September 2023 - Linux-kselftest-mirror

[PATCH v2 0/4] kunit: Fix some bugs in kunit_filter_suites()

by Jinjie Ruan

The state handle in kunit_module_notify() is not correct when the mod->state switch from MODULE_STATE_COMING to MODULE_STATE_GOING. And it's necessary to check NULL for kzalloc() in kunit_parse_glob_filter(). The order in which memory is released in err path in kunit_filter_suites() is also problematic. And there is a possible memory leak in kunit_filter_suites(). This patchset fix the above issues. Changes in v2: - Adjust the 4th patch to be the second. - Add goto labels in kunit_filter_suites() and adapt to it. - Fix the issue in the third patch. - Update the commit message and title. Jinjie Ruan (4): kunit: Fix wild-memory-access bug in kunit_free_suite_set() kunit: Fix the wrong err path and add goto labels in kunit_filter_suites() kunit: Fix possible null-ptr-deref in kunit_parse_glob_filter() kunit: Fix possible memory leak in kunit_filter_suites() lib/kunit/executor.c | 48 ++++++++++++++++++++++++++++++-------------- lib/kunit/test.c | 3 ++- 2 files changed, 35 insertions(+), 16 deletions(-) -- 2.34.1

8 months, 2 weeks

3
10
0 0

[PATCH v4 10/10] selftests/bpf/sockopt: Add io_uring support

by Breno Leitao

Expand the sockopt test to use also check for io_uring {g,s}etsockopt commands operations. This patch starts by marking each test if they support io_uring support or not. Right now, io_uring cmd getsockopt() has a limitation of only accepting level == SOL_SOCKET, otherwise it returns -EOPNOTSUPP. Since there aren't any test exercising getsockopt(level == SOL_SOCKET), this patch changes two tests to use level == SOL_SOCKET, they are "getsockopt: support smaller ctx->optlen" and "getsockopt: read ctx->optlen". There is no limitation for the setsockopt() part. Later, each test runs using regular {g,s}etsockopt systemcalls, and, if liburing is supported, execute the same test (again), but calling liburing {g,s}setsockopt commands. This patch also changes the level of two tests to use SOL_SOCKET for the following two tests. This is going to help to exercise the io_uring subsystem: * getsockopt: read ctx->optlen * getsockopt: support smaller ctx->optlen Signed-off-by: Breno Leitao <leitao(a)debian.org> --- .../selftests/bpf/prog_tests/sockopt.c | 113 +++++++++++++++++- 1 file changed, 107 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt.c b/tools/testing/selftests/bpf/prog_tests/sockopt.c index 9e6a5e3ed4de..9b1f7f0b1f7e 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockopt.c +++ b/tools/testing/selftests/bpf/prog_tests/sockopt.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> +#include <io_uring/mini_liburing.h> #include "cgroup_helpers.h" static char bpf_log_buf[4096]; @@ -38,6 +39,7 @@ static struct sockopt_test { socklen_t get_optlen_ret; enum sockopt_test_error error; + bool io_uring_support; } tests[] = { /* ==================== getsockopt ==================== */ @@ -251,7 +253,9 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + .get_level = SOL_SOCKET, .get_optlen = 64, + .io_uring_support = true, }, { .descr = "getsockopt: deny bigger ctx->optlen", @@ -276,6 +280,7 @@ static struct sockopt_test { .get_optlen = 64, .error = EFAULT_GETSOCKOPT, + .io_uring_support = true, }, { .descr = "getsockopt: ignore >PAGE_SIZE optlen", @@ -318,6 +323,7 @@ static struct sockopt_test { .get_optval = {}, /* the changes are ignored */ .get_optlen = PAGE_SIZE + 1, .error = EOPNOTSUPP_GETSOCKOPT, + .io_uring_support = true, }, { .descr = "getsockopt: support smaller ctx->optlen", @@ -337,8 +343,10 @@ static struct sockopt_test { .attach_type = BPF_CGROUP_GETSOCKOPT, .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + .get_level = SOL_SOCKET, .get_optlen = 64, .get_optlen_ret = 32, + .io_uring_support = true, }, { .descr = "getsockopt: deny writing to ctx->optval", @@ -518,6 +526,7 @@ static struct sockopt_test { .set_level = 123, .set_optlen = 1, + .io_uring_support = true, }, { .descr = "setsockopt: allow changing ctx->level", @@ -572,6 +581,7 @@ static struct sockopt_test { .set_optname = 123, .set_optlen = 1, + .io_uring_support = true, }, { .descr = "setsockopt: allow changing ctx->optname", @@ -624,6 +634,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .set_optlen = 64, + .io_uring_support = true, }, { .descr = "setsockopt: ctx->optlen == -1 is ok", @@ -640,6 +651,7 @@ static struct sockopt_test { .expected_attach_type = BPF_CGROUP_SETSOCKOPT, .set_optlen = 64, + .io_uring_support = true, }, { .descr = "setsockopt: deny ctx->optlen < 0 (except -1)", @@ -658,6 +670,7 @@ static struct sockopt_test { .set_optlen = 4, .error = EFAULT_SETSOCKOPT, + .io_uring_support = true, }, { .descr = "setsockopt: deny ctx->optlen > input optlen", @@ -675,6 +688,7 @@ static struct sockopt_test { .set_optlen = 64, .error = EFAULT_SETSOCKOPT, + .io_uring_support = true, }, { .descr = "setsockopt: ignore >PAGE_SIZE optlen", @@ -940,7 +954,89 @@ static int load_prog(const struct bpf_insn *insns, return fd; } -static int run_test(int cgroup_fd, struct sockopt_test *test) +/* Core function that handles io_uring ring initialization, + * sending SQE with sockopt command and waiting for the CQE. + */ +static int uring_sockopt(int op, int fd, int level, int optname, + const void *optval, socklen_t optlen) +{ + struct io_uring_cqe *cqe; + struct io_uring_sqe *sqe; + struct io_uring ring; + int err; + + err = io_uring_queue_init(1, &ring, 0); + if (!ASSERT_OK(err, "Failed to initialize io_uring ring")) + return err; + + sqe = io_uring_get_sqe(&ring); + if (!ASSERT_NEQ(sqe, NULL, "Failed to get an SQE")) { + err = -1; + goto fail; + } + + io_uring_prep_cmd(sqe, op, fd, level, optname, optval, optlen); + + err = io_uring_submit(&ring); + if (!ASSERT_EQ(err, 1, "Failed to submit SQE")) + goto fail; + + err = io_uring_wait_cqe(&ring, &cqe); + if (!ASSERT_OK(err, "Failed to wait for CQE")) + goto fail; + + err = cqe->res; + +fail: + io_uring_queue_exit(&ring); + + return err; +} + +static int uring_setsockopt(int fd, int level, int optname, const void *optval, + socklen_t optlen) +{ + return uring_sockopt(SOCKET_URING_OP_SETSOCKOPT, fd, level, optname, + optval, optlen); +} + +static int uring_getsockopt(int fd, int level, int optname, void *optval, + socklen_t *optlen) +{ + int ret = uring_sockopt(SOCKET_URING_OP_GETSOCKOPT, fd, level, optname, + optval, *optlen); + if (ret < 0) + return ret; + + /* Populate optlen back to be compatible with systemcall interface, + * and simplify the test. + */ + *optlen = ret; + + return 0; +} + +/* Execute the setsocktopt operation */ +static int call_setsockopt(bool use_io_uring, int fd, int level, int optname, + const void *optval, socklen_t optlen) +{ + if (use_io_uring) + return uring_setsockopt(fd, level, optname, optval, optlen); + + return setsockopt(fd, level, optname, optval, optlen); +} + +/* Execute the getsocktopt operation */ +static int call_getsockopt(bool use_io_uring, int fd, int level, int optname, + void *optval, socklen_t *optlen) +{ + if (use_io_uring) + return uring_getsockopt(fd, level, optname, optval, optlen); + + return getsockopt(fd, level, optname, optval, optlen); +} + +static int run_test(int cgroup_fd, struct sockopt_test *test, bool use_io_uring) { int sock_fd, err, prog_fd; void *optval = NULL; @@ -980,8 +1076,9 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) test->set_optlen = num_pages * sysconf(_SC_PAGESIZE) + remainder; } - err = setsockopt(sock_fd, test->set_level, test->set_optname, - test->set_optval, test->set_optlen); + err = call_setsockopt(use_io_uring, sock_fd, test->set_level, + test->set_optname, test->set_optval, + test->set_optlen); if (err) { if (errno == EPERM && test->error == EPERM_SETSOCKOPT) goto close_sock_fd; @@ -1008,8 +1105,8 @@ static int run_test(int cgroup_fd, struct sockopt_test *test) socklen_t expected_get_optlen = test->get_optlen_ret ?: test->get_optlen; - err = getsockopt(sock_fd, test->get_level, test->get_optname, - optval, &optlen); + err = call_getsockopt(use_io_uring, sock_fd, test->get_level, + test->get_optname, optval, &optlen); if (err) { if (errno == EOPNOTSUPP && test->error == EOPNOTSUPP_GETSOCKOPT) goto free_optval; @@ -1063,7 +1160,11 @@ void test_sockopt(void) if (!test__start_subtest(tests[i].descr)) continue; - ASSERT_OK(run_test(cgroup_fd, &tests[i]), tests[i].descr); + ASSERT_OK(run_test(cgroup_fd, &tests[i], false), + tests[i].descr); + if (tests[i].io_uring_support) + ASSERT_OK(run_test(cgroup_fd, &tests[i], true), + tests[i].descr); } close(cgroup_fd); -- 2.34.1

8 months, 2 weeks

1
0
0 0

[PATCH v4 06/10] selftests/net: Extract uring helpers to be reusable

by Breno Leitao

Instead of defining basic io_uring functions in the test case, move them to a common directory, so, other tests can use them. This simplify the test code and reuse the common liburing infrastructure. This is basically a copy of what we have in io_uring_zerocopy_tx with some minor improvements to make checkpatch happy. A follow-up test will use the same helpers in a BPF sockopt test. Signed-off-by: Breno Leitao <leitao(a)debian.org> --- tools/include/io_uring/mini_liburing.h | 282 ++++++++++++++++++ tools/testing/selftests/net/Makefile | 1 + .../selftests/net/io_uring_zerocopy_tx.c | 268 +---------------- 3 files changed, 285 insertions(+), 266 deletions(-) create mode 100644 tools/include/io_uring/mini_liburing.h diff --git a/tools/include/io_uring/mini_liburing.h b/tools/include/io_uring/mini_liburing.h new file mode 100644 index 000000000000..9ccb16074eb5 --- /dev/null +++ b/tools/include/io_uring/mini_liburing.h @@ -0,0 +1,282 @@ +/* SPDX-License-Identifier: MIT */ + +#include <linux/io_uring.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <stdio.h> +#include <string.h> +#include <unistd.h> + +struct io_sq_ring { + unsigned int *head; + unsigned int *tail; + unsigned int *ring_mask; + unsigned int *ring_entries; + unsigned int *flags; + unsigned int *array; +}; + +struct io_cq_ring { + unsigned int *head; + unsigned int *tail; + unsigned int *ring_mask; + unsigned int *ring_entries; + struct io_uring_cqe *cqes; +}; + +struct io_uring_sq { + unsigned int *khead; + unsigned int *ktail; + unsigned int *kring_mask; + unsigned int *kring_entries; + unsigned int *kflags; + unsigned int *kdropped; + unsigned int *array; + struct io_uring_sqe *sqes; + + unsigned int sqe_head; + unsigned int sqe_tail; + + size_t ring_sz; +}; + +struct io_uring_cq { + unsigned int *khead; + unsigned int *ktail; + unsigned int *kring_mask; + unsigned int *kring_entries; + unsigned int *koverflow; + struct io_uring_cqe *cqes; + + size_t ring_sz; +}; + +struct io_uring { + struct io_uring_sq sq; + struct io_uring_cq cq; + int ring_fd; +}; + +#if defined(__x86_64) || defined(__i386__) +#define read_barrier() __asm__ __volatile__("":::"memory") +#define write_barrier() __asm__ __volatile__("":::"memory") +#else +#define read_barrier() __sync_synchronize() +#define write_barrier() __sync_synchronize() +#endif + +static inline int io_uring_mmap(int fd, struct io_uring_params *p, + struct io_uring_sq *sq, struct io_uring_cq *cq) +{ + size_t size; + void *ptr; + int ret; + + sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned int); + ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); + if (ptr == MAP_FAILED) + return -errno; + sq->khead = ptr + p->sq_off.head; + sq->ktail = ptr + p->sq_off.tail; + sq->kring_mask = ptr + p->sq_off.ring_mask; + sq->kring_entries = ptr + p->sq_off.ring_entries; + sq->kflags = ptr + p->sq_off.flags; + sq->kdropped = ptr + p->sq_off.dropped; + sq->array = ptr + p->sq_off.array; + + size = p->sq_entries * sizeof(struct io_uring_sqe); + sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES); + if (sq->sqes == MAP_FAILED) { + ret = -errno; +err: + munmap(sq->khead, sq->ring_sz); + return ret; + } + + cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe); + ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING); + if (ptr == MAP_FAILED) { + ret = -errno; + munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe)); + goto err; + } + cq->khead = ptr + p->cq_off.head; + cq->ktail = ptr + p->cq_off.tail; + cq->kring_mask = ptr + p->cq_off.ring_mask; + cq->kring_entries = ptr + p->cq_off.ring_entries; + cq->koverflow = ptr + p->cq_off.overflow; + cq->cqes = ptr + p->cq_off.cqes; + return 0; +} + +static inline int io_uring_setup(unsigned int entries, + struct io_uring_params *p) +{ + return syscall(__NR_io_uring_setup, entries, p); +} + +static inline int io_uring_enter(int fd, unsigned int to_submit, + unsigned int min_complete, + unsigned int flags, sigset_t *sig) +{ + return syscall(__NR_io_uring_enter, fd, to_submit, min_complete, + flags, sig, _NSIG / 8); +} + +static inline int io_uring_queue_init(unsigned int entries, + struct io_uring *ring, + unsigned int flags) +{ + struct io_uring_params p; + int fd, ret; + + memset(ring, 0, sizeof(*ring)); + memset(&p, 0, sizeof(p)); + p.flags = flags; + + fd = io_uring_setup(entries, &p); + if (fd < 0) + return fd; + ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); + if (!ret) + ring->ring_fd = fd; + else + close(fd); + return ret; +} + +/* Get a sqe */ +static inline struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + + if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries) + return NULL; + return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask]; +} + +static inline int io_uring_wait_cqe(struct io_uring *ring, + struct io_uring_cqe **cqe_ptr) +{ + struct io_uring_cq *cq = &ring->cq; + const unsigned int mask = *cq->kring_mask; + unsigned int head = *cq->khead; + int ret; + + *cqe_ptr = NULL; + do { + read_barrier(); + if (head != *cq->ktail) { + *cqe_ptr = &cq->cqes[head & mask]; + break; + } + ret = io_uring_enter(ring->ring_fd, 0, 1, + IORING_ENTER_GETEVENTS, NULL); + if (ret < 0) + return -errno; + } while (1); + + return 0; +} + +static inline int io_uring_submit(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + const unsigned int mask = *sq->kring_mask; + unsigned int ktail, submitted, to_submit; + int ret; + + read_barrier(); + if (*sq->khead != *sq->ktail) { + submitted = *sq->kring_entries; + goto submit; + } + if (sq->sqe_head == sq->sqe_tail) + return 0; + + ktail = *sq->ktail; + to_submit = sq->sqe_tail - sq->sqe_head; + for (submitted = 0; submitted < to_submit; submitted++) { + read_barrier(); + sq->array[ktail++ & mask] = sq->sqe_head++ & mask; + } + if (!submitted) + return 0; + + if (*sq->ktail != ktail) { + write_barrier(); + *sq->ktail = ktail; + write_barrier(); + } +submit: + ret = io_uring_enter(ring->ring_fd, submitted, 0, + IORING_ENTER_GETEVENTS, NULL); + return ret < 0 ? -errno : ret; +} + +static inline void io_uring_queue_exit(struct io_uring *ring) +{ + struct io_uring_sq *sq = &ring->sq; + + munmap(sq->sqes, *sq->kring_entries * sizeof(struct io_uring_sqe)); + munmap(sq->khead, sq->ring_sz); + close(ring->ring_fd); +} + +/* Prepare and send the SQE */ +static inline void io_uring_prep_cmd(struct io_uring_sqe *sqe, int op, + int sockfd, + int level, int optname, + const void *optval, + int optlen) +{ + memset(sqe, 0, sizeof(*sqe)); + sqe->opcode = (__u8)IORING_OP_URING_CMD; + sqe->fd = sockfd; + sqe->cmd_op = op; + + sqe->level = level; + sqe->optname = optname; + sqe->optval = (unsigned long long)optval; + sqe->optlen = optlen; +} + +static inline int io_uring_register_buffers(struct io_uring *ring, + const struct iovec *iovecs, + unsigned int nr_iovecs) +{ + int ret; + + ret = syscall(__NR_io_uring_register, ring->ring_fd, + IORING_REGISTER_BUFFERS, iovecs, nr_iovecs); + return (ret < 0) ? -errno : ret; +} + +static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd, + const void *buf, size_t len, int flags) +{ + memset(sqe, 0, sizeof(*sqe)); + sqe->opcode = (__u8)IORING_OP_SEND; + sqe->fd = sockfd; + sqe->addr = (unsigned long)buf; + sqe->len = len; + sqe->msg_flags = (__u32)flags; +} + +static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd, + const void *buf, size_t len, int flags, + unsigned int zc_flags) +{ + io_uring_prep_send(sqe, sockfd, buf, len, flags); + sqe->opcode = (__u8)IORING_OP_SEND_ZC; + sqe->ioprio = zc_flags; +} + +static inline void io_uring_cqe_seen(struct io_uring *ring) +{ + *(&ring->cq)->khead += 1; + write_barrier(); +} diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 8b017070960d..f8d99837b9dc 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -98,6 +98,7 @@ $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto $(OUTPUT)/tcp_inq: LDLIBS += -lpthread $(OUTPUT)/bind_bhash: LDLIBS += -lpthread +$(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/ # Rules to generate bpf obj nat6to4.o CLANG ?= clang diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c index 154287740172..76e604e4810e 100644 --- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c @@ -36,6 +36,8 @@ #include <sys/un.h> #include <sys/wait.h> +#include <io_uring/mini_liburing.h> + #define NOTIF_TAG 0xfffffffULL #define NONZC_TAG 0 #define ZC_TAG 1 @@ -60,272 +62,6 @@ static struct sockaddr_storage cfg_dst_addr; static char payload[IP_MAXPACKET] __attribute__((aligned(4096))); -struct io_sq_ring { - unsigned *head; - unsigned *tail; - unsigned *ring_mask; - unsigned *ring_entries; - unsigned *flags; - unsigned *array; -}; - -struct io_cq_ring { - unsigned *head; - unsigned *tail; - unsigned *ring_mask; - unsigned *ring_entries; - struct io_uring_cqe *cqes; -}; - -struct io_uring_sq { - unsigned *khead; - unsigned *ktail; - unsigned *kring_mask; - unsigned *kring_entries; - unsigned *kflags; - unsigned *kdropped; - unsigned *array; - struct io_uring_sqe *sqes; - - unsigned sqe_head; - unsigned sqe_tail; - - size_t ring_sz; -}; - -struct io_uring_cq { - unsigned *khead; - unsigned *ktail; - unsigned *kring_mask; - unsigned *kring_entries; - unsigned *koverflow; - struct io_uring_cqe *cqes; - - size_t ring_sz; -}; - -struct io_uring { - struct io_uring_sq sq; - struct io_uring_cq cq; - int ring_fd; -}; - -#ifdef __alpha__ -# ifndef __NR_io_uring_setup -# define __NR_io_uring_setup 535 -# endif -# ifndef __NR_io_uring_enter -# define __NR_io_uring_enter 536 -# endif -# ifndef __NR_io_uring_register -# define __NR_io_uring_register 537 -# endif -#else /* !__alpha__ */ -# ifndef __NR_io_uring_setup -# define __NR_io_uring_setup 425 -# endif -# ifndef __NR_io_uring_enter -# define __NR_io_uring_enter 426 -# endif -# ifndef __NR_io_uring_register -# define __NR_io_uring_register 427 -# endif -#endif - -#if defined(__x86_64) || defined(__i386__) -#define read_barrier() __asm__ __volatile__("":::"memory") -#define write_barrier() __asm__ __volatile__("":::"memory") -#else - -#define read_barrier() __sync_synchronize() -#define write_barrier() __sync_synchronize() -#endif - -static int io_uring_setup(unsigned int entries, struct io_uring_params *p) -{ - return syscall(__NR_io_uring_setup, entries, p); -} - -static int io_uring_enter(int fd, unsigned int to_submit, - unsigned int min_complete, - unsigned int flags, sigset_t *sig) -{ - return syscall(__NR_io_uring_enter, fd, to_submit, min_complete, - flags, sig, _NSIG / 8); -} - -static int io_uring_register_buffers(struct io_uring *ring, - const struct iovec *iovecs, - unsigned nr_iovecs) -{ - int ret; - - ret = syscall(__NR_io_uring_register, ring->ring_fd, - IORING_REGISTER_BUFFERS, iovecs, nr_iovecs); - return (ret < 0) ? -errno : ret; -} - -static int io_uring_mmap(int fd, struct io_uring_params *p, - struct io_uring_sq *sq, struct io_uring_cq *cq) -{ - size_t size; - void *ptr; - int ret; - - sq->ring_sz = p->sq_off.array + p->sq_entries * sizeof(unsigned); - ptr = mmap(0, sq->ring_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQ_RING); - if (ptr == MAP_FAILED) - return -errno; - sq->khead = ptr + p->sq_off.head; - sq->ktail = ptr + p->sq_off.tail; - sq->kring_mask = ptr + p->sq_off.ring_mask; - sq->kring_entries = ptr + p->sq_off.ring_entries; - sq->kflags = ptr + p->sq_off.flags; - sq->kdropped = ptr + p->sq_off.dropped; - sq->array = ptr + p->sq_off.array; - - size = p->sq_entries * sizeof(struct io_uring_sqe); - sq->sqes = mmap(0, size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_SQES); - if (sq->sqes == MAP_FAILED) { - ret = -errno; -err: - munmap(sq->khead, sq->ring_sz); - return ret; - } - - cq->ring_sz = p->cq_off.cqes + p->cq_entries * sizeof(struct io_uring_cqe); - ptr = mmap(0, cq->ring_sz, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_POPULATE, fd, IORING_OFF_CQ_RING); - if (ptr == MAP_FAILED) { - ret = -errno; - munmap(sq->sqes, p->sq_entries * sizeof(struct io_uring_sqe)); - goto err; - } - cq->khead = ptr + p->cq_off.head; - cq->ktail = ptr + p->cq_off.tail; - cq->kring_mask = ptr + p->cq_off.ring_mask; - cq->kring_entries = ptr + p->cq_off.ring_entries; - cq->koverflow = ptr + p->cq_off.overflow; - cq->cqes = ptr + p->cq_off.cqes; - return 0; -} - -static int io_uring_queue_init(unsigned entries, struct io_uring *ring, - unsigned flags) -{ - struct io_uring_params p; - int fd, ret; - - memset(ring, 0, sizeof(*ring)); - memset(&p, 0, sizeof(p)); - p.flags = flags; - - fd = io_uring_setup(entries, &p); - if (fd < 0) - return fd; - ret = io_uring_mmap(fd, &p, &ring->sq, &ring->cq); - if (!ret) - ring->ring_fd = fd; - else - close(fd); - return ret; -} - -static int io_uring_submit(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - const unsigned mask = *sq->kring_mask; - unsigned ktail, submitted, to_submit; - int ret; - - read_barrier(); - if (*sq->khead != *sq->ktail) { - submitted = *sq->kring_entries; - goto submit; - } - if (sq->sqe_head == sq->sqe_tail) - return 0; - - ktail = *sq->ktail; - to_submit = sq->sqe_tail - sq->sqe_head; - for (submitted = 0; submitted < to_submit; submitted++) { - read_barrier(); - sq->array[ktail++ & mask] = sq->sqe_head++ & mask; - } - if (!submitted) - return 0; - - if (*sq->ktail != ktail) { - write_barrier(); - *sq->ktail = ktail; - write_barrier(); - } -submit: - ret = io_uring_enter(ring->ring_fd, submitted, 0, - IORING_ENTER_GETEVENTS, NULL); - return ret < 0 ? -errno : ret; -} - -static inline void io_uring_prep_send(struct io_uring_sqe *sqe, int sockfd, - const void *buf, size_t len, int flags) -{ - memset(sqe, 0, sizeof(*sqe)); - sqe->opcode = (__u8) IORING_OP_SEND; - sqe->fd = sockfd; - sqe->addr = (unsigned long) buf; - sqe->len = len; - sqe->msg_flags = (__u32) flags; -} - -static inline void io_uring_prep_sendzc(struct io_uring_sqe *sqe, int sockfd, - const void *buf, size_t len, int flags, - unsigned zc_flags) -{ - io_uring_prep_send(sqe, sockfd, buf, len, flags); - sqe->opcode = (__u8) IORING_OP_SEND_ZC; - sqe->ioprio = zc_flags; -} - -static struct io_uring_sqe *io_uring_get_sqe(struct io_uring *ring) -{ - struct io_uring_sq *sq = &ring->sq; - - if (sq->sqe_tail + 1 - sq->sqe_head > *sq->kring_entries) - return NULL; - return &sq->sqes[sq->sqe_tail++ & *sq->kring_mask]; -} - -static int io_uring_wait_cqe(struct io_uring *ring, struct io_uring_cqe **cqe_ptr) -{ - struct io_uring_cq *cq = &ring->cq; - const unsigned mask = *cq->kring_mask; - unsigned head = *cq->khead; - int ret; - - *cqe_ptr = NULL; - do { - read_barrier(); - if (head != *cq->ktail) { - *cqe_ptr = &cq->cqes[head & mask]; - break; - } - ret = io_uring_enter(ring->ring_fd, 0, 1, - IORING_ENTER_GETEVENTS, NULL); - if (ret < 0) - return -errno; - } while (1); - - return 0; -} - -static inline void io_uring_cqe_seen(struct io_uring *ring) -{ - *(&ring->cq)->khead += 1; - write_barrier(); -} - static unsigned long gettimeofday_ms(void) { struct timeval tv; -- 2.34.1

8 months, 2 weeks

1
0
0 0

[PATCH v2 0/8] Add printf attribute to kselftest functions

by Wieczor-Retman Maciej

Kselftest.h declares many variadic functions that can print some formatted message while also executing selftest logic. These declarations don't have any compiler mechanism to verify if passed arguments are valid in comparison with format specifiers used in printf() calls. Attribute addition can make debugging easier, the code more consistent and prevent mismatched or missing variables. Add a __printf() macro that validates types of variables passed to the format string. The macro is similarly used in other tools in the kernel. Add __printf() attributes to function definitions inside kselftest.h that use printing. Adding the __printf() macro exposes some mismatches in format strings across different selftests. Fix the mismatched format specifiers in multiple tests. Changelog v2: - Add review and fixes tags to patches. - Add two patches with mismatch fixes. - Fix missed attribute in selftests/kvm. (Andrew) - Fix previously missed issues in selftests/mm (Ilpo) Wieczor-Retman Maciej (8): selftests: Add printf attribute to ksefltest prints selftests/cachestat: Fix print_cachestat format selftests/openat2: Fix wrong format specifier selftests/pidfd: Fix ksft print formats selftests/sigaltstack: Fix wrong format specifier selftests/kvm: Replace attribute with macro selftests/mm: Substitute attribute with a macro selftests/resctrl: Fix wrong format specifier .../selftests/cachestat/test_cachestat.c | 2 +- tools/testing/selftests/kselftest.h | 18 ++++++++++-------- .../testing/selftests/kvm/include/test_util.h | 8 ++++---- tools/testing/selftests/mm/mremap_test.c | 2 +- tools/testing/selftests/mm/pkey-helpers.h | 2 +- tools/testing/selftests/openat2/openat2_test.c | 2 +- .../selftests/pidfd/pidfd_fdinfo_test.c | 2 +- tools/testing/selftests/pidfd/pidfd_test.c | 12 ++++++------ tools/testing/selftests/resctrl/cache.c | 2 +- tools/testing/selftests/sigaltstack/sas.c | 2 +- 10 files changed, 27 insertions(+), 25 deletions(-) base-commit: 9b1db732866bee060b9bca9493e5ebf5e8874c48 -- 2.42.0

8 months, 2 weeks

2
9
0 0

[PATCH bpf-next v10 2/2] selftests/bpf: trace_helpers.c: Add a global ksyms initialization mutex

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> As Jirka said [0], we just need to make sure that global ksyms initialization won't race. [0] https://lore.kernel.org/lkml/ZPCbAs3ItjRd8XVh@krava/ Signed-off-by: Rong Tao <rongtao(a)cestc.cn> --- tools/testing/selftests/bpf/trace_helpers.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c index d64c4ef336e1..500b60226e5e 100644 --- a/tools/testing/selftests/bpf/trace_helpers.c +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -7,6 +7,7 @@ #include <errno.h> #include <fcntl.h> #include <poll.h> +#include <pthread.h> #include <unistd.h> #include <linux/perf_event.h> #include <sys/mman.h> @@ -26,6 +27,7 @@ struct ksyms { }; static struct ksyms *ksyms; +static pthread_mutex_t ksyms_mutex = PTHREAD_MUTEX_INITIALIZER; static int ksyms__add_symbol(struct ksyms *ksyms, const char *name, unsigned long addr) @@ -115,8 +117,10 @@ struct ksyms *load_kallsyms_local(void) int load_kallsyms(void) { + pthread_mutex_lock(&ksyms_mutex); if (!ksyms) ksyms = load_kallsyms_local(); + pthread_mutex_unlock(&ksyms_mutex); return ksyms ? 0 : 1; } -- 2.41.0

8 months, 2 weeks

1
0
0 0

[PATCH bpf-next v10 0/2] selftests/bpf: Optimize kallsyms cache

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> We need to optimize the kallsyms cache, including optimizations for the number of symbols limit, and, some test cases add new kernel symbols (such as testmods) and we need to refresh kallsyms (reload or refresh). Rong Tao (2): selftests/bpf: trace_helpers.c: optimize kallsyms cache selftests/bpf: trace_helpers.c: Add a global ksyms initialization mutex samples/bpf/Makefile | 4 + .../selftests/bpf/prog_tests/fill_link_info.c | 9 +- .../prog_tests/kprobe_multi_testmod_test.c | 24 ++- tools/testing/selftests/bpf/trace_helpers.c | 141 +++++++++++++----- tools/testing/selftests/bpf/trace_helpers.h | 10 +- 5 files changed, 141 insertions(+), 47 deletions(-) -- 2.41.0

8 months, 2 weeks

1
0
0 0

[RFC] tools/nolibc: replace duplicated -ENOSYS return with single -ENOSYS return

by Zhangjin Wu

Hi, Willy Since we have already finished the size inflate regression task [1], to share and discuss the progress about the -ENOSYS return work, here launchs a new thread, it is split from [2]. [1]: https://lore.kernel.org/lkml/ZNtszQeigYuItaKA@1wt.eu/ [2]: https://lore.kernel.org/lkml/20230814172233.225944-1-falcon@tinylab.org/#R This is only for brain storming, it is far from a solution ;-) > > > [...] > > > > > > > > /* __systry2() is used to select one of two provided low level syscalls */ > > > > #define __systry2(a, sys_a, sys_b) \ > > > > ((NOLIBC__NR_##a != NOLIBC__NR_NOSYS) ? (sys_a) : (sys_b)) > > > > > > But this supposes that all of them are manually defined as you did above. > > > I'd rather implement an ugly is_numeric() macro based on argument > > > resolution. I've done it once in another project, I don't remember > > > precisely where it is but I vaguely remember that it used to check > > > that the string resolution of the argument gave a letter (when it > > > does not exist) or a digit (when it does). I can look into that later > > > if needed. But please avoid extra macro definitions as much as possible, > > > they're a real pain to handle in the code. There's no error when one is > > > missing or has a typo, it's difficult to follow them and they don't > > > appear in the debugger. > > > > > > > Yeah, your reply inspired me to look into the IS_ENABLED() from > > ../include/linux/kconfig.h macro again, there was a __is_defined() there, let's > > throw away the ugly sysnr.h. I thought of IS_ENABLED() was only for y/n/m > > before, but it does return 0 when the macro is not defined, it uses the same > > trick in syscall() to calculate the number of arguments, if the macro is not > > defined, then, 0 "argument". > > > > The above trick is only for ""#define something 1" ;-) > Here shares a little progress on this, I have found it is easy to implement an ugly is_numeric() like macro as following: /* Imported from include/linux/stringify.h */ #define __stringify_1(x...) #x #define __stringify(x...) __stringify_1(x) /* * Check __NR_* definition by stringizing * * - The stringizing is to silence compile error about undefined macro * - If defined, the result looks like "3", "(4000 + 168)", not begin with '_' * - If not defined, the result looks like "__NR_read", begins with '_' */ #define __is_nr_defined(nr) ___is_nr_defined(__stringify(nr)) #define ___is_nr_defined(str) (str[0] != '_') __is_nr_defined() is able to check if __NR_xxx is defined, but the harder part is getting the number of defined __NR_* without the error about undefined macro. Of course, we can also use the __stringify() trick to do so, but it is expensive (bigger size, worse performance) to unstringify and get the number again, the expensive atoi() 'works' for the numeric __NR_*, but not work for (__NR_*_base + offset) like __NR_* definitions (used by ARM and MIPS), a simple interpreter is required for such cases and it is more expensive than atoi(). /* not for ARM and MIPS */ static int atoi(const char *s); #define __get_nr(name) __nr_atoi(__stringify(__NR_##name)) #define __nr_atoi(str) (str[0] == '_' ? -1L : ___nr_atoi(str)) #define ___nr_atoi(str) (str[0] == '(' ? -1L : atoi(str)) Welcome more discussion or let's simply throw away this direction ;-) But it may really help us to drop tons of duplicated code pieces like this: #ifdef __NR_xxxx ... #else return -ENOSYS; #endif David, Thomas and Arnd, any inspiration on this, or is this really impossible (or make things worse) in language level? ;-) What I'm thinking about is something like this or similar (As Willy commented before, the __sysdef() itself is not that good, please ignore itself, the core target here is using a single -ENOSYS return for all of the undefined branches): #define __sysdef(name, ...) \ (__is_nr_defined(__NR_##name) ? my_syscall(__get_nr(name), ##__VA_ARGS__) : (long)-ENOSYS) Or as Arnd replied in an old email thread before, perhaps the whole #ifdef's code piece (and even the input types and return types of sys_*) above can be generated from .tbl or the generic unistd.h automatically in the sysroot installation stage? BR, Zhangjin

8 months, 2 weeks

5
14
0 0

[PATCH 0/4] kunit: Fix some bugs in kunit_filter_suites()

by Jinjie Ruan

The state handle in kunit_module_notify() is not correct when the mod->state switch from MODULE_STATE_COMING to MODULE_STATE_GOING. And it's necessary to check NULL for kzalloc() in kunit_parse_glob_filter(). The order in which memory is released in err path in kunit_filter_suites() is also problematic. And there is a possible memory leak in kunit_filter_suites(). This patchset fix the above issues. Jinjie Ruan (4): kunit: Fix wild-memory-access bug in kunit_free_suite_set() kunit: Fix possible null-ptr-deref in kunit_parse_glob_filter() kunit: Fix possible memory leak in kunit_filter_suites() kunit: Fix the wrong error path in kunit_filter_suites() lib/kunit/executor.c | 39 +++++++++++++++++++++++++++------------ lib/kunit/test.c | 3 ++- 2 files changed, 29 insertions(+), 13 deletions(-) -- 2.34.1

8 months, 2 weeks

4
13
0 0

[PATCH bpf-next v10 0/2] selftests/bpf: Optimize kallsyms cache

by Rong Tao

From: Rong Tao <rongtao(a)cestc.cn> We need to optimize the kallsyms cache, including optimizations for the number of symbols limit, and, some test cases add new kernel symbols (such as testmods) and we need to refresh kallsyms (reload or refresh). Rong Tao (2): selftests/bpf: trace_helpers.c: optimize kallsyms cache selftests/bpf: trace_helpers.c: Add a global ksyms initialization mutex samples/bpf/Makefile | 4 + .../selftests/bpf/prog_tests/fill_link_info.c | 9 +- .../prog_tests/kprobe_multi_testmod_test.c | 24 ++- tools/testing/selftests/bpf/trace_helpers.c | 141 +++++++++++++----- tools/testing/selftests/bpf/trace_helpers.h | 10 +- 5 files changed, 141 insertions(+), 47 deletions(-) -- 2.41.0

8 months, 2 weeks

2
3
0 0

[PATCH] rcu/torture: Improve badness extraction from console logs

by Joel Fernandes (Google)

Currently console.log.diags contains an output like follows: [ 2457.293734] WARNING: CPU: 2 PID: 13 at kernel/rcu/tasks.h:1061 rcu_tasks_trace_pregp_step+0x4a/0x50 [ 2457.542385] Call Trace: This is not very useful and the Call trace is desired. Improve the script by Extracting more lines after each grep match. With this the above becomes: Issue 1: [ 2457.293734] WARNING: CPU: 2 PID: 13 at kernel/rcu/tasks.h:1061 rcu_tasks_trace_pregp_step+0x4a/0x50 [ 2457.326661] Modules linked in: [ 2457.334818] CPU: 2 PID: 13 Comm: rcu_tasks_trace Not tainted 5.15.128+ #381 [ 2457.349782] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 [ 2457.373309] RIP: 0010:rcu_tasks_trace_pregp_step+0x4a/0x50 [ 2457.386691] Code: 48 63 c7 48 8b 0 [ 2457.421803] RSP: 0018:ffffa80fc0073e40 EFLAGS: 00010202 [ 2457.431940] RAX: ffff8db91f580000 RBX: 000000000001b900 RCX: 0000000000000003 [ 2457.443206] RDX: 0000000000000008 RSI: ffffffffac6bebd8 RDI: 0000000000000003 [ 2457.454428] RBP: 0000000000000004 R08: 0000000000000001 R09: 0000000000000001 [ 2457.465668] R10: 0000000000000000 R11: 00000000ffffffff R12: ffff8db902d87f40 [ 2457.476971] R13: ffffffffac556620 R14: ffffffffac556630 R15: ffff8db9011a3200 [ 2457.488251] FS: 0000000000000000(0000) GS:ffff8db91f500000(0000) knlGS:0000000000000000 [ 2457.500834] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 2457.509602] CR2: 0000000000000000 CR3: 0000000002cbc000 CR4: 00000000000006e0 [ 2457.520378] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 2457.531440] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 2457.542385] Call Trace: [ 2457.546756] <TASK> [ 2457.550349] ? __warn+0x7b/0x100 [ 2457.567214] ? rcu_tasks_trace_pregp_step+0x4a/0x50 ------------------------------------- Issue 2: [ 2457.542385] Call Trace: [ 2457.546756] <TASK> [ 2457.550349] ? __warn+0x7b/0x100 [ 2457.567214] ? rcu_tasks_trace_pregp_step+0x4a/0x50 [ 2457.574948] ? report_bug+0x99/0xc0 [ 2457.593824] ? handle_bug+0x3c/0x70 [ 2457.599534] ? exc_invalid_op+0x13/0x60 [ 2457.625729] ? asm_exc_invalid_op+0x16/0x20 [ 2457.632249] ? rcu_tasks_trace_pregp_step+0x4a/0x50 [ 2457.660010] rcu_tasks_wait_gp+0x54/0x360 [ 2457.677761] ? _raw_spin_unlock_irqrestore+0x2b/0x60 [ 2457.705658] rcu_tasks_kthread+0x114/0x200 [ 2457.712450] ? wait_woken+0x70/0x70 [ 2457.727283] ? synchronize_rcu_tasks_rude+0x10/0x10 [ 2457.746221] kthread+0x130/0x160 [ 2457.751487] ? set_kthread_struct+0x40/0x40 [ 2457.758178] ret_from_fork+0x22/0x30 [ 2457.763909] </TASK> [ 2457.767546] irq event stamp: 29544441 [ 2457.773344] hardirqs last enabled at (29544451): [<ffffffffaace6cbd>] __up_console_sem+0x4d/0x60 [ 2457.786967] hardirqs last disabled at (29544460): [<ffffffffaace6ca2>] __up_console_sem+0x32/0x60 ------------------------------------- Signed-off-by: Joel Fernandes (Google) <joel(a)joelfernandes.org> --- .../rcutorture/bin/console-badness.sh | 24 ++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh index aad51e7c0183..d28efcd86b64 100755 --- a/tools/testing/selftests/rcutorture/bin/console-badness.sh +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -9,10 +9,32 @@ # Copyright (C) 2020 Facebook, Inc. # # Authors: Paul E. McKenney <paulmck(a)kernel.org> +INPUT_DATA=$(< /dev/stdin) -grep -E 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | +# Get the line numbers for all the grep matches +GREP_LINES="$(echo "$INPUT_DATA" | +grep -n -E 'Badness|WARNING:|Warn|BUG|===========|BUG: KCSAN:|Call Trace:|Oops:|detected stalls on CPUs/tasks:|self-detected stall on CPU|Stall ended before state dump start|\?\?\? Writer stall state|rcu_.*kthread starved for|!!!' | grep -v 'ODEBUG: ' | grep -v 'This means that this is a DEBUG kernel and it is' | grep -v 'Warning: unable to open an initial console' | grep -v 'Warning: Failed to add ttynull console. No stdin, stdout, and stderr.*the init process!' | grep -v 'NOHZ tick-stop error: Non-RCU local softirq work is pending, handler' +)" + +# Exit if no grep matches +if [ ! -n "$GREP_LINES" ]; then exit 0; fi + +# Go through each line of GREP_LINES, extract the line number and then +# print from that line and 20 lines after that line. Do that for each +# grep match. +issue_num=1 +while IFS= read -r line; do + # Extract the line number from the line + num=$(echo "$line" | awk -F: '{print $1}') + # Print 20 lines after the matched line + echo "Issue $issue_num:" + issue_num="$(($issue_num + 1))" + echo "$INPUT_DATA" | sed -n "${num},$(($num + 20))p" + echo "-------------------------------------" +done <<< "$GREP_LINES" + -- 2.42.0.rc2.253.gd59a3bf2b4-goog

8 months, 2 weeks

3
7
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror September 2023