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

[PATCH v4] selftests/mm: add process_madvise() tests

by wang lian

Add tests for process_madvise(), focusing on verifying behavior under various conditions including valid usage and error cases. Signed-off-by: wang lian <lianux.mm(a)gmail.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Suggested-by: Zi Yan <ziy(a)nvidia.com> Acked-by: SeongJae Park <sj(a)kernel.org> --- Changelog v4: - Refine resource cleanup logic in test teardown to be more robust. - Improve remote_collapse test to correctly handle different THP (Transparent Huge Page) policies ('always', 'madvise', 'never'), including handling race conditions with khugepaged. - Resolve build errors Changelog v3: https://lore.kernel.org/lkml/20250703044326.65061-1-lianux.mm@gmail.com/ - Rebased onto the latest mm-stable branch to ensure clean application. - Refactor common signal handling logic into vm_util to reduce code duplication. - Improve test robustness and diagnostics based on community feedback. - Address minor code style and script corrections. Changelog v2: https://lore.kernel.org/lkml/20250630140957.4000-1-lianux.mm@gmail.com/ - Drop MADV_DONTNEED tests based on feedback. - Focus solely on process_madvise() syscall. - Improve error handling and structure. - Add future-proof flag test. - Style and comment cleanups. -V1: https://lore.kernel.org/lkml/20250621133003.4733-1-lianux.mm@gmail.com/ tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/guard-regions.c | 51 --- tools/testing/selftests/mm/process_madv.c | 447 +++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + tools/testing/selftests/mm/vm_util.c | 35 ++ tools/testing/selftests/mm/vm_util.h | 22 + 7 files changed, 511 insertions(+), 51 deletions(-) create mode 100644 tools/testing/selftests/mm/process_madv.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 824266982aa3..95bd9c6ead9e 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -25,6 +25,7 @@ pfnmap protection_keys protection_keys_32 protection_keys_64 +process_madv madv_populate uffd-stress uffd-unit-tests diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ae6f994d3add..d13b3cef2a2b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -85,6 +85,7 @@ TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += pfnmap +TEST_GEN_FILES += process_madv TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index 93af3d3760f9..4cf101b0fe5e 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -9,8 +9,6 @@ #include <linux/limits.h> #include <linux/userfaultfd.h> #include <linux/fs.h> -#include <setjmp.h> -#include <signal.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -24,24 +22,6 @@ #include "../pidfd/pidfd.h" -/* - * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: - * - * "If the signal occurs other than as the result of calling the abort or raise - * function, the behavior is undefined if the signal handler refers to any - * object with static storage duration other than by assigning a value to an - * object declared as volatile sig_atomic_t" - */ -static volatile sig_atomic_t signal_jump_set; -static sigjmp_buf signal_jmp_buf; - -/* - * Ignore the checkpatch warning, we must read from x but don't want to do - * anything with it in order to trigger a read page fault. We therefore must use - * volatile to stop the compiler from optimising this away. - */ -#define FORCE_READ(x) (*(volatile typeof(x) *)x) - /* * How is the test backing the mapping being tested? */ @@ -120,14 +100,6 @@ static int userfaultfd(int flags) return syscall(SYS_userfaultfd, flags); } -static void handle_fatal(int c) -{ - if (!signal_jump_set) - return; - - siglongjmp(signal_jmp_buf, c); -} - static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, size_t n, int advice, unsigned int flags) { @@ -180,29 +152,6 @@ static bool try_read_write_buf(char *ptr) return try_read_buf(ptr) && try_write_buf(ptr); } -static void setup_sighandler(void) -{ - struct sigaction act = { - .sa_handler = &handle_fatal, - .sa_flags = SA_NODEFER, - }; - - sigemptyset(&act.sa_mask); - if (sigaction(SIGSEGV, &act, NULL)) - ksft_exit_fail_perror("sigaction"); -} - -static void teardown_sighandler(void) -{ - struct sigaction act = { - .sa_handler = SIG_DFL, - .sa_flags = SA_NODEFER, - }; - - sigemptyset(&act.sa_mask); - sigaction(SIGSEGV, &act, NULL); -} - static int open_file(const char *prefix, char *path) { int fd; diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..7d7509486d46 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,447 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <errno.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <linux/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <sched.h> +#include <linux/pidfd.h> +#include <linux/uio.h> +#include "vm_util.h" + +FIXTURE(process_madvise) +{ + int pidfd; + int flag; + pid_t child_pid; +}; + +FIXTURE_SETUP(process_madvise) +{ + self->pidfd = PIDFD_SELF; + self->flag = 0; + self->child_pid = -1; + setup_sighandler(); +}; + +FIXTURE_TEARDOWN_PARENT(process_madvise) +{ + teardown_sighandler(); + if (self->child_pid > 0) { + kill(self->child_pid, SIGKILL); + waitpid(self->child_pid, NULL, 0); + } +} + +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t vlen, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags); +} + +/* + * Enable our signal catcher and try to read the specified buffer. The + * return value indicates whether the read succeeds without a fatal + * signal. + */ +static bool try_read_buf(char *ptr) +{ + bool failed; + + /* Tell signal handler to jump back here on fatal signal. */ + signal_jump_set = true; + /* If a fatal signal arose, we will jump back here and failed is set. */ + failed = sigsetjmp(signal_jmp_buf, 0) != 0; + + if (!failed) + FORCE_READ(ptr); + + signal_jump_set = false; + return !failed; +} + +TEST_F(process_madvise, basic) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + const int madvise_pages = 4; + char *map; + ssize_t ret; + struct iovec vec[madvise_pages]; + + /* + * Create a single large mapping. We will pick pages from this + * mapping to advise on. This ensures we test non-contiguous iovecs. + */ + map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (map == MAP_FAILED) + ksft_exit_skip("mmap failed, not enough memory.\n"); + + /* Fill the entire region with a known pattern. */ + memset(map, 'A', pagesize * 10); + + /* + * Setup the iovec to point to 4 non-contiguous pages + * within the mapping. + */ + vec[0].iov_base = &map[0 * pagesize]; + vec[0].iov_len = pagesize; + vec[1].iov_base = &map[3 * pagesize]; + vec[1].iov_len = pagesize; + vec[2].iov_base = &map[5 * pagesize]; + vec[2].iov_len = pagesize; + vec[3].iov_base = &map[8 * pagesize]; + vec[3].iov_len = pagesize; + + ret = sys_process_madvise(PIDFD_SELF, vec, madvise_pages, MADV_DONTNEED, + 0); + if (ret == -1 && errno == EPERM) + ksft_exit_skip( + "process_madvise() unsupported or permission denied, try running as root.\n"); + else if (errno == EINVAL) + ksft_exit_skip( + "process_madvise() unsupported or parameter invalid, please check arguments.\n"); + + /* The call should succeed and report the total bytes processed. */ + ASSERT_EQ(ret, madvise_pages * pagesize); + + /* Check that advised pages are now zero. */ + for (int i = 0; i < madvise_pages; i++) { + char *advised_page = (char *)vec[i].iov_base; + + /* Access should be successful (kernel provides a new page). */ + ASSERT_TRUE(try_read_buf(advised_page)); + /* Content must be 0, not 'A'. */ + ASSERT_EQ(*advised_page, 0); + } + + /* Check that an un-advised page in between is still 'A'. */ + char *unadvised_page = &map[1 * pagesize]; + + ASSERT_TRUE(try_read_buf(unadvised_page)); + for (int i = 0; i < pagesize; i++) + ASSERT_EQ(unadvised_page[i], 'A'); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize * 10), 0); +} + +static long get_smaps_anon_huge_pages(pid_t pid, void *addr) +{ + char smaps_path[64]; + char *line = NULL; + unsigned long start, end; + long anon_huge_kb; + size_t len; + FILE *f; + bool in_vma; + + in_vma = false; + snprintf(smaps_path, sizeof(smaps_path), "/proc/%d/smaps", pid); + f = fopen(smaps_path, "r"); + if (!f) + return -1; + + while (getline(&line, &len, f) != -1) { + /* Check if the line describes a VMA range */ + if (sscanf(line, "%lx-%lx", &start, &end) == 2) { + if ((unsigned long)addr >= start && + (unsigned long)addr < end) + in_vma = true; + else + in_vma = false; + continue; + } + + /* If we are in the correct VMA, look for the AnonHugePages field */ + if (in_vma && + sscanf(line, "AnonHugePages: %ld kB", &anon_huge_kb) == 1) + break; + } + + free(line); + fclose(f); + + return (anon_huge_kb > 0) ? (anon_huge_kb * 1024) : 0; +} + +static bool is_thp_always(void) +{ + const char *path = "/sys/kernel/mm/transparent_hugepage/enabled"; + char buf[32]; + FILE *f = fopen(path, "r"); + + if (!f) + return false; + + if (fgets(buf, sizeof(buf), f)) + if (strstr(buf, "[always]")) { + fclose(f); + return true; + } + + fclose(f); + return false; +} + +/** + * TEST_F(process_madvise, remote_collapse) + * + * This test deterministically validates process_madvise() with MADV_COLLAPSE + * on a remote process, other advices are difficult to verify reliably. + * + * The test verifies that a memory region in a child process, initially + * backed by small pages, can be collapsed into a Transparent Huge Page by a + * request from the parent. The result is verified by parsing the child's + * /proc/<pid>/smaps file. + */ +TEST_F(process_madvise, remote_collapse) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + int pidfd; + long huge_page_size; + int pipe_info[2]; + ssize_t ret; + struct iovec vec; + + struct child_info { + pid_t pid; + void *map_addr; + } info; + + huge_page_size = default_huge_page_size(); + if (huge_page_size <= 0) + ksft_exit_skip("Could not determine a valid huge page size.