATEGORY="mdwe" run_test ./mdwe_test +CATEGORY="page_frag" run_test ./test_page_frag.sh smoke + +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh new file mode 100755 index 000000000000..f55b105084cf --- /dev/null +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -0,0 +1,175 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Copyright (C) 2024 Yunsheng Lin <linyunsheng(a)huawei.com> +# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki(a)gmail.com> +# +# This is a test script for the kernel test driver to test the +# correctness and performance of page_frag's implementation. +# Therefore it is just a kernel module loader. You can specify +# and pass different parameters in order to: +# a) analyse performance of page fragment allocations; +# b) stressing and stability check of page_frag subsystem. + +DRIVER="./page_frag/page_frag_test.ko" +CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2) +TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}') + +if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then + TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}') + NR_TEST=100000000 +else + TEST_CPU_1=$TEST_CPU_0 + NR_TEST=1000000 +fi + +# 1 if fails +exitcode=1 + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +check_test_failed_prefix() { + if dmesg | grep -q 'page_frag_test failed:';then + echo "page_frag_test failed, please check dmesg" + exit $exitcode + fi +} + +# +# Static templates for testing of page_frag APIs. +# Also it is possible to pass any supported parameters manually. +# +SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" +NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" +ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" + +check_test_requirements() +{ + uid=$(id -u) + if [ $uid -ne 0 ]; then + echo "$0: Must be run as root" + exit $ksft_skip + fi + + if ! which insmod > /dev/null 2>&1; then + echo "$0: You need insmod installed" + exit $ksft_skip + fi + + if [ ! -f $DRIVER ]; then + echo "$0: You need to compile page_frag_test module" + exit $ksft_skip + fi +} + +run_nonaligned_check() +{ + echo "Run performance tests to evaluate how fast nonaligned alloc API is." + + insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1 +} + +run_aligned_check() +{ + echo "Run performance tests to evaluate how fast aligned alloc API is." + + insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 +} + +run_smoke_check() +{ + echo "Run smoke test." + + insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1 +} + +usage() +{ + echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "manual parameters" + echo + echo "Valid tests and parameters:" + echo + modinfo $DRIVER + echo + echo "Example usage:" + echo + echo "# Shows help message" + echo "$0" + echo + echo "# Smoke testing" + echo "$0 smoke" + echo + echo "# Performance testing for nonaligned alloc API" + echo "$0 nonaligned" + echo + echo "# Performance testing for aligned alloc API" + echo "$0 aligned" + echo + exit 0 +} + +function validate_passed_args() +{ + VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'` + + # + # Something has been passed, check it. + # + for passed_arg in $@; do + key=${passed_arg//=*/} + valid=0 + + for valid_arg in $VALID_ARGS; do + if [[ $key = $valid_arg ]]; then + valid=1 + break + fi + done + + if [[ $valid -ne 1 ]]; then + echo "Error: key is not correct: ${key}" + exit $exitcode + fi + done +} + +function run_manual_check() +{ + # + # Validate passed parameters. If there is wrong one, + # the script exists and does not execute further. + # + validate_passed_args $@ + + echo "Run the test with following parameters: $@" + insmod $DRIVER $@ > /dev/null 2>&1 +} + +function run_test() +{ + if [ $# -eq 0 ]; then + usage + else + if [[ "$1" = "smoke" ]]; then + run_smoke_check + elif [[ "$1" = "nonaligned" ]]; then + run_nonaligned_check + elif [[ "$1" = "aligned" ]]; then + run_aligned_check + else + run_manual_check $@ + fi + fi + + check_test_failed_prefix + + echo "Done." + echo "Check the kernel ring buffer to see the summary." +} + +check_test_requirements +run_test $@ + +exit 0 -- 2.33.0

7 months, 2 weeks

4
6
0 0

[PATCH v1] selftest/mm: remove seal_elf

by jeffxu＠chromium.org

From: Jeff Xu <jeffxu(a)chromium.org> Remove seal_elf, which is a demo of mseal, we no longer need this. Signed-off-by: Jeff Xu <jeffxu(a)chromium.org> --- tools/testing/selftests/mm/.gitignore | 1 - tools/testing/selftests/mm/Makefile | 1 - tools/testing/selftests/mm/seal_elf.c | 137 -------------------------- 3 files changed, 139 deletions(-) delete mode 100644 tools/testing/selftests/mm/seal_elf.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 8f01f4da1c0d..6a273bdbc70b 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -49,7 +49,6 @@ 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 72ec4403032d..869b6a40f290 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -64,7 +64,6 @@ 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 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(); -} -- 2.47.0.338.g60cca15819-goog

7 months, 2 weeks

1
0
0 0

[PATCH net-next v3 0/6] net: Improve netns handling in RTNL and ip_tunnel

by Xiao Liang

This patch series includes some netns-related improvements and fixes for RTNL and ip_tunnel, to make link creation more intuitive: - Creating link in another net namespace doesn't conflict with link names in current one. - Refector rtnetlink link creation. Create link in target namespace directly. Pass both source and link netns to drivers via newlink() callback. So that # ip link add netns ns1 link-netns ns2 tun0 type gre ... will create tun0 in ns1, rather than create it in ns2 and move to ns1. And don't conflict with another interface named "tun0" in current netns. Patch 1 from Donald is included just as a dependency. --- v3: - Drop "netns_atomic" flag and module parameter. Add netns parameter to newlink() instead, and convert drivers accordingly. - Move python NetNSEnter helper to net selftest lib. v2: link: https://lore.kernel.org/all/20241107133004.7469-1-shaw.leon@gmail.com/ - Check NLM_F_EXCL to ensure only link creation is affected. - Add self tests for link name/ifindex conflict and notifications in different netns. - Changes in dummy driver and ynl in order to add the test case. v1: link: https://lore.kernel.org/all/20241023023146.372653-1-shaw.leon@gmail.com/ Donald Hunter (1): Revert "tools/net/ynl: improve async notification handling" Xiao Liang (5): net: ip_tunnel: Build flow in underlay net namespace rtnetlink: Lookup device in target netns when creating link rtnetlink: Decouple net namespaces in rtnl_newlink_create() selftests: net: Add python context manager for netns entering selftests: net: Add two test cases for link netns drivers/infiniband/ulp/ipoib/ipoib_netlink.c | 6 ++- drivers/net/amt.c | 6 +-- drivers/net/bareudp.c | 4 +- drivers/net/bonding/bond_netlink.c | 3 +- drivers/net/can/dev/netlink.c | 2 +- drivers/net/can/vxcan.c | 4 +- .../ethernet/qualcomm/rmnet/rmnet_config.c | 5 +- drivers/net/geneve.c | 4 +- drivers/net/gtp.c | 4 +- drivers/net/ipvlan/ipvlan.h | 2 +- drivers/net/ipvlan/ipvlan_main.c | 5 +- drivers/net/ipvlan/ipvtap.c | 4 +- drivers/net/macsec.c | 5 +- drivers/net/macvlan.c | 5 +- drivers/net/macvtap.c | 5 +- drivers/net/netkit.c | 4 +- drivers/net/pfcp.c | 4 +- drivers/net/ppp/ppp_generic.c | 4 +- drivers/net/team/team_core.c | 2 +- drivers/net/veth.c | 4 +- drivers/net/vrf.c | 2 +- drivers/net/vxlan/vxlan_core.c | 4 +- drivers/net/wireguard/device.c | 4 +- drivers/net/wireless/virtual/virt_wifi.c | 5 +- drivers/net/wwan/wwan_core.c | 6 ++- include/net/ip_tunnels.h | 5 +- include/net/rtnetlink.h | 22 ++++++++- net/8021q/vlan_netlink.c | 5 +- net/batman-adv/soft-interface.c | 5 +- net/bridge/br_netlink.c | 2 +- net/caif/chnl_net.c | 2 +- net/core/rtnetlink.c | 25 ++++++---- net/hsr/hsr_netlink.c | 8 +-- net/ieee802154/6lowpan/core.c | 5 +- net/ipv4/ip_gre.c | 13 +++-- net/ipv4/ip_tunnel.c | 16 +++--- net/ipv4/ip_vti.c | 5 +- net/ipv4/ipip.c | 5 +- net/ipv6/ip6_gre.c | 17 ++++--- net/ipv6/ip6_tunnel.c | 11 ++--- net/ipv6/ip6_vti.c | 11 ++--- net/ipv6/sit.c | 11 ++--- net/xfrm/xfrm_interface_core.c | 13 +++-- tools/net/ynl/cli.py | 10 ++-- tools/net/ynl/lib/ynl.py | 49 ++++++++----------- tools/testing/selftests/net/Makefile | 1 + .../testing/selftests/net/lib/py/__init__.py | 2 +- tools/testing/selftests/net/lib/py/netns.py | 18 +++++++ tools/testing/selftests/net/netns-name.sh | 10 ++++ tools/testing/selftests/net/netns_atomic.py | 38 ++++++++++++++ 50 files changed, 255 insertions(+), 157 deletions(-) create mode 100755 tools/testing/selftests/net/netns_atomic.py -- 2.47.0

7 months, 2 weeks

2
7
0 0

[PATCH] kunit: debugfs: Use IS_ERR() for alloc_string_stream() error check

by Kuan-Wei Chiu

The alloc_string_stream() function only returns ERR_PTR(-ENOMEM) on failure and never returns NULL. Therefore, switching the error check in the caller from IS_ERR_OR_NULL to IS_ERR improves clarity, indicating that this function will return an error pointer (not NULL) when an error occurs. This change avoids any ambiguity regarding the function's return behavior. Link: https://lore.kernel.org/lkml/Zy9deU5VK3YR+r9N@visitorckw-System-Product-Name Signed-off-by: Kuan-Wei Chiu <visitorckw(a)gmail.com> --- lib/kunit/debugfs.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c index d548750a325a..6273fa9652df 100644 --- a/lib/kunit/debugfs.c +++ b/lib/kunit/debugfs.c @@ -181,7 +181,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) * successfully. */ stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) return; string_stream_set_append_newlines(stream, true); @@ -189,7 +189,7 @@ void kunit_debugfs_create_suite(struct kunit_suite *suite) kunit_suite_for_each_test_case(suite, test_case) { stream = alloc_string_stream(GFP_KERNEL); - if (IS_ERR_OR_NULL(stream)) + if (IS_ERR(stream)) goto err; string_stream_set_append_newlines(stream, true); -- 2.34.1

7 months, 2 weeks

2
1
0 0

[PATCH v2] kunit: Fix potential null dereference in kunit_device_driver_test()

by Gax-c

From: Zichen Xie <zichenxie0106(a)gmail.com> kunit_kzalloc() may return a NULL pointer, dereferencing it without NULL check may lead to NULL dereference. Add a NULL check for test_state. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: Zichen Xie <zichenxie0106(a)gmail.com> Cc: stable(a)vger.kernel.org --- v2: Add Cc tag. --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); -- 2.34.1

