From 8b401f9ed2441ad9e219953927a842d24ed051fc Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Thu, 23 May 2019 14:47:45 -0700 Subject: 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 --- kernel/trace/bpf_trace.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 72 insertions(+) (limited to 'kernel/trace') 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 */ -- cgit v1.2.3 From e1afb70252a8614e1ef7aec05ff1b84fd324b782 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sat, 25 May 2019 11:57:53 -0700 Subject: bpf: check signal validity in nmi for bpf_send_signal() helper Commit 8b401f9ed244 ("bpf: implement bpf_send_signal() helper