September 2023 - Linux-kselftest-mirror

[PATCH v6 4/8] 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 | 292 ++++++++++++++++++ tools/testing/selftests/net/Makefile | 1 + .../selftests/net/io_uring_zerocopy_tx.c | 268 +--------------- 3 files changed, 295 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..e0e1e76def25 --- /dev/null +++ b/tools/include/io_uring/mini_liburing.h @@ -0,0 +1,292 @@ +/* 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, + const socklen_t 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 = (unsigned long long)optlen; +} + +static inline void io_uring_prep_cmd_get(struct io_uring_sqe *sqe, int op, + int sockfd, + int level, int optname, + const void *optval, + const socklen_t *optlen) +{ + io_uring_prep_cmd(sqe, op, sockfd, level, optname, optval, 0); + sqe->optlen = (unsigned long long)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

2 years

1
0
0 0

[PATCH 1/1] selftests/resctrl: Move _GNU_SOURCE define into Makefile

by Ilpo Järvinen

Currently, _GNU_SOURCE is defined in resctrl.h. Defining _GNU_SOURCE has a large impact on what gets defined when including headers either before or after it. This can result in compile failures if .c file decides to include a standard header file before resctrl.h. It is safer to define _GNU_SOURCE in Makefile so it is always defined regardless of in which order includes are done. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen(a)linux.intel.com> --- tools/testing/selftests/resctrl/Makefile | 2 +- tools/testing/selftests/resctrl/resctrl.h | 1 - 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/tools/testing/selftests/resctrl/Makefile b/tools/testing/selftests/resctrl/Makefile index 5073dbc96125..2deac2031de9 100644 --- a/tools/testing/selftests/resctrl/Makefile +++ b/tools/testing/selftests/resctrl/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS = -g -Wall -O2 -D_FORTIFY_SOURCE=2 +CFLAGS = -g -Wall -O2 -D_FORTIFY_SOURCE=2 -D_GNU_SOURCE CFLAGS += $(KHDR_INCLUDES) TEST_GEN_PROGS := resctrl_tests diff --git a/tools/testing/selftests/resctrl/resctrl.h b/tools/testing/selftests/resctrl/resctrl.h index 838d1a438f33..eff178befe4a 100644 --- a/tools/testing/selftests/resctrl/resctrl.h +++ b/tools/testing/selftests/resctrl/resctrl.h @@ -1,5 +1,4 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#define _GNU_SOURCE #ifndef RESCTRL_H #define RESCTRL_H #include <stdio.h> -- 2.30.2

2 years

1
0
0 0

[PATCH 3/3] selftests/bpf: Add selftest for packet-pointer Spectre v1 gadget

by Luis Gerhorst

When allowing speculative leaks by enabling packet pointer accesses without CAP_PERFMON (i.e., without having [1] reverted): $ tools/testing/selftests/bpf/test_progs --name=tc_bpf tc_bpf_non_root:PASS:set_cap_bpf_cap_net_admin 0 nsec tc_bpf_non_root:PASS:disable_cap_sys_admin 0 nsec tc_bpf_non_root:FAIL:test_tc_bpf__open_and_load unexpected pointer: 0x55bbd81969a0 Summary: 0/1 PASSED, 0 SKIPPED, 1 FAILED With [1] reverted: $ tools/testing/selftests/bpf/test_progs --name=tc_bpf #238/1 tc_bpf/tc_bpf_root:OK #238/2 tc_bpf/tc_bpf_non_root:OK #238 tc_bpf:OK Summary: 1/2 PASSED, 0 SKIPPED, 0 FAILED [1] d75e30dddf73449bc2d10bb8e2f1a2c446bc67a2 ("bpf: Fix issue in verifying allow_ptr_leaks") Signed-off-by: Luis Gerhorst <gerhorst(a)amazon.de> Signed-off-by: Luis Gerhorst <gerhorst(a)cs.fau.de> Based-on-patch-by: Yafang Shao <laoar.shao(a)gmail.com> --- .../testing/selftests/bpf/prog_tests/tc_bpf.c | 37 +++++++- .../testing/selftests/bpf/progs/test_tc_bpf.c | 95 +++++++++++++++++++ 2 files changed, 131 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c index e873766276d1..5319cb94a0ae 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_bpf.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_bpf.c @@ -3,6 +3,7 @@ #include <test_progs.h> #include <linux/pkt_cls.h> +#include "cap_helpers.h" #include "test_tc_bpf.skel.h" #define LO_IFINDEX 1 @@ -327,7 +328,7 @@ static int test_tc_bpf_api(struct bpf_tc_hook *hook, int fd) return 0; } -void test_tc_bpf(void) +void tc_bpf_root(void) { DECLARE_LIBBPF_OPTS(bpf_tc_hook, hook, .ifindex = LO_IFINDEX, .attach_point = BPF_TC_INGRESS); @@ -393,3 +394,37 @@ void test_tc_bpf(void) } test_tc_bpf__destroy(skel); } + +void tc_bpf_non_root(void) +{ + struct test_tc_bpf *skel = NULL; + __u64 caps = 0; + int ret; + + /* In case CAP_BPF and CAP_PERFMON is not set */ + ret = cap_enable_effective(1ULL << CAP_BPF | 1ULL << CAP_NET_ADMIN, &caps); + if (!ASSERT_OK(ret, "set_cap_bpf_cap_net_admin")) + return; + ret = cap_disable_effective(1ULL << CAP_SYS_ADMIN | 1ULL << CAP_PERFMON, NULL); + if (!ASSERT_OK(ret, "disable_cap_sys_admin")) + goto restore_cap; + + skel = test_tc_bpf__open_and_load(); + if (!ASSERT_ERR_PTR(skel, "test_tc_bpf__open_and_load")) + goto destroy; + + goto restore_cap; +destroy: + test_tc_bpf__destroy(skel); +restore_cap: + if (caps) + cap_enable_effective(caps, NULL); +} + +void test_tc_bpf(void) +{ + if (test__start_subtest("tc_bpf_root")) + tc_bpf_root(); + if (test__start_subtest("tc_bpf_non_root")) + tc_bpf_non_root(); +} diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c index d28ca8d1f3d0..3b3f9ce6b9d4 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c +++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c @@ -2,6 +2,8 @@ #include <linux/bpf.h> #include <bpf/bpf_helpers.h> +#include <linux/if_ether.h> +#include <linux/ip.h> /* Dummy prog to test TC-BPF API */ @@ -10,3 +12,96 @@ int cls(struct __sk_buff *skb) { return 0; } + +/* Prog to verify tc-bpf without cap_sys_admin and cap_perfmon is rejected as + * required to prevent Spectre v1 using CPU multiplication port contention + * side-channel. This is not a full exploit but rather a PoC for x86_64. With + * extensions to the verifier's mitigations this may become obsolete. + * + * This should compile to the following bytecode if the kernel would allow + * unprivileged packet pointer accesses: + * + +0000000000000000 <pkt_ptr>: + 0: b4 00 00 00 00 00 00 00 w0 = 0 + 1: 61 12 50 00 00 00 00 00 r2 = *(u32 *)(r1 + 80) + 2: 61 11 4c 00 00 00 00 00 r1 = *(u32 *)(r1 + 76) + 3: bf 13 00 00 00 00 00 00 r3 = r1 + 4: 07 03 00 00 22 00 00 00 r3 += 34 + 5: bd 23 07 00 00 00 00 00 if r3 <= r2 goto +7 <LBB1_3> + 6: 71 10 0e 00 00 00 00 00 r0 = *(u8 *)(r1 + 14) + 7: 64 00 00 00 18 00 00 00 w0 <<= 24 + 8: c4 00 00 00 18 00 00 00 w0 s>>= 24 + 9: bc 01 00 00 00 00 00 00 w1 = w0 + 10: 54 01 00 00 01 00 00 00 w1 &= 1 + 11: 16 01 01 00 00 00 00 00 if w1 == 0 goto +1 <LBB1_3> + 12: 24 00 00 00 61 00 00 00 w0 *= 97 + +0000000000000068 <LBB1_3>: + 13: 95 00 00 00 00 00 00 00 exit + + * + * Which should in turn translate to this x86_64 assembly with !allow_ptr_leaks + * and !bypass_spec_v1: + * + +int pkt_ptr(struct __sk_buff * skb): +bpf_prog_7c3834bad32f2b0f_pkt_ptr: +; int pkt_ptr(struct __sk_buff *skb) + 0: endbr64 + 4: nopl 0x0(%rax,%rax,1) + 9: xchg %ax,%ax + b: push %rbp + c: mov %rsp,%rbp + f: endbr64 + 13: xor %eax,%eax +; if ((long)(iph + 1) > (long)skb->data_end) + 15: mov 0x50(%rdi),%rsi +; struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr); + 19: mov 0xc8(%rdi),%rdi +; if ((long)(iph + 1) > (long)skb->data_end) + 20: mov %rdi,%rdx + 23: add $0x22,%rdx +; if ((long)(iph + 1) > (long)skb->data_end) + 27: cmp %rsi,%rdx + 2a: ja 0x0000000000000043 +; char secret = *((char *) iph); + 2c: movzbq 0xe(%rdi),%rax + 31: shl $0x18,%eax + 34: sar $0x18,%eax +; if (secret & 1) { + 37: mov %eax,%edi + 39: and $0x1,%edi +; if (secret & 1) { + 3c: test %edi,%edi + 3e: je 0x0000000000000043 + 40: imul $0x61,%eax,%eax +; } + 43: leaveq + 44: retq + + * + */ +SEC("tcx/ingress") +int pkt_ptr(struct __sk_buff *skb) +{ + struct iphdr *iph = (void *)(long)skb->data + sizeof(struct ethhdr); + + /* Branch to be speculatively bypassed. */ + if ((long)(iph + 1) > (long)skb->data_end) + return 0; + + /* Speculative access to be prevented. */ + char secret = *((char *) iph); + + /* Leak the first bit of the secret value that lies behind data_end to a + * SMP silbling thread that also executes imul instructions. If the bit + * is 1, the silbling will experience a slowdown. */ + long long x = secret; + if (secret & 1) { + x *= 97; + } + + /* To prevent optimization. */ + return x; +} -- 2.40.1 Amazon Development Center Germany GmbH Krausenstr. 38 10117 Berlin Geschaeftsfuehrung: Christian Schlaeger, Jonathan Weiss Eingetragen am Amtsgericht Charlottenburg unter HRB 149173 B Sitz: Berlin Ust-ID: DE 289 237 879

2 years

1
0
0 0

[PATCH] tracing/user_events: fix long size check in the ABI selftest

by Alexander Lobakin

The current check for 64-bit architecture is double-bugged. First of all, %BITS_PER_LONG is not available in the userspace, the underscored version from <asm/bitsperlong.h> must be used. The following check: #if BITS_PER_LONG == 0 #error #endif triggers the error in this source file -- the macro is undefined and thus is implicitly evaluated to 0. Next, %BITS_PER_LONG means "bits", not "bytes". In the Linux kernel, it can be 32 or 64, never 8. Given that the tests guarded by that check are meant to be run on a 64-bit system, the correct value would be 64. Prefix the macro name and fix the value it's compared to. Fixes: 60b1af8de8c1 ("tracing/user_events: Add ABI self-test") Cc: stable(a)vger.kernel.org # 6.4+ Reviewed-by: Ira Weiny <ira.weiny(a)intel.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin(a)intel.com> --- tools/testing/selftests/user_events/abi_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 5125c42efe65..4b30461fc741 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -129,7 +129,7 @@ TEST_F(user, bit_sizes) { ASSERT_EQ(0, reg_disable(&self->check, 0)); ASSERT_EQ(0, reg_disable(&self->check, 31)); -#if BITS_PER_LONG == 8 +#if __BITS_PER_LONG == 64 /* Allow 0-64 bits for 64-bit */ ASSERT_EQ(0, reg_enable(&self->check, sizeof(long), 63)); ASSERT_NE(0, reg_enable(&self->check, sizeof(long), 64)); -- 2.41.0

2 years

1
1
0 0

[PATCH] selftests: cgroup: fix test_zswap error path and meaningless check

by Domenico Cerasuolo

Replace destruction paths with simple returns before the test cgroup is created, there is nothing to free or destroy at that point. Remove pointless check, stored_pages is a size_t and cannot be < 0. Fixes: a549f9f31561 ("selftests: cgroup: add test_zswap with no kmem bypass test") Reported-by: Dan Carpenter <dan.carpenter(a)linaro.org> Signed-off-by: Domenico Cerasuolo <cerasuolodomenico(a)gmail.com> --- tools/testing/selftests/cgroup/test_zswap.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/tools/testing/selftests/cgroup/test_zswap.c b/tools/testing/selftests/cgroup/test_zswap.c index 49def87a909b..5257106776d5 100644 --- a/tools/testing/selftests/cgroup/test_zswap.c +++ b/tools/testing/selftests/cgroup/test_zswap.c @@ -178,10 +178,10 @@ static int test_no_kmem_bypass(const char *root) /* Set up test memcg */ if (cg_write(root, "cgroup.subtree_control", "+memory")) - goto out; + return KSFT_FAIL; test_group = cg_name(root, "kmem_bypass_test"); if (!test_group) - goto out; + return KSFT_FAIL; /* Spawn memcg child and wait for it to allocate */ set_min_free_kb(min_free_kb_low); @@ -208,8 +208,6 @@ static int test_no_kmem_bypass(const char *root) free(trigger_allocation); if (get_zswap_stored_pages(&stored_pages)) break; - if (stored_pages < 0) - break; /* If memory was pushed to zswap, verify it belongs to memcg */ if (stored_pages > stored_pages_threshold) { int zswapped = cg_read_key_long(test_group, "memory.stat", "zswapped "); -- 2.34.1

2 years

2
2
0 0

[FIX PATCH v2] selftests: tracing: Fix to unmount tracefs for recovering environment

by Masami Hiramatsu (Google)

From: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> Fix to unmount the tracefs if the ftracetest mounted it for recovering system environment. If the tracefs is already mounted, this does nothing. Suggested-by: Mark Brown <broonie(a)kernel.org> Link: https://lore.kernel.org/all/29fce076-746c-4650-8358-b4e0fa215cf7@sirena.org… Fixes: cbd965bde74c ("ftrace/selftests: Return the skip code when tracing directory not configured in kernel") Signed-off-by: Masami Hiramatsu (Google) <mhiramat(a)kernel.org> --- Changes in v2: - use -n option explictly for testing the string is non-zero. --- tools/testing/selftests/ftrace/ftracetest | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index cb5f18c06593..d68264a5f3f0 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -31,6 +31,9 @@ err_ret=1 # kselftest skip code is 4 err_skip=4 +# umount required +UMOUNT_DIR="" + # cgroup RT scheduling prevents chrt commands from succeeding, which # induces failures in test wakeup tests. Disable for the duration of # the tests. @@ -45,6 +48,9 @@ setup() { cleanup() { echo $sched_rt_runtime_orig > $sched_rt_runtime + if [ -n "${UMOUNT_DIR}" ]; then + umount ${UMOUNT_DIR} ||: + fi } errexit() { # message @@ -160,11 +166,13 @@ if [ -z "$TRACING_DIR" ]; then mount -t tracefs nodev /sys/kernel/tracing || errexit "Failed to mount /sys/kernel/tracing" TRACING_DIR="/sys/kernel/tracing" + UMOUNT_DIR=${TRACING_DIR} # If debugfs exists, then so does /sys/kernel/debug elif [ -d "/sys/kernel/debug" ]; then mount -t debugfs nodev /sys/kernel/debug || errexit "Failed to mount /sys/kernel/debug" TRACING_DIR="/sys/kernel/debug/tracing" + UMOUNT_DIR=${TRACING_DIR} else err_ret=$err_skip errexit "debugfs and tracefs are not configured in this kernel"

2 years

5
4
0 0

[PATCH V6 0/7] amd-pstate preferred core

by Meng Li

Hi all: The core frequency is subjected to the process variation in semiconductors. Not all cores are able to reach the maximum frequency respecting the infrastructure limits. Consequently, AMD has redefined the concept of maximum frequency of a part. This means that a fraction of cores can reach maximum frequency. To find the best process scheduling policy for a given scenario, OS needs to know the core ordering informed by the platform through highest performance capability register of the CPPC interface. Earlier implementations of amd-pstate preferred core only support a static core ranking and targeted performance. Now it has the ability to dynamically change the preferred core based on the workload and platform conditions and accounting for thermals and aging. Amd-pstate driver utilizes the functions and data structures provided by the ITMT architecture to enable the scheduler to favor scheduling on cores which can be get a higher frequency with lower voltage. We call it amd-pstate preferred core. Here sched_set_itmt_core_prio() is called to set priorities and sched_set_itmt_support() is called to enable ITMT feature. Amd-pstate driver uses the highest performance value to indicate the priority of CPU. The higher value has a higher priority. Amd-pstate driver will provide an initial core ordering at boot time. It relies on the CPPC interface to communicate the core ranking to the operating system and scheduler to make sure that OS is choosing the cores with highest performance firstly for scheduling the process. When amd-pstate driver receives a message with the highest performance change, it will update the core ranking. Changes form V5->V6: - cpufreq: amd-pstate: - - modify the wrong tag order. - - modify warning about hw_prefcore sysfs attribute. - - delete duplicate comments. - - modify the variable name cppc_highest_perf to prefcore_ranking. - - modify judgment conditions for setting highest_perf. - - modify sysfs attribute for CPPC highest perf to pr_debug message. - Documentation: amd-pstate: - - modify warning: title underline too short. Changes form V4->V5: - cpufreq: amd-pstate: - - modify sysfs attribute for CPPC highest perf. - - modify warning about comments - - rebase linux-next - cpufreq: - - Moidfy warning about function declarations. - Documentation: amd-pstate: - - align with ``amd-pstat`` Changes form V3->V4: - Documentation: amd-pstate: - - Modify inappropriate descriptions. Changes form V2->V3: - x86: - - Modify kconfig and description. - cpufreq: amd-pstate: - - Add Co-developed-by tag in commit message. - cpufreq: - - Modify commit message. - Documentation: amd-pstate: - - Modify inappropriate descriptions. Changes form V1->V2: - acpi: cppc: - - Add reference link. - cpufreq: - - Moidfy link error. - cpufreq: amd-pstate: - - Init the priorities of all online CPUs - - Use a single variable to represent the status of preferred core. - Documentation: - - Default enabled preferred core. - Documentation: amd-pstate: - - Modify inappropriate descriptions. - - Default enabled preferred core. - - Use a single variable to represent the status of preferred core. Meng Li (7): x86: Drop CPU_SUP_INTEL from SCHED_MC_PRIO for the expansion. acpi: cppc: Add get the highest performance cppc control cpufreq: amd-pstate: Enable amd-pstate preferred core supporting. cpufreq: Add a notification message that the highest perf has changed cpufreq: amd-pstate: Update amd-pstate preferred core ranking dynamically Documentation: amd-pstate: introduce amd-pstate preferred core Documentation: introduce amd-pstate preferrd core mode kernel command line options .../admin-guide/kernel-parameters.txt | 5 + Documentation/admin-guide/pm/amd-pstate.rst | 58 ++++++- arch/x86/Kconfig | 5 +- drivers/acpi/cppc_acpi.c | 13 ++ drivers/acpi/processor_driver.c | 6 + drivers/cpufreq/amd-pstate.c | 161 ++++++++++++++++-- drivers/cpufreq/cpufreq.c | 13 ++ include/acpi/cppc_acpi.h | 5 + include/linux/amd-pstate.h | 6 + include/linux/cpufreq.h | 5 + 10 files changed, 255 insertions(+), 22 deletions(-) -- 2.34.1

2 years

4
11
0 0

kselftest/fixes build: 3 builds: 0 failed, 3 passed, 1 warning (v6.6-rc1-4-g7e021da80f48)

by kernelci.org bot

kselftest/fixes build: 3 builds: 0 failed, 3 passed, 1 warning (v6.6-rc1-4-g7e021da80f48) Full Build Summary: https://kernelci.org/build/kselftest/branch/fixes/kernel/v6.6-rc1-4-g7e021d… Tree: kselftest Branch: fixes Git Describe: v6.6-rc1-4-g7e021da80f48 Git Commit: 7e021da80f48582171029714f8a487347f29dddb Git URL: https://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest.git Built: 3 unique architectures Warnings Detected: arm: i386: x86_64: x86_64_defconfig+kselftest (clang-16): 1 warning Warnings summary: 1 vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x1393eb ================================================================================ Detailed per-defconfig build reports: -------------------------------------------------------------------------------- i386_defconfig+kselftest (i386, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- multi_v7_defconfig+kselftest (arm, gcc-10) — PASS, 0 errors, 0 warnings, 0 section mismatches -------------------------------------------------------------------------------- x86_64_defconfig+kselftest (x86_64, clang-16) — PASS, 0 errors, 1 warning, 0 section mismatches Warnings: vmlinux.o: warning: objtool: set_ftrace_ops_ro+0x23: relocation to !ENDBR: .text+0x1393eb --- For more info write to <info(a)kernelci.org>

2 years

1
0
0 0

[GIT PULL] KUnit fixes update for Linux 6.6-rc2

by Shuah Khan

Hi Linus, Please pull the following KUnit fixes update for Linux 6.6-rc2. This kunit update for Linux 6.6-rc2 consists of important fixes to possible memory leak, null-ptr-deref, wild-memory-access, and error path bugs. diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 25e324bc9cf2ee956eec1db384c39c1a17b7c44a: kunit: fix struct kunit_attr header (2023-08-21 08:07:56 -0600) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-kunit-6.6-rc2 for you to fetch changes up to 9076bc476d7ebf0565903c4b048442131825c1c3: kunit: Fix possible memory leak in kunit_filter_suites() (2023-09-05 12:30:06 -0600) ---------------------------------------------------------------- linux-kselftest-kunit-6.6-rc2 This kunit update for Linux 6.6-rc2 consists of important fixes to possible memory leak, null-ptr-deref, wild-memory-access, and error path bugs. ---------------------------------------------------------------- David Gow (1): kunit: test: Make filter strings in executor_test writable 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/executor_test.c | 13 ++++++++----- lib/kunit/test.c | 3 ++- 3 files changed, 43 insertions(+), 21 deletions(-) ----------------------------------------------------------------

2 years

2
1
0 0

[GIT PULL] Kselftest fixes update for Linux 6.6-rc2

by Shuah Khan

Hi Linus, Please pull the following Kselftest fixes update for Linux 6.6-rc2. This kselftest fixes update for Linux 6.6-rc2 consists of fixes -- kselftest runner script to propagate SIGTERM to runner child to avoid kselftest hang. -- to install symlinks required for test execution to avoid test failures. -- kselftest dependency checker script argument parsing. diff is attached. thanks, -- Shuah ---------------------------------------------------------------- The following changes since commit 9b1db732866bee060b9bca9493e5ebf5e8874c48: selftests: cachestat: use proper syscall number macro (2023-08-16 11:12:44 -0600) are available in the Git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/shuah/linux-kselftest tags/linux-kselftest-next-6.6-rc2 for you to fetch changes up to 3f3f384139ed147c71e1d770accf610133d5309b: selftests: Keep symlinks, when possible (2023-09-08 10:06:56 -0600) ---------------------------------------------------------------- linux-kselftest-next-6.6-rc2 This kselftest fixes update for Linux 6.6-rc2 consists of fixes -- kselftest runner script to propagate SIGTERM to runner child to avoid kselftest hang. -- to install symlinks required for test execution to avoid test failures. -- kselftest dependency checker script argument parsing. ---------------------------------------------------------------- Björn Töpel (2): kselftest/runner.sh: Propagate SIGTERM to runner child selftests: Keep symlinks, when possible Ricardo B. Marliere (1): selftests: fix dependency checker script Zheng Yejian (1): selftests/ftrace: Correctly enable event in instance-event.tc .../ftrace/test.d/instances/instance-event.tc | 2 +- tools/testing/selftests/kselftest/runner.sh | 3 +- tools/testing/selftests/kselftest_deps.sh | 77 ++++++++++++++++++---- tools/testing/selftests/lib.mk | 4 +- 4 files changed, 70 insertions(+), 16 deletions(-) ----------------------------------------------------------------

2 years

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror September 2023