June 2025 - Linux-kselftest-mirror

[PATCH v2] selftests/mm: Add process_madvise() tests

by wang lian

This patch adds tests for the 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> --- 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/process_madv.c | 414 ++++++++++++++++++++++ tools/testing/selftests/mm/run_vmtests.sh | 5 + 4 files changed, 421 insertions(+) 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 911f39d634be..a8c3be02188c 100644 --- a/tools/testing/selftests/mm/.gitignore +++ b/tools/testing/selftests/mm/.gitignore @@ -42,6 +42,7 @@ memfd_secret hugetlb_dio pkey_sighandler_tests_32 pkey_sighandler_tests_64 +process_madv soft-dirty split_huge_page_test ksm_tests diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile index 2352252f3914..725612e09582 100644 --- a/tools/testing/selftests/mm/Makefile +++ b/tools/testing/selftests/mm/Makefile @@ -86,6 +86,7 @@ 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/process_madv.c b/tools/testing/selftests/mm/process_madv.c new file mode 100644 index 000000000000..73999c8e3570 --- /dev/null +++ b/tools/testing/selftests/mm/process_madv.c @@ -0,0 +1,414 @@ +// 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" + +/* + * 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) + +static void handle_fatal(int c) +{ + if (!signal_jump_set) + return; + + siglongjmp(signal_jmp_buf, c); +} + +FIXTURE(process_madvise) +{ + int pidfd; + int flag; +}; + +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); +} + +FIXTURE_SETUP(process_madvise) +{ + self->pidfd = PIDFD_SELF; + self->flag = 0; + setup_sighandler(); +}; + +FIXTURE_TEARDOWN_PARENT(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/write the specified buffer. The + * return value indicates whether the read/write succeeds without a fatal + * signal. + */ +static bool try_access_buf(char *ptr, bool write) +{ + 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) { + if (write) + *ptr = 'x'; + else + FORCE_READ(ptr); + } + + signal_jump_set = false; + return !failed; +} + +/* Try and read from a buffer, return true if no fatal signal. */ +static bool try_read_buf(char *ptr) +{ + return try_access_buf(ptr, false); +} + +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); + ASSERT_NE(map, MAP_FAILED); + + /* 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)); + ASSERT_EQ(*unadvised_page, '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; + sprintf(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); + ASSERT_NE(map, MAP_FAILED); + + 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 \ No newline at end of file diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index f96d43153fc0..5c28ebcf1ea9 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -61,6 +61,8 @@ separated by spaces: ksm tests that require >=2 NUMA nodes - pkey memory protection key tests +- process_madvise + test process_madvise - soft_dirty test soft dirty page bit semantics - pagemap @@ -424,6 +426,9 @@ 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_DONTNEED and PROCESS_DONTNEED tests CATEGORY="madv_dontneed" run_test ./madv_dontneed -- 2.43.0

2 months, 1 week

3
3
0 0

[PATCH v3 0/7] Add support for FEAT_{LS64, LS64_V} and related tests

by Yicong Yang

From: Yicong Yang <yangyicong(a)hisilicon.com> Armv8.7 introduces single-copy atomic 64-byte loads and stores instructions and its variants named under FEAT_{LS64, LS64_V}. Add support for Armv8.7 FEAT_{LS64, LS64_V}: - Add identifying and enabling in the cpufeature list - Expose the support of these features to userspace through HWCAP3 and cpuinfo - Add related hwcap test - Handle the trap of unsupported memory (normal/uncacheable) access in a VM A real scenario for this feature is that the userspace driver can make use of this to implement direct WQE (workqueue entry) - a mechanism to fill WQE directly into the hardware. Picked Marc's 2 patches form [1] for handling the LS64 trap in a VM on emulated MMIO and the introduce of KVM_EXIT_ARM_LDST64B. [1] https://lore.kernel.org/linux-arm-kernel/20240815125959.2097734-1-maz@kerne… Tested with hwcap test [*]: [*] https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-5-yangyicong@… On host: root@localhost:/tmp# dmesg | grep "All CPU(s) started" [ 0.504846] CPU: All CPU(s) started at EL2 root@localhost:/tmp# ./hwcap [...] # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 On guest: root@localhost:/# dmesg | grep "All CPU(s) started" [ 0.451482] CPU: All CPU(s) started at EL1 root@localhost:/mnt# ./hwcap [...] # LS64 present ok 217 cpuinfo_match_LS64 ok 218 sigill_LS64 ok 219 # SKIP sigbus_LS64 # LS64_V present ok 220 cpuinfo_match_LS64_V ok 221 sigill_LS64_V ok 222 # SKIP sigbus_LS64_V # 115 skipped test(s) detected. Consider enabling relevant config options to improve coverage. # Totals: pass:107 fail:0 xfail:0 xpass:0 skip:115 error:0 Change since v2: - Handle the LS64 fault to userspace and allow userspace to inject LS64 fault - Reorder the patches to make KVM handling prior to feature support Link: https://lore.kernel.org/linux-arm-kernel/20250331094320.35226-1-yangyicong@… Change since v1: - Drop the support for LS64_ACCDATA - handle the DABT of unsupported memory type after checking the memory attributes Link: https://lore.kernel.org/linux-arm-kernel/20241202135504.14252-1-yangyicong@… Marc Zyngier (2): KVM: arm64: Add exit to userspace on {LD,ST}64B* outside of memslots KVM: arm64: Add documentation for KVM_EXIT_ARM_LDST64B Yicong Yang (5): KVM: arm64: Handle DABT caused by LS64* instructions on unsupported memory KVM: arm/arm64: Allow user injection of unsupported exclusive/atomic DABT arm64: Provide basic EL2 setup for FEAT_{LS64, LS64_V} usage at EL0/1 arm64: Add support for FEAT_{LS64, LS64_V} KVM: arm64: Enable FEAT_{LS64, LS64_V} in the supported guest Documentation/arch/arm64/booting.rst | 12 ++++++ Documentation/arch/arm64/elf_hwcaps.rst | 6 +++ Documentation/virt/kvm/api.rst | 43 +++++++++++++++++---- arch/arm64/include/asm/el2_setup.h | 12 +++++- arch/arm64/include/asm/esr.h | 8 ++++ arch/arm64/include/asm/hwcap.h | 2 + arch/arm64/include/asm/kvm_emulate.h | 7 ++++ arch/arm64/include/uapi/asm/hwcap.h | 2 + arch/arm64/include/uapi/asm/kvm.h | 3 +- arch/arm64/kernel/cpufeature.c | 51 +++++++++++++++++++++++++ arch/arm64/kernel/cpuinfo.c | 2 + arch/arm64/kvm/guest.c | 4 ++ arch/arm64/kvm/inject_fault.c | 29 ++++++++++++++ arch/arm64/kvm/mmio.c | 27 ++++++++++++- arch/arm64/kvm/mmu.c | 21 +++++++++- arch/arm64/tools/cpucaps | 2 + include/uapi/linux/kvm.h | 3 +- 17 files changed, 222 insertions(+), 12 deletions(-) -- 2.24.0

2 months, 1 week

2
12
0 0

[RFC PATCH 0/7] platform/chrome: Add Kunit tests for protocol device drivers

by Tzung-Bi Shih

The protocol device drivers under drivers/platform/chrome/ are responsible to communicate to the ChromeOS EC (Embedded Controller). They need to pack the data in a pre-defined format and check if the EC responds accordingly. The series adds some fundamental unit tests for the protocol. It calls the .cmd_xfer() and .pkt_xfer() callbacks (which are the most crucial parts for the protocol), mocks the rest of the system, and checks if the interactions are all correct. The series isn't ready for landing. It's more like a PoC for the binary-level function redirection and its use cases. The 1st patch adds ftrace stub which is originally from [1][2]. There is no follow-up discussion about the ftrace stub. As a result, the patch is still on the mailing list. The 2nd patch adds Kunit tests for cros_ec_i2c. It relies on the ftrace stub for redirecting cros_ec_{un,}register(). The 3rd patch uses static stub instead (if ftrace stub isn't really an option). However, I'm not a big fan to change the production code (i.e. adding the prologue in cros_ec_{un,}register()) for testing. The 4th patch adds Kunit tests for cros_ec_spi. It relies on the ftrace stub for redirecting cros_ec_{un,}register() again. The 5th patch calls .probe() directly instead of forcing the driver probe needs to be synchronous. In comparison with the 4th patch, I don't think this is simpler. I'd prefer to the way in the 4th patch. After talked to Masami about the work, he suggested to use Kprobes for function redirection. The 6th patch adds kprobes stub. The 7th patch uses kprobes stub instead for cros_ec_spi. Questions: - Are we going to support ftrace stub so that tests can use it? - If ftrace stub isn't on the plate (e.g. due to too many dependencies), how about the kprobes stub? Is it something we could pursue? - (minor) I'm unsure if people would prefer 'kprobes stub' vs. 'kprobe stub'. [1]: https://kunit.dev/mocking.html#binary-level-ftrace-et-al [2]: https://lore.kernel.org/linux-kselftest/20220318021314.3225240-3-davidgow@g… Daniel Latypov (1): kunit: expose ftrace-based API for stubbing out functions during tests Tzung-Bi Shih (6): platform/chrome: kunit: cros_ec_i2c: Add tests with ftrace stub platform/chrome: kunit: cros_ec_i2c: Use static stub instead platform/chrome: kunit: cros_ec_spi: Add tests with ftrace stub platform/chrome: kunit: cros_ec_spi: Call .probe() directly kunit: Expose 'kprobes stub' API to redirect functions platform/chrome: kunit: cros_ec_spi: Use kprobes stub instead drivers/platform/chrome/Kconfig | 17 + drivers/platform/chrome/Makefile | 2 + drivers/platform/chrome/cros_ec.c | 6 + drivers/platform/chrome/cros_ec_i2c_test.c | 479 +++++++++++++++++++++ drivers/platform/chrome/cros_ec_spi_test.c | 355 +++++++++++++++ include/kunit/ftrace_stub.h | 84 ++++ include/kunit/kprobes_stub.h | 19 + kernel/trace/ftrace.c | 3 + lib/kunit/Kconfig | 18 + lib/kunit/Makefile | 8 + lib/kunit/ftrace_stub.c | 139 ++++++ lib/kunit/kprobes_stub.c | 113 +++++ lib/kunit/kunit-example-test.c | 27 +- lib/kunit/stubs_example.kunitconfig | 11 + 14 files changed, 1280 insertions(+), 1 deletion(-) create mode 100644 drivers/platform/chrome/cros_ec_i2c_test.c create mode 100644 drivers/platform/chrome/cros_ec_spi_test.c create mode 100644 include/kunit/ftrace_stub.h create mode 100644 include/kunit/kprobes_stub.h create mode 100644 lib/kunit/ftrace_stub.c create mode 100644 lib/kunit/kprobes_stub.c create mode 100644 lib/kunit/stubs_example.kunitconfig -- 2.49.0.1101.gccaa498523-goog

2 months, 1 week

2
11
0 0

[PATCH v5 0/7] futex: Create set_robust_list2

by André Almeida

This patch adds a new robust_list() syscall. The current syscall can't be expanded to cover the following use case, so a new one is needed. This new syscall allows users to set multiple robust lists per process and to have either 32bit or 64bit pointers in the list. * Use case FEX-Emu[1] is an application that runs x86 and x86-64 binaries on an AArch64 Linux host. One of the tasks of FEX-Emu is to translate syscalls from one platform to another. Existing set_robust_list() can't be easily translated because of two limitations: 1) x86 apps can have 32bit pointers robust lists. For a x86-64 kernel this is not a problem, because of the compat entry point. But there's no such compat entry point for AArch64, so the kernel would do the pointer arithmetic wrongly. Is also unviable to userspace to keep track every addition/removal to the robust list and keep a 64bit version of it somewhere else to feed the kernel. Thus, the new interface has an option of telling the kernel if the list is filled with 32bit or 64bit pointers. 2) Apps can set just one robust list (in theory, x86-64 can set two if they also use the compat entry point). That means that when a x86 app asks FEX-Emu to call set_robust_list(), FEX have two options: to overwrite their own robust list pointer and make the app robust, or to ignore the app robust list and keep the emulator robust. The new interface allows for multiple robust lists per application, solving this. * Interface This is the proposed interface: long set_robust_list2(void *head, int index, unsigned int flags) `head` is the head of the userspace struct robust_list_head, just as old set_robust_list(). It needs to be a void pointer since it can point to a normal robust_list_head or a compat_robust_list_head. `flags` can be used for defining the list type: enum robust_list_type { ROBUST_LIST_32BIT, ROBUST_LIST_64BIT, }; `index` is the index in the internal robust_list's linked list (the naming starts to get confusing, I reckon). If `index == -1`, that means that user wants to set a new robust_list, and the kernel will append it in the end of the list, assign a new index and return this index to the user. If `index >= 0`, that means that user wants to re-set `*head` of an already existing list (similarly to what happens when you call set_robust_list() twice with different `*head`). If `index` is out of range, or it points to a non-existing robust_list, or if the internal list is full, an error is returned. * Implementation The implementation re-uses most of the existing robust list interface as possible. The new task_struct member `struct list_head robust_list2` is just a linked list where new lists are appended as the user requests more lists, and by futex_cleanup(), the kernel walks through the internal list feeding exit_robust_list() with the robust_list's. This implementation supports up to 10 lists (defined at ROBUST_LISTS_PER_TASK), but it was an arbitrary number for this RFC. For the described use case above, 4 should be enough, I'm not sure which should be the limit. It doesn't support list removal (should it support?). It doesn't have a proper get_robust_list2() yet as well, but I can add it in a next revision. We could also have a generic robust_list() syscall that can be used to set/get and be controlled by flags. The new interface has a `unsigned int flags` argument, making it extensible for future use cases as well. It refuses unaligned `head` addresses. It doesn't have a limit for elements in a single list (like ROBUST_LIST_LIMIT), it destroys the list as it is parsed to be safe against circular lists. * Testing This patcheset has a selftest patch that expands this one: https://lore.kernel.org/lkml/20250212131123.37431-1-andrealmeid@igalia.com/ Also, FEX-Emu added support for this interface to validate it: https://github.com/FEX-Emu/FEX/pull/3966 Feedback is very welcomed! Thanks, André [1] https://github.com/FEX-Emu/FEX Changelog: - Fixed compilation issues when CONFIG_COMPAT or CONFIG_FUTEX are not set - Rebased on top of new futex work (private hash) v4: https://lore.kernel.org/lkml/20250225183531.682556-1-andrealmeid@igalia.com/ - Refuse unaligned head pointers - Ignore ROBUST_LIST_LIMIT for lists created with this interface and make it robust against circular lists - Fix a get_robust_list() syscall bug for getting the list from another thread - Adapt selftest to use the new interface v3: https://lore.kernel.org/lkml/20241217174958.477692-1-andrealmeid@igalia.com/ - Old syscall set_robust_list() adds new head to the internal linked list of robust lists pointers, instead of having a field just for them. Remove tsk->robust_list and use only tsk->robust_list2 v2: https://lore.kernel.org/lkml/20241101162147.284993-1-andrealmeid@igalia.com/ - Added a patch to properly deal with exit_robust_list() in 64bit vs 32bit - Wired-up syscall for all archs - Added more of the cover letter to the commit message v1: https://lore.kernel.org/lkml/20241024145735.162090-1-andrealmeid@igalia.com/ --- André Almeida (7): selftests/futex: Add ASSERT_ macros selftests/futex: Create test for robust list futex: Use explicit sizes for compat_exit_robust_list futex: Create set_robust_list2 futex: Remove the limit of elements for sys_set_robust_list2 lists futex: Wire up set_robust_list2 syscall selftests: futex: Expand robust list test for the new interface arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/compat.h | 12 +- include/linux/futex.h | 30 +- include/linux/sched.h | 5 +- include/uapi/asm-generic/unistd.h | 2 + include/uapi/linux/futex.h | 10 + kernel/futex/core.c | 156 ++++- kernel/futex/futex.h | 5 + kernel/futex/syscalls.c | 85 ++- kernel/sys_ni.c | 1 + scripts/syscall.tbl | 1 + .../testing/selftests/futex/functional/.gitignore | 1 + tools/testing/selftests/futex/functional/Makefile | 3 +- .../selftests/futex/functional/robust_list.c | 706 +++++++++++++++++++++ tools/testing/selftests/futex/include/logging.h | 38 ++ 29 files changed, 1021 insertions(+), 49 deletions(-) --- base-commit: a24cc6ce1933eade12aa2b9859de0fcd2dac2c06 change-id: 20250225-tonyk-robust_futex-60adeedac695 Best regards, -- André Almeida <andrealmeid(a)igalia.com>

2 months, 1 week

3
17
0 0

[RESEND PATCH net-next 6/6] selftests: net: extend SCM_PIDFD test to cover stale pidfds

by Alexander Mikhalitsyn

Extend SCM_PIDFD test scenarios to also cover dead task's pidfd retrieval and reading its exit info. Cc: linux-kselftest(a)vger.kernel.org Cc: linux-kernel(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: Shuah Khan <shuah(a)kernel.org> 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: Christian Brauner <brauner(a)kernel.org> Cc: Kuniyuki Iwashima <kuniyu(a)google.com> Cc: Lennart Poettering <mzxreary(a)0pointer.de> Cc: Luca Boccassi <bluca(a)debian.org> Cc: David Rheinsberg <david(a)readahead.eu> Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn(a)canonical.com> --- .../testing/selftests/net/af_unix/scm_pidfd.c | 217 ++++++++++++++---- 1 file changed, 173 insertions(+), 44 deletions(-) diff --git a/tools/testing/selftests/net/af_unix/scm_pidfd.c b/tools/testing/selftests/net/af_unix/scm_pidfd.c index 7e534594167e..37e034874034 100644 --- a/tools/testing/selftests/net/af_unix/scm_pidfd.c +++ b/tools/testing/selftests/net/af_unix/scm_pidfd.c @@ -15,6 +15,7 @@ #include <sys/types.h> #include <sys/wait.h> +#include "../../pidfd/pidfd.h" #include "../../kselftest_harness.h" #define clean_errno() (errno == 0 ? "None" : strerror(errno)) @@ -26,6 +27,8 @@ #define SCM_PIDFD 0x04 #endif +#define CHILD_EXIT_CODE_OK 123 + static void child_die() { exit(1); @@ -126,16 +129,65 @@ static pid_t get_pid_from_fdinfo_file(int pidfd, const char *key, size_t keylen) return result; } +struct cmsg_data { + struct ucred *ucred; + int *pidfd; +}; + +static int parse_cmsg(struct msghdr *msg, struct cmsg_data *res) +{ + struct cmsghdr *cmsg; + int data = 0; + + if (msg->msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + for (cmsg = CMSG_FIRSTHDR(msg); cmsg != NULL; + cmsg = CMSG_NXTHDR(msg, cmsg)) { + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_PIDFD) { + if (cmsg->cmsg_len < sizeof(*res->pidfd)) { + log_err("CMSG parse: SCM_PIDFD wrong len"); + return 1; + } + + res->pidfd = (void *)CMSG_DATA(cmsg); + } + + if (cmsg->cmsg_level == SOL_SOCKET && + cmsg->cmsg_type == SCM_CREDENTIALS) { + if (cmsg->cmsg_len < sizeof(*res->ucred)) { + log_err("CMSG parse: SCM_CREDENTIALS wrong len"); + return 1; + } + + res->ucred = (void *)CMSG_DATA(cmsg); + } + } + + if (!res->pidfd) { + log_err("CMSG parse: SCM_PIDFD not found"); + return 1; + } + + if (!res->ucred) { + log_err("CMSG parse: SCM_CREDENTIALS not found"); + return 1; + } + + return 0; +} + static int cmsg_check(int fd) { struct msghdr msg = { 0 }; - struct cmsghdr *cmsg; + struct cmsg_data res; struct iovec iov; - struct ucred *ucred = NULL; int data = 0; char control[CMSG_SPACE(sizeof(struct ucred)) + CMSG_SPACE(sizeof(int))] = { 0 }; - int *pidfd = NULL; pid_t parent_pid; int err; @@ -158,53 +210,99 @@ static int cmsg_check(int fd) return 1; } - for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; - cmsg = CMSG_NXTHDR(&msg, cmsg)) { - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_PIDFD) { - if (cmsg->cmsg_len < sizeof(*pidfd)) { - log_err("CMSG parse: SCM_PIDFD wrong len"); - return 1; - } + /* send(pfd, "x", sizeof(char), 0) */ + if (data != 'x') { + log_err("recvmsg: data corruption"); + return 1; + } - pidfd = (void *)CMSG_DATA(cmsg); - } + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); + return 1; + } - if (cmsg->cmsg_level == SOL_SOCKET && - cmsg->cmsg_type == SCM_CREDENTIALS) { - if (cmsg->cmsg_len < sizeof(*ucred)) { - log_err("CMSG parse: SCM_CREDENTIALS wrong len"); - return 1; - } + /* pidfd from SCM_PIDFD should point to the parent process PID */ + parent_pid = + get_pid_from_fdinfo_file(*res.pidfd, "Pid:", sizeof("Pid:") - 1); + if (parent_pid != getppid()) { + log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + close(*res.pidfd); + return 1; + } - ucred = (void *)CMSG_DATA(cmsg); - } + close(*res.pidfd); + return 0; +} + +static int cmsg_check_dead(int fd, int expected_pid) +{ + int err; + struct msghdr msg = { 0 }; + struct cmsg_data res; + struct iovec iov; + int data = 0; + char control[CMSG_SPACE(sizeof(struct ucred)) + + CMSG_SPACE(sizeof(int))] = { 0 }; + pid_t client_pid; + struct pidfd_info info = { + .mask = PIDFD_INFO_EXIT, + }; + + iov.iov_base = &data; + iov.iov_len = sizeof(data); + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + err = recvmsg(fd, &msg, 0); + if (err < 0) { + log_err("recvmsg"); + return 1; } - /* send(pfd, "x", sizeof(char), 0) */ - if (data != 'x') { + if (msg.msg_flags & (MSG_TRUNC | MSG_CTRUNC)) { + log_err("recvmsg: truncated"); + return 1; + } + + /* send(cfd, "y", sizeof(char), 0) */ + if (data != 'y') { log_err("recvmsg: data corruption"); return 1; } - if (!pidfd) { - log_err("CMSG parse: SCM_PIDFD not found"); + if (parse_cmsg(&msg, &res)) { + log_err("CMSG parse: parse_cmsg() failed"); return 1; } - if (!ucred) { - log_err("CMSG parse: SCM_CREDENTIALS not found"); + /* + * pidfd from SCM_PIDFD should point to the client_pid. + * Let's read exit information and check if it's what + * we expect to see. + */ + if (ioctl(*res.pidfd, PIDFD_GET_INFO, &info)) { + log_err("%s: ioctl(PIDFD_GET_INFO) failed", __func__); + close(*res.pidfd); 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); - if (parent_pid != getppid()) { - log_err("wrong SCM_PIDFD %d != %d", parent_pid, getppid()); + if (!(info.mask & PIDFD_INFO_EXIT)) { + log_err("%s: No exit information from ioctl(PIDFD_GET_INFO)", __func__); + close(*res.pidfd); return 1; } + err = WIFEXITED(info.exit_code) ? WEXITSTATUS(info.exit_code) : 1; + if (err != CHILD_EXIT_CODE_OK) { + log_err("%s: wrong exit_code %d != %d", __func__, err, CHILD_EXIT_CODE_OK); + close(*res.pidfd); + return 1; + } + + close(*res.pidfd); return 0; } @@ -291,6 +389,24 @@ static void fill_sockaddr(struct sock_addr *addr, bool abstract) memcpy(sun_path_buf, addr->sock_name, strlen(addr->sock_name)); } +static int sk_enable_cred_pass(int sk) +{ + int on = 0; + + on = 1; + if (setsockopt(sk, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { + log_err("Failed to set SO_PASSCRED"); + return 1; + } + + if (setsockopt(sk, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { + log_err("Failed to set SO_PASSPIDFD"); + return 1; + } + + return 0; +} + static void client(FIXTURE_DATA(scm_pidfd) *self, const FIXTURE_VARIANT(scm_pidfd) *variant) { @@ -299,7 +415,6 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, struct ucred peer_cred; int peer_pidfd; pid_t peer_pid; - int on = 0; cfd = socket(AF_UNIX, variant->type, 0); if (cfd < 0) { @@ -322,14 +437,8 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } - on = 1; - if (setsockopt(cfd, SOL_SOCKET, SO_PASSCRED, &on, sizeof(on))) { - log_err("Failed to set SO_PASSCRED"); - child_die(); - } - - if (setsockopt(cfd, SOL_SOCKET, SO_PASSPIDFD, &on, sizeof(on))) { - log_err("Failed to set SO_PASSPIDFD"); + if (sk_enable_cred_pass(cfd)) { + log_err("sk_enable_cred_pass() failed"); child_die(); } @@ -340,6 +449,12 @@ static void client(FIXTURE_DATA(scm_pidfd) *self, child_die(); } + /* send something to the parent so it can receive SCM_PIDFD too and validate it */ + if (send(cfd, "y", sizeof(char), 0) == -1) { + log_err("Failed to send(cfd, \"y\", sizeof(char), 0)"); + child_die(); + } + /* skip further for SOCK_DGRAM as it's not applicable */ if (variant->type == SOCK_DGRAM) return; @@ -398,7 +513,13 @@ TEST_F(scm_pidfd, test) close(self->server); close(self->startup_pipe[0]); client(self, variant); - exit(0); + + /* + * It's a bit unusual, but in case of success we return non-zero + * exit code (CHILD_EXIT_CODE_OK) and then we expect to read it + * from ioctl(PIDFD_GET_INFO) in cmsg_check_dead(). + */ + exit(CHILD_EXIT_CODE_OK); } close(self->startup_pipe[1]); @@ -421,9 +542,17 @@ TEST_F(scm_pidfd, test) ASSERT_NE(-1, err); } - close(pfd); waitpid(self->client_pid, &child_status, 0); - ASSERT_EQ(0, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + /* see comment before exit(CHILD_EXIT_CODE_OK) */ + ASSERT_EQ(CHILD_EXIT_CODE_OK, WIFEXITED(child_status) ? WEXITSTATUS(child_status) : 1); + + err = sk_enable_cred_pass(pfd); + ASSERT_EQ(0, err); + + err = cmsg_check_dead(pfd, self->client_pid); + ASSERT_EQ(0, err); + + close(pfd); } TEST_HARNESS_MAIN -- 2.43.0

2 months, 1 week

3
2
0 0

[kvm-unit-tests PATCH v7] riscv: sbi: Add SBI Debug Triggers Extension tests

by Jesse Taube

Add tests for the DBTR SBI extension. Signed-off-by: Jesse Taube <jesse(a)rivosinc.com> Reviewed-by: Charlie Jenkins <charlie(a)rivosinc.com> Tested-by: Charlie Jenkins <charlie(a)rivosinc.com> --- V1 -> V2: - Call report_prefix_pop before returning - Disable compressed instructions in exec_call, update related comment - Remove extra "| 1" in dbtr_test_load - Remove extra newlines - Remove extra tabs in check_exec - Remove typedefs from enums - Return when dbtr_install_trigger fails - s/avalible/available/g - s/unistall/uninstall/g V2 -> V3: - Change SBI_DBTR_SHMEM_INVALID_ADDR to -1UL - Move all dbtr functions to sbi-dbtr.c - Move INSN_LEN to processor.h - Update include list - Use C-style comments V3 -> V4: - Include libcflat.h - Remove #define SBI_DBTR_SHMEM_INVALID_ADDR V4 -> V5: - Sort includes - Add kfail for update triggers V5 -> V6: - Add assert in gen_tdata1 - Add prefix to dbtr_test_type - Add TRIG_STATE_DMODE - Add TRIG_STATE_RESERVED - Align function paramaters with opening parenthesis - Change OpenSBI < v1.7 to < v1.5 - Constantly use spaces in prefix rather than _ - Export split_phys_addr - Fix MCONTROL_U and MCONTROL_M mix up - Fix swapped VU and VS - Move /* to own line - Print type in dbtr_test_type - Remove _BIT suffix from macros - Remove duplicate MODE_S - Remove spaces before include - Rename tdata1,2 to trigger and control in dbtr_install_trigger - Report skip in dbtr_test_multiple - Report variables in info not pass or fail - s/save/store/g - sbi_debug_set_shmem use split_phys_addr - Use if (!report(... in dbtr_test_disable_enable V6 -> V7: - Alphabetize Makefile - Only print read info on failure - Remove return after assert - Remove unnecessary OpenSBI version check - Rename error to exit_test in check_dbtr - Use prefix in dbtr_test_num_triggers and dbtr_test_type --- lib/riscv/asm/sbi.h | 1 + riscv/Makefile | 1 + riscv/sbi-dbtr.c | 834 ++++++++++++++++++++++++++++++++++++++++++++ riscv/sbi-tests.h | 2 + riscv/sbi.c | 3 +- 5 files changed, 840 insertions(+), 1 deletion(-) create mode 100644 riscv/sbi-dbtr.c diff --git a/lib/riscv/asm/sbi.h b/lib/riscv/asm/sbi.h index a5738a5c..78fd6e2a 100644 --- a/lib/riscv/asm/sbi.h +++ b/lib/riscv/asm/sbi.h @@ -51,6 +51,7 @@ enum sbi_ext_id { SBI_EXT_SUSP = 0x53555350, SBI_EXT_FWFT = 0x46574654, SBI_EXT_SSE = 0x535345, + SBI_EXT_DBTR = 0x44425452, }; enum sbi_ext_base_fid { diff --git a/riscv/Makefile b/riscv/Makefile index 11e68eae..9309ac12 100644 --- a/riscv/Makefile +++ b/riscv/Makefile @@ -18,6 +18,7 @@ tests += $(TEST_DIR)/sieve.$(exe) all: $(tests) $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-asm.o +$(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-dbtr.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-fwft.o $(TEST_DIR)/sbi-deps += $(TEST_DIR)/sbi-sse.o diff --git a/riscv/sbi-dbtr.c b/riscv/sbi-dbtr.c new file mode 100644 index 00000000..71ffcd32 --- /dev/null +++ b/riscv/sbi-dbtr.c @@ -0,0 +1,834 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SBI DBTR testsuite + * + * Copyright (C) 2025, Rivos Inc., Jesse Taube <jesse(a)rivosinc.com> + */ + +#include <libcflat.h> +#include <bitops.h> + +#include <asm/io.h> +#include <asm/processor.h> + +#include "sbi-tests.h" + +#define RV_MAX_TRIGGERS 32 + +#define SBI_DBTR_TRIG_STATE_MAPPED BIT(0) +#define SBI_DBTR_TRIG_STATE_U BIT(1) +#define SBI_DBTR_TRIG_STATE_S BIT(2) +#define SBI_DBTR_TRIG_STATE_VU BIT(3) +#define SBI_DBTR_TRIG_STATE_VS BIT(4) +#define SBI_DBTR_TRIG_STATE_HAVE_HW_TRIG BIT(5) +#define SBI_DBTR_TRIG_STATE_RESERVED GENMASK(7, 6) + +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT 8 +#define SBI_DBTR_TRIG_STATE_HW_TRIG_IDX(trig_state) (trig_state >> SBI_DBTR_TRIG_STATE_HW_TRIG_IDX_SHIFT) + +#define SBI_DBTR_TDATA1_TYPE_SHIFT (__riscv_xlen - 4) +#define SBI_DBTR_TDATA1_DMODE BIT_UL(__riscv_xlen - 5) + +#define SBI_DBTR_TDATA1_MCONTROL6_LOAD BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL6_STORE BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL6_EXECUTE BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL6_U BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL6_S BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL6_M BIT(6) +#define SBI_DBTR_TDATA1_MCONTROL6_SELECT BIT(21) +#define SBI_DBTR_TDATA1_MCONTROL6_VU BIT(23) +#define SBI_DBTR_TDATA1_MCONTROL6_VS BIT(24) + +#define SBI_DBTR_TDATA1_MCONTROL_LOAD BIT(0) +#define SBI_DBTR_TDATA1_MCONTROL_STORE BIT(1) +#define SBI_DBTR_TDATA1_MCONTROL_EXECUTE BIT(2) +#define SBI_DBTR_TDATA1_MCONTROL_U BIT(3) +#define SBI_DBTR_TDATA1_MCONTROL_S BIT(4) +#define SBI_DBTR_TDATA1_MCONTROL_M BIT(6) +#define SBI_DBTR_TDATA1_MCONTROL_SELECT BIT(19) + +enum McontrolType { + SBI_DBTR_TDATA1_TYPE_NONE = (0UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_LEGACY = (1UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL = (2UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ICOUNT = (3UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ITRIGGER = (4UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_ETRIGGER = (5UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_MCONTROL6 = (6UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_TMEXTTRIGGER = (7UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED0 = (8UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED1 = (9UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED2 = (10UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_RESERVED3 = (11UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM0 = (12UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM1 = (13UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_CUSTOM2 = (14UL << SBI_DBTR_TDATA1_TYPE_SHIFT), + SBI_DBTR_TDATA1_TYPE_DISABLED = (15UL << SBI_DBTR_TDATA1_TYPE_SHIFT), +}; + +enum Tdata1Value { + VALUE_NONE = 0, + VALUE_LOAD = BIT(0), + VALUE_STORE = BIT(1), + VALUE_EXECUTE = BIT(2), +}; + +enum Tdata1Mode { + MODE_NONE = 0, + MODE_M = BIT(0), + MODE_U = BIT(1), + MODE_S = BIT(2), + MODE_VU = BIT(3), + MODE_VS = BIT(4), +}; + +enum sbi_ext_dbtr_fid { + SBI_EXT_DBTR_NUM_TRIGGERS = 0, + SBI_EXT_DBTR_SETUP_SHMEM, + SBI_EXT_DBTR_TRIGGER_READ, + SBI_EXT_DBTR_TRIGGER_INSTALL, + SBI_EXT_DBTR_TRIGGER_UPDATE, + SBI_EXT_DBTR_TRIGGER_UNINSTALL, + SBI_EXT_DBTR_TRIGGER_ENABLE, + SBI_EXT_DBTR_TRIGGER_DISABLE, +}; + +struct sbi_dbtr_data_msg { + unsigned long tstate; + unsigned long tdata1; + unsigned long tdata2; + unsigned long tdata3; +}; + +struct sbi_dbtr_id_msg { + unsigned long idx; +}; + +/* SBI shared mem messages layout */ +struct sbi_dbtr_shmem_entry { + union { + struct sbi_dbtr_data_msg data; + struct sbi_dbtr_id_msg id; + }; +}; + +static bool dbtr_handled; + +/* Expected to be leaf function as not to disrupt frame-pointer */ +static __attribute__((naked)) void exec_call(void) +{ + /* skip over nop when triggered instead of ret. */ + asm volatile (".option push\n" + ".option arch, -c\n" + "nop\n" + "ret\n" + ".option pop\n"); +} + +static void dbtr_exception_handler(struct pt_regs *regs) +{ + dbtr_handled = true; + + /* Reading *epc may cause a fault, skip over nop */ + if ((void *)regs->epc == exec_call) { + regs->epc += 4; + return; + } + + /* WARNING: Skips over the trapped intruction */ + regs->epc += RV_INSN_LEN(readw((void *)regs->epc)); +} + +static bool do_store(void *tdata2) +{ + bool ret; + + writel(0, tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_load(void *tdata2) +{ + bool ret; + + readl(tdata2); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static bool do_exec(void) +{ + bool ret; + + exec_call(); + + ret = dbtr_handled; + dbtr_handled = false; + + return ret; +} + +static unsigned long gen_tdata1_mcontrol(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_LOAD; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_STORE; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_EXECUTE; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_M; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_U; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL_S; + + return tdata1; +} + +static unsigned long gen_tdata1_mcontrol6(enum Tdata1Mode mode, enum Tdata1Value value) +{ + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + if (value & VALUE_LOAD) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_LOAD; + + if (value & VALUE_STORE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_STORE; + + if (value & VALUE_EXECUTE) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_EXECUTE; + + if (mode & MODE_M) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_M; + + if (mode & MODE_U) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_U; + + if (mode & MODE_S) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_S; + + if (mode & MODE_VU) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VU; + + if (mode & MODE_VS) + tdata1 |= SBI_DBTR_TDATA1_MCONTROL6_VS; + + return tdata1; +} + +static unsigned long gen_tdata1(enum McontrolType type, enum Tdata1Value value, enum Tdata1Mode mode) +{ + switch (type) { + case SBI_DBTR_TDATA1_TYPE_MCONTROL: + return gen_tdata1_mcontrol(mode, value); + case SBI_DBTR_TDATA1_TYPE_MCONTROL6: + return gen_tdata1_mcontrol6(mode, value); + default: + assert_msg(false, "Invalid mcontrol type: %lu", type); + } +} + +static struct sbiret sbi_debug_num_triggers(unsigned long trig_tdata1) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_NUM_TRIGGERS, trig_tdata1, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_set_shmem_raw(unsigned long shmem_phys_lo, + unsigned long shmem_phys_hi, + unsigned long flags) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_SETUP_SHMEM, shmem_phys_lo, + shmem_phys_hi, flags, 0, 0, 0); +} + +static struct sbiret sbi_debug_set_shmem(void *shmem) +{ + unsigned long base_addr_lo, base_addr_hi; + + split_phys_addr(virt_to_phys(shmem), &base_addr_hi, &base_addr_lo); + return sbi_debug_set_shmem_raw(base_addr_lo, base_addr_hi, 0); +} + +static struct sbiret sbi_debug_read_triggers(unsigned long trig_idx_base, + unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_READ, trig_idx_base, + trig_count, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_install_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_INSTALL, trig_count, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_update_triggers(unsigned long trig_count) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UPDATE, trig_count, 0, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_uninstall_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_UNINSTALL, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_enable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_ENABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static struct sbiret sbi_debug_disable_triggers(unsigned long trig_idx_base, + unsigned long trig_idx_mask) +{ + return sbi_ecall(SBI_EXT_DBTR, SBI_EXT_DBTR_TRIGGER_DISABLE, trig_idx_base, + trig_idx_mask, 0, 0, 0, 0); +} + +static bool dbtr_install_trigger(struct sbi_dbtr_shmem_entry *shmem, void *trigger, + unsigned long control) +{ + struct sbiret sbi_ret; + bool ret; + + shmem->data.tdata1 = control; + shmem->data.tdata2 = (unsigned long)trigger; + + sbi_ret = sbi_debug_install_triggers(1); + ret = sbiret_report_error(&sbi_ret, SBI_SUCCESS, "sbi_debug_install_triggers"); + if (ret) + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + return ret; +} + +static bool dbtr_uninstall_trigger(void) +{ + struct sbiret ret; + + install_exception_handler(EXC_BREAKPOINT, NULL); + + ret = sbi_debug_uninstall_triggers(0, 1); + return sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static unsigned long dbtr_test_num_triggers(void) +{ + struct sbiret ret; + unsigned long tdata1 = 0; + /* sbi_debug_num_triggers will return trig_max in sbiret.value when trig_tdata1 == 0 */ + + report_prefix_push("available triggers"); + + /* should be at least one trigger. */ + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_num_triggers"); + + if (ret.value == 0) { + report_fail("Returned 0 triggers available"); + } else { + report_pass("Returned triggers available"); + report_info("Returned %lu triggers available", ret.value); + } + + report_prefix_pop(); + return ret.value; +} + +static enum McontrolType dbtr_test_type(unsigned long *num_trig) +{ + struct sbiret ret; + unsigned long tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL6; + + report_prefix_push("test type"); + report_prefix_push("sbi_debug_num_triggers"); + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "mcontrol6"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("Returned mcontrol6 triggers available"); + report_info("Returned %lu mcontrol6 triggers available", + ret.value); + report_prefix_popn(2); + return tdata1; + } + + tdata1 = SBI_DBTR_TDATA1_TYPE_MCONTROL; + + ret = sbi_debug_num_triggers(tdata1); + sbiret_report_error(&ret, SBI_SUCCESS, "mcontrol"); + *num_trig = ret.value; + if (ret.value > 0) { + report_pass("Returned mcontrol triggers available"); + report_info("Returned %lu mcontrol triggers available", + ret.value); + report_prefix_popn(2); + return tdata1; + } + + report_fail("Returned 0 mcontrol(6) triggers available"); + report_prefix_popn(2); + + return SBI_DBTR_TDATA1_TYPE_NONE; +} + +static struct sbiret dbtr_test_store_install_uninstall(struct sbi_dbtr_shmem_entry *shmem, + enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("store trigger"); + + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_install_triggers(1); + if (!sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_install_triggers")) { + report_prefix_pop(); + return ret; + } + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(do_store(&test), "triggered"); + + if (do_load(&test)) + report_fail("triggered by load"); + + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_store(&test)) + report_fail("triggered after uninstall"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); + + return ret; +} + +static void dbtr_test_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + bool kfail; + + report_prefix_push("update trigger"); + + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + ret = sbi_debug_update_triggers(1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_update_triggers"); + + /* + * Known broken update_triggers. + * https://lore.kernel.org/opensbi/aDdp1UeUh7GugeHp@ghost/T/#t + */ + kfail = __sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 7); + report_kfail(kfail, do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_load(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("load trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_LOAD, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "triggered"); + + if (do_store(&test)) + report_fail("triggered by store"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable trigger"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + if (!report(!do_store(&test), "should not trigger")) { + dbtr_uninstall_trigger(); + report_prefix_pop(); + report_skip("enable trigger: no disable"); + + return; + } + + report_prefix_pop(); + report_prefix_push("enable trigger"); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + report(do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_exec(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + + report_prefix_push("exec trigger"); + /* check if loads and stores trigger exec */ + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + + if (do_load(&test)) + report_fail("triggered by load"); + + if (do_store(&test)) + report_fail("triggered by store"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + report_prefix_pop(); + return; + } + report(do_exec(), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("read trigger"); + if (!dbtr_install_trigger(shmem, &test, tdata1)) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + if (!report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx", tdata1)) + report_info("tdata1 found: 0x%016lx", shmem->data.tdata1); + if (!report(shmem->data.tdata2 == ((unsigned long)&test), "tdata2 expected: 0x%016lx", + (unsigned long)&test)) + report_info("tdata2 found: 0x%016lx", shmem->data.tdata2); + if (!report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx", tstatus_expected)) + report_info("tstate found: 0x%016lx", shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void check_exec(unsigned long base) +{ + struct sbiret ret; + + report(do_exec(), "exec triggered"); + + ret = sbi_debug_uninstall_triggers(base, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); +} + +static void dbtr_test_multiple(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type, + unsigned long num_trigs) +{ + static unsigned long test[2]; + struct sbiret ret; + bool have_three = num_trigs > 2; + + if (num_trigs < 2) { + report_skip("test multiple"); + return; + } + + report_prefix_push("test multiple"); + + if (!dbtr_install_trigger(shmem, &test[0], gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + if (!dbtr_install_trigger(shmem, &test[1], gen_tdata1(type, VALUE_LOAD, MODE_S))) + goto error; + if (have_three && + !dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) { + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + goto error; + } + + report(do_store(&test[0]), "store triggered"); + + if (do_load(&test[0])) + report_fail("store triggered by load"); + + report(do_load(&test[1]), "load triggered"); + + if (do_store(&test[1])) + report_fail("load triggered by store"); + + if (have_three) + check_exec(2); + + ret = sbi_debug_uninstall_triggers(1, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + if (do_load(&test[1])) + report_fail("load triggered after uninstall"); + + report(do_store(&test[0]), "store triggered"); + + if (!have_three && + dbtr_install_trigger(shmem, exec_call, gen_tdata1(type, VALUE_EXECUTE, MODE_S))) + check_exec(1); + +error: + ret = sbi_debug_uninstall_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_uninstall_triggers"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_multiple_types(struct sbi_dbtr_shmem_entry *shmem, unsigned long type) +{ + static unsigned long test; + + report_prefix_push("test multiple types"); + + /* check if loads and stores trigger exec */ + if (!dbtr_install_trigger(shmem, &test, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_load(&test), "load triggered"); + + report(do_store(&test), "store triggered"); + + dbtr_uninstall_trigger(); + + /* Check if exec works */ + if (!dbtr_install_trigger(shmem, exec_call, + gen_tdata1(type, VALUE_EXECUTE | VALUE_LOAD | VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_exec(), "exec triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_disable_uninstall(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable uninstall"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + dbtr_uninstall_trigger(); + + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + report(do_store(&test), "triggered"); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_enable(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + + report_prefix_push("uninstall enable"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + dbtr_uninstall_trigger(); + + ret = sbi_debug_enable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_enable_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_store(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_uninstall_update(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + static unsigned long test; + struct sbiret ret; + bool kfail; + + report_prefix_push("uninstall update"); + if (!dbtr_install_trigger(shmem, NULL, gen_tdata1(type, VALUE_NONE, MODE_NONE))) { + report_prefix_pop(); + return; + } + + dbtr_uninstall_trigger(); + + shmem->id.idx = 0; + shmem->data.tdata1 = gen_tdata1(type, VALUE_STORE, MODE_S); + shmem->data.tdata2 = (unsigned long)&test; + + /* + * Known broken update_triggers. + * https://lore.kernel.org/opensbi/aDdp1UeUh7GugeHp@ghost/T/#t + */ + kfail = __sbi_get_imp_id() == SBI_IMPL_OPENSBI && + __sbi_get_imp_version() < sbi_impl_opensbi_mk_version(1, 7); + ret = sbi_debug_update_triggers(1); + sbiret_kfail_error(kfail, &ret, SBI_ERR_FAILURE, "sbi_debug_update_triggers"); + + install_exception_handler(EXC_BREAKPOINT, dbtr_exception_handler); + + report(!do_store(&test), "should not trigger"); + + install_exception_handler(EXC_BREAKPOINT, NULL); + report_prefix_pop(); +} + +static void dbtr_test_disable_read(struct sbi_dbtr_shmem_entry *shmem, enum McontrolType type) +{ + const unsigned long tstatus_expected = SBI_DBTR_TRIG_STATE_S | SBI_DBTR_TRIG_STATE_MAPPED; + const unsigned long tdata1 = gen_tdata1(type, VALUE_STORE, MODE_NONE); + static unsigned long test; + struct sbiret ret; + + report_prefix_push("disable read"); + if (!dbtr_install_trigger(shmem, &test, gen_tdata1(type, VALUE_STORE, MODE_S))) { + report_prefix_pop(); + return; + } + + ret = sbi_debug_disable_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_disable_triggers"); + + ret = sbi_debug_read_triggers(0, 1); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_read_triggers"); + + if (!report(shmem->data.tdata1 == tdata1, "tdata1 expected: 0x%016lx", tdata1)) + report_info("tdata1 found: 0x%016lx", shmem->data.tdata1); + if (!report(shmem->data.tdata2 == ((unsigned long)&test), "tdata2 expected: 0x%016lx", + (unsigned long)&test)) + report_info("tdata2 found: 0x%016lx", shmem->data.tdata2); + if (!report(shmem->data.tstate == tstatus_expected, "tstate expected: 0x%016lx", tstatus_expected)) + report_info("tstate found: 0x%016lx", shmem->data.tstate); + + dbtr_uninstall_trigger(); + report_prefix_pop(); +} + +void check_dbtr(void) +{ + static struct sbi_dbtr_shmem_entry shmem[RV_MAX_TRIGGERS] = {}; + unsigned long num_trigs; + enum McontrolType trig_type; + struct sbiret ret; + + report_prefix_push("dbtr"); + + if (!sbi_probe(SBI_EXT_DBTR)) { + report_skip("extension not available"); + goto exit_test; + } + + num_trigs = dbtr_test_num_triggers(); + if (!num_trigs) + goto exit_test; + + trig_type = dbtr_test_type(&num_trigs); + if (trig_type == SBI_DBTR_TDATA1_TYPE_NONE) + goto exit_test; + + ret = sbi_debug_set_shmem(shmem); + sbiret_report_error(&ret, SBI_SUCCESS, "sbi_debug_set_shmem"); + + ret = dbtr_test_store_install_uninstall(&shmem[0], trig_type); + /* install or uninstall failed */ + if (ret.error != SBI_SUCCESS) + goto exit_test; + + dbtr_test_load(&shmem[0], trig_type); + dbtr_test_exec(&shmem[0], trig_type); + dbtr_test_read(&shmem[0], trig_type); + dbtr_test_disable_enable(&shmem[0], trig_type); + dbtr_test_update(&shmem[0], trig_type); + dbtr_test_multiple_types(&shmem[0], trig_type); + dbtr_test_multiple(shmem, trig_type, num_trigs); + dbtr_test_disable_uninstall(&shmem[0], trig_type); + dbtr_test_uninstall_enable(&shmem[0], trig_type); + dbtr_test_uninstall_update(&shmem[0], trig_type); + dbtr_test_disable_read(&shmem[0], trig_type); + +exit_test: + report_prefix_pop(); +} diff --git a/riscv/sbi-tests.h b/riscv/sbi-tests.h index d5c4ae70..c1ebf016 100644 --- a/riscv/sbi-tests.h +++ b/riscv/sbi-tests.h @@ -97,8 +97,10 @@ static inline bool env_enabled(const char *env) return s && (*s == '1' || *s == 'y' || *s == 'Y'); } +void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo); void sbi_bad_fid(int ext); void check_sse(void); +void check_dbtr(void); #endif /* __ASSEMBLER__ */ #endif /* _RISCV_SBI_TESTS_H_ */ diff --git a/riscv/sbi.c b/riscv/sbi.c index edb1a6be..3b8aadce 100644 --- a/riscv/sbi.c +++ b/riscv/sbi.c @@ -105,7 +105,7 @@ static int rand_online_cpu(prng_state *ps) return cpu; } -static void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo) +void split_phys_addr(phys_addr_t paddr, unsigned long *hi, unsigned long *lo) { *lo = (unsigned long)paddr; *hi = 0; @@ -1561,6 +1561,7 @@ int main(int argc, char **argv) check_susp(); check_sse(); check_fwft(); + check_dbtr(); return report_summary(); } -- 2.43.0

2 months, 1 week

2
1
0 0

[PATCH resend] rtc: Rename lib_test to rtc_lib_test

by Geert Uytterhoeven

When compiling the RTC library functions test as a module, the module has the non-descriptive name "lib_test.ko". Fix this by adding the subsystem's name as a prefix. Signed-off-by: Geert Uytterhoeven <geert(a)linux-m68k.org> --- drivers/rtc/Makefile | 2 +- drivers/rtc/{lib_test.c => rtc_lib_test.c} | 0 2 files changed, 1 insertion(+), 1 deletion(-) rename drivers/rtc/{lib_test.c => rtc_lib_test.c} (100%) diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile index 4619aa2ac4697591..aa08d1c8a32ec23d 100644 --- a/drivers/rtc/Makefile +++ b/drivers/rtc/Makefile @@ -15,7 +15,7 @@ rtc-core-$(CONFIG_RTC_INTF_DEV) += dev.o rtc-core-$(CONFIG_RTC_INTF_PROC) += proc.o rtc-core-$(CONFIG_RTC_INTF_SYSFS) += sysfs.o -obj-$(CONFIG_RTC_LIB_KUNIT_TEST) += lib_test.o +obj-$(CONFIG_RTC_LIB_KUNIT_TEST) += rtc_lib_test.o # Keep the list ordered. diff --git a/drivers/rtc/lib_test.c b/drivers/rtc/rtc_lib_test.c similarity index 100% rename from drivers/rtc/lib_test.c rename to drivers/rtc/rtc_lib_test.c -- 2.43.0

2 months, 1 week

2
2
0 0

[PATCH net-next] selftests: devmem: configure HDS threshold

by Taehee Yoo

The devmem TCP requires the hds-thresh value to be 0, but it doesn't change it automatically. Therefore, configure_hds_thresh() is added to handle this. The run_devmem_tests() now tests hds_thresh, but it skips test if the hds_thresh_max value is 0. Signed-off-by: Taehee Yoo <ap420073(a)gmail.com> --- .../selftests/drivers/net/hw/ncdevmem.c | 86 +++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index cc9b40d9c5d5..d78b5e5697d7 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -349,6 +349,72 @@ static int configure_headersplit(bool on) return ret; } +static int configure_hds_thresh(int len) +{ + struct ethtool_rings_get_req *get_req; + struct ethtool_rings_get_rsp *get_rsp; + struct ethtool_rings_set_req *req; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret; + + ys = ynl_sock_create(&ynl_ethtool_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + req = ethtool_rings_set_req_alloc(); + ethtool_rings_set_req_set_header_dev_index(req, ifindex); + ethtool_rings_set_req_set_hds_thresh(req, len); + ret = ethtool_rings_set(ys, req); + if (ret < 0) + fprintf(stderr, "YNL failed: %s\n", ys->err.msg); + ethtool_rings_set_req_free(req); + + if (ret == 0) { + get_req = ethtool_rings_get_req_alloc(); + ethtool_rings_get_req_set_header_dev_index(get_req, ifindex); + get_rsp = ethtool_rings_get(ys, get_req); + ethtool_rings_get_req_free(get_req); + if (get_rsp) + fprintf(stderr, "HDS threshold: %d\n", + get_rsp->hds_thresh); + ethtool_rings_get_rsp_free(get_rsp); + } + + ynl_sock_destroy(ys); + + return ret; +} + +static int get_hds_thresh_max(void) +{ + struct ethtool_rings_get_req *get_req; + struct ethtool_rings_get_rsp *get_rsp; + struct ynl_error yerr; + unsigned int ret = 0; + struct ynl_sock *ys; + + ys = ynl_sock_create(&ynl_ethtool_family, &yerr); + if (!ys) { + fprintf(stderr, "YNL: %s\n", yerr.msg); + return -1; + } + + get_req = ethtool_rings_get_req_alloc(); + ethtool_rings_get_req_set_header_dev_index(get_req, ifindex); + get_rsp = ethtool_rings_get(ys, get_req); + ethtool_rings_get_req_free(get_req); + if (get_rsp) + ret = get_rsp->hds_thresh_max; + ethtool_rings_get_rsp_free(get_rsp); + + ynl_sock_destroy(ys); + + return ret; +} + static int configure_rss(void) { return run_command("sudo ethtool -X %s equal %d >&2", ifname, start_queue); @@ -565,6 +631,9 @@ static int do_server(struct memory_buffer *mem) if (configure_headersplit(1)) error(1, 0, "Failed to enable TCP header split\n"); + if (configure_hds_thresh(0)) + error(1, 0, "Failed to set HDS threshold\n"); + /* Configure RSS to divert all traffic from our devmem queues */ if (configure_rss()) error(1, 0, "Failed to configure rss\n"); @@ -725,10 +794,14 @@ static int do_server(struct memory_buffer *mem) void run_devmem_tests(void) { struct memory_buffer *mem; + int hds_thresh_max = 0; struct ynl_sock *ys; mem = provider->alloc(getpagesize() * NUM_PAGES); + hds_thresh_max = get_hds_thresh_max(); + if (hds_thresh_max < 0) + error(1, 0, "Failed to get hds_thresh_max"); /* Configure RSS to divert all traffic from our devmem queues */ if (configure_rss()) error(1, 0, "rss error\n"); @@ -750,6 +823,19 @@ void run_devmem_tests(void) if (configure_headersplit(1)) error(1, 0, "Failed to configure header split\n"); + /* Do not test hds_thresh if hds_thresh_max value is 0 */ + if (hds_thresh_max) { + if (configure_hds_thresh(1)) + error(1, 0, "Failed to configure HDS threshold\n"); + + if (!bind_rx_queue(ifindex, mem->fd, create_queues(), + num_queues, &ys)) + error(1, 0, "Configure dmabuf with non-zero HDS threshold should have failed\n"); + + if (configure_hds_thresh(0)) + error(1, 0, "Failed to configure HDS threshold\n"); + } + if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) error(1, 0, "Failed to bind\n"); -- 2.34.1

2 months, 1 week

3
4
0 0

[PATCH] selftests: cachestat: add tests for mmap

by Suresh K C

From: Suresh K C <suresh.k.chandrappa(a)gmail.com> Add a test case to verify cachestat behavior with memory-mapped files using mmap(). This ensures that pages accessed via mmap are correctly accounted for in the page cache. Tested on x86_64 with default kernel config Signed-off-by: Suresh K C <suresh.k.chandrappa(a)gmail.com> --- .../selftests/cachestat/test_cachestat.c | 39 ++++++++++++++++--- 1 file changed, 33 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/cachestat/test_cachestat.c b/tools/testing/selftests/cachestat/test_cachestat.c index 632ab44737ec..b6452978dae0 100644 --- a/tools/testing/selftests/cachestat/test_cachestat.c +++ b/tools/testing/selftests/cachestat/test_cachestat.c @@ -33,6 +33,11 @@ void print_cachestat(struct cachestat *cs) cs->nr_evicted, cs->nr_recently_evicted); } +enum file_type { + FILE_MMAP, + FILE_SHMEM +}; + bool write_exactly(int fd, size_t filesize) { int random_fd = open("/dev/urandom", O_RDONLY); @@ -202,7 +207,7 @@ static int test_cachestat(const char *filename, bool write_random, bool create, return ret; } -bool test_cachestat_shmem(void) +bool run_cachestat_test(enum file_type type) { size_t PS = sysconf(_SC_PAGESIZE); size_t filesize = PS * 512 * 2; /* 2 2MB huge pages */ @@ -212,27 +217,43 @@ bool test_cachestat_shmem(void) char *filename = "tmpshmcstat"; struct cachestat cs; bool ret = true; + int fd; unsigned long num_pages = compute_len / PS; - int fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + if (type == FILE_SHMEM) + fd = shm_open(filename, O_CREAT | O_RDWR, 0600); + else + fd = open(filename, O_RDWR | O_CREAT | O_TRUNC, 0666); if (fd < 0) { - ksft_print_msg("Unable to create shmem file.\n"); + ksft_print_msg("Unable to create file.\n"); ret = false; goto out; } if (ftruncate(fd, filesize)) { - ksft_print_msg("Unable to truncate shmem file.\n"); + ksft_print_msg("Unable to truncate file.\n"); ret = false; goto close_fd; } if (!write_exactly(fd, filesize)) { - ksft_print_msg("Unable to write to shmem file.\n"); + ksft_print_msg("Unable to write to file.\n"); ret = false; goto close_fd; } + if (type == FILE_MMAP){ + char *map = mmap(NULL, filesize, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (map == MAP_FAILED) { + ksft_print_msg("mmap failed.\n"); + ret = false; + goto close_fd; + } + for (int i = 0; i < filesize; i++) { + map[i] = 'A'; + } + map[filesize - 1] = 'X'; + } syscall_ret = syscall(__NR_cachestat, fd, &cs_range, &cs, 0); if (syscall_ret) { @@ -308,12 +329,18 @@ int main(void) break; } - if (test_cachestat_shmem()) + if (run_cachestat_test(FILE_SHMEM)) ksft_test_result_pass("cachestat works with a shmem file\n"); else { ksft_test_result_fail("cachestat fails with a shmem file\n"); ret = 1; } + if (run_cachestat_test(FILE_MMAP)) + ksft_test_result_pass("cachestat works with a mmap file\n"); + else { + ksft_test_result_fail("cachestat fails with a mmap file\n"); + ret = 1; + } return ret; } -- 2.43.0

2 months, 1 week

3
2
0 0

[PATCH v9 net-next 00/15] AccECN protocol patch series

by chia-yu.chang＠nokia-bell-labs.com

From: Chia-Yu Chang <chia-yu.chang(a)nokia-bell-labs.com> Hello, Please find the v9 AccECN protocol patch series, which covers the core functionality of Accurate ECN, AccECN negotiation, AccECN TCP options, and AccECN failure handling. The Accurate ECN draft can be found in https://datatracker.ietf.org/doc/html/draft-ietf-tcpm-accurate-ecn-28 This patch series is part of the full AccECN patch series, which is available at https://github.com/L4STeam/linux-net-next/commits/upstream_l4steam/ Best Regards, Chia-Yu --- v9 (21-Jun-2025) - Use tcp_data_ecn_check() to set TCP_ECN_SEE flag only for RFC3168 ECN (Paolo Abeni <pabeni(a)redhat.com>) - Add comments about setting TCP_ECN_SEEN flag for RFC3168 and Accruate ECN (Paolo Abeni <pabeni(a)redhat.com>) - Restruct the code in the for loop of tcp_accecn_process_option() (Paolo Abeni <pabeni(a)redhat.com>) - Remove ecn_bytes and add use_synack_ecn_bytes flag to identify whether syn_ack_bytes or received_ecn_bytes is used (Paolo Abeni <pabeni(a)redhat.com>) - Replace leftover_bytes and leftover_size with leftover_highbyte and leftover_lowbyte and add comments in tcp_options_write() (Paolo Abeni <pabeni(a)redhat.com>) - Add comments and commit message about the 1st retx SYN still attempt AccECN negotiation (Paolo Abeni <pabeni(a)redhat.com>) v8 (10-Jun-2025) - Add new helper function tcp_ecn_received_counters_payload() in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Set opts->num_sack_blocks=0 to avoid potential undefined value in #8 (Paolo Abeni <pabeni(a)redhat.com>) - Reset leftover_size to 2 once leftover_bytes is used in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_opt_demand_min() in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Add new helper function tcp_accecn_saw_opt_fail_recv() in #11 (Paolo Abeni <pabeni(a)redhat.com>) - Update tcp_options_fit_accecn() to avoid using recursion in #14 (Paolo Abeni <pabeni(a)redhat.com>) v7 (14-May-2025) - Modify group sizes of tcp_sock_write_txrx and tcp_sock_write_rx in #3 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Fix the issue in #4 and #5 where the RFC3168 ECN behavior in tcp_ecn_send() is changed (Paolo Abeni <pabeni(a)redhat.com>) - Modify group size of tcp_sock_write_txrx in #4 and #6 based on pahole results (Paolo Abeni <pabeni(a)redhat.com>) - Update commit message for #9 to explain the increase in tcp_sock_write_rx group size - Modify group size of tcp_sock_write_tx in #10 based on pahole results v6 (09-May-2025) - Add #3 to utilize exisintg holes of tcp_sock_write_txrx group for later patches (#4, #9, #10) with new u8 members (Paolo Abeni <pabeni(a)redhat.com>) - Add pahole outcomes before and after commit in #4, #5, #6, #9, #10, #15 (Paolo Abeni <pabeni(a)redhat.com>) - Define new helper function tcp_send_ack_reflect_ect() for sending ACK with reflected ECT in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add comments for function tcp_ecn_rcv_synack() in #5 (Paolo Abeni <pabeni(a)redhat.com>) - Add enum/define to be used by sysctl_tcp_ecn in #5, sysctl_tcp_ecn_option in #9, and sysctl_tcp_ecn_option_beacon in #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move accecn_fail_mode and saw_accecn_opt in #5 and #11 to use exisintg holes of tcp_sock (Paolo Abeni <pabeni(a)redhat.com>) - Change data type of new members of tcp_request_sock and move them to the end of struct in #5 and #11 (Paolo Abeni <pabeni(a)redhat.com>) - Move new members of tcp_info to the end of struct in #6 (Paolo Abeni <pabeni(a)redhat.com>) - Merge previous #7 into #9 (Paolo Abeni <pabeni(a)redhat.com>) - Mask ecnfield with INET_ECN_MASK to remove WARN_ONCE in #9 (Paolo Abeni <pabeni(a)redhat.com>) - Reduce the indentation levels for reabability in #9 and #10 (Paolo Abeni <pabeni(a)redhat.com>) - Move delivered_ecn_bytes to the RX group in #9, accecn_opt_tstamp to the TX group in #10, pkts_acked_ewma to the RX group in #15 (Paolo Abeni <pabeni(a)redhat.com>) - Add changes in Documentation/networking/net_cachelines/tcp_sock.rst for new tcp_sock members in #3, #5, #6, #9, #10, #15 v5 (22-Apr-2025) - Further fix for 32-bit ARM alignment in tcp.c (Simon Horman <horms(a)kernel.org>) v4 (18-Apr-2025) - Fix 32-bit ARM assertion for alignment requirement (Simon Horman <horms(a)kernel.org>) v3 (14-Apr-2025) - Fix patch apply issue in v2 (Jakub Kicinski <kuba(a)kernel.org>) v2 (18-Mar-2025) - Add one missing patch from the previous AccECN protocol preparation patch series to this patch series. --- Chia-Yu Chang (3): tcp: reorganize tcp_sock_write_txrx group for variables later tcp: accecn: AccECN option failure handling tcp: accecn: try to fit AccECN option with SACK Ilpo Järvinen (12): tcp: reorganize SYN ECN code tcp: fast path functions later tcp: AccECN core tcp: accecn: AccECN negotiation tcp: accecn: add AccECN rx byte counters tcp: accecn: AccECN needs to know delivered bytes tcp: sack option handling improvements tcp: accecn: AccECN option tcp: accecn: AccECN option send control tcp: accecn: AccECN option ceb/cep heuristic tcp: accecn: AccECN ACE field multi-wrap heuristic tcp: try to avoid safer when ACKs are thinned .../networking/net_cachelines/tcp_sock.rst | 14 + include/linux/tcp.h | 34 +- include/net/netns/ipv4.h | 2 + include/net/tcp.h | 225 ++++++- include/uapi/linux/tcp.h | 7 + net/ipv4/syncookies.c | 3 + net/ipv4/sysctl_net_ipv4.c | 19 + net/ipv4/tcp.c | 30 +- net/ipv4/tcp_input.c | 622 +++++++++++++++++- net/ipv4/tcp_ipv4.c | 7 +- net/ipv4/tcp_minisocks.c | 91 ++- net/ipv4/tcp_output.c | 325 ++++++++- net/ipv6/syncookies.c | 1 + net/ipv6/tcp_ipv6.c | 1 + 14 files changed, 1285 insertions(+), 96 deletions(-) -- 2.34.1

2 months, 1 week

3
28
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror June 2025