July 2024 - Linux-kselftest-mirror

[GIT PULL] Kselftest fixes for Linux 6.10

by Shuah Khan

Hi Linus, Please pull this kselftest fixes update for Linux 6.10. This kselftest fixes update for Linux 6.10 consists of fixes to clang build failures to timerns, vDSO tests and fixes to vDSO makefile. Note: makefile fixes are included to avoid conflicts during 6.11 merge window. diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 48236960c06d32370bfa6f2cc408e786873262c8: selftests/resctrl: Fix non-contiguous CBM for AMD (2024-06-26 13:22:34 -0600) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux_kselftest-fixes-6.10 for you to fetch changes up to 66cde337fa1b7c6cf31f856fa015bd91a4d383e7: selftests/vDSO: remove duplicate compiler invocations from Makefile (2024-07-05 14:12:34 -0600) ---------------------------------------------------------------- linux_kselftest-fixes-6.10 This kselftest fixes update for Linux 6.10 consists of fixes to clang build failures to timerns, vDSO tests and fixes to vDSO makefile. ---------------------------------------------------------------- John Hubbard (4): selftest/timerns: fix clang build failures for abs() calls selftests/vDSO: fix clang build errors and warnings selftests/vDSO: remove partially duplicated "all:" target in Makefile selftests/vDSO: remove duplicate compiler invocations from Makefile tools/testing/selftests/timens/exec.c | 6 ++--- tools/testing/selftests/timens/timer.c | 2 +- tools/testing/selftests/timens/timerfd.c | 2 +- tools/testing/selftests/timens/vfork_exec.c | 4 +-- tools/testing/selftests/vDSO/Makefile | 29 +++++++++------------- tools/testing/selftests/vDSO/parse_vdso.c | 16 ++++++++---- .../selftests/vDSO/vdso_standalone_test_x86.c | 18 ++++++++++++-- 7 files changed, 46 insertions(+), 31 deletions(-) ----------------------------------------------------------------

5 months, 2 weeks

2
1
0 0

[PATCH v22 4/4] selftests/vDSO: add tests for vgetrandom

by Jason A. Donenfeld

This adds two tests for vgetrandom. The first one, vdso_test_chacha, simply checks that the assembly implementation of chacha20 matches that of libsodium, a basic sanity check that should catch most errors. The second, vdso_test_getrandom, is a full "libc-like" implementation of the userspace side of vgetrandom() support. It's meant to be used also as example code for libcs that might be integrating this. Cc: linux-kselftest(a)vger.kernel.org Signed-off-by: Jason A. Donenfeld <Jason(a)zx2c4.com> --- tools/include/asm/rwonce.h | 0 tools/testing/selftests/vDSO/.gitignore | 2 + tools/testing/selftests/vDSO/Makefile | 18 ++ .../testing/selftests/vDSO/vdso_test_chacha.c | 43 +++ .../selftests/vDSO/vdso_test_getrandom.c | 288 ++++++++++++++++++ 5 files changed, 351 insertions(+) create mode 100644 tools/include/asm/rwonce.h create mode 100644 tools/testing/selftests/vDSO/vdso_test_chacha.c create mode 100644 tools/testing/selftests/vDSO/vdso_test_getrandom.c diff --git a/tools/include/asm/rwonce.h b/tools/include/asm/rwonce.h new file mode 100644 index 000000000000..e69de29bb2d1 diff --git a/tools/testing/selftests/vDSO/.gitignore b/tools/testing/selftests/vDSO/.gitignore index a8dc51af5a9c..30d5c8f0e5c7 100644 --- a/tools/testing/selftests/vDSO/.gitignore +++ b/tools/testing/selftests/vDSO/.gitignore @@ -6,3 +6,5 @@ vdso_test_correctness vdso_test_gettimeofday vdso_test_getcpu vdso_standalone_test_x86 +vdso_test_getrandom +vdso_test_chacha diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile index 98d8ba2afa00..3de8e7e052ae 100644 --- a/tools/testing/selftests/vDSO/Makefile +++ b/tools/testing/selftests/vDSO/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 uname_M := $(shell uname -m 2>/dev/null || echo not) ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/) +SODIUM := $(shell pkg-config --libs libsodium 2>/dev/null) TEST_GEN_PROGS := vdso_test_gettimeofday TEST_GEN_PROGS += vdso_test_getcpu @@ -10,6 +11,12 @@ ifeq ($(ARCH),$(filter $(ARCH),x86 x86_64)) TEST_GEN_PROGS += vdso_standalone_test_x86 endif TEST_GEN_PROGS += vdso_test_correctness +ifeq ($(uname_M),x86_64) +TEST_GEN_PROGS += vdso_test_getrandom +ifneq ($(SODIUM),) +TEST_GEN_PROGS += vdso_test_chacha +endif +endif CFLAGS := -std=gnu99 @@ -28,3 +35,14 @@ $(OUTPUT)/vdso_standalone_test_x86: CFLAGS +=-nostdlib -fno-asynchronous-unwind- $(OUTPUT)/vdso_test_correctness: vdso_test_correctness.c $(OUTPUT)/vdso_test_correctness: LDFLAGS += -ldl + +$(OUTPUT)/vdso_test_getrandom: parse_vdso.c +$(OUTPUT)/vdso_test_getrandom: CFLAGS += -isystem $(top_srcdir)/tools/include \ + -isystem $(top_srcdir)/include/uapi + +$(OUTPUT)/vdso_test_chacha: $(top_srcdir)/arch/$(ARCH)/entry/vdso/vgetrandom-chacha.S +$(OUTPUT)/vdso_test_chacha: CFLAGS += -idirafter $(top_srcdir)/tools/include \ + -isystem $(top_srcdir)/arch/$(ARCH)/include \ + -isystem $(top_srcdir)/include \ + -D__ASSEMBLY__ -DBULID_VDSO -DCONFIG_FUNCTION_ALIGNMENT=0 \ + -Wa,--noexecstack $(SODIUM) diff --git a/tools/testing/selftests/vDSO/vdso_test_chacha.c b/tools/testing/selftests/vDSO/vdso_test_chacha.c new file mode 100644 index 000000000000..e38f44e5f803 --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_test_chacha.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason(a)zx2c4.com>. All Rights Reserved. + */ + +#include <sodium/crypto_stream_chacha20.h> +#include <sys/random.h> +#include <string.h> +#include <stdint.h> +#include "../kselftest.h" + +extern void __arch_chacha20_blocks_nostack(uint8_t *dst_bytes, const uint8_t *key, uint32_t *counter, size_t nblocks); + +int main(int argc, char *argv[]) +{ + enum { TRIALS = 1000, BLOCKS = 128, BLOCK_SIZE = 64 }; + static const uint8_t nonce[8] = { 0 }; + uint32_t counter[2]; + uint8_t key[32]; + uint8_t output1[BLOCK_SIZE * BLOCKS], output2[BLOCK_SIZE * BLOCKS]; + + ksft_print_header(); + ksft_set_plan(1); + + for (unsigned int trial = 0; trial < TRIALS; ++trial) { + if (getrandom(key, sizeof(key), 0) != sizeof(key)) { + printf("getrandom() failed!\n"); + return KSFT_SKIP; + } + crypto_stream_chacha20(output1, sizeof(output1), nonce, key); + for (unsigned int split = 0; split < BLOCKS; ++split) { + memset(output2, 'X', sizeof(output2)); + memset(counter, 0, sizeof(counter)); + if (split) + __arch_chacha20_blocks_nostack(output2, key, counter, split); + __arch_chacha20_blocks_nostack(output2 + split * BLOCK_SIZE, key, counter, BLOCKS - split); + if (memcmp(output1, output2, sizeof(output1))) + return KSFT_FAIL; + } + } + ksft_test_result_pass("chacha: PASS\n"); + return KSFT_PASS; +} diff --git a/tools/testing/selftests/vDSO/vdso_test_getrandom.c b/tools/testing/selftests/vDSO/vdso_test_getrandom.c new file mode 100644 index 000000000000..05122425a873 --- /dev/null +++ b/tools/testing/selftests/vDSO/vdso_test_getrandom.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason(a)zx2c4.com>. All Rights Reserved. + */ + +#include <assert.h> +#include <pthread.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <signal.h> +#include <sys/auxv.h> +#include <sys/mman.h> +#include <sys/random.h> +#include <sys/syscall.h> +#include <sys/types.h> +#include <linux/random.h> + +#include "../kselftest.h" +#include "parse_vdso.h" + +#ifndef timespecsub +#define timespecsub(tsp, usp, vsp) \ + do { \ + (vsp)->tv_sec = (tsp)->tv_sec - (usp)->tv_sec; \ + (vsp)->tv_nsec = (tsp)->tv_nsec - (usp)->tv_nsec; \ + if ((vsp)->tv_nsec < 0) { \ + (vsp)->tv_sec--; \ + (vsp)->tv_nsec += 1000000000L; \ + } \ + } while (0) +#endif + +static struct { + pthread_mutex_t lock; + void **states; + size_t len, cap; +} grnd_allocator = { + .lock = PTHREAD_MUTEX_INITIALIZER +}; + +static struct { + ssize_t(*fn)(void *, size_t, unsigned long, void *, size_t); + pthread_key_t key; + pthread_once_t initialized; + struct vgetrandom_opaque_params params; +} grnd_ctx = { + .initialized = PTHREAD_ONCE_INIT +}; + +static void *vgetrandom_get_state(void) +{ + void *state = NULL; + + pthread_mutex_lock(&grnd_allocator.lock); + if (!grnd_allocator.len) { + size_t page_size = getpagesize(); + size_t new_cap; + size_t alloc_size, num = sysconf(_SC_NPROCESSORS_ONLN); /* Just a decent heuristic. */ + void *new_block, *new_states; + + alloc_size = (num * grnd_ctx.params.size_of_opaque_state + page_size - 1) & (~(page_size - 1)); + num = (page_size / grnd_ctx.params.size_of_opaque_state) * (alloc_size / page_size); + new_block = mmap(0, alloc_size, grnd_ctx.params.mmap_prot, grnd_ctx.params.mmap_flags, -1, 0); + if (new_block == MAP_FAILED) + goto out; + + new_cap = grnd_allocator.cap + num; + new_states = reallocarray(grnd_allocator.states, new_cap, sizeof(*grnd_allocator.states)); + if (!new_states) + goto unmap; + grnd_allocator.cap = new_cap; + grnd_allocator.states = new_states; + + for (size_t i = 0; i < num; ++i) { + if (((uintptr_t)new_block & (page_size - 1)) + grnd_ctx.params.size_of_opaque_state > page_size) + new_block = (void *)(((uintptr_t)new_block + page_size - 1) & (~(page_size - 1))); + grnd_allocator.states[i] = new_block; + new_block += grnd_ctx.params.size_of_opaque_state; + } + grnd_allocator.len = num; + goto success; + + unmap: + munmap(new_block, alloc_size); + goto out; + } +success: + state = grnd_allocator.states[--grnd_allocator.len]; + +out: + pthread_mutex_unlock(&grnd_allocator.lock); + return state; +} + +static void vgetrandom_put_state(void *state) +{ + if (!state) + return; + pthread_mutex_lock(&grnd_allocator.lock); + grnd_allocator.states[grnd_allocator.len++] = state; + pthread_mutex_unlock(&grnd_allocator.lock); +} + +static void vgetrandom_init(void) +{ + if (pthread_key_create(&grnd_ctx.key, vgetrandom_put_state) != 0) + return; + unsigned long sysinfo_ehdr = getauxval(AT_SYSINFO_EHDR); + if (!sysinfo_ehdr) { + printf("AT_SYSINFO_EHDR is not present!\n"); + exit(KSFT_SKIP); + } + vdso_init_from_sysinfo_ehdr(sysinfo_ehdr); + grnd_ctx.fn = (__typeof__(grnd_ctx.fn))vdso_sym("LINUX_2.6", "__vdso_getrandom"); + if (!grnd_ctx.fn) { + printf("__vdso_getrandom is missing!\n"); + exit(KSFT_FAIL); + } + if (grnd_ctx.fn(NULL, 0, 0, &grnd_ctx.params, ~0UL) != 0) { + printf("failed to fetch vgetrandom params!\n"); + exit(KSFT_FAIL); + } +} + +static ssize_t vgetrandom(void *buf, size_t len, unsigned long flags) +{ + void *state; + + pthread_once(&grnd_ctx.initialized, vgetrandom_init); + state = pthread_getspecific(grnd_ctx.key); + if (!state) { + state = vgetrandom_get_state(); + if (pthread_setspecific(grnd_ctx.key, state) != 0) { + vgetrandom_put_state(state); + state = NULL; + } + if (!state) { + printf("vgetrandom_get_state failed!\n"); + exit(KSFT_FAIL); + } + } + return grnd_ctx.fn(buf, len, flags, state, grnd_ctx.params.size_of_opaque_state); +} + +enum { TRIALS = 25000000, THREADS = 256 }; + +static void *test_vdso_getrandom(void *) +{ + for (size_t i = 0; i < TRIALS; ++i) { + unsigned int val; + ssize_t ret = vgetrandom(&val, sizeof(val), 0); + assert(ret == sizeof(val)); + } + return NULL; +} + +static void *test_libc_getrandom(void *) +{ + for (size_t i = 0; i < TRIALS; ++i) { + unsigned int val; + ssize_t ret = getrandom(&val, sizeof(val), 0); + assert(ret == sizeof(val)); + } + return NULL; +} + +static void *test_syscall_getrandom(void *) +{ + for (size_t i = 0; i < TRIALS; ++i) { + unsigned int val; + ssize_t ret = syscall(__NR_getrandom, &val, sizeof(val), 0); + assert(ret == sizeof(val)); + } + return NULL; +} + +static void bench_single(void) +{ + struct timespec start, end, diff; + + clock_gettime(CLOCK_MONOTONIC, &start); + test_vdso_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + test_libc_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + test_syscall_getrandom(NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf("syscall: %u times in %lu.%09lu seconds\n", TRIALS, diff.tv_sec, diff.tv_nsec); +} + +static void bench_multi(void) +{ + struct timespec start, end, diff; + pthread_t threads[THREADS]; + + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_vdso_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" vdso: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_libc_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" libc: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); + + clock_gettime(CLOCK_MONOTONIC, &start); + for (size_t i = 0; i < THREADS; ++i) + assert(pthread_create(&threads[i], NULL, test_syscall_getrandom, NULL) == 0); + for (size_t i = 0; i < THREADS; ++i) + pthread_join(threads[i], NULL); + clock_gettime(CLOCK_MONOTONIC, &end); + timespecsub(&end, &start, &diff); + printf(" syscall: %u x %u times in %lu.%09lu seconds\n", TRIALS, THREADS, diff.tv_sec, diff.tv_nsec); +} + +static void fill(void) +{ + uint8_t weird_size[323929]; + for (;;) + vgetrandom(weird_size, sizeof(weird_size), 0); +} + +static void kselftest(void) +{ + uint8_t weird_size[1263]; + + ksft_print_header(); + ksft_set_plan(1); + + for (size_t i = 0; i < 1000; ++i) { + ssize_t ret = vgetrandom(weird_size, sizeof(weird_size), 0); + if (ret != sizeof(weird_size)) + exit(KSFT_FAIL); + } + + ksft_test_result_pass("getrandom: PASS\n"); + exit(KSFT_PASS); +} + +static void usage(const char *argv0) +{ + fprintf(stderr, "Usage: %s [bench-single|bench-multi|fill]\n", argv0); +} + +int main(int argc, char *argv[]) +{ + if (argc == 1) { + kselftest(); + return 0; + } + + if (argc != 2) { + usage(argv[0]); + return 1; + } + if (!strcmp(argv[1], "bench-single")) + bench_single(); + else if (!strcmp(argv[1], "bench-multi")) + bench_multi(); + else if (!strcmp(argv[1], "fill")) + fill(); + else { + usage(argv[0]); + return 1; + } + return 0; +} -- 2.45.2

5 months, 2 weeks

1
0
0 0

[PATCH 0/6] defconfig: drop RT_GROUP_SCHED=y

by Celeste Liu

For cgroup v1, if turned on, and there's any cgroup in the "cpu" hierarchy it needs an RT budget assigned, otherwise the processes in it will not be able to get RT at all. The problem with RT group scheduling is that it requires the budget assigned but there's no way we could assign a default budget, since the values to assign are both upper and lower time limits, are absolute, and need to be sum up to < 1 for each individal cgroup. That means we cannot really come up with values that would work by default in the general case.[1] For cgroup v2, it's almost unusable as well. If it turned on, the cpu controller can only be enabled when all RT processes are in the root cgroup. But it will lose the benefits of cgroup v2 if all RT process were placed in the same cgroup. Red Hat, Gentoo, Arch Linux and Debian all disable it. systemd also doesn't support it.[2] I leave tools/testing/selftests/bpf/config.{s390x,aarch64} untouched because I don't whether bpf testing requires it. [1]: https://bugzilla.redhat.com/show_bug.cgi?id=1229700 [2]: https://github.com/systemd/systemd/issues/13781#issuecomment-549164383 Celeste Liu (6): riscv: defconfig: drop RT_GROUP_SCHED=y loongarch: defconfig: drop RT_GROUP_SCHED=y mips: defconfig: drop RT_GROUP_SCHED=y from generic/db1xxx/eyeq5 powerpc: defconfig: drop RT_GROUP_SCHED=y from ppc6xx_defconfig sh: defconfig: drop RT_GROUP_SCHED=y from sdk7786/urquell arm: defconfig: drop RT_GROUP_SCHED=y from bcm2855/tegra/omap2plus arch/arm/configs/bcm2835_defconfig | 1 - arch/arm/configs/omap2plus_defconfig | 1 - arch/arm/configs/tegra_defconfig | 1 - arch/loongarch/configs/loongson3_defconfig | 1 - arch/mips/configs/db1xxx_defconfig | 1 - arch/mips/configs/eyeq5_defconfig | 1 - arch/mips/configs/generic_defconfig | 1 - arch/powerpc/configs/ppc6xx_defconfig | 1 - arch/riscv/configs/defconfig | 1 - arch/sh/configs/sdk7786_defconfig | 1 - arch/sh/configs/urquell_defconfig | 1 - 11 files changed, 11 deletions(-) -- 2.45.1

5 months, 2 weeks

6
12
0 0

[PATCH] selftests/bpf:fix a resource leak

by Zhu Jun

The requested resources should be closed before return in main(), otherwise resource leak will occur Signed-off-by: Zhu Jun <zhujun2(a)cmss.chinamobile.com> --- v1 -> v2: check for cg_fd >= 0 and have just one out label tools/testing/selftests/bpf/test_sockmap.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index a34e95040994..285a9a714666 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -2075,8 +2075,10 @@ int main(int argc, char **argv) if (!cg_fd) { cg_fd = cgroup_setup_and_join(CG_PATH); - if (cg_fd < 0) - return cg_fd; + if (cg_fd < 0) { + err = cg_fd; + goto out; + } cg_created = 1; } @@ -2092,7 +2094,7 @@ int main(int argc, char **argv) if (err) { fprintf(stderr, "populate program: (%s) %s\n", bpf_file, strerror(errno)); - return 1; + goto out; } running = 1; @@ -2109,7 +2111,8 @@ int main(int argc, char **argv) free(options.whitelist); if (options.blacklist) free(options.blacklist); - close(cg_fd); + if (cg_fd >= 0) + close(cg_fd); if (cg_created) cleanup_cgroup_environment(); return err; -- 2.17.1

5 months, 2 weeks

2
1
0 0

[PATCH] selftests/net: missing close function in randomize function

by Liu Jing

in randomize function, there is a open function, but there is no close function in the randomize, which is easy to cause memory leaks. Signed-off-by: Liu Jing <liujing(a)cmss.chinamobile.com> --- tools/testing/selftests/net/tcp_mmap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c index 4fcce5150850..ab305e262d0a 100644 --- a/tools/testing/selftests/net/tcp_mmap.c +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -438,6 +438,7 @@ static void randomize(void *target, size_t count) perror("read /dev/urandom"); exit(1); } + close(urandom); } int main(int argc, char *argv[]) -- 2.33.0

5 months, 2 weeks

2
1
0 0

Re: [PATCH net-next v7 3/3] selftests: add MSG_ZEROCOPY msg_control notification test

by Simon Horman

+ Dave Miller, Jakub Kicinski, Paolo Abeni, Shuah Khan, linux-kselftest(a)vger.kernel.org On Mon, Jul 08, 2024 at 09:04:05PM +0000, zijianzhang(a)bytedance.com wrote: > From: Zijian Zhang <zijianzhang(a)bytedance.com> > > We update selftests/net/msg_zerocopy.c to accommodate the new mechanism, > cfg_notification_limit has the same semantics for both methods. Test > results are as follows, we update skb_orphan_frags_rx to the same as > skb_orphan_frags to support zerocopy in the localhost test. > > cfg_notification_limit = 1, both method get notifications after 1 calling > of sendmsg. In this case, the new method has around 17% cpu savings in TCP > and 23% cpu savings in UDP. > +---------------------+---------+---------+---------+---------+ > | Test Type / Protocol| TCP v4 | TCP v6 | UDP v4 | UDP v6 | > +---------------------+---------+---------+---------+---------+ > | ZCopy (MB) | 7523 | 7706 | 7489 | 7304 | > +---------------------+---------+---------+---------+---------+ > | New ZCopy (MB) | 8834 | 8993 | 9053 | 9228 | > +---------------------+---------+---------+---------+---------+ > | New ZCopy / ZCopy | 117.42% | 116.70% | 120.88% | 126.34% | > +---------------------+---------+---------+---------+---------+ > > cfg_notification_limit = 32, both get notifications after 32 calling of > sendmsg, which means more chances to coalesce notifications, and less > overhead of poll + recvmsg for the original method. In this case, the new > method has around 7% cpu savings in TCP and slightly better cpu usage in > UDP. In the context of selftest, notifications of TCP are more likely to > out of order than UDP, it's easier to coalesce more notifications in UDP. > The original method can get one notification with range of 32 in a recvmsg > most of the time. In TCP, most notifications' range is around 2, so the > original method needs around 16 recvmsgs to get notified in one round. > That's the reason for the "New ZCopy / ZCopy" diff in TCP and UDP here. > +---------------------+---------+---------+---------+---------+ > | Test Type / Protocol| TCP v4 | TCP v6 | UDP v4 | UDP v6 | > +---------------------+---------+---------+---------+---------+ > | ZCopy (MB) | 8842 | 8735 | 10072 | 9380 | > +---------------------+---------+---------+---------+---------+ > | New ZCopy (MB) | 9366 | 9477 | 10108 | 9385 | > +---------------------+---------+---------+---------+---------+ > | New ZCopy / ZCopy | 106.00% | 108.28% | 100.31% | 100.01% | > +---------------------+---------+---------+---------+---------+ > > In conclusion, when notification interval is small or notifications are > hard to be coalesced, the new mechanism is highly recommended. Otherwise, > the performance gain from the new mechanism is very limited. > > Signed-off-by: Zijian Zhang <zijianzhang(a)bytedance.com> > Signed-off-by: Xiaochun Lu <xiaochun.lu(a)bytedance.com> > --- > tools/testing/selftests/net/msg_zerocopy.c | 111 ++++++++++++++++++-- > tools/testing/selftests/net/msg_zerocopy.sh | 1 + > 2 files changed, 105 insertions(+), 7 deletions(-) > > diff --git a/tools/testing/selftests/net/msg_zerocopy.c b/tools/testing/selftests/net/msg_zerocopy.c ... > @@ -466,6 +504,44 @@ static void do_recv_completions(int fd, int domain) > sends_since_notify = 0; > } > > +static void do_recv_completions2(void) > +{ > + struct cmsghdr *cm = (struct cmsghdr *)zc_ckbuf; > + struct zc_info *zc_info; > + __u32 hi, lo, range; > + __u8 zerocopy; > + int i; > + > + zc_info = (struct zc_info *)CMSG_DATA(cm); > + for (i = 0; i < zc_info->size; i++) { > + hi = zc_info->arr[i].hi; > + lo = zc_info->arr[i].lo; > + zerocopy = zc_info->arr[i].zerocopy; > + range = hi - lo + 1; > + > + if (cfg_verbose && lo != next_completion) > + fprintf(stderr, "gap: %u..%u does not append to %u\n", > + lo, hi, next_completion); > + next_completion = hi + 1; > + > + if (zerocopied == -1) > + zerocopied = zerocopy; > + else if (zerocopied != zerocopy) { > + fprintf(stderr, "serr: inconsistent\n"); > + zerocopied = zerocopy; > + } nit: If any arms of a conditional have {}, then all arms should have them > + > + completions += range; > + > + if (cfg_verbose >= 2) > + fprintf(stderr, "completed: %u (h=%u l=%u)\n", > + range, hi, lo); > + } > + > + sends_since_notify = 0; > + added_zcopy_info = false; > +} ...

5 months, 2 weeks

1
0
0 0

[PATCH net v5] skmsg: skip zero length skb in sk_msg_recvmsg

by Geliang Tang

From: Geliang Tang <tanggeliang(a)kylinos.cn> Run this BPF selftests (./test_progs -t sockmap_basic) on a Loongarch platform, a kernel panic occurs: ''' Oops[#1]: CPU: 22 PID: 2824 Comm: test_progs Tainted: G OE 6.10.0-rc2+ #18 Hardware name: LOONGSON Dabieshan/Loongson-TC542F0, BIOS Loongson-UDK2018 ... ... ra: 90000000048bf6c0 sk_msg_recvmsg+0x120/0x560 ERA: 9000000004162774 copy_page_to_iter+0x74/0x1c0 CRMD: 000000b0 (PLV0 -IE -DA +PG DACF=CC DACM=CC -WE) PRMD: 0000000c (PPLV0 +PIE +PWE) EUEN: 00000007 (+FPE +SXE +ASXE -BTE) ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7) ESTAT: 00010000 [PIL] (IS= ECode=1 EsubCode=0) BADV: 0000000000000040 PRID: 0014c011 (Loongson-64bit, Loongson-3C5000) Modules linked in: bpf_testmod(OE) xt_CHECKSUM xt_MASQUERADE xt_conntrack Process test_progs (pid: 2824, threadinfo=0000000000863a31, task=...) Stack : ... ... Call Trace: [<9000000004162774>] copy_page_to_iter+0x74/0x1c0 [<90000000048bf6c0>] sk_msg_recvmsg+0x120/0x560 [<90000000049f2b90>] tcp_bpf_recvmsg_parser+0x170/0x4e0 [<90000000049aae34>] inet_recvmsg+0x54/0x100 [<900000000481ad5c>] sock_recvmsg+0x7c/0xe0 [<900000000481e1a8>] __sys_recvfrom+0x108/0x1c0 [<900000000481e27c>] sys_recvfrom+0x1c/0x40 [<9000000004c076ec>] do_syscall+0x8c/0xc0 [<9000000003731da4>] handle_syscall+0xc4/0x160 Code: ... ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Fatal exception Kernel relocated by 0x3510000 .text @ 0x9000000003710000 .data @ 0x9000000004d70000 .bss @ 0x9000000006469400 ---[ end Kernel panic - not syncing: Fatal exception ]--- ''' This crash happens every time when running sockmap_skb_verdict_shutdown subtest in sockmap_basic. This crash is because a NULL pointer is passed to page_address() in sk_msg_recvmsg(). Due to the difference implementations depending on the architecture, page_address(NULL) will trigger a panic on Loongarch platform but not on X86 platform. So this bug was hidden on X86 platform for a while, but now it is exposed on Loongarch platform. The root cause is a zero length skb (skb->len == 0) is put on the queue. This zero length skb is a TCP FIN packet, which is sent by shutdown(), invoked in test_sockmap_skb_verdict_shutdown(): shutdown(p1, SHUT_WR); In this case, in sk_psock_skb_ingress_enqueue(), num_sge is zero, and no page is put to this sge (see sg_set_page in sg_set_page), but this empty sge is queued into ingress_msg list. And in sk_msg_recvmsg(), this empty sge is used, and a NULL page is got by sg_page(sge). Pass this NULL page to copy_page_to_iter(), which passes it to kmap_local_page() and to page_address(), then kernel panics. To solve this, we should skip this zero length skb. So in sk_msg_recvmsg(), if copy is zero, that means it's a zero length skb, skip invoking copy_page_to_iter(). We are using the EFAULT return triggered by copy_page_to_iter to check for is_fin in tcp_bpf.c. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Suggested-by: John Fastabend <john.fastabend(a)gmail.com> Signed-off-by: Geliang Tang <tanggeliang(a)kylinos.cn> --- v5: - update v5 as John suggested. - skmsg: skip zero length skb in sk_msg_recvmsg v4: - skmsg: skip empty sge in sk_msg_recvmsg v3: - skmsg: prevent empty ingress skb from enqueuing v2: - skmsg: null check for sg_page in sk_msg_recvmsg --- net/core/skmsg.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/core/skmsg.c b/net/core/skmsg.c index fd20aae30be2..bbf40b999713 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -434,7 +434,8 @@ int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg, page = sg_page(sge); if (copied + copy > len) copy = len - copied; - copy = copy_page_to_iter(page, sge->offset, copy, iter); + if (copy) + copy = copy_page_to_iter(page, sge->offset, copy, iter); if (!copy) { copied = copied ? copied : -EFAULT; goto out; -- 2.43.0

5 months, 2 weeks

3
2
0 0

[PATCH v3 0/2] selftests/resctrl: SNC kernel support discovery

by Maciej Wieczor-Retman

Changes v3: - Reworked patch 2. - Changed minor things in patch 1 like function name and made corrections to the patch message. Changes v2: - Removed patches 2 and 3 since now this part will be supported by the kernel. Sub-Numa Clustering (SNC) allows splitting CPU cores, caches and memory into multiple NUMA nodes. When enabled, NUMA-aware applications can achieve better performance on bigger server platforms. SNC support in the kernel is currently in review [1]. With SNC enabled and kernel support in place all the tests will function normally (aside from effective cache size). There might be a problem when SNC is enabled but the system is still using an older kernel version without SNC support. Currently the only message displayed in that situation is a guess that SNC might be enabled and is causing issues. That message also is displayed whenever the test fails on an Intel platform. Add a mechanism to discover kernel support for SNC which will add more meaning and certainty to the error message. Add runtime SNC mode detection and verify how reliable that information is. Series was tested on Ice Lake server platforms with SNC disabled, SNC-2 and SNC-4. The tests were also ran with and without kernel support for SNC. Series applies cleanly on kselftest/next. [1] https://lore.kernel.org/all/20240628215619.76401-1-tony.luck@intel.com/ Previous versions of this series: [v1] https://lore.kernel.org/all/cover.1709721159.git.maciej.wieczor-retman@inte… [v2] https://lore.kernel.org/all/cover.1715769576.git.maciej.wieczor-retman@inte… Maciej Wieczor-Retman (2): selftests/resctrl: Adjust effective L3 cache size with SNC enabled selftests/resctrl: Adjust SNC support messages tools/testing/selftests/resctrl/cache.c | 3 + tools/testing/selftests/resctrl/cmt_test.c | 4 +- tools/testing/selftests/resctrl/mba_test.c | 4 + tools/testing/selftests/resctrl/mbm_test.c | 6 +- tools/testing/selftests/resctrl/resctrl.h | 8 + .../testing/selftests/resctrl/resctrl_tests.c | 7 + tools/testing/selftests/resctrl/resctrlfs.c | 138 ++++++++++++++++++ 7 files changed, 166 insertions(+), 4 deletions(-) -- 2.45.2

5 months, 2 weeks

5
17
0 0

[PATCH] kselftests: dmabuf-heaps: Ensure the driver name is null-terminated

by Zenghui Yu

Even if a vgem device is configured in, we will skip the import_vgem_fd() test almost every time. TAP version 13 1..11 # Testing heap: system # ======================================= # Testing allocation and importing: ok 1 # SKIP Could not open vgem -1 The problem is that we use the DRM_IOCTL_VERSION ioctl to query the driver version information but leave the name field a non-null-terminated string. Terminate it properly to actually test against the vgem device. Signed-off-by: Zenghui Yu <yuzenghui(a)huawei.com> --- tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c index 5f541522364f..2fcc74998fa9 100644 --- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c +++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c @@ -32,6 +32,8 @@ static int check_vgem(int fd) if (ret) return 0; + name[4] = '\0'; + return !strcmp(name, "vgem"); } -- 2.33.0

5 months, 2 weeks

2
2
0 0

[PATCH v1] selftests: openvswitch: retry instead of sleep

by Adrian Moreno

There are a couple of places where the test script "sleep"s to wait for some external condition to be met. This is error prone, specially in slow systems (identified in CI by "KSFT_MACHINE_SLOW=yes"). To fix this, add a "ovs_wait" function that tries to execute a command a few times until it succeeds. The timeout used is set to 5s for "normal" systems and doubled if a slow CI machine is detected. This should make the following work: $ vng --build \ --config tools/testing/selftests/net/config \ --config kernel/configs/debug.config $ vng --run . --user root -- "make -C tools/testing/selftests/ \ KSFT_MACHINE_SLOW=yes TARGETS=net/openvswitch run_tests" Signed-off-by: Adrian Moreno <amorenoz(a)redhat.com> --- .../selftests/net/openvswitch/openvswitch.sh | 49 ++++++++++++++++--- .../selftests/net/openvswitch/ovs-dpctl.py | 1 + 2 files changed, 42 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index bc71dbc18b21..83407b42073a 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -11,6 +11,7 @@ ksft_skip=4 PAUSE_ON_FAIL=no VERBOSE=0 TRACING=0 +WAIT_TIMEOUT=5 tests=" arp_ping eth-arp: Basic arp ping between two NS @@ -29,6 +30,32 @@ info() { [ $VERBOSE = 0 ] || echo $* } +ovs_wait() { + info "waiting $WAIT_TIMEOUT s for: $@" + + "$@" + if [[ $? -eq 0 ]]; then + info "wait succeeded inmediately" + return 0 + fi + + # A quick re-check helps speed up small races in fast systems. + # However, fractional sleeps might not necessarily work. + local start=0 + sleep 0.1 || { sleep 1; start=1; } + + for (( i=start; i<WAIT_TIMEOUT; i++ )); do + "$@" + if [[ $? -eq 0 ]]; then + info "wait succeeded after $i seconds" + return 0 + fi + sleep 1 + done + info "wait failed after $i seconds" + return 1 +} + ovs_base=`pwd` sbxs= sbx_add () { @@ -278,20 +305,21 @@ test_psample() { # Record psample data. ovs_spawn_daemon "test_psample" python3 $ovs_base/ovs-dpctl.py psample-events + ovs_wait grep -q "listening for psample events" ${ovs_dir}/stdout # Send a single ping. - sleep 1 ovs_sbx "test_psample" ip netns exec client ping -I c1 172.31.110.20 -c 1 || return 1 - sleep 1 # We should have received one userspace action upcall and 2 psample packets. - grep -E "userspace action command" $ovs_dir/s0.out >/dev/null 2>&1 || return 1 + ovs_wait grep -q "userspace action command" $ovs_dir/s0.out + [[ $? -eq 0 ]] || return 1 # client -> server samples should only contain the first 14 bytes of the packet. - grep -E "rate:4294967295,group:1,cookie:c0ffee data:[0-9a-f]{28}$" \ - $ovs_dir/stdout >/dev/null 2>&1 || return 1 - grep -E "rate:4294967295,group:2,cookie:eeff0c" \ - $ovs_dir/stdout >/dev/null 2>&1 || return 1 + ovs_wait grep -qE "rate:4294967295,group:1,cookie:c0ffee data:[0-9a-f]{28}$" $ovs_dir/stdout + [[ $? -eq 0 ]] || return 1 + + ovs_wait grep -q "rate:4294967295,group:2,cookie:eeff0c" $ovs_dir/stdout + [[ $? -eq 0 ]] || return 1 return 0 } @@ -711,7 +739,8 @@ test_upcall_interfaces() { ovs_add_netns_and_veths "test_upcall_interfaces" ui0 upc left0 l0 \ 172.31.110.1/24 -u || return 1 - sleep 1 + ovs_wait grep -q "listening on upcall packet handler" ${ovs_dir}/left0.out + info "sending arping" ip netns exec upc arping -I l0 172.31.110.20 -c 1 \ >$ovs_dir/arping.stdout 2>$ovs_dir/arping.stderr @@ -811,6 +840,10 @@ shift $(($OPTIND-1)) IFS=" " +if test "X$KSFT_MACHINE_SLOW" == "Xyes"; then + WAIT_TIMEOUT=10 +fi + for arg do # Check first that all requested tests are available before running any command -v > /dev/null "test_${arg}" || { echo "=== Test ${arg} not found"; usage; } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 1e15b0818074..8a0396bfaf99 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -2520,6 +2520,7 @@ class PsampleEvent(EventSocket): marshal_class = psample_msg def read_samples(self): + print("listening for psample events", flush=True) while True: try: for msg in self.get(): -- 2.45.2

5 months, 2 weeks

4
4
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror July 2024