\n"); + + ASSERT_EQ(pipe(pipe_info), 0); + + self->child_pid = fork(); + ASSERT_NE(self->child_pid, -1); + + if (self->child_pid == 0) { + char *map; + size_t map_size = 2 * huge_page_size; + + close(pipe_info[0]); + + map = mmap(NULL, map_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fault in as small pages */ + for (size_t i = 0; i < map_size; i += pagesize) + map[i] = 'A'; + + /* Send info and pause */ + info.pid = getpid(); + info.map_addr = map; + ret = write(pipe_info[1], &info, sizeof(info)); + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[1]); + + pause(); + exit(0); + } + + close(pipe_info[1]); + + /* Receive child info */ + ret = read(pipe_info[0], &info, sizeof(info)); + if (ret <= 0) { + waitpid(self->child_pid, NULL, 0); + ksft_exit_skip("Failed to read child info from pipe.\n"); + } + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[0]); + self->child_pid = info.pid; + + pidfd = syscall(__NR_pidfd_open, self->child_pid, 0); + ASSERT_GE(pidfd, 0); + + vec.iov_base = info.map_addr; + vec.iov_len = huge_page_size; + + if (is_thp_always()) { + long initial_huge_pages; + + /* + * When THP is 'always', khugepaged may pre-emptively + * collapse the pages before our MADV_COLLAPSE call. Check + * the initial state to provide a more accurate test report. + */ + initial_huge_pages = + get_smaps_anon_huge_pages(self->child_pid, info.map_addr); + + if (initial_huge_pages == 2 * huge_page_size) { + /* + * The pages were already collapsed by khugepaged. + * The test goal narrows to verifying that MADV_COLLAPSE + * correctly returns success on an already-collapsed + * region, as documented. + */ + ksft_test_result_skip( + "THP is 'always' and pages were pre-collapsed; verifying success on already-collapsed page.\n"); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, + 0); + ASSERT_EQ(ret, huge_page_size); + goto cleanup; + } + + /* + * Pages are still small, creating a race between our call + * and khugepaged. This is the main test scenario for 'always'. + */ + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, 0); + + if (ret == -1) { + /* + * MADV_COLLAPSE lost the race to khugepaged, which + * likely held a page lock. The kernel correctly + * reports this temporary contention with EAGAIN. + */ + if (errno == EAGAIN) { + ksft_test_result_skip( + "THP is 'always', process_madvise returned EAGAIN due to an expected race with khugepaged.\n"); + } else { + ksft_test_result_fail( + "process_madvise failed with unexpected errno %d in 'always' mode.\n", + errno); + } + goto cleanup; + } + + /* + * MADV_COLLAPSE won the race and successfully collapsed + * the pages. Verify the final state. + */ + ASSERT_EQ(ret, huge_page_size); + ASSERT_EQ(get_smaps_anon_huge_pages(self->child_pid, info.map_addr), + huge_page_size); + ksft_test_result_pass( + "THP is 'always', MADV_COLLAPSE won race and collapsed pages.\n"); + goto cleanup; + } + + /* + * THP is 'madvise' or 'never'. No race is expected with khugepaged. + * We can perform a straightforward state-change verification. + */ + ASSERT_EQ(get_smaps_anon_huge_pages(self->child_pid, info.map_addr), 0); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, 0); + if (ret == -1) { + if (errno == EINVAL) + ksft_exit_skip( + "PROCESS_MADV_ADVISE is not supported.\n"); + else if (errno == EPERM) + ksft_exit_skip( + "No process_madvise() permissions, try running as root.\n"); + goto cleanup; + } + ASSERT_EQ(ret, huge_page_size); + + ASSERT_EQ(get_smaps_anon_huge_pages(self->child_pid, info.map_addr), + huge_page_size); + + ksft_test_result_pass( + "MADV_COLLAPSE successfully verified via smaps.\n"); + +cleanup: + /* Cleanup */ + kill(self->child_pid, SIGKILL); + waitpid(self->child_pid, NULL, 0); + if (pidfd >= 0) + close(pidfd); +} + +/* + * Test process_madvise() with various invalid pidfds to ensure correct error + * handling. This includes negative fds, non-pidfd fds, and pidfds for + * processes that no longer exist. + */ +TEST_F(process_madvise, invalid_pidfd) +{ + struct iovec vec; + pid_t child_pid; + ssize_t ret; + int pidfd; + + vec.iov_base = (void *)0x1234; + vec.iov_len = 4096; + + /* Using an invalid fd number (-1) should fail with EBADF. */ + ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a valid fd that is not a pidfd (e.g. stdin) should fail + * with EBADF. + */ + ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a pidfd for a process that has already exited should fail + * with ESRCH. + */ + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) + exit(0); + + pidfd = syscall(__NR_pidfd_open, child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Wait for the child to ensure it has terminated. */ + waitpid(child_pid, NULL, 0); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ESRCH); + close(pidfd); +} + +/* + * Test process_madvise() with an invalid flag value. Now we only support flag=0 + * future we will use it support sync so reserve this test. + */ +TEST_F(process_madvise, flag) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + unsigned int invalid_flag; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + ksft_exit_skip("mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + invalid_flag = 0x80000000; + + ret = sys_process_madvise(PIDFD_SELF, &vec, 1, MADV_DONTNEED, + invalid_flag); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index dddd1dd8af14..84fb51902c3e 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -65,6 +65,8 @@ separated by spaces: test pagemap_scan IOCTL - pfnmap tests for VM_PFNMAP handling +- process_madv + test process_madvise - cow test copy-on-write semantics - thp @@ -422,6 +424,9 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests CATEGORY="madv_guard" run_test ./guard-regions +# PROCESS_MADVISE TEST +CATEGORY="process_madv" run_test ./process_madv + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 5492e3f784df..85b209260e5a 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -20,6 +20,9 @@ unsigned int __page_size; unsigned int __page_shift; +volatile sig_atomic_t signal_jump_set; +sigjmp_buf signal_jmp_buf; + uint64_t pagemap_get_entry(int fd, char *start) { const unsigned long pfn = (unsigned long)start / getpagesize(); @@ -524,3 +527,35 @@ int read_sysfs(const char *file_path, unsigned long *val) return 0; } + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +void setup_sighandler(void) +{ + struct sigaction act = { + .sa_handler = &handle_fatal, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction in setup"); +} + +void teardown_sighandler(void) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction in teardown"); +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b8136d12a0f8..6bc4177a2807 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -8,6 +8,8 @@ #include <unistd.h> /* _SC_PAGESIZE */ #include "../kselftest.h" #include <linux/fs.h> +#include <setjmp.h> +#include <signal.h> #define BIT_ULL(nr) (1ULL << (nr)) #define PM_SOFT_DIRTY BIT_ULL(55) @@ -61,6 +63,24 @@ static inline void skip_test_dodgy_fs(const char *op_name) ksft_test_result_skip("%s failed with ENOENT. Filesystem might be buggy (9pfs?)\n", op_name); } +/* + * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: + * + * "If the signal occurs other than as the result of calling the abort or raise + * function, the behavior is undefined if the signal handler refers to any + * object with static storage duration other than by assigning a value to an + * object declared as volatile sig_atomic_t" + */ +extern volatile sig_atomic_t signal_jump_set; +extern sigjmp_buf signal_jmp_buf; + +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(volatile typeof(x) *)x) + uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); bool pagemap_is_swapped(int fd, char *start); @@ -90,6 +110,8 @@ bool find_vma_procmap(struct procmap_fd *procmap, void *address); int close_procmap(struct procmap_fd *procmap); int write_sysfs(const char *file_path, unsigned long val); int read_sysfs(const char *file_path, unsigned long *val); +void setup_sighandler(void); +void teardown_sighandler(void); static inline int open_self_procmap(struct procmap_fd *procmap_out) { -- 2.43.0