7 months, 2 weeks

2
1
0 0

[PATCH v1] MAINTAINERS: Update KUnit email address for Brendan Higgins

by Brendan Higgins

Update Brendan's email address for the KUnit entry. Signed-off-by: Brendan Higgins <brendanhiggins(a)google.com> --- I am leaving Google and am going through and cleaning up my @google.com address in the relevant places. This patch updates my email address for the KUnit entry. I am removing myself from the ASPEED I2C entry in a separate patch. Do note that Friday, November 15 2024 is my last day at Google after which I will lose access to this email account so any future updates or comments after Friday will come from my @linux.dev account. --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index b878ddc99f94e..d077a3deeb386 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12405,7 +12405,7 @@ F: fs/smb/common/ F: fs/smb/server/ KERNEL UNIT TESTING FRAMEWORK (KUnit) -M: Brendan Higgins <brendanhiggins(a)google.com> +M: Brendan Higgins <brendan.higgins(a)linux.dev> M: David Gow <davidgow(a)google.com> R: Rae Moar <rmoar(a)google.com> L: linux-kselftest(a)vger.kernel.org base-commit: cfaaa7d010d1fc58f9717fcc8591201e741d2d49 -- 2.47.0.338.g60cca15819-goog

7 months, 2 weeks

2
1
0 0

[RFC PATCH v3 0/6] Direct Map Removal for guest_memfd

by Patrick Roy

Unmapping virtual machine guest memory from the host kernel's direct map is a successful mitigation against Spectre-style transient execution issues: If the kernel page tables do not contain entries pointing to guest memory, then any attempted speculative read through the direct map will necessarily be blocked by the MMU before any observable microarchitectural side-effects happen. This means that Spectre-gadgets and similar cannot be used to target virtual machine memory. Roughly 60% of speculative execution issues fall into this category [1, Table 1]. This patch series extends guest_memfd with the ability to remove its memory from the host kernel's direct map, to be able to attain the above protection for KVM guests running inside guest_memfd. === Changes to v2 === - Handle direct map removal for physically contiguous pages in arch code (Mike R.) - Track the direct map state in guest_memfd itself instead of at the folio level, to prepare for huge pages support (Sean C.) - Allow configuring direct map state of not-yet faulted in memory (Vishal A.) - Pay attention to alignment in ftrace structs (Steven R.) Most significantly, I've reduced the patch series to focus only on direct map removal for guest_memfd for now, leaving the whole "how to do non-CoCo VMs in guest_memfd" for later. If this separation is acceptable, then I think I can drop the RFC tag in the next revision (I've mainly kept it here because I'm not entirely sure what to do with patches 3 and 4). === Implementation === This patch series introduces a new flag to the KVM_CREATE_GUEST_MEMFD that causes guest_memfd to remove its pages from the host kernel's direct map immediately after population/preparation. It also adds infrastructure for tracking the direct map state of all gmem folios inside the guest_memfd inode. Storing this information in the inode has the advantage that the code is ready for future hugepages extensions, where only removing/reinserting direct map entries for sub-ranges of a huge folio is a valid usecase, and it allows pre-configuring the direct map state of not-yet faulted in parts of memory (for example, when the VMM is receiving a RX virtio buffer from the guest). === Summary === Patch 1 (from Mike Rapoport) adds arch APIs for manipulating the direct map for ranges of physically contiguous pages, which are used by guest_memfd in follow up patches. Patch 2 adds the KVM_GMEM_NO_DIRECT_MAP flag and the logic for configuring direct map state of freshly prepared folios. Patches 3 and 4 mainly serve an illustrative purpose, to show how the framework from patch 2 can be extended with routines for runtime direct map manipulation. Patches 5 and 6 deal with documentation and self-tests respectively. [1]: https://download.vusec.net/papers/quarantine_raid23.pdf [RFC v1]: https://lore.kernel.org/kvm/20240709132041.3625501-1-roypat@amazon.co.uk/ [RFC v2]: https://lore.kernel.org/kvm/20240910163038.1298452-1-roypat@amazon.co.uk/ Mike Rapoport (Microsoft) (1): arch: introduce set_direct_map_valid_noflush() Patrick Roy (5): kvm: gmem: add flag to remove memory from kernel direct map kvm: gmem: implement direct map manipulation routines kvm: gmem: add trace point for direct map state changes kvm: document KVM_GMEM_NO_DIRECT_MAP flag kvm: selftests: run gmem tests with KVM_GMEM_NO_DIRECT_MAP set Documentation/virt/kvm/api.rst | 14 + arch/arm64/include/asm/set_memory.h | 1 + arch/arm64/mm/pageattr.c | 10 + arch/loongarch/include/asm/set_memory.h | 1 + arch/loongarch/mm/pageattr.c | 21 ++ arch/riscv/include/asm/set_memory.h | 1 + arch/riscv/mm/pageattr.c | 15 + arch/s390/include/asm/set_memory.h | 1 + arch/s390/mm/pageattr.c | 11 + arch/x86/include/asm/set_memory.h | 1 + arch/x86/mm/pat/set_memory.c | 8 + include/linux/set_memory.h | 6 + include/trace/events/kvm.h | 22 ++ include/uapi/linux/kvm.h | 2 + .../testing/selftests/kvm/guest_memfd_test.c | 2 +- .../kvm/x86_64/private_mem_conversions_test.c | 7 +- virt/kvm/guest_memfd.c | 280 +++++++++++++++++- 17 files changed, 384 insertions(+), 19 deletions(-) base-commit: 5cb1659f412041e4780f2e8ee49b2e03728a2ba6 -- 2.47.0

7 months, 2 weeks

9
35
0 0

LKFT CI: improving Networking selftests results when validating stable kernels

by Matthieu Baerts

Hello LKFT maintainers, CI operators, First, I would like to say thank you to the people behind the LKFT project for validating stable kernels (and more), and including some Network selftests in their tests suites. A lot of improvements around the networking kselftests have been done this year. At the last Netconf [1], we discussed how these tests were validated on stable kernels from CIs like the LKFT one, and we have some suggestions to improve the situation. KSelftests from the same version -------------------------------- According to the doc [2], kselftests should support all previous kernel versions. The LKFT CI is then using the kselftests from the last stable release to validate all stable versions. Even if there are good reasons to do that, we would like to ask for an opt-out for this policy for the networking tests: this is hard to maintain with the increased complexity, hard to validate on all stable kernels before applying patches, and hard to put in place in some situations. As a result, many tests are failing on older kernels, and it looks like it is a lot of work to support older kernels, and to maintain this. Many networking tests are validating the internal behaviour that is not exposed to the userspace. A typical example: some tests look at the raw packets being exchanged during a test, and this behaviour can change without modifying how the userspace is interacting with the kernel. The kernel could expose capabilities, but that's not something that seems natural to put in place for internal behaviours that are not exposed to end users. Maybe workarounds could be used, e.g. looking at kernel symbols, etc. Nut that doesn't always work, increase the complexity, and often "false positive" issue will be noticed only after a patch hits stable, and will cause a bunch of tests to be ignored. Regarding fixes, ideally they will come with a new or modified test that can also be backported. So the coverage can continue to grow in stable versions too. Do you think that from the kernel v6.12 (or before?), the LKFT CI could run the networking kselftests from the version that is being validated, and not from a newer one? So validating the selftests from v6.12.1 on a v6.12.1, and not the ones from a future v6.16.y on a v6.12.42. Skipped tests ------------- It looks like many tests are skipped: - Some have been in a skip file [3] for a while: maybe they can be removed? - Some are skipped because of missing tools: maybe they can be added? e.g. iputils, tshark, ipv6toolkit, etc. - Some tests are in 'net', but in subdirectories, and hence not tested, e.g. forwarding, packetdrill, netfilter, tcp_ao. Could they be tested too? How can we change this to increase the code coverage using existing tests? KVM --- It looks like different VMs are being used to execute the different tests. Do these VMs benefit from any accelerations like KVM? If not, some tests might fail because the environment is too slow. The KSFT_MACHINE_SLOW=yes env var can be set to increase some tolerances, timeout or to skip some parts, but that might not be enough for some tests. Notifications ------------- In case of new regressions, who is being notified? Are the people from the MAINTAINERS file, and linked to the corresponding selftests being notified or do they need to do the monitoring on their side? Looking forward to improving the networking selftests results when validating stable kernels! [1] https://netdev.bots.linux.dev/netconf/2024/ [2] https://docs.kernel.org/dev-tools/kselftest.html [3] https://github.com/Linaro/test-definitions/blob/master/automated/linux/ksel… Cheers, Matt -- Sponsored by the NGI0 Core fund.

7 months, 2 weeks

3
6
0 0

[PATCH] kunit: Fix potential null dereference in kunit_device_driver_test()

by Gax-c

From: Zichen Xie <zichenxie0106(a)gmail.com> kunit_kzalloc() may return a NULL pointer, dereferencing it without NULL check may lead to NULL dereference. Add a NULL check for test_state. Fixes: d03c720e03bd ("kunit: Add APIs for managing devices") Signed-off-by: Zichen Xie <zichenxie0106(a)gmail.com> --- lib/kunit/kunit-test.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/lib/kunit/kunit-test.c b/lib/kunit/kunit-test.c index 37e02be1e710..d9c781c859fd 100644 --- a/lib/kunit/kunit-test.c +++ b/lib/kunit/kunit-test.c @@ -805,6 +805,8 @@ static void kunit_device_driver_test(struct kunit *test) struct device *test_device; struct driver_test_state *test_state = kunit_kzalloc(test, sizeof(*test_state), GFP_KERNEL); + KUNIT_ASSERT_NOT_ERR_OR_NULL(test, test_state); + test->priv = test_state; test_driver = kunit_driver_create(test, "my_driver"); -- 2.34.1

7 months, 2 weeks

2
1
0 0

[PATCH v8 00/29] riscv control-flow integrity for usermode

by Deepak Gupta

Basics and overview =================== Software with larger attack surfaces (e.g. network facing apps like databases, browsers or apps relying on browser runtimes) suffer from memory corruption issues which can be utilized by attackers to bend control flow of the program to eventually gain control (by making their payload executable). Attackers are able to perform such attacks by leveraging call-sites which rely on indirect calls or return sites which rely on obtaining return address from stack memory. To mitigate such attacks, risc-v extension zicfilp enforces that all indirect calls must land on a landing pad instruction `lpad` else cpu will raise software check exception (a new cpu exception cause code on riscv). Similarly for return flow, risc-v extension zicfiss extends architecture with - `sspush` instruction to push return address on a shadow stack - `sspopchk` instruction to pop return address from shadow stack and compare with input operand (i.e. return address on stack) - `sspopchk` to raise software check exception if comparision above was a mismatch - Protection mechanism using which shadow stack is not writeable via regular store instructions More information an details can be found at extensions github repo [1]. Equivalent to landing pad (zicfilp) on x86 is `ENDBRANCH` instruction in Intel CET [3] and branch target identification (BTI) [4] on arm. Similarly x86's Intel CET has shadow stack [5] and arm64 has guarded control stack (GCS) [6] which are very similar to risc-v's zicfiss shadow stack. x86 already supports shadow stack for user mode and arm64 support for GCS in usermode [7] is in -next. Kernel awareness for user control flow integrity ================================================ This series picks up Samuel Holland's envcfg changes [2] as well. So if those are being applied independently, they should be removed from this series. Enabling: In order to maintain compatibility and not break anything in user mode, kernel doesn't enable control flow integrity cpu extensions on binary by default. Instead exposes a prctl interface to enable, disable and lock the shadow stack or landing pad feature for a task. This allows userspace (loader) to enumerate if all objects in its address space are compiled with shadow stack and landing pad support and accordingly enable the feature. Additionally if a subsequent `dlopen` happens on a library, user mode can take a decision again to disable the feature (if incoming library is not compiled with support) OR terminate the task (if user mode policy is strict to have all objects in address space to be compiled with control flow integirty cpu feature). prctl to enable shadow stack results in allocating shadow stack from virtual memory and activating for user address space. x86 and arm64 are also following same direction due to similar reason(s). clone/fork: On clone and fork, cfi state for task is inherited by child. Shadow stack is part of virtual memory and is a writeable memory from kernel perspective (writeable via a restricted set of instructions aka shadow stack instructions) Thus kernel changes ensure that this memory is converted into read-only when fork/clone happens and COWed when fault is taken due to sspush, sspopchk or ssamoswap. In case `CLONE_VM` is specified and shadow stack is to be enabled, kernel will automatically allocate a shadow stack for that clone call. map_shadow_stack: x86 introduced `map_shadow_stack` system call to allow user space to explicitly map shadow stack memory in its address space. It is useful to allocate shadow for different contexts managed by a single thread (green threads or contexts) risc-v implements this system call as well. signal management: If shadow stack is enabled for a task, kernel performs an asynchronous control flow diversion to deliver the signal and eventually expects userspace to issue sigreturn so that original execution can be resumed. Even though resume context is prepared by kernel, it is in user space memory and is subject to memory corruption and corruption bugs can be utilized by attacker in this race window to perform arbitrary sigreturn and eventually bypass cfi mechanism. Another issue is how to ensure that cfi related state on sigcontext area is not trampled by legacy apps or apps compiled with old kernel headers. In order to mitigate control-flow hijacting, kernel prepares a token and place it on shadow stack before signal delivery and places address of token in sigcontext structure. During sigreturn, kernel obtains address of token from sigcontext struture, reads token from shadow stack and validates it and only then allow sigreturn to succeed. Compatiblity issue is solved by adopting dynamic sigcontext management introduced for vector extension. This series re-factor the code little bit to allow future sigcontext management easy (as proposed by Andy Chiu from SiFive) config and compilation: Introduce a new risc-v config option `CONFIG_RISCV_USER_CFI`. Selecting this config option picks the kernel support for user control flow integrity. This optin is presented only if toolchain has shadow stack and landing pad support. And is on purpose guarded by toolchain support. Reason being that eventually vDSO also needs to be compiled in with shadow stack and landing pad support. vDSO compile patches are not included as of now because landing pad labeling scheme is yet to settle for usermode runtime. To get more information on kernel interactions with respect to zicfilp and zicfiss, patch series adds documentation for `zicfilp` and `zicfiss` in following: Documentation/arch/riscv/zicfiss.rst Documentation/arch/riscv/zicfilp.rst How to test this series ======================= Toolchain --------- $ git clone git@github.com:sifive/riscv-gnu-toolchain.git -b cfi-dev $ riscv-gnu-toolchain/configure --prefix=<path-to-where-to-build> --with-arch=rv64gc_zicfilp_zicfiss --enable-linux --disable-gdb --with-extra-multilib-test="rv64gc_zicfilp_zicfiss-lp64d:-static" $ make -j$(nproc) Qemu ---- $ git clone git@github.com:deepak0414/qemu.git -b zicfilp_zicfiss_ratified_master_july11 $ cd qemu $ mkdir build $ cd build $ ../configure --target-list=riscv64-softmmu $ make -j$(nproc) Opensbi ------- $ git clone git@github.com:deepak0414/opensbi.git -b v6_cfi_spec_split_opensbi $ make CROSS_COMPILE=<your riscv toolchain> -j$(nproc) PLATFORM=generic Linux ----- Running defconfig is fine. CFI is enabled by default if the toolchain supports it. $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) defconfig $ make ARCH=riscv CROSS_COMPILE=<path-to-cfi-riscv-gnu-toolchain>/build/bin/riscv64-unknown-linux-gnu- -j$(nproc) Branch where user cfi enabling patches are maintained https://github.com/deepak0414/linux-riscv-cfi/tree/vdso_user_cfi_v6.12-rc1 In case you're building your own rootfs using toolchain, please make sure you pick following patch to ensure that vDSO compiled with lpad and shadow stack. "arch/riscv: compile vdso with landing pad" Running ------- Modify your qemu command to have: -bios <path-to-cfi-opensbi>/build/platform/generic/firmware/fw_dynamic.bin -cpu rv64,zicfilp=true,zicfiss=true,zimop=true,zcmop=true vDSO related Opens (in the flux) ================================= I am listing these opens for laying out plan and what to expect in future patch sets. And of course for the sake of discussion. Shadow stack and landing pad enabling in vDSO ---------------------------------------------- vDSO must have shadow stack and landing pad support compiled in for task to have shadow stack and landing pad support. This patch series doesn't enable that (yet). Enabling shadow stack support in vDSO should be straight forward (intend to do that in next versions of patch set). Enabling landing pad support in vDSO requires some collaboration with toolchain folks to follow a single label scheme for all object binaries. This is necessary to ensure that all indirect call-sites are setting correct label and target landing pads are decorated with same label scheme. How many vDSOs --------------- Shadow stack instructions are carved out of zimop (may be operations) and if CPU doesn't implement zimop, they're illegal instructions. Kernel could be running on a CPU which may or may not implement zimop. And thus kernel will have to carry 2 different vDSOs and expose the appropriate one depending on whether CPU implements zimop or not. References ========== [1] - https://github.com/riscv/riscv-cfi [2] - https://lore.kernel.org/all/20240814081126.956287-1-samuel.holland@sifive.c… [3] - https://lwn.net/Articles/889475/ [4] - https://developer.arm.com/documentation/109576/0100/Branch-Target-Identific… [5] - https://www.intel.com/content/dam/develop/external/us/en/documents/catc17-i… [6] - https://lwn.net/Articles/940403/ [7] - https://lore.kernel.org/all/20241001-arm64-gcs-v13-0-222b78d87eee@kernel.or… --- changelog --------- v8: - rebased on palmer/for-next - dropped samuel holland's `envcfg` context switch patches. they are in parlmer/for-next v7: - Removed "riscv/Kconfig: enable HAVE_EXIT_THREAD for riscv" Instead using `deactivate_mm` flow to clean up. see here for more context https://lore.kernel.org/all/20230908203655.543765-1-rick.p.edgecombe@intel.… - Changed the header include in `kselftest`. Hopefully this fixes compile issue faced by Zong Li at SiFive. - Cleaned up an orphaned change to `mm/mmap.c` in below patch "riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE" - Lock interfaces for shadow stack and indirect branch tracking expect arg == 0 Any future evolution of this interface should accordingly define how arg should be setup. - `mm/map.c` has an instance of using `VM_SHADOW_STACK`. Fixed it to use helper `is_shadow_stack_vma`. - Link to v6: https://lore.kernel.org/r/20241008-v5_user_cfi_series-v6-0-60d9fe073f37@riv… v6: - Picked up Samuel Holland's changes as is with `envcfg` placed in `thread` instead of `thread_info` - fixed unaligned newline escapes in kselftest - cleaned up messages in kselftest and included test output in commit message - fixed a bug in clone path reported by Zong Li - fixed a build issue if CONFIG_RISCV_ISA_V is not selected (this was introduced due to re-factoring signal context management code) v5: - rebased on v6.12-rc1 - Fixed schema related issues in device tree file - Fixed some of the documentation related issues in zicfilp/ss.rst (style issues and added index) - added `SHADOW_STACK_SET_MARKER` so that implementation can define base of shadow stack. - Fixed warnings on definitions added in usercfi.h when CONFIG_RISCV_USER_CFI is not selected. - Adopted context header based signal handling as proposed by Andy Chiu - Added support for enabling kernel mode access to shadow stack using FWFT (https://github.com/riscv-non-isa/riscv-sbi-doc/blob/master/src/ext-firmware…) - Link to v5: https://lore.kernel.org/r/20241001-v5_user_cfi_series-v1-0-3ba65b6e550f@riv… (Note: I had an issue in my workflow due to which version number wasn't picked up correctly while sending out patches) v4: - rebased on 6.11-rc6 - envcfg: Converged with Samuel Holland's patches for envcfg management on per- thread basis. - vma_is_shadow_stack is renamed to is_vma_shadow_stack - picked up Mark Brown's `ARCH_HAS_USER_SHADOW_STACK` patch - signal context: using extended context management to maintain compatibility. - fixed `-Wmissing-prototypes` compiler warnings for prctl functions - Documentation fixes and amending typos. - Link to v4: https://lore.kernel.org/all/20240912231650.3740732-1-debug@rivosinc.com/ v3: - envcfg logic to pick up base envcfg had a bug where `ENVCFG_CBZE` could have been picked on per task basis, even though CPU didn't implement it. Fixed in this series. - dt-bindings As suggested, split into separate commit. fixed the messaging that spec is in public review - arch_is_shadow_stack change arch_is_shadow_stack changed to vma_is_shadow_stack - hwprobe zicfiss / zicfilp if present will get enumerated in hwprobe - selftests As suggested, added object and binary filenames to .gitignore Selftest binary anyways need to be compiled with cfi enabled compiler which will make sure that landing pad and shadow stack are enabled. Thus removed separate enable/disable tests. Cleaned up tests a bit. - Link to v3: https://lore.kernel.org/lkml/20240403234054.2020347-1-debug@rivosinc.com/ v2: - Using config `CONFIG_RISCV_USER_CFI`, kernel support for riscv control flow integrity for user mode programs can be compiled in the kernel. - Enabling of control flow integrity for user programs is left to user runtime - This patch series introduces arch agnostic `prctls` to enable shadow stack and indirect branch tracking. And implements them on riscv. --- Changes in v8: - EDITME: describe what is new in this series revision. - EDITME: use bulletpoints and terse descriptions. - Link to v7: https://lore.kernel.org/r/20241029-v5_user_cfi_series-v7-0-2727ce9936cb@riv… --- Andy Chiu (1): riscv: signal: abstract header saving for setup_sigcontext Clément Léger (1): riscv: Add Firmware Feature SBI extensions definitions Deepak Gupta (25): mm: helper `is_shadow_stack_vma` to check shadow stack vma dt-bindings: riscv: zicfilp and zicfiss in dt-bindings (extensions.yaml) riscv: zicfiss / zicfilp enumeration riscv: zicfiss / zicfilp extension csr and bit definitions riscv: usercfi state for task and save/restore of CSR_SSP on trap entry/exit riscv/mm : ensure PROT_WRITE leads to VM_READ | VM_WRITE riscv mm: manufacture shadow stack pte riscv mmu: teach pte_mkwrite to manufacture shadow stack PTEs riscv mmu: write protect and shadow stack riscv/mm: Implement map_shadow_stack() syscall riscv/shstk: If needed allocate a new shadow stack on clone prctl: arch-agnostic prctl for indirect branch tracking riscv: Implements arch agnostic shadow stack prctls riscv: Implements arch agnostic indirect branch tracking prctls riscv/traps: Introduce software check exception riscv/signal: save and restore of shadow stack for signal riscv/kernel: update __show_regs to print shadow stack register riscv/ptrace: riscv cfi status and state via ptrace and in core files riscv/hwprobe: zicfilp / zicfiss enumeration in hwprobe riscv: enable kernel access to shadow stack memory via FWFT sbi call riscv: kernel command line option to opt out of user cfi riscv: create a config for shadow stack and landing pad instr support riscv: Documentation for landing pad / indirect branch tracking riscv: Documentation for shadow stack on riscv kselftest/riscv: kselftest for user mode cfi Mark Brown (2): mm: Introduce ARCH_HAS_USER_SHADOW_STACK prctl: arch-agnostic prctl for shadow stack Documentation/arch/riscv/index.rst | 2 + Documentation/arch/riscv/zicfilp.rst | 115 +++++ Documentation/arch/riscv/zicfiss.rst | 176 +++++++ .../devicetree/bindings/riscv/extensions.yaml | 14 + arch/riscv/Kconfig | 20 + arch/riscv/include/asm/asm-prototypes.h | 1 + arch/riscv/include/asm/cpufeature.h | 13 + arch/riscv/include/asm/csr.h | 16 + arch/riscv/include/asm/entry-common.h | 2 + arch/riscv/include/asm/hwcap.h | 2 + arch/riscv/include/asm/mman.h | 24 + arch/riscv/include/asm/mmu_context.h | 7 + arch/riscv/include/asm/pgtable.h | 30 +- arch/riscv/include/asm/processor.h | 2 + arch/riscv/include/asm/sbi.h | 27 ++ arch/riscv/include/asm/thread_info.h | 3 + arch/riscv/include/asm/usercfi.h | 89 ++++ arch/riscv/include/asm/vector.h | 3 + arch/riscv/include/uapi/asm/hwprobe.h | 2 + arch/riscv/include/uapi/asm/ptrace.h | 22 + arch/riscv/include/uapi/asm/sigcontext.h | 1 + arch/riscv/kernel/Makefile | 2 + arch/riscv/kernel/asm-offsets.c | 8 + arch/riscv/kernel/cpufeature.c | 2 + arch/riscv/kernel/entry.S | 31 +- arch/riscv/kernel/head.S | 12 + arch/riscv/kernel/process.c | 26 +- arch/riscv/kernel/ptrace.c | 83 ++++ arch/riscv/kernel/signal.c | 140 +++++- arch/riscv/kernel/sys_hwprobe.c | 2 + arch/riscv/kernel/sys_riscv.c | 10 + arch/riscv/kernel/traps.c | 42 ++ arch/riscv/kernel/usercfi.c | 526 +++++++++++++++++++++ arch/riscv/mm/init.c | 2 +- arch/riscv/mm/pgtable.c | 17 + arch/x86/Kconfig | 1 + fs/proc/task_mmu.c | 2 +- include/linux/cpu.h | 4 + include/linux/mm.h | 5 +- include/uapi/asm-generic/mman.h | 4 + include/uapi/linux/elf.h | 1 + include/uapi/linux/prctl.h | 48 ++ kernel/sys.c | 60 +++ mm/Kconfig | 6 + mm/gup.c | 2 +- mm/mmap.c | 2 +- mm/vma.h | 10 +- tools/testing/selftests/riscv/Makefile | 2 +- tools/testing/selftests/riscv/cfi/.gitignore | 3 + tools/testing/selftests/riscv/cfi/Makefile | 10 + tools/testing/selftests/riscv/cfi/cfi_rv_test.h | 84 ++++ tools/testing/selftests/riscv/cfi/riscv_cfi_test.c | 78 +++ tools/testing/selftests/riscv/cfi/shadowstack.c | 373 +++++++++++++++ tools/testing/selftests/riscv/cfi/shadowstack.h | 37 ++ 54 files changed, 2171 insertions(+), 35 deletions(-) --- base-commit: 64f7b77f0bd9271861ed9e410e9856b6b0b21c48 change-id: 20240930-v5_user_cfi_series-3dc332f8f5b2 -- - debug

7 months, 2 weeks

2
36
0 0

[PATCH net 2/2] selftests: net: test extacks in netlink dumps

by Jakub Kicinski

Test that extacks in dumps work. The test fills up the receive buffer to test both the inline dump (as part of sendmsg()) and delayed one (run during recvmsg()). Use YNL helpers to parse the messages. We need to add the test to YNL file to make sure the right include path are used. Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> --- CC: linux-kselftest(a)vger.kernel.org --- tools/testing/selftests/net/Makefile | 3 +- tools/testing/selftests/net/netlink-dumps.c | 129 ++++++++++++++++++++ 2 files changed, 130 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 5e86f7a51b43..c427ee32b193 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -78,7 +78,6 @@ TEST_PROGS += test_vxlan_vnifiltering.sh TEST_GEN_FILES += io_uring_zerocopy_tx TEST_PROGS += io_uring_zerocopy_tx.sh TEST_GEN_FILES += bind_bhash -TEST_GEN_PROGS += netlink-dumps TEST_GEN_PROGS += sk_bind_sendto_listen TEST_GEN_PROGS += sk_connect_zero_addr TEST_GEN_PROGS += sk_so_peek_off @@ -100,7 +99,7 @@ TEST_PROGS += bpf_offload.py # YNL files, must be before "include ..lib.mk" EXTRA_CLEAN += $(OUTPUT)/libynl.a -YNL_GEN_FILES := ncdevmem +YNL_GEN_FILES := ncdevmem netlink-dumps TEST_GEN_FILES += $(YNL_GEN_FILES) TEST_FILES := settings diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 7ee6dcd334df..195febbf6a61 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -12,11 +12,140 @@ #include <unistd.h> #include <linux/genetlink.h> +#include <linux/neighbour.h> +#include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/mqueue.h> +#include <linux/rtnetlink.h> #include "../kselftest_harness.h" +#include <ynl.h> + +struct ext_ack { + int err; + + __u32 attr_offs; + __u32 miss_type; + __u32 miss_nest; + const char *str; +}; + +/* 0: no done, 1: done found, 2: extack found, -1: error */ +static int nl_get_extack(char *buf, size_t n, struct ext_ack *ea) +{ + const struct nlmsghdr *nlh; + const struct nlattr *attr; + ssize_t rem; + + for (rem = n; rem > 0; NLMSG_NEXT(nlh, rem)) { + nlh = (struct nlmsghdr *)&buf[n - rem]; + if (!NLMSG_OK(nlh, rem)) + return -1; + + if (nlh->nlmsg_type != NLMSG_DONE) + continue; + + ea->err = -*(int *)NLMSG_DATA(nlh); + + if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS)) + return 1; + + ynl_attr_for_each(attr, nlh, sizeof(int)) { + switch (ynl_attr_type(attr)) { + case NLMSGERR_ATTR_OFFS: + ea->attr_offs = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_TYPE: + ea->miss_type = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MISS_NEST: + ea->miss_nest = ynl_attr_get_u32(attr); + break; + case NLMSGERR_ATTR_MSG: + ea->str = ynl_attr_get_str(attr); + break; + } + } + + return 2; + } + + return 0; +} + +static const struct { + struct nlmsghdr nlhdr; + struct ndmsg ndm; + struct nlattr ahdr; + __u32 val; +} dump_neigh_bad = { + .nlhdr = { + .nlmsg_len = sizeof(dump_neigh_bad), + .nlmsg_type = RTM_GETNEIGH, + .nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP, + .nlmsg_seq = 1, + }, + .ndm = { + .ndm_family = 123, + }, + .ahdr = { + .nla_len = 4 + 4, + .nla_type = NDA_FLAGS_EXT, + }, + .val = -1, // should fail MASK validation +}; + +TEST(dump_extack) +{ + int netlink_sock; + char buf[8192]; + int one = 1; + int i, cnt; + ssize_t n; + + netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + ASSERT_GE(netlink_sock, 0); + + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_CAP_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + n = setsockopt(netlink_sock, SOL_NETLINK, NETLINK_GET_STRICT_CHK, + &one, sizeof(one)); + ASSERT_EQ(n, 0); + + /* Dump so many times we fill up the buffer */ + cnt = 64; + for (i = 0; i < cnt; i++) { + n = send(netlink_sock, &dump_neigh_bad, + sizeof(dump_neigh_bad), 0); + ASSERT_EQ(n, sizeof(dump_neigh_bad)); + } + + /* Read out the ENOBUFS */ + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + EXPECT_EQ(n, -1); + EXPECT_EQ(errno, ENOBUFS); + + for (i = 0; i < cnt; i++) { + struct ext_ack ea = {}; + + n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT); + if (n < 0) { + ASSERT_GE(i, 10); + break; + } + ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr)); + + EXPECT_EQ(nl_get_extack(buf, n, &ea), 2); + EXPECT_EQ(ea.attr_offs, + sizeof(struct nlmsghdr) + sizeof(struct ndmsg)); + } +} + static const struct { struct nlmsghdr nlhdr; struct genlmsghdr genlhdr; -- 2.47.0

7 months, 2 weeks

1
0
0 0

[PATCH net-next v4 7/7] selftests: net: fdb_notify: Add a test for FDB notifications

by Petr Machata

Check that only one notification is produced for various FDB edit operations. Regarding the ip_link_add() and ip_link_master() helpers. This pattern of action plus corresponding defer is bound to come up often, and a dedicated vocabulary to capture it will be handy. tunnel_create() and vlan_create() from forwarding/lib.sh are somewhat opaque and perhaps too kitchen-sinky, so I tried to go in the opposite direction with these ones, and wrapped only the bare minimum to schedule a corresponding cleanup. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: v4: - Adjust the sleep around the FDB op --- CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/Makefile | 2 +- tools/testing/selftests/net/fdb_notify.sh | 96 +++++++++++++++++++++++ tools/testing/selftests/net/lib.sh | 17 ++++ 3 files changed, 114 insertions(+), 1 deletion(-) create mode 100755 tools/testing/selftests/net/fdb_notify.sh diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 2b2a5ec7fa6a..d1494700f501 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -92,7 +92,7 @@ TEST_PROGS += test_vxlan_mdb.sh TEST_PROGS += test_bridge_neigh_suppress.sh TEST_PROGS += test_vxlan_nolocalbypass.sh TEST_PROGS += test_bridge_backup_port.sh -TEST_PROGS += fdb_flush.sh +TEST_PROGS += fdb_flush.sh fdb_notify.sh TEST_PROGS += fq_band_pktlimit.sh TEST_PROGS += vlan_hw_filter.sh TEST_PROGS += bpf_offload.py diff --git a/tools/testing/selftests/net/fdb_notify.sh b/tools/testing/selftests/net/fdb_notify.sh new file mode 100755 index 000000000000..c03151e7791c --- /dev/null +++ b/tools/testing/selftests/net/fdb_notify.sh @@ -0,0 +1,96 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +source lib.sh + +ALL_TESTS=" + test_dup_bridge + test_dup_vxlan_self + test_dup_vxlan_master + test_dup_macvlan_self + test_dup_macvlan_master +" + +do_test_dup() +{ + local op=$1; shift + local what=$1; shift + local tmpf + + RET=0 + + tmpf=$(mktemp) + defer rm "$tmpf" + + defer_scope_push + bridge monitor fdb &> "$tmpf" & + defer kill_process $! + + sleep 0.5 + bridge fdb "$op" 00:11:22:33:44:55 vlan 1 "$@" + sleep 0.5 + defer_scope_pop + + local count=$(grep -c -e 00:11:22:33:44:55 $tmpf) + ((count == 1)) + check_err $? "Got $count notifications, expected 1" + + log_test "$what $op: Duplicate notifications" +} + +test_dup_bridge() +{ + ip_link_add br up type bridge vlan_filtering 1 + do_test_dup add "bridge" dev br self + do_test_dup del "bridge" dev br self +} + +test_dup_vxlan_self() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add vx up type vxlan id 2000 dstport 4789 + ip_link_master vx br + + do_test_dup add "vxlan" dev vx self dst 192.0.2.1 + do_test_dup del "vxlan" dev vx self dst 192.0.2.1 +} + +test_dup_vxlan_master() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add vx up type vxlan id 2000 dstport 4789 + ip_link_master vx br + + do_test_dup add "vxlan master" dev vx master + do_test_dup del "vxlan master" dev vx master +} + +test_dup_macvlan_self() +{ + ip_link_add dd up type dummy + ip_link_add mv up link dd type macvlan mode passthru + + do_test_dup add "macvlan self" dev mv self + do_test_dup del "macvlan self" dev mv self +} + +test_dup_macvlan_master() +{ + ip_link_add br up type bridge vlan_filtering 1 + ip_link_add dd up type dummy + ip_link_add mv up link dd type macvlan mode passthru + ip_link_master mv br + + do_test_dup add "macvlan master" dev mv self + do_test_dup del "macvlan master" dev mv self +} + +cleanup() +{ + defer_scopes_cleanup +} + +trap cleanup EXIT +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 24f63e45735d..8994fec1c38f 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -442,3 +442,20 @@ kill_process() # Suppress noise from killing the process. { kill $pid && wait $pid; } 2>/dev/null } + +ip_link_add() +{ + local name=$1; shift + + ip link add name "$name" "$@" + defer ip link del dev "$name" +} + +ip_link_master() +{ + local member=$1; shift + local master=$1; shift + + ip link set dev "$member" master "$master" + defer ip link set dev "$member" nomaster +} -- 2.45.0

7 months, 2 weeks

1
0
0 0

[PATCH net-next v4 6/7] selftests: net: lib: Add kill_process

by Petr Machata

A number of selftests run processes in the background and need to kill them afterwards. Instead for everyone to open-code the kill / wait / redirect mantra, add a helper in net/lib.sh. Convert existing open-code sites. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> CC: Andrew Lunn <andrew+netdev(a)lunn.ch> .../selftests/drivers/net/mlxsw/devlink_trap.sh | 2 +- .../drivers/net/mlxsw/devlink_trap_l3_drops.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_l3_exceptions.sh | 12 ++++++------ .../drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh | 4 ++-- .../drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh | 4 ++-- .../net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh | 4 ++-- .../testing/selftests/drivers/net/mlxsw/tc_sample.sh | 4 ++-- .../drivers/net/netdevsim/fib_notifications.sh | 6 +++--- tools/testing/selftests/net/drop_monitor_tests.sh | 2 +- tools/testing/selftests/net/fib_tests.sh | 8 ++++---- .../testing/selftests/net/forwarding/devlink_lib.sh | 2 +- tools/testing/selftests/net/forwarding/lib.sh | 3 +-- tools/testing/selftests/net/forwarding/tc_police.sh | 8 ++++---- tools/testing/selftests/net/lib.sh | 8 ++++++++ 15 files changed, 41 insertions(+), 34 deletions(-) diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh index 89b55e946eed..36055279ba92 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap.sh @@ -116,7 +116,7 @@ dev_del_test() log_test "Device delete" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid } trap cleanup EXIT diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh index 160891dcb4bc..db5806d189bb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_drops.sh @@ -595,7 +595,7 @@ irif_disabled_test() log_test "Ingress RIF disabled" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid ip link set dev $rp1 nomaster __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge @@ -645,7 +645,7 @@ erif_disabled_test() log_test "Egress RIF disabled" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid __addr_add_del $rp1 add 192.0.2.2/24 2001:db8:1::2/64 ip link del dev br0 type bridge devlink_trap_action_set $trap_name "drop" diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh index 190c1b6b5365..5d6d88b600f0 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_l3_exceptions.sh @@ -202,7 +202,7 @@ mtu_value_is_too_small_test() mtu_restore $rp2 - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower } @@ -235,7 +235,7 @@ __ttl_value_is_too_small_test() log_test "TTL value is too small: TTL=$ttl_val" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower } @@ -299,7 +299,7 @@ __mc_reverse_path_forwarding_test() log_test "Multicast reverse path forwarding: $desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $rp2 egress protocol $proto pref 1 handle 101 flower } @@ -347,7 +347,7 @@ __reject_route_test() log_test "Reject route: $desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid ip route del unreachable $unreachable tc filter del dev $h1 ingress protocol $proto pref 1 handle 101 flower } @@ -542,7 +542,7 @@ ipv4_lpm_miss_test() log_test "LPM miss: IPv4" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid vrf_without_routes_destroy } @@ -569,7 +569,7 @@ ipv6_lpm_miss_test() log_test "LPM miss: IPv6" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid vrf_without_routes_destroy } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh index e9a82cae8c9a..4ac1dae92d0f 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh @@ -176,7 +176,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } @@ -207,7 +207,7 @@ no_matching_tunnel_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh index 878125041fc3..fce885184404 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip6.sh @@ -176,7 +176,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } @@ -207,7 +207,7 @@ no_matching_tunnel_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh index 5f6eb965cfd1..7aca8e5922cf 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan.sh @@ -183,7 +183,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } @@ -253,7 +253,7 @@ corrupted_packet_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh index f6c16cbb6cf7..4599c331240b 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_vxlan_ipv6.sh @@ -188,7 +188,7 @@ ecn_decap_test() log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } @@ -262,7 +262,7 @@ corrupted_packet_test() log_test "$desc" - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower } diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh index 83a0210e7544..bc7ea2df49fb 100755 --- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh +++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh @@ -218,7 +218,7 @@ psample_capture_start() psample_capture_stop() { - { kill %% && wait %%; } 2>/dev/null + kill_process %% } __tc_sample_rate_test() @@ -499,7 +499,7 @@ tc_sample_md_out_tc_occ_test() backlog=$(tc -j -p -s qdisc show dev $rp2 | jq '.[0]["backlog"]') # Kill mausezahn. - { kill %% && wait %%; } 2>/dev/null + kill_process %% psample_capture_stop diff --git a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh index 8d91191a098c..9896580c3d85 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/fib_notifications.sh @@ -94,7 +94,7 @@ route_addition_check() sleep 1 $IP route add $route dev dummy1 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications $offload_failed rm -f $outfile @@ -148,7 +148,7 @@ route_deletion_check() sleep 1 $IP route del $route dev dummy1 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications rm -f $outfile @@ -191,7 +191,7 @@ route_replacement_check() sleep 1 $IP route replace $route dev dummy2 sleep 1 - kill %% && wait %% &> /dev/null + kill_process %% route_notify_check $outfile $expected_num_notifications rm -f $outfile diff --git a/tools/testing/selftests/net/drop_monitor_tests.sh b/tools/testing/selftests/net/drop_monitor_tests.sh index 7c4818c971fc..507d0a82f5f0 100755 --- a/tools/testing/selftests/net/drop_monitor_tests.sh +++ b/tools/testing/selftests/net/drop_monitor_tests.sh @@ -77,7 +77,7 @@ sw_drops_test() rm ${dir}/packets.pcap - { kill %% && wait %%; } 2>/dev/null + kill_process %% timeout 5 dwdump -o sw -w ${dir}/packets.pcap (( $(tshark -r ${dir}/packets.pcap \ -Y 'ip.dst == 192.0.2.10' 2> /dev/null | wc -l) == 0)) diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 5f3c28fc8624..3ea6f886a210 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -689,7 +689,7 @@ fib6_notify_test() log_test $ret 0 "ipv6 route add notify" - { kill %% && wait %%; } 2>/dev/null + kill_process %% #rm errors.txt @@ -736,7 +736,7 @@ fib_notify_test() log_test $ret 0 "ipv4 route add notify" - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm errors.txt @@ -2328,7 +2328,7 @@ ipv4_mangle_test() $IP route del table 123 172.16.101.0/24 dev veth1 $IP rule del pref 100 - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm $tmp_file route_cleanup @@ -2386,7 +2386,7 @@ ipv6_mangle_test() $IP -6 route del table 123 2001:db8:101::/64 dev veth1 $IP -6 rule del pref 100 - { kill %% && wait %%; } 2>/dev/null + kill_process %% rm $tmp_file route_cleanup diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh index 62a05bca1e82..18afa89ebbcc 100644 --- a/tools/testing/selftests/net/forwarding/devlink_lib.sh +++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh @@ -501,7 +501,7 @@ devlink_trap_drop_cleanup() local pref=$1; shift local handle=$1; shift - kill $mz_pid && wait $mz_pid &> /dev/null + kill_process $mz_pid tc filter del dev $dev egress protocol $proto pref $pref handle $handle flower } diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 8625e3c99f55..7337f398f9cc 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1574,8 +1574,7 @@ stop_traffic() { local pid=${1-%%}; shift - # Suppress noise from killing mausezahn. - { kill $pid && wait $pid; } 2>/dev/null + kill_process "$pid" } declare -A cappid diff --git a/tools/testing/selftests/net/forwarding/tc_police.sh b/tools/testing/selftests/net/forwarding/tc_police.sh index 5103f64a71d6..509fdedfcfa1 100755 --- a/tools/testing/selftests/net/forwarding/tc_police.sh +++ b/tools/testing/selftests/net/forwarding/tc_police.sh @@ -148,7 +148,7 @@ police_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower } @@ -198,7 +198,7 @@ police_shared_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% } police_shared_test() @@ -278,7 +278,7 @@ police_mirror_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $pol_if $dir protocol ip pref 1 handle 101 flower tc filter del dev $h3 ingress protocol ip pref 1 handle 101 flower tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower @@ -320,7 +320,7 @@ police_pps_common_test() log_test "$test_name" - { kill %% && wait %%; } 2>/dev/null + kill_process %% tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower } diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 6bcf5d13879d..24f63e45735d 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -434,3 +434,11 @@ xfail_on_veth() "$@" fi } + +kill_process() +{ + local pid=$1; shift + + # Suppress noise from killing the process. + { kill $pid && wait $pid; } 2>/dev/null +} -- 2.45.0

7 months, 2 weeks

1
0
0 0

[PATCH net-next v4 5/7] selftests: net: lib: Move checks from forwarding/lib.sh here

by Petr Machata

For logging to be useful, something has to set RET and retmsg by calling ret_set_ksft_status(). There is a suite of functions to that end in forwarding/lib: check_err, check_fail et.al. Move them to net/lib.sh so that every net test can use them. Existing lib.sh users might be using these same names for their functions. However lib.sh is always sourced near the top of the file (checked), and whatever new definitions will simply override the ones provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 73 ------------------- tools/testing/selftests/net/lib.sh | 73 +++++++++++++++++++ 2 files changed, 73 insertions(+), 73 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index d28dbf27c1f0..8625e3c99f55 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -445,79 +445,6 @@ done ############################################################################## # Helpers -# Whether FAILs should be interpreted as XFAILs. Internal. -FAIL_TO_XFAIL= - -check_err() -{ - local err=$1 - local msg=$2 - - if ((err)); then - if [[ $FAIL_TO_XFAIL = yes ]]; then - ret_set_ksft_status $ksft_xfail "$msg" - else - ret_set_ksft_status $ksft_fail "$msg" - fi - fi -} - -check_fail() -{ - local err=$1 - local msg=$2 - - check_err $((!err)) "$msg" -} - -check_err_fail() -{ - local should_fail=$1; shift - local err=$1; shift - local what=$1; shift - - if ((should_fail)); then - check_fail $err "$what succeeded, but should have failed" - else - check_err $err "$what failed" - fi -} - -xfail() -{ - FAIL_TO_XFAIL=yes "$@" -} - -xfail_on_slow() -{ - if [[ $KSFT_MACHINE_SLOW = yes ]]; then - FAIL_TO_XFAIL=yes "$@" - else - "$@" - fi -} - -omit_on_slow() -{ - if [[ $KSFT_MACHINE_SLOW != yes ]]; then - "$@" - fi -} - -xfail_on_veth() -{ - local dev=$1; shift - local kind - - kind=$(ip -j -d link show dev $dev | - jq -r '.[].linkinfo.info_kind') - if [[ $kind = veth ]]; then - FAIL_TO_XFAIL=yes "$@" - else - "$@" - fi -} - not() { "$@" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 4f52b8e48a3a..6bcf5d13879d 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -361,3 +361,76 @@ tests_run() $current_test done } + +# Whether FAILs should be interpreted as XFAILs. Internal. +FAIL_TO_XFAIL= + +check_err() +{ + local err=$1 + local msg=$2 + + if ((err)); then + if [[ $FAIL_TO_XFAIL = yes ]]; then + ret_set_ksft_status $ksft_xfail "$msg" + else + ret_set_ksft_status $ksft_fail "$msg" + fi + fi +} + +check_fail() +{ + local err=$1 + local msg=$2 + + check_err $((!err)) "$msg" +} + +check_err_fail() +{ + local should_fail=$1; shift + local err=$1; shift + local what=$1; shift + + if ((should_fail)); then + check_fail $err "$what succeeded, but should have failed" + else + check_err $err "$what failed" + fi +} + +xfail() +{ + FAIL_TO_XFAIL=yes "$@" +} + +xfail_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW = yes ]]; then + FAIL_TO_XFAIL=yes "$@" + else + "$@" + fi +} + +omit_on_slow() +{ + if [[ $KSFT_MACHINE_SLOW != yes ]]; then + "$@" + fi +} + +xfail_on_veth() +{ + local dev=$1; shift + local kind + + kind=$(ip -j -d link show dev $dev | + jq -r '.[].linkinfo.info_kind') + if [[ $kind = veth ]]; then + FAIL_TO_XFAIL=yes "$@" + else + "$@" + fi +} -- 2.45.0

7 months, 2 weeks

1
0
0 0

[PATCH net-next v4 4/7] selftests: net: lib: Move tests_run from forwarding/lib.sh here

by Petr Machata

It would be good to use the same mechanism for scheduling and dispatching general net tests as the many forwarding tests already use. To that end, move the logging helpers to net/lib.sh so that every net test can use them. Existing lib.sh users might be using the name themselves. However lib.sh is always sourced near the top of the file (checked), and whatever new definition will simply override the one provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 10 ---------- tools/testing/selftests/net/lib.sh | 10 ++++++++++ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 41dd14c42c48..d28dbf27c1f0 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -1285,16 +1285,6 @@ matchall_sink_create() action drop } -tests_run() -{ - local current_test - - for current_test in ${TESTS:-$ALL_TESTS}; do - in_defer_scope \ - $current_test - done -} - cleanup() { pre_cleanup diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 691318b1ec55..4f52b8e48a3a 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -351,3 +351,13 @@ log_info() echo "INFO: $msg" } + +tests_run() +{ + local current_test + + for current_test in ${TESTS:-$ALL_TESTS}; do + in_defer_scope \ + $current_test + done +} -- 2.45.0

7 months, 2 weeks

1
0
0 0

[PATCH net-next v4 3/7] selftests: net: lib: Move logging from forwarding/lib.sh here

by Petr Machata

Many net selftests invent their own logging helpers. These really should be in a library sourced by these tests. Currently forwarding/lib.sh has a suite of perfectly fine logging helpers, but sourcing a forwarding/ library from a higher-level directory smells of layering violation. In this patch, move the logging helpers to net/lib.sh so that every net test can use them. Together with the logging helpers, it's also necessary to move pause_on_fail(), and EXIT_STATUS and RET. Existing lib.sh users might be using these same names for their functions or variables. However lib.sh is always sourced near the top of the file (checked), and whatever new definitions will simply override the ones provided by lib.sh. Signed-off-by: Petr Machata <petrm(a)nvidia.com> Reviewed-by: Amit Cohen <amcohen(a)nvidia.com> Acked-by: Shuah Khan <skhan(a)linuxfoundation.org> --- Notes: CC: Shuah Khan <shuah(a)kernel.org> CC: Benjamin Poirier <bpoirier(a)nvidia.com> CC: Hangbin Liu <liuhangbin(a)gmail.com> CC: linux-kselftest(a)vger.kernel.org CC: Jiri Pirko <jiri(a)resnulli.us> tools/testing/selftests/net/forwarding/lib.sh | 113 ----------------- tools/testing/selftests/net/lib.sh | 115 ++++++++++++++++++ 2 files changed, 115 insertions(+), 113 deletions(-) diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 89c25f72b10c..41dd14c42c48 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -48,7 +48,6 @@ declare -A NETIFS=( : "${WAIT_TIME:=5}" # Whether to pause on, respectively, after a failure and before cleanup. -: "${PAUSE_ON_FAIL:=no}" : "${PAUSE_ON_CLEANUP:=no}" # Whether to create virtual interfaces, and what netdevice type they should be. @@ -446,22 +445,6 @@ done ############################################################################## # Helpers -# Exit status to return at the end. Set in case one of the tests fails. -EXIT_STATUS=0 -# Per-test return value. Clear at the beginning of each test. -RET=0 - -ret_set_ksft_status() -{ - local ksft_status=$1; shift - local msg=$1; shift - - RET=$(ksft_status_merge $RET $ksft_status) - if (( $? )); then - retmsg=$msg - fi -} - # Whether FAILs should be interpreted as XFAILs. Internal. FAIL_TO_XFAIL= @@ -535,102 +518,6 @@ xfail_on_veth() fi } -log_test_result() -{ - local test_name=$1; shift - local opt_str=$1; shift - local result=$1; shift - local retmsg=$1; shift - - printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" - if [[ $retmsg ]]; then - printf "\t%s\n" "$retmsg" - fi -} - -pause_on_fail() -{ - if [[ $PAUSE_ON_FAIL == yes ]]; then - echo "Hit enter to continue, 'q' to quit" - read a - [[ $a == q ]] && exit 1 - fi -} - -handle_test_result_pass() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" " OK " -} - -handle_test_result_fail() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" FAIL "$retmsg" - pause_on_fail -} - -handle_test_result_xfail() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" - pause_on_fail -} - -handle_test_result_skip() -{ - local test_name=$1; shift - local opt_str=$1; shift - - log_test_result "$test_name" "$opt_str" SKIP "$retmsg" -} - -log_test() -{ - local test_name=$1 - local opt_str=$2 - - if [[ $# -eq 2 ]]; then - opt_str="($opt_str)" - fi - - if ((RET == ksft_pass)); then - handle_test_result_pass "$test_name" "$opt_str" - elif ((RET == ksft_xfail)); then - handle_test_result_xfail "$test_name" "$opt_str" - elif ((RET == ksft_skip)); then - handle_test_result_skip "$test_name" "$opt_str" - else - handle_test_result_fail "$test_name" "$opt_str" - fi - - EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) - return $RET -} - -log_test_skip() -{ - RET=$ksft_skip retmsg= log_test "$@" -} - -log_test_xfail() -{ - RET=$ksft_xfail retmsg= log_test "$@" -} - -log_info() -{ - local msg=$1 - - echo "INFO: $msg" -} - not() { "$@" diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index c8991cc6bf28..691318b1ec55 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -9,6 +9,9 @@ source "$net_dir/lib/sh/defer.sh" : "${WAIT_TIMEOUT:=20}" +# Whether to pause on after a failure. +: "${PAUSE_ON_FAIL:=no}" + BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms # Kselftest framework constants. @@ -20,6 +23,11 @@ ksft_skip=4 # namespace list created by setup_ns NS_LIST=() +# Exit status to return at the end. Set in case one of the tests fails. +EXIT_STATUS=0 +# Per-test return value. Clear at the beginning of each test. +RET=0 + ############################################################################## # Helpers @@ -236,3 +244,110 @@ tc_rule_handle_stats_get() | jq ".[] | select(.options.handle == $handle) | \ .options.actions[0].stats$selector" } + +ret_set_ksft_status() +{ + local ksft_status=$1; shift + local msg=$1; shift + + RET=$(ksft_status_merge $RET $ksft_status) + if (( $? )); then + retmsg=$msg + fi +} + +log_test_result() +{ + local test_name=$1; shift + local opt_str=$1; shift + local result=$1; shift + local retmsg=$1; shift + + printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" + if [[ $retmsg ]]; then + printf "\t%s\n" "$retmsg" + fi +} + +pause_on_fail() +{ + if [[ $PAUSE_ON_FAIL == yes ]]; then + echo "Hit enter to continue, 'q' to quit" + read a + [[ $a == q ]] && exit 1 + fi +} + +handle_test_result_pass() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" " OK " +} + +handle_test_result_fail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" FAIL "$retmsg" + pause_on_fail +} + +handle_test_result_xfail() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" XFAIL "$retmsg" + pause_on_fail +} + +handle_test_result_skip() +{ + local test_name=$1; shift + local opt_str=$1; shift + + log_test_result "$test_name" "$opt_str" SKIP "$retmsg" +} + +log_test() +{ + local test_name=$1 + local opt_str=$2 + + if [[ $# -eq 2 ]]; then + opt_str="($opt_str)" + fi + + if ((RET == ksft_pass)); then + handle_test_result_pass "$test_name" "$opt_str" + elif ((RET == ksft_xfail)); then + handle_test_result_xfail "$test_name" "$opt_str" + elif ((RET == ksft_skip)); then + handle_test_result_skip "$test_name" "$opt_str" + else + handle_test_result_fail "$test_name" "$opt_str" + fi + + EXIT_STATUS=$(ksft_exit_status_merge $EXIT_STATUS $RET) + return $RET +} + +log_test_skip() +{ + RET=$ksft_skip retmsg= log_test "$@" +} + +log_test_xfail() +{ + RET=$ksft_xfail retmsg= log_test "$@" +} + +log_info() +{ + local msg=$1 + + echo "INFO: $msg" +} -- 2.45.0

7 months, 2 weeks

1
0
0 0

[PATCH net-next v1 08/10] mm: page_frag: add testing for the newly added API

by Yunsheng Lin

Add testing for the newly added prepare API, for both aligned and non-aligned API, also probe API is also tested along with prepare API. CC: Alexander Duyck <alexander.duyck(a)gmail.com> CC: Andrew Morton <akpm(a)linux-foundation.org> CC: Linux-MM <linux-mm(a)kvack.org> Signed-off-by: Yunsheng Lin <linyunsheng(a)huawei.com> --- .../selftests/mm/page_frag/page_frag_test.c | 76 +++++++++++++++++-- tools/testing/selftests/mm/run_vmtests.sh | 4 + tools/testing/selftests/mm/test_page_frag.sh | 27 +++++++ 3 files changed, 102 insertions(+), 5 deletions(-) diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c index e806c1866e36..3b3c32389def 100644 --- a/tools/testing/selftests/mm/page_frag/page_frag_test.c +++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c @@ -32,6 +32,10 @@ static bool test_align; module_param(test_align, bool, 0); MODULE_PARM_DESC(test_align, "use align API for testing"); +static bool test_prepare; +module_param(test_prepare, bool, 0); +MODULE_PARM_DESC(test_prepare, "use prepare API for testing"); + static int test_alloc_len = 2048; module_param(test_alloc_len, int, 0); MODULE_PARM_DESC(test_alloc_len, "alloc len for testing"); @@ -74,6 +78,21 @@ static int page_frag_pop_thread(void *arg) return 0; } +static void frag_frag_test_commit(struct page_frag_cache *nc, + struct page_frag *prepare_pfrag, + struct page_frag *probe_pfrag, + unsigned int used_sz) +{ + if (prepare_pfrag->page != probe_pfrag->page || + prepare_pfrag->offset != probe_pfrag->offset || + prepare_pfrag->size != probe_pfrag->size) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "wrong probed info\n"); + } + + page_frag_refill_commit(nc, prepare_pfrag, used_sz); +} + static int page_frag_push_thread(void *arg) { struct ptr_ring *ring = arg; @@ -86,15 +105,61 @@ static int page_frag_push_thread(void *arg) int ret; if (test_align) { - va = page_frag_alloc_align(&test_nc, test_alloc_len, - GFP_KERNEL, SMP_CACHE_BYTES); + if (test_prepare) { + struct page_frag prepare_frag, probe_frag; + void *probe_va; + + va = page_frag_alloc_refill_prepare_align(&test_nc, + test_alloc_len, + &prepare_frag, + GFP_KERNEL, + SMP_CACHE_BYTES); + + probe_va = __page_frag_alloc_refill_probe_align(&test_nc, + test_alloc_len, + &probe_frag, + -SMP_CACHE_BYTES); + if (va != probe_va) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "wrong va\n"); + } + + if (likely(va)) + frag_frag_test_commit(&test_nc, &prepare_frag, + &probe_frag, test_alloc_len); + } else { + va = page_frag_alloc_align(&test_nc, + test_alloc_len, + GFP_KERNEL, + SMP_CACHE_BYTES); + } if ((unsigned long)va & (SMP_CACHE_BYTES - 1)) { force_exit = true; WARN_ONCE(true, TEST_FAILED_PREFIX "unaligned va returned\n"); } } else { - va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + if (test_prepare) { + struct page_frag prepare_frag, probe_frag; + void *probe_va; + + va = page_frag_alloc_refill_prepare(&test_nc, test_alloc_len, + &prepare_frag, GFP_KERNEL); + + probe_va = page_frag_alloc_refill_probe(&test_nc, test_alloc_len, + &probe_frag); + + if (va != probe_va) { + force_exit = true; + WARN_ONCE(true, TEST_FAILED_PREFIX "wrong va\n"); + } + + if (likely(va)) + frag_frag_test_commit(&test_nc, &prepare_frag, + &probe_frag, test_alloc_len); + } else { + va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL); + } } if (!va) @@ -176,8 +241,9 @@ static int __init page_frag_test_init(void) } duration = (u64)ktime_us_delta(ktime_get(), start); - pr_info("%d of iterations for %s testing took: %lluus\n", nr_test, - test_align ? "aligned" : "non-aligned", duration); + pr_info("%d of iterations for %s %s API testing took: %lluus\n", nr_test, + test_align ? "aligned" : "non-aligned", + test_prepare ? "prepare" : "alloc", duration); out: ptr_ring_cleanup(&ptr_ring, NULL); diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 2c5394584af4..f6ff9080a6f2 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -464,6 +464,10 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned +CATEGORY="page_frag" run_test ./test_page_frag.sh aligned_prepare + +CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned_prepare + echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix echo "1..${count_total}" | tap_output diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh index f55b105084cf..1c757fd11844 100755 --- a/tools/testing/selftests/mm/test_page_frag.sh +++ b/tools/testing/selftests/mm/test_page_frag.sh @@ -43,6 +43,8 @@ check_test_failed_prefix() { SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1" NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST" ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1" +NONALIGNED_PREPARE_PARAM="$NONALIGNED_PARAM test_prepare=1" +ALIGNED_PREPARE_PARAM="$ALIGNED_PARAM test_prepare=1" check_test_requirements() { @@ -77,6 +79,20 @@ run_aligned_check() insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1 } +run_nonaligned_prepare_check() +{ + echo "Run performance tests to evaluate how fast nonaligned prepare API is." + + insmod $DRIVER $NONALIGNED_PREPARE_PARAM > /dev/null 2>&1 +} + +run_aligned_prepare_check() +{ + echo "Run performance tests to evaluate how fast aligned prepare API is." + + insmod $DRIVER $ALIGNED_PREPARE_PARAM > /dev/null 2>&1 +} + run_smoke_check() { echo "Run smoke test." @@ -87,6 +103,7 @@ run_smoke_check() usage() { echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | " + echo "[ aligned_prepare ] | [ nonaligned_prepare ] | " echo "manual parameters" echo echo "Valid tests and parameters:" @@ -107,6 +124,12 @@ usage() echo "# Performance testing for aligned alloc API" echo "$0 aligned" echo + echo "# Performance testing for nonaligned prepare API" + echo "$0 nonaligned_prepare" + echo + echo "# Performance testing for aligned prepare API" + echo "$0 aligned_prepare" + echo exit 0 } @@ -158,6 +181,10 @@ function run_test() run_nonaligned_check elif [[ "$1" = "aligned" ]]; then run_aligned_check + elif [[ "$1" = "nonaligned_prepare" ]]; then + run_nonaligned_prepare_check + elif [[ "$1" = "aligned_prepare" ]]; then + run_aligned_prepare_check else run_manual_check $@ fi -- 2.33.0

7 months, 2 weeks

1
0
0 0

[PATCH] net/unix: pass pidfd flags via SCM_PIDFD cmsg

by Stas Sergeev

Currently SCM_PIDFD cmsg cannot be sent via unix socket (returns -EINVAL) and SO_PASSPIDFD doesn't support flags. The created pidfd always has flags set to 0. This patch implements SCM_PIDFD cmsg in AF_UNIX socket, which can be used to send flags to SO_PASSPIDFD-enabled recipient. Self-test is added for the propagation of PIDFD_NONBLOCK flag. This is mainly needed for the future extensions, like eg this one: https://lore.kernel.org/lkml/8288a08e-448b-43c2-82dc-59f87d0d9072@yandex.ru… where it was suggested to try solving the supplementary groups problem with pidfd. Signed-off-by: Stas Sergeev <stsp2(a)yandex.ru> CC: "David S. Miller" <davem(a)davemloft.net> CC: Eric Dumazet <edumazet(a)google.com> CC: Jakub Kicinski <kuba(a)kernel.org> CC: Paolo Abeni <pabeni(a)redhat.com> CC: Simon Horman <horms(a)kernel.org> CC: Shuah Khan <shuah(a)kernel.org> CC: Christian Brauner <brauner(a)kernel.org> CC: Jens Axboe <axboe(a)kernel.dk> CC: Willem de Bruijn <willemb(a)google.com> CC: Pavel Begunkov <asml.silence(a)gmail.com> CC: Gabriel Krisman Bertazi <krisman(a)suse.de> CC: Mina Almasry <almasrymina(a)google.com> CC: Oleg Nesterov <oleg(a)redhat.com> CC: Tycho Andersen <tandersen(a)netflix.com> CC: Al Viro <viro(a)zeniv.linux.org.uk> CC: Kuniyuki Iwashima <kuniyu(a)amazon.com> CC: Gou Hao <gouhao(a)uniontech.com> CC: Abhishek Chauhan <quic_abchauha(a)quicinc.com> CC: Michal Luczaj <mhal(a)rbox.co> CC: Kees Cook <kees(a)kernel.org> CC: linux-kernel(a)vger.kernel.org CC: netdev(a)vger.kernel.org CC: linux-kselftest(a)vger.kernel.org --- include/linux/pidfs.h | 9 +++ include/linux/socket.h | 2 +- include/net/af_unix.h | 1 + include/net/scm.h | 10 ++- kernel/pid.c | 6 +- net/core/scm.c | 14 ++++ net/core/sock.c | 1 + net/unix/af_unix.c | 3 + .../testing/selftests/net/af_unix/scm_pidfd.c | 70 +++++++++++++++++-- 9 files changed, 106 insertions(+), 10 deletions(-) diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h index 75bdf9807802..c4c5c1a0c2ad 100644 --- a/include/linux/pidfs.h +++ b/include/linux/pidfs.h @@ -2,7 +2,16 @@ #ifndef _LINUX_PID_FS_H #define _LINUX_PID_FS_H +#include <uapi/linux/pidfd.h> + struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); void __init pidfs_init(void); +static inline int pidfd_validate_flags(unsigned int flags) +{ + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) + return -EINVAL; + return 0; +} + #endif /* _LINUX_PID_FS_H */ diff --git a/include/linux/socket.h b/include/linux/socket.h index d18cc47e89bd..ee27d391e5aa 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -178,7 +178,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ -#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ +#define SCM_PIDFD 0x04 /* r: pidfd, w: pidfd_flags (int) */ struct ucred { __u32 pid; diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 63129c79b8cb..4bc197548c2f 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -62,6 +62,7 @@ struct unix_skb_parms { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ #endif + u32 pidfd_flags; u32 consumed; } __randomize_layout; diff --git a/include/net/scm.h b/include/net/scm.h index 0d35c7c77a74..bc64d516b226 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -8,6 +8,7 @@ #include <linux/file.h> #include <linux/security.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/sched/signal.h> #include <net/compat.h> @@ -48,6 +49,7 @@ struct scm_cookie { #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Passed security ID */ #endif + u32 pidfd_flags; }; void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm); @@ -137,6 +139,7 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm { struct file *pidfd_file = NULL; int len, pidfd; + int err; /* put_cmsg() doesn't return an error if CMSG is truncated, * that's why we need to opencode these checks here. @@ -154,7 +157,12 @@ static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm if (!scm->pid) return; - pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + err = pidfd_validate_flags(scm->pidfd_flags); + if (err) { + msg->msg_flags |= MSG_CTRUNC; + return; + } + pidfd = pidfd_prepare(scm->pid, scm->pidfd_flags, &pidfd_file); if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { if (pidfd_file) { diff --git a/kernel/pid.c b/kernel/pid.c index 2715afb77eab..b1100ae8ea63 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -629,10 +629,12 @@ static int pidfd_create(struct pid *pid, unsigned int flags) SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) { int fd; + int err; struct pid *p; - if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) - return -EINVAL; + err = pidfd_validate_flags(flags); + if (err) + return err; if (pid <= 0) return -EINVAL; diff --git a/net/core/scm.c b/net/core/scm.c index 4f6a14babe5a..3bcdecdacd7e 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -23,6 +23,7 @@ #include <linux/security.h> #include <linux/pid_namespace.h> #include <linux/pid.h> +#include <linux/pidfs.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/errqueue.h> @@ -210,6 +211,19 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) p->creds.gid = gid; break; } + case SCM_PIDFD: + { + unsigned int flags; + + if (cmsg->cmsg_len != CMSG_LEN(sizeof(flags))) + goto error; + memcpy(&flags, CMSG_DATA(cmsg), sizeof(flags)); + err = pidfd_validate_flags(flags); + if (err) + goto error; + p->pidfd_flags = flags; + break; + } default: goto error; } diff --git a/net/core/sock.c b/net/core/sock.c index 039be95c40cf..d1fce437c035 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2930,6 +2930,7 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg, /* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */ case SCM_RIGHTS: case SCM_CREDENTIALS: + case SCM_PIDFD: break; default: return -EINVAL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 001ccc55ef0f..8b19dfec0221 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1892,6 +1892,7 @@ static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool sen UNIXCB(skb).uid = scm->creds.uid; UNIXCB(skb).gid = scm->creds.gid; UNIXCB(skb).fp = NULL; + UNIXCB(skb).pidfd_flags = scm->pidfd_flags; unix_get_secdata(scm, skb); if (scm->fp && send_fds) err = unix_attach_fds(scm, skb); @@ -2486,6 +2487,7 @@ int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, memset(&scm, 0, sizeof(scm)); scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); if (!(flags & MSG_PEEK)) { @@ -2873,6 +2875,7 @@ static int unix_stream_read_generic(struct unix_stream_read_state *state, test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); + scm.pidfd_flags = UNIXCB(skb).pidfd_flags; unix_set_secdata(&scm, skb); check_creds = true; } diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..1e70ff253a1d 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -5,6 +5,7 @@ #include <stddef.h> #include <stdio.h> #include <stdlib.h> +#include <fcntl.h> #include <sys/socket.h> #include <linux/socket.h> #include <unistd.h> @@ -15,6 +16,11 @@ #include <sys/types.h> #include <sys/wait.h> +/* There are problems including linux/pidfd.h, so define. */ +#ifndef PIDFD_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#endif + #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -126,7 +132,7 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } -static int cmsg_check(int fd) +static int cmsg_check(int fd, unsigned int pidfd_flags) { struct msghdr msg = { 0 }; struct cmsghdr *cmsg; @@ -136,6 +142,7 @@ static int cmsg_check(int fd) char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; int *pidfd = NULL; + unsigned int flags; pid_t parent_pid; int err; @@ -197,6 +204,13 @@ static int cmsg_check(int fd) return 1; } + flags = fcntl(*pidfd, F_GETFL, 0); + flags &= ~O_ACCMODE; + if (flags != pidfd_flags) { + log_err("SCM_PIDFD flags mismatch: %x != %x", flags, pidfd_flags); + return 1; + } + /* pidfd from SCM_PIDFD should point to the parent process PID */ parent_pid = get_pid_from_fdinfo_file(*pidfd, "Pid:", sizeof("Pid:") - 1); @@ -227,30 +241,49 @@ FIXTURE_VARIANT(scm_pidfd) { int type; bool abstract; + unsigned int flags; }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_pathname) { .type = SOCK_STREAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, stream_abstract) { .type = SOCK_STREAM, .abstract = 1, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_pathname) { .type = SOCK_DGRAM, .abstract = 0, + .flags = 0, }; FIXTURE_VARIANT_ADD(scm_pidfd, dgram_abstract) { .type = SOCK_DGRAM, .abstract = 1, + .flags = 0, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, stream_nonblock) +{ + .type = SOCK_STREAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, +}; + +FIXTURE_VARIANT_ADD(scm_pidfd, dgram_nonblock) +{ + .type = SOCK_DGRAM, + .abstract = 0, + .flags = PIDFD_NONBLOCK, }; FIXTURE_SETUP(scm_pidfd) @@ -335,7 +368,7 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, close(self->startup_pipe[1]); - if (cmsg_check(cfd)) { + if (cmsg_check(cfd, variant->flags)) { log_err("cmsg_check failed"); child_die(); } @@ -375,6 +408,27 @@ TEST_F(scm_pidfd, test) int err; int pfd; int child_status = 0; + char iobuf; + unsigned int pidfd_flags; + struct msghdr msg = { 0 }; + struct cmsghdr *cmsg; + struct iovec io = { + .iov_base = &iobuf, + .iov_len = sizeof(iobuf) + }; + union { + char buf[CMSG_SPACE(sizeof(pidfd_flags))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_PIDFD; + cmsg->cmsg_len = CMSG_LEN(sizeof(pidfd_flags)); self->server = socket(AF_UNIX, variant->type, 0); ASSERT_NE(-1, self->server); @@ -414,12 +468,16 @@ TEST_F(scm_pidfd, test) close(self->startup_pipe[0]); if (variant->type == SOCK_DGRAM) { - err = sendto(pfd, "x", sizeof(char), 0, (struct sockaddr *)&self->client_addr->listen_addr, self->client_addr->addrlen); - ASSERT_NE(-1, err); - } else { - err = send(pfd, "x", sizeof(char), 0); + err = connect(pfd, + (struct sockaddr *)&self->client_addr->listen_addr, + self->client_addr->addrlen); ASSERT_NE(-1, err); } + iobuf = 'x'; + pidfd_flags = variant->flags; + memcpy(CMSG_DATA(cmsg), &pidfd_flags, sizeof(pidfd_flags)); + err = sendmsg(pfd, &msg, 0); + ASSERT_NE(-1, err); close(pfd); waitpid(self->client_pid, &child_status, 0); -- 2.47.0

7 months, 2 weeks

3
2
0 0

[PATCH bpf-next 00/10] selftests/bpf: migrate test_flow_dissector.sh to test_progs

by Alexis Lothoré (eBPF Foundation)

Hello, this new series aims to migrate test_flow_dissector.sh into test_progs. There are 2 "main" parts in test_flow_dissector.sh: - a set of tests checking flow_dissector programs attachment to either root namespace or non-root namespace - dissection test The first set is integrated in flow_dissector.c, which already contains some existing tests for flow_dissector programs. This series uses the opportunity to update a bit this file (use new assert, re-split tests, etc) The second part is migrated into a new file under test_progs, flow_dissector_classification.c. It uses the same eBPF programs as flow_dissector.c, but the difference is rather about how those program are executed: - flow_dissector.c manually runs programs with BPF_PROG_RUN - flow_dissector_classification.c sends real packets to be dissected, and so it also executes kernel code related to eBPF flow dissector (eg: __skb_flow_bpf_to_target) --- Alexis Lothoré (eBPF Foundation) (10): selftests/bpf: add a macro to compare raw memory selftests/bpf: use ASSERT_MEMEQ to compare bpf flow keys selftests/bpf: replace CHECK calls with ASSERT macros in flow_dissector test selftests/bpf: re-split main function into dedicated tests selftests/bpf: expose all subtests from flow_dissector selftests/bpf: add gre packets testing to flow_dissector selftests/bpf: migrate flow_dissector namespace exclusivity test selftests/bpf: Enable generic tc actions in selftests config selftests/bpf: migrate bpf flow dissectors tests to test_progs selftests/bpf: remove test_flow_dissector.sh tools/testing/selftests/bpf/.gitignore | 1 - tools/testing/selftests/bpf/Makefile | 3 +- tools/testing/selftests/bpf/config | 1 + .../selftests/bpf/prog_tests/flow_dissector.c | 307 ++++++-- .../bpf/prog_tests/flow_dissector_classification.c | 851 +++++++++++++++++++++ tools/testing/selftests/bpf/test_flow_dissector.c | 780 ------------------- tools/testing/selftests/bpf/test_flow_dissector.sh | 178 ----- tools/testing/selftests/bpf/test_progs.h | 25 + 8 files changed, 1107 insertions(+), 1039 deletions(-) --- base-commit: 16e1d1c377aa4c56223701a31f3bfa88505e7e4f change-id: 20241019-flow_dissector-3eb0c07fc163 Best regards, -- Alexis Lothoré, Bootlin Embedded Linux and Kernel engineering https://bootlin.com

7 months, 2 weeks

3
24
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror