From 8b401f9ed2441ad9e219953927a842d24ed051fc Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 May 2019 14:47:45 -0700 Subject: [PATCH 1/3] bpf: implement bpf_send_signal() helper This patch tries to solve the following specific use case. Currently, bpf program can already collect stack traces through kernel function get_perf_callchain() when certain events happens (e.g., cache miss counter or cpu clock counter overflows). But such stack traces are not enough for jitted programs, e.g., hhvm (jited php). To get real stack trace, jit engine internal data structures need to be traversed in order to get the real user functions. bpf program itself may not be the best place to traverse the jit engine as the traversing logic could be complex and it is not a stable interface either. Instead, hhvm implements a signal handler, e.g. for SIGALARM, and a set of program locations which it can dump stack traces. When it receives a signal, it will dump the stack in next such program location. Such a mechanism can be implemented in the following way: . a perf ring buffer is created between bpf program and tracing app. . once a particular event happens, bpf program writes to the ring buffer and the tracing app gets notified. . the tracing app sends a signal SIGALARM to the hhvm. But this method could have large delays and causing profiling results skewed. This patch implements bpf_send_signal() helper to send a signal to hhvm in real time, resulting in intended stack traces. Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- include/uapi/linux/bpf.h | 17 +++++++++- kernel/trace/bpf_trace.c | 72 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 88 insertions(+), 1 deletion(-) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 63e0cf66f01a..68d4470523a0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2672,6 +2672,20 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2782,7 +2796,8 @@ union bpf_attr { FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index f92d6ad5e080..70029eafc71f 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -567,6 +567,63 @@ static const struct bpf_func_proto bpf_probe_read_str_proto = { .arg3_type = ARG_ANYTHING, }; +struct send_signal_irq_work { + struct irq_work irq_work; + struct task_struct *task; + u32 sig; +}; + +static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work); + +static void do_bpf_send_signal(struct irq_work *entry) +{ + struct send_signal_irq_work *work; + + work = container_of(entry, struct send_signal_irq_work, irq_work); + group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID); +} + +BPF_CALL_1(bpf_send_signal, u32, sig) +{ + struct send_signal_irq_work *work = NULL; + + /* Similar to bpf_probe_write_user, task needs to be + * in a sound condition and kernel memory access be + * permitted in order to send signal to the current + * task. + */ + if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING))) + return -EPERM; + if (unlikely(uaccess_kernel())) + return -EPERM; + if (unlikely(!nmi_uaccess_okay())) + return -EPERM; + + if (in_nmi()) { + work = this_cpu_ptr(&send_signal_work); + if (work->irq_work.flags & IRQ_WORK_BUSY) + return -EBUSY; + + /* Add the current task, which is the target of sending signal, + * to the irq_work. The current task may change when queued + * irq works get executed. + */ + work->task = current; + work->sig = sig; + irq_work_queue(&work->irq_work); + return 0; + } + + return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID); +} + +static const struct bpf_func_proto bpf_send_signal_proto = { + .func = bpf_send_signal, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -617,6 +674,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_current_cgroup_id: return &bpf_get_current_cgroup_id_proto; #endif + case BPF_FUNC_send_signal: + return &bpf_send_signal_proto; default: return NULL; } @@ -1343,5 +1402,18 @@ static int __init bpf_event_init(void) return 0; } +static int __init send_signal_irq_work_init(void) +{ + int cpu; + struct send_signal_irq_work *work; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&send_signal_work, cpu); + init_irq_work(&work->irq_work, do_bpf_send_signal); + } + return 0; +} + fs_initcall(bpf_event_init); +subsys_initcall(send_signal_irq_work_init); #endif /* CONFIG_MODULES */ From edaccf8985305967c22903a78283c8c837ea48dd Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 May 2019 14:47:46 -0700 Subject: [PATCH 2/3] tools/bpf: sync bpf uapi header bpf.h to tools directory The bpf uapi header include/uapi/linux/bpf.h is sync'ed to tools/include/uapi/linux/bpf.h. Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/include/uapi/linux/bpf.h | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 63e0cf66f01a..68d4470523a0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2672,6 +2672,20 @@ union bpf_attr { * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -2782,7 +2796,8 @@ union bpf_attr { FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call From 16f0efc3b46352018c297bbdb2c405e7d8a63095 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 May 2019 14:47:47 -0700 Subject: [PATCH 3/3] tools/bpf: add selftest in test_progs for bpf_send_signal() helper The test covered both nmi and tracepoint perf events. $ ./test_progs ... test_send_signal_tracepoint:PASS:tracepoint 0 nsec ... test_send_signal_common:PASS:tracepoint 0 nsec ... test_send_signal_common:PASS:perf_event 0 nsec ... test_send_signal:OK Acked-by: Andrii Nakryiko Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- tools/testing/selftests/bpf/bpf_helpers.h | 1 + .../selftests/bpf/prog_tests/send_signal.c | 198 ++++++++++++++++++ .../bpf/progs/test_send_signal_kern.c | 51 +++++ 3 files changed, 250 insertions(+) create mode 100644 tools/testing/selftests/bpf/prog_tests/send_signal.c create mode 100644 tools/testing/selftests/bpf/progs/test_send_signal_kern.c diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index 4b27840b8109..e6d243b7cd74 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -224,6 +224,7 @@ static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk, (void *) BPF_FUNC_sk_storage_get; static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) = (void *)BPF_FUNC_sk_storage_delete; +static int (*bpf_send_signal)(unsigned sig) = (void *)BPF_FUNC_send_signal; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c new file mode 100644 index 000000000000..67cea1686305 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0 +#include + +static volatile int sigusr1_received = 0; + +static void sigusr1_handler(int signum) +{ + sigusr1_received++; +} + +static int test_send_signal_common(struct perf_event_attr *attr, + int prog_type, + const char *test_name) +{ + int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd; + const char *file = "./test_send_signal_kern.o"; + struct bpf_object *obj = NULL; + int pipe_c2p[2], pipe_p2c[2]; + __u32 key = 0, duration = 0; + char buf[256]; + pid_t pid; + __u64 val; + + if (CHECK(pipe(pipe_c2p), test_name, + "pipe pipe_c2p error: %s\n", strerror(errno))) + goto no_fork_done; + + if (CHECK(pipe(pipe_p2c), test_name, + "pipe pipe_p2c error: %s\n", strerror(errno))) { + close(pipe_c2p[0]); + close(pipe_c2p[1]); + goto no_fork_done; + } + + pid = fork(); + if (CHECK(pid < 0, test_name, "fork error: %s\n", strerror(errno))) { + close(pipe_c2p[0]); + close(pipe_c2p[1]); + close(pipe_p2c[0]); + close(pipe_p2c[1]); + goto no_fork_done; + } + + if (pid == 0) { + /* install signal handler and notify parent */ + signal(SIGUSR1, sigusr1_handler); + + close(pipe_c2p[0]); /* close read */ + close(pipe_p2c[1]); /* close write */ + + /* notify parent signal handler is installed */ + write(pipe_c2p[1], buf, 1); + + /* make sure parent enabled bpf program to send_signal */ + read(pipe_p2c[0], buf, 1); + + /* wait a little for signal handler */ + sleep(1); + + if (sigusr1_received) + write(pipe_c2p[1], "2", 1); + else + write(pipe_c2p[1], "0", 1); + + /* wait for parent notification and exit */ + read(pipe_p2c[0], buf, 1); + + close(pipe_c2p[1]); + close(pipe_p2c[0]); + exit(0); + } + + close(pipe_c2p[1]); /* close write */ + close(pipe_p2c[0]); /* close read */ + + err = bpf_prog_load(file, prog_type, &obj, &prog_fd); + if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n", + strerror(errno))) + goto prog_load_failure; + + pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1, + -1 /* group id */, 0 /* flags */); + if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n", + strerror(errno))) { + err = -1; + goto close_prog; + } + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n", + strerror(errno))) + goto disable_pmu; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd); + if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n", + strerror(errno))) + goto disable_pmu; + + err = -1; + info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map"); + if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map")) + goto disable_pmu; + + status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map"); + if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map")) + goto disable_pmu; + + /* wait until child signal handler installed */ + read(pipe_c2p[0], buf, 1); + + /* trigger the bpf send_signal */ + key = 0; + val = (((__u64)(SIGUSR1)) << 32) | pid; + bpf_map_update_elem(info_map_fd, &key, &val, 0); + + /* notify child that bpf program can send_signal now */ + write(pipe_p2c[1], buf, 1); + + /* wait for result */ + err = read(pipe_c2p[0], buf, 1); + if (CHECK(err < 0, test_name, "reading pipe error: %s\n", strerror(errno))) + goto disable_pmu; + if (CHECK(err == 0, test_name, "reading pipe error: size 0\n")) { + err = -1; + goto disable_pmu; + } + + err = CHECK(buf[0] != '2', test_name, "incorrect result\n"); + + /* notify child safe to exit */ + write(pipe_p2c[1], buf, 1); + +disable_pmu: + close(pmu_fd); +close_prog: + bpf_object__close(obj); +prog_load_failure: + close(pipe_c2p[0]); + close(pipe_p2c[1]); + wait(NULL); +no_fork_done: + return err; +} + +static int test_send_signal_tracepoint(void) +{ + const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id"; + struct perf_event_attr attr = { + .type = PERF_TYPE_TRACEPOINT, + .sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN, + .sample_period = 1, + .wakeup_events = 1, + }; + __u32 duration = 0; + int bytes, efd; + char buf[256]; + + efd = open(id_path, O_RDONLY, 0); + if (CHECK(efd < 0, "tracepoint", + "open syscalls/sys_enter_nanosleep/id failure: %s\n", + strerror(errno))) + return -1; + + bytes = read(efd, buf, sizeof(buf)); + close(efd); + if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint", + "read syscalls/sys_enter_nanosleep/id failure: %s\n", + strerror(errno))) + return -1; + + attr.config = strtol(buf, NULL, 0); + + return test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint"); +} + +static int test_send_signal_nmi(void) +{ + struct perf_event_attr attr = { + .sample_freq = 50, + .freq = 1, + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + }; + + return test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT, "perf_event"); +} + +void test_send_signal(void) +{ + int ret = 0; + + ret |= test_send_signal_tracepoint(); + ret |= test_send_signal_nmi(); + if (!ret) + printf("test_send_signal:OK\n"); + else + printf("test_send_signal:FAIL\n"); +} diff --git a/tools/testing/selftests/bpf/progs/test_send_signal_kern.c b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c new file mode 100644 index 000000000000..45a1a1a2c345 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_send_signal_kern.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Facebook +#include +#include +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") info_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 1, +}; + +BPF_ANNOTATE_KV_PAIR(info_map, __u32, __u64); + +struct bpf_map_def SEC("maps") status_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 1, +}; + +BPF_ANNOTATE_KV_PAIR(status_map, __u32, __u64); + +SEC("send_signal_demo") +int bpf_send_signal_test(void *ctx) +{ + __u64 *info_val, *status_val; + __u32 key = 0, pid, sig; + int ret; + + status_val = bpf_map_lookup_elem(&status_map, &key); + if (!status_val || *status_val != 0) + return 0; + + info_val = bpf_map_lookup_elem(&info_map, &key); + if (!info_val || *info_val == 0) + return 0; + + sig = *info_val >> 32; + pid = *info_val & 0xffffFFFF; + + if ((bpf_get_current_pid_tgid() >> 32) == pid) { + ret = bpf_send_signal(sig); + if (ret == 0) + *status_val = 1; + } + + return 0; +} +char __license[] SEC("license") = "GPL";