4 months

4
11
0 0

[PATCH v3] selftests/mm: add process_madvise() tests

by wang lian

Add tests for process_madvise(), focusing on verifying behavior under various conditions including valid usage and error cases. Signed-off-by: wang lian <lianux.mm(a)gmail.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes(a)oracle.com> Suggested-by: David Hildenbrand <david(a)redhat.com> Acked-by: SeongJae Park <sj(a)kernel.org> --- Changelog v3: - Rebased onto the latest mm-stable branch to ensure clean application. - Refactor common signal handling logic into vm_util to reduce code duplication. - Improve test robustness and diagnostics based on community feedback. - Address minor code style and script corrections. Changelog v2: - Drop MADV_DONTNEED tests based on feedback. - Focus solely on process_madvise() syscall. - Improve error handling and structure. - Add future-proof flag test. - Style and comment cleanups. tools/testing/selftests/mm/.gitignore | 1 + tools/testing/selftests/mm/Makefile | 1 + tools/testing/selftests/mm/guard-regions.c | 51 --- tools/testing/selftests/mm/process_madv.c | 358 +++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + tools/testing/selftests/mm/vm_util.c | 35 ++ tools/testing/selftests/mm/vm_util.h | 22 ++ 7 files changed, 422 insertions(+), 51 deletions(-) create mode 100644 tools/testing/selftests/mm/process_madv.c diff --git a/tools/testing/selftests/mm/.gitignore b/tools/testing/selftests/mm/.gitignore index 824266982aa3..95bd9c6ead9e 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -25,6 +25,7 @@ pfnmap protection_keys protection_keys_32 protection_keys_64 +process_madv madv_populate uffd-stress uffd-unit-tests diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index ae6f994d3add..d13b3cef2a2b 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -85,6 +85,7 @@ TEST_GEN_FILES += mseal_test TEST_GEN_FILES += on-fault-limit TEST_GEN_FILES += pagemap_ioctl TEST_GEN_FILES += pfnmap +TEST_GEN_FILES += process_madv TEST_GEN_FILES += thuge-gen TEST_GEN_FILES += transhuge-stress TEST_GEN_FILES += uffd-stress diff --git a/tools/testing/selftests/mm/guard-regions.c b/tools/testing/selftests/mm/guard-regions.c index 93af3d3760f9..4cf101b0fe5e 100644 --- a/tools/testing/selftests/mm/guard-regions.c +++ b/tools/testing/selftests/mm/guard-regions.c @@ -9,8 +9,6 @@ #include <linux/limits.h> #include <linux/userfaultfd.h> #include <linux/fs.h> -#include <setjmp.h> -#include <signal.h> #include <stdbool.h> #include <stdio.h> #include <stdlib.h> @@ -24,24 +22,6 @@ #include "../pidfd/pidfd.h" -/* - * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: - * - * "If the signal occurs other than as the result of calling the abort or raise - * function, the behavior is undefined if the signal handler refers to any - * object with static storage duration other than by assigning a value to an - * object declared as volatile sig_atomic_t" - */ -static volatile sig_atomic_t signal_jump_set; -static sigjmp_buf signal_jmp_buf; - -/* - * Ignore the checkpatch warning, we must read from x but don't want to do - * anything with it in order to trigger a read page fault. We therefore must use - * volatile to stop the compiler from optimising this away. - */ -#define FORCE_READ(x) (*(volatile typeof(x) *)x) - /* * How is the test backing the mapping being tested? */ @@ -120,14 +100,6 @@ static int userfaultfd(int flags) return syscall(SYS_userfaultfd, flags); } -static void handle_fatal(int c) -{ - if (!signal_jump_set) - return; - - siglongjmp(signal_jmp_buf, c); -} - static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, size_t n, int advice, unsigned int flags) { @@ -180,29 +152,6 @@ static bool try_read_write_buf(char *ptr) return try_read_buf(ptr) && try_write_buf(ptr); } -static void setup_sighandler(void) -{ - struct sigaction act = { - .sa_handler = &handle_fatal, - .sa_flags = SA_NODEFER, - }; - - sigemptyset(&act.sa_mask); - if (sigaction(SIGSEGV, &act, NULL)) - ksft_exit_fail_perror("sigaction"); -} - -static void teardown_sighandler(void) -{ - struct sigaction act = { - .sa_handler = SIG_DFL, - .sa_flags = SA_NODEFER, - }; - - sigemptyset(&act.sa_mask); - sigaction(SIGSEGV, &act, NULL); -} - static int open_file(const char *prefix, char *path) { int fd; diff --git a/tools/testing/selftests/mm/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..3d26105b4781 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#define _GNU_SOURCE +#include "../kselftest_harness.h" +#include <errno.h> +#include <setjmp.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +#include <sched.h> +#include <sys/pidfd.h> +#include "vm_util.h" + +#include "../pidfd/pidfd.h" + +FIXTURE(process_madvise) +{ + int pidfd; + int flag; +}; + +FIXTURE_SETUP(process_madvise) +{ + self->pidfd = PIDFD_SELF; + self->flag = 0; + setup_sighandler(); +}; + +FIXTURE_TEARDOWN(process_madvise) +{ + teardown_sighandler(); +} + +static ssize_t sys_process_madvise(int pidfd, const struct iovec *iovec, + size_t vlen, int advice, unsigned int flags) +{ + return syscall(__NR_process_madvise, pidfd, iovec, vlen, advice, flags); +} + +/* + * Enable our signal catcher and try to read the specified buffer. The + * return value indicates whether the read succeeds without a fatal + * signal. + */ +static bool try_read_buf(char *ptr) +{ + bool failed; + + /* Tell signal handler to jump back here on fatal signal. */ + signal_jump_set = true; + /* If a fatal signal arose, we will jump back here and failed is set. */ + failed = sigsetjmp(signal_jmp_buf, 0) != 0; + + if (!failed) + FORCE_READ(ptr); + + signal_jump_set = false; + return !failed; +} + +TEST_F(process_madvise, basic) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + const int madvise_pages = 4; + char *map; + ssize_t ret; + struct iovec vec[madvise_pages]; + + /* + * Create a single large mapping. We will pick pages from this + * mapping to advise on. This ensures we test non-contiguous iovecs. + */ + map = mmap(NULL, pagesize * 10, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (map == MAP_FAILED) + ksft_exit_skip("mmap failed, not enough memory.\n"); + + /* Fill the entire region with a known pattern. */ + memset(map, 'A', pagesize * 10); + + /* + * Setup the iovec to point to 4 non-contiguous pages + * within the mapping. + */ + vec[0].iov_base = &map[0 * pagesize]; + vec[0].iov_len = pagesize; + vec[1].iov_base = &map[3 * pagesize]; + vec[1].iov_len = pagesize; + vec[2].iov_base = &map[5 * pagesize]; + vec[2].iov_len = pagesize; + vec[3].iov_base = &map[8 * pagesize]; + vec[3].iov_len = pagesize; + + ret = sys_process_madvise(PIDFD_SELF, vec, madvise_pages, MADV_DONTNEED, + 0); + if (ret == -1 && errno == EPERM) + ksft_exit_skip( + "process_madvise() unsupported or permission denied, try running as root.\n"); + else if (errno == EINVAL) + ksft_exit_skip( + "process_madvise() unsupported or parameter invalid, please check arguments.\n"); + + /* The call should succeed and report the total bytes processed. */ + ASSERT_EQ(ret, madvise_pages * pagesize); + + /* Check that advised pages are now zero. */ + for (int i = 0; i < madvise_pages; i++) { + char *advised_page = (char *)vec[i].iov_base; + + /* Access should be successful (kernel provides a new page). */ + ASSERT_TRUE(try_read_buf(advised_page)); + /* Content must be 0, not 'A'. */ + ASSERT_EQ(*advised_page, 0); + } + + /* Check that an un-advised page in between is still 'A'. */ + char *unadvised_page = &map[1 * pagesize]; + + ASSERT_TRUE(try_read_buf(unadvised_page)); + for (int i = 0; i < pagesize; i++) + ASSERT_EQ(unadvised_page[i], 'A'); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize * 10), 0); +} + +static long get_smaps_anon_huge_pages(pid_t pid, void *addr) +{ + char smaps_path[64]; + char *line = NULL; + unsigned long start, end; + long anon_huge_kb; + size_t len; + FILE *f; + bool in_vma; + + in_vma = false; + snprintf(smaps_path, sizeof(smaps_path), "/proc/%d/smaps", pid); + f = fopen(smaps_path, "r"); + if (!f) + return -1; + + while (getline(&line, &len, f) != -1) { + /* Check if the line describes a VMA range */ + if (sscanf(line, "%lx-%lx", &start, &end) == 2) { + if ((unsigned long)addr >= start && + (unsigned long)addr < end) + in_vma = true; + else + in_vma = false; + continue; + } + + /* If we are in the correct VMA, look for the AnonHugePages field */ + if (in_vma && + sscanf(line, "AnonHugePages: %ld kB", &anon_huge_kb) == 1) + break; + } + + free(line); + fclose(f); + + return (anon_huge_kb > 0) ? (anon_huge_kb * 1024) : 0; +} + +/** + * TEST_F(process_madvise, remote_collapse) + * + * This test deterministically validates process_madvise() with MADV_COLLAPSE + * on a remote process, other advices are difficult to verify reliably. + * + * The test verifies that a memory region in a child process, initially + * backed by small pages, can be collapsed into a Transparent Huge Page by a + * request from the parent. The result is verified by parsing the child's + * /proc/<pid>/smaps file. + */ +TEST_F(process_madvise, remote_collapse) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + pid_t child_pid; + int pidfd; + long huge_page_size; + int pipe_info[2]; + ssize_t ret; + struct iovec vec; + + struct child_info { + pid_t pid; + void *map_addr; + } info; + + huge_page_size = default_huge_page_size(); + if (huge_page_size <= 0) + ksft_exit_skip("Could not determine a valid huge page size.\n"); + + ASSERT_EQ(pipe(pipe_info), 0); + + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) { + char *map; + size_t map_size = 2 * huge_page_size; + + close(pipe_info[0]); + + map = mmap(NULL, map_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + ASSERT_NE(map, MAP_FAILED); + + /* Fault in as small pages */ + for (size_t i = 0; i < map_size; i += pagesize) + map[i] = 'A'; + + /* Send info and pause */ + info.pid = getpid(); + info.map_addr = map; + ret = write(pipe_info[1], &info, sizeof(info)); + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[1]); + + pause(); + exit(0); + } + + close(pipe_info[1]); + + /* Receive child info */ + ret = read(pipe_info[0], &info, sizeof(info)); + if (ret <= 0) { + waitpid(child_pid, NULL, 0); + ksft_exit_skip("Failed to read child info from pipe.\n"); + } + ASSERT_EQ(ret, sizeof(info)); + close(pipe_info[0]); + child_pid = info.pid; + + pidfd = pidfd_open(child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Baseline Check from Parent's perspective */ + ASSERT_EQ(get_smaps_anon_huge_pages(child_pid, info.map_addr), 0); + + vec.iov_base = info.map_addr; + vec.iov_len = huge_page_size; + ret = sys_process_madvise(pidfd, &vec, 1, MADV_COLLAPSE, 0); + if (ret == -1) { + if (errno == EINVAL) + ksft_exit_skip( + "PROCESS_MADV_ADVISE is not supported.\n"); + else if (errno == EPERM) + ksft_exit_skip( + "No process_madvise() permissions, try running as root.\n"); + goto cleanup; + } + ASSERT_EQ(ret, huge_page_size); + + ASSERT_EQ(get_smaps_anon_huge_pages(child_pid, info.map_addr), + huge_page_size); + + ksft_test_result_pass( + "MADV_COLLAPSE successfully verified via smaps.\n"); + +cleanup: + /* Cleanup */ + kill(child_pid, SIGKILL); + waitpid(child_pid, NULL, 0); + if (pidfd >= 0) + close(pidfd); +} + +/* + * Test process_madvise() with various invalid pidfds to ensure correct error + * handling. This includes negative fds, non-pidfd fds, and pidfds for + * processes that no longer exist. + */ +TEST_F(process_madvise, invalid_pidfd) +{ + struct iovec vec; + pid_t child_pid; + ssize_t ret; + int pidfd; + + vec.iov_base = (void *)0x1234; + vec.iov_len = 4096; + + /* Using an invalid fd number (-1) should fail with EBADF. */ + ret = sys_process_madvise(-1, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a valid fd that is not a pidfd (e.g. stdin) should fail + * with EBADF. + */ + ret = sys_process_madvise(STDIN_FILENO, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBADF); + + /* + * Using a pidfd for a process that has already exited should fail + * with ESRCH. + */ + child_pid = fork(); + ASSERT_NE(child_pid, -1); + + if (child_pid == 0) + exit(0); + + pidfd = pidfd_open(child_pid, 0); + ASSERT_GE(pidfd, 0); + + /* Wait for the child to ensure it has terminated. */ + waitpid(child_pid, NULL, 0); + + ret = sys_process_madvise(pidfd, &vec, 1, MADV_DONTNEED, 0); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, ESRCH); + close(pidfd); +} + +/* + * Test process_madvise() with an invalid flag value. Now we only support flag=0 + * future we will use it support sync so reserve this test. + */ +TEST_F(process_madvise, flag) +{ + const unsigned long pagesize = (unsigned long)sysconf(_SC_PAGESIZE); + unsigned int invalid_flag; + struct iovec vec; + char *map; + ssize_t ret; + + map = mmap(NULL, pagesize, PROT_READ, MAP_PRIVATE | MAP_ANONYMOUS, -1, + 0); + if (map == MAP_FAILED) + ksft_exit_skip("mmap failed, not enough memory.\n"); + + vec.iov_base = map; + vec.iov_len = pagesize; + + invalid_flag = 0x80000000; + + ret = sys_process_madvise(PIDFD_SELF, &vec, 1, MADV_DONTNEED, + invalid_flag); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EINVAL); + + /* Cleanup. */ + ASSERT_EQ(munmap(map, pagesize), 0); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index dddd1dd8af14..84fb51902c3e 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -65,6 +65,8 @@ separated by spaces: test pagemap_scan IOCTL - pfnmap tests for VM_PFNMAP handling +- process_madv + test process_madvise - cow test copy-on-write semantics - thp @@ -422,6 +424,9 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke # MADV_GUARD_INSTALL and MADV_GUARD_REMOVE tests CATEGORY="madv_guard" run_test ./guard-regions +# PROCESS_MADVISE TEST +CATEGORY="process_madv" run_test ./process_madv + # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests CATEGORY="madv_populate" run_test ./madv_populate diff --git a/tools/testing/selftests/mm/vm_util.c b/tools/testing/selftests/mm/vm_util.c index 5492e3f784df..85b209260e5a 100644 --- a/tools/testing/selftests/mm/vm_util.c +++ b/tools/testing/selftests/mm/vm_util.c @@ -20,6 +20,9 @@ unsigned int __page_size; unsigned int __page_shift; +volatile sig_atomic_t signal_jump_set; +sigjmp_buf signal_jmp_buf; + uint64_t pagemap_get_entry(int fd, char *start) { const unsigned long pfn = (unsigned long)start / getpagesize(); @@ -524,3 +527,35 @@ int read_sysfs(const char *file_path, unsigned long *val) return 0; } + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +void setup_sighandler(void) +{ + struct sigaction act = { + .sa_handler = &handle_fatal, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction in setup"); +} + +void teardown_sighandler(void) +{ + struct sigaction act = { + .sa_handler = SIG_DFL, + .sa_flags = SA_NODEFER, + }; + + sigemptyset(&act.sa_mask); + if (sigaction(SIGSEGV, &act, NULL)) + ksft_exit_fail_perror("sigaction in teardown"); +} diff --git a/tools/testing/selftests/mm/vm_util.h b/tools/testing/selftests/mm/vm_util.h index b8136d12a0f8..6bc4177a2807 100644 --- a/tools/testing/selftests/mm/vm_util.h +++ b/tools/testing/selftests/mm/vm_util.h @@ -8,6 +8,8 @@ #include <unistd.h> /* _SC_PAGESIZE */ #include "../kselftest.h" #include <linux/fs.h> +#include <setjmp.h> +#include <signal.h> #define BIT_ULL(nr) (1ULL << (nr)) #define PM_SOFT_DIRTY BIT_ULL(55) @@ -61,6 +63,24 @@ static inline void skip_test_dodgy_fs(const char *op_name) ksft_test_result_skip("%s failed with ENOENT. Filesystem might be buggy (9pfs?)\n", op_name); } +/* + * Ignore the checkpatch warning, as per the C99 standard, section 7.14.1.1: + * + * "If the signal occurs other than as the result of calling the abort or raise + * function, the behavior is undefined if the signal handler refers to any + * object with static storage duration other than by assigning a value to an + * object declared as volatile sig_atomic_t" + */ +extern volatile sig_atomic_t signal_jump_set; +extern sigjmp_buf signal_jmp_buf; + +/* + * Ignore the checkpatch warning, we must read from x but don't want to do + * anything with it in order to trigger a read page fault. We therefore must use + * volatile to stop the compiler from optimising this away. + */ +#define FORCE_READ(x) (*(volatile typeof(x) *)x) + uint64_t pagemap_get_entry(int fd, char *start); bool pagemap_is_softdirty(int fd, char *start); bool pagemap_is_swapped(int fd, char *start); @@ -90,6 +110,8 @@ bool find_vma_procmap(struct procmap_fd *procmap, void *address); int close_procmap(struct procmap_fd *procmap); int write_sysfs(const char *file_path, unsigned long val); int read_sysfs(const char *file_path, unsigned long *val); +void setup_sighandler(void); +void teardown_sighandler(void); static inline int open_self_procmap(struct procmap_fd *procmap_out) { -- 2.43.0

4 months

5
13
0 0

[PATCH bpf-next 0/3] bpf: Show precise rejected function when attaching to __noreturn and __btf_id functions

by KaFai Wan

Show precise rejected function name when attaching to __noreturn and __btf_id functions. Add selftest for attaching tracing to __btf_id functions. --- KaFai Wan (3): bpf: Show precise rejected function when attaching to __noreturn functions bpf: Show precise rejected function when attaching to __btf_id functions selftests/bpf: Add selftest for attaching tracing to __btf_id functions kernel/bpf/verifier.c | 5 ++++- .../selftests/bpf/prog_tests/tracing_btf_ids.c | 16 ++++++++++++++++ .../selftests/bpf/progs/fexit_noreturns.c | 2 +- .../selftests/bpf/progs/tracing_btf_ids.c | 15 +++++++++++++++ 4 files changed, 36 insertions(+), 2 deletions(-) create mode 100644 tools/testing/selftests/bpf/prog_tests/tracing_btf_ids.c create mode 100644 tools/testing/selftests/bpf/progs/tracing_btf_ids.c -- 2.43.0

4 months

3
7
0 0

[PATCH 00/10] mm/mremap: permit mremap() move of multiple VMAs

by Lorenzo Stoakes

Historically we've made it a uAPI requirement that mremap() may only operate on a single VMA at a time. For instances where VMAs need to be resized, this makes sense, as it becomes very difficult to determine what a user actually wants should they indicate a desire to expand or shrink the size of multiple VMAs (truncate? Adjust sizes individually? Some other strategy?). However, in instances where a user is moving VMAs, it is restrictive to disallow this. This is especially the case when anonymous mapping remap may or may not be mergeable depending on whether VMAs have or have not been faulted due to anon_vma assignment and folio index alignment with vma->vm_pgoff. Often this can result in surprising impact where a moved region is faulted, then moved back and a user fails to observe a merge from otherwise compatible, adjacent VMAs. This change allows such cases to work without the user having to be cognizant of whether a prior mremap() move or other VMA operations has resulted in VMA fragmentation. In order to do this, this series performs a large amount of refactoring, most pertinently - grouping sanity checks together, separately those that check input parameters and those relating to VMAs. we also simplify the post-mmap lock drop processing for uffd and mlock()'d VMAs. With this done, we can then fairly straightforwardly implement this functionality. This works exclusively for mremap() invocations which specify MREMAP_FIXED. It is not compatible with VMAs which use userfaultfd, as the notification of the userland fault handler would require us to drop the mmap lock. The input and output addresses ranges must not overlap. We carefully account for moves which would result in VMA merges or would otherwise result in VMA iterator invalidation. Lorenzo Stoakes (10): mm/mremap: perform some simple cleanups mm/mremap: refactor initial parameter sanity checks mm/mremap: put VMA check and prep logic into helper function mm/mremap: cleanup post-processing stage of mremap mm/mremap: use an explicit uffd failure path for mremap mm/mremap: check remap conditions earlier mm/mremap: move remap_is_valid() into check_prep_vma() mm/mremap: clean up mlock populate behaviour mm/mremap: permit mremap() move of multiple VMAs tools/testing/selftests: extend mremap_test to test multi-VMA mremap fs/userfaultfd.c | 15 +- include/linux/userfaultfd_k.h | 1 + mm/mremap.c | 502 ++++++++++++++--------- tools/testing/selftests/mm/mremap_test.c | 145 ++++++- 4 files changed, 462 insertions(+), 201 deletions(-) -- 2.50.0

4 months

6
30
0 0

[PATCH] kunit: Enable PCI on UML without triggering WARN()

by Thomas Weißschuh

Various KUnit tests require PCI infrastructure to work. All normal platforms enable PCI by default, but UML does not. Enabling PCI from .kunitconfig files is problematic as it would not be portable. So in commit 6fc3a8636a7b ("kunit: tool: Enable virtio/PCI by default on UML") PCI was enabled by way of CONFIG_UML_PCI_OVER_VIRTIO=y. However CONFIG_UML_PCI_OVER_VIRTIO requires additional configuration of CONFIG_UML_PCI_OVER_VIRTIO_DEVICE_ID or will otherwise trigger a WARN() in virtio_pcidev_init(). However there is no one correct value for UML_PCI_OVER_VIRTIO_DEVICE_ID which could be used by default. This warning is confusing when debugging test failures. On the other hand, the functionality of CONFIG_UML_PCI_OVER_VIRTIO is not used at all, given that it is completely non-functional as indicated by the WARN() in question. Instead it is only used as a way to enable CONFIG_UML_PCI which itself is not directly configurable. Instead of going through CONFIG_UML_PCI_OVER_VIRTIO, introduce a custom configuration option which enables CONFIG_UML_PCI without triggering warnings or building dead code. Signed-off-by: Thomas Weißschuh <thomas.weissschuh(a)linutronix.de> --- lib/kunit/Kconfig | 7 +++++++ tools/testing/kunit/configs/arch_uml.config | 5 ++--- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/lib/kunit/Kconfig b/lib/kunit/Kconfig index a97897edd9642f3e5df7fdd9dee26ee5cf00d6a4..c8ca155521b2455a221ddbec3f6fc55662c83475 100644 --- a/lib/kunit/Kconfig +++ b/lib/kunit/Kconfig @@ -93,4 +93,11 @@ config KUNIT_AUTORUN_ENABLED In most cases this should be left as Y. Only if additional opt-in behavior is needed should this be set to N. +config KUNIT_UML_PCI + bool "KUnit UML PCI Support" + depends on UML + select UML_PCI + help + Enables the PCI subsystem on UML for use by KUnit tests. + endif # KUNIT diff --git a/tools/testing/kunit/configs/arch_uml.config b/tools/testing/kunit/configs/arch_uml.config index 54ad8972681a2cc724e6122b19407188910b9025..28edf816aa70e6f408d9486efff8898df79ee090 100644 --- a/tools/testing/kunit/configs/arch_uml.config +++ b/tools/testing/kunit/configs/arch_uml.config @@ -1,8 +1,7 @@ # Config options which are added to UML builds by default -# Enable virtio/pci, as a lot of tests require it. -CONFIG_VIRTIO_UML=y -CONFIG_UML_PCI_OVER_VIRTIO=y +# Enable pci, as a lot of tests require it. +CONFIG_KUNIT_UML_PCI=y # Enable FORTIFY_SOURCE for wider checking. CONFIG_FORTIFY_SOURCE=y --- base-commit: 19272b37aa4f83ca52bdf9c16d5d81bdd1354494 change-id: 20250626-kunit-uml-pci-a2b687553746 Best regards, -- Thomas Weißschuh <thomas.weissschuh(a)linutronix.de>

4 months

2
1
0 0

[PATCH 0/3] signal handling support for nolibc

by Benjamin Berg

From: Benjamin Berg <benjamin.berg(a)intel.com> Hi, This patchset adds signal handling to nolibc. Initially, I would like to use this for tests. But in the long run, the goal is to use nolibc for the UML kernel itself. In both cases, signal handling will be needed. Benjamin Benjamin Berg (3): tools/nolibc: show failed run if test process crashes tools/nolibc: add more generic BITSET_* macros for FD_* tools/nolibc: add signal support tools/include/nolibc/arch-arm.h | 7 ++ tools/include/nolibc/arch-arm64.h | 3 + tools/include/nolibc/arch-loongarch.h | 3 + tools/include/nolibc/arch-m68k.h | 10 ++ tools/include/nolibc/arch-mips.h | 3 + tools/include/nolibc/arch-powerpc.h | 8 ++ tools/include/nolibc/arch-riscv.h | 3 + tools/include/nolibc/arch-s390.h | 8 +- tools/include/nolibc/arch-sh.h | 5 + tools/include/nolibc/arch-sparc.h | 47 ++++++++ tools/include/nolibc/arch-x86.h | 13 +++ tools/include/nolibc/signal.h | 103 ++++++++++++++++++ tools/include/nolibc/sys.h | 2 +- tools/include/nolibc/time.h | 3 +- tools/include/nolibc/types.h | 67 ++++++------ .../testing/selftests/nolibc/Makefile.nolibc | 3 +- tools/testing/selftests/nolibc/nolibc-test.c | 67 ++++++++++++ 17 files changed, 319 insertions(+), 36 deletions(-) -- 2.50.0

4 months

3
9
0 0

[PATCH net] selftests: net: lib: fix shift count out of range

by Hangbin Liu

I got the following warning when writing other tests: + handle_test_result_pass 'bond 802.3ad' '(lacp_active off)' + local 'test_name=bond 802.3ad' + shift + local 'opt_str=(lacp_active off)' + shift + log_test_result 'bond 802.3ad' '(lacp_active off)' ' OK ' + local 'test_name=bond 802.3ad' + shift + local 'opt_str=(lacp_active off)' + shift + local 'result= OK ' + shift + local retmsg= + shift /net/tools/testing/selftests/net/forwarding/../lib.sh: line 315: shift: shift count out of range This happens because an extra shift is executed even after all arguments have been consumed. Remove the last shift in log_test_result() to avoid this warning. Fixes: a923af1ceee7 ("selftests: forwarding: Convert log_test() to recognize RET values") Signed-off-by: Hangbin Liu <liuhangbin(a)gmail.com> --- tools/testing/selftests/net/lib.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 006fdadcc4b9..86a216e9aca8 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -312,7 +312,7 @@ log_test_result() local test_name=$1; shift local opt_str=$1; shift local result=$1; shift - local retmsg=$1; shift + local retmsg=$1 printf "TEST: %-60s [%s]\n" "$test_name $opt_str" "$result" if [[ $retmsg ]]; then -- 2.46.0

4 months

2
1
0 0

[PATCH net-next 0/5] ethtool: rss: report which fields are configured for hashing

by Jakub Kicinski

Add support for reading flow hash configuration via Netlink ethtool. $ ynl --family ethtool --dump rss-get [{ "header": { "dev-index": 1, "dev-name": "enp1s0" }, "hfunc": 1, "hkey": b"...", "indir": [0, 1, ...], "flow-hash": { "ether": {"l2da"}, "ah-esp4": {"ip-src", "ip-dst"}, "ah-esp6": {"ip-src", "ip-dst"}, "ah4": {"ip-src", "ip-dst"}, "ah6": {"ip-src", "ip-dst"}, "esp4": {"ip-src", "ip-dst"}, "esp6": {"ip-src", "ip-dst"}, "ip4": {"ip-src", "ip-dst"}, "ip6": {"ip-src", "ip-dst"}, "sctp4": {"ip-src", "ip-dst"}, "sctp6": {"ip-src", "ip-dst"}, "udp4": {"ip-src", "ip-dst"}, "udp6": {"ip-src", "ip-dst"} "tcp4": {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"}, "tcp6": {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"}, }, }] Jakub Kicinski (5): ethtool: rss: make sure dump takes the rss lock tools: ynl: decode enums in auto-ints ethtool: mark ETHER_FLOW as usable for Rx hash ethtool: rss: report which fields are configured for hashing selftests: drv-net: test RSS header field configuration Documentation/netlink/specs/ethtool.yaml | 151 ++++++++++++++++++ Documentation/networking/ethtool-netlink.rst | 9 +- include/uapi/linux/ethtool.h | 4 +- .../uapi/linux/ethtool_netlink_generated.h | 34 ++++ net/ethtool/ioctl.c | 7 +- net/ethtool/rss.c | 145 +++++++++++++---- tools/net/ynl/pyynl/lib/ynl.py | 2 + .../selftests/drivers/net/hw/rss_api.py | 47 ++++++ 8 files changed, 364 insertions(+), 35 deletions(-) -- 2.50.0

4 months

3
7
0 0

[PATCH] KVM: selftests: Add CONFIG_EVENTFD for irqfd selftest

by Mark Brown

In 7e9b231c402a ("KVM: selftests: Add a KVM_IRQFD test to verify uniqueness requirements") we added a test for the newly added irqfd support but since this feature works with eventfds it won't work unless the kernel has been built wth eventfd support. Add CONFIG_EVENTFD to the list of required options for the KVM selftests. Signed-off-by: Mark Brown <broonie(a)kernel.org> --- tools/testing/selftests/kvm/config | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/kvm/config b/tools/testing/selftests/kvm/config index 8835fed09e9f..96d874b239eb 100644 --- a/tools/testing/selftests/kvm/config +++ b/tools/testing/selftests/kvm/config @@ -1,5 +1,6 @@ CONFIG_KVM=y CONFIG_KVM_INTEL=y CONFIG_KVM_AMD=y +CONFIG_EVENTFD=y CONFIG_USERFAULTFD=y CONFIG_IDLE_PAGE_TRACKING=y --- base-commit: 7e9b231c402a297251b3e6e0f5cc16cef7dd3ce5 change-id: 20250709-kvm-selftests-eventfd-config-123bb022fa04 Best regards, -- Mark Brown <broonie(a)kernel.org>

4 months

2
1
0 0

[PATCH v3 RESEND] kunit: fix longest symbol length test

by Sergio González Collado

The kunit test that checks the longests symbol length [1], has triggered warnings in some pilelines when symbol prefixes are used [2][3]. The test will to depend on !PREFIX_SYMBOLS and !CFI_CLANG as sujested in [4] and on !GCOV_KERNEL. [1] https://lore.kernel.org/rust-for-linux/CABVgOSm=5Q0fM6neBhxSbOUHBgNzmwf2V22… [2] https://lore.kernel.org/all/20250328112156.2614513-1-arnd@kernel.org/T/#u [3] https://lore.kernel.org/rust-for-linux/bbd03b37-c4d9-4a92-9be2-75aaf8c19815… [4] https://lore.kernel.org/linux-kselftest/20250427200916.GA1661412@ax162/T/#t Reviewed-by: Rae Moar <rmoar(a)google.com> Signed-off-by: Sergio González Collado <sergio.collado(a)gmail.com> Acked-by: Randy Dunlap <rdunlap(a)infradead.org> Tested-by: Randy Dunlap <rdunlap(a)infradead.org> --- lib/Kconfig.debug | 1 + lib/tests/longest_symbol_kunit.c | 3 +-- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index ebe33181b6e6..4a75a52803b6 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -2885,6 +2885,7 @@ config FORTIFY_KUNIT_TEST config LONGEST_SYM_KUNIT_TEST tristate "Test the longest symbol possible" if !KUNIT_ALL_TESTS depends on KUNIT && KPROBES + depends on !PREFIX_SYMBOLS && !CFI_CLANG && !GCOV_KERNEL default KUNIT_ALL_TESTS help Tests the longest symbol possible diff --git a/lib/tests/longest_symbol_kunit.c b/lib/tests/longest_symbol_kunit.c index e3c28ff1807f..9b4de3050ba7 100644 --- a/lib/tests/longest_symbol_kunit.c +++ b/lib/tests/longest_symbol_kunit.c @@ -3,8 +3,7 @@ * Test the longest symbol length. Execute with: * ./tools/testing/kunit/kunit.py run longest-symbol * --arch=x86_64 --kconfig_add CONFIG_KPROBES=y --kconfig_add CONFIG_MODULES=y - * --kconfig_add CONFIG_RETPOLINE=n --kconfig_add CONFIG_CFI_CLANG=n - * --kconfig_add CONFIG_MITIGATION_RETPOLINE=n + * --kconfig_add CONFIG_CPU_MITIGATIONS=n --kconfig_add CONFIG_GCOV_KERNEL=n */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt base-commit: 772b78c2abd85586bb90b23adff89f7303c704c7 -- 2.39.2

4 months

3
3
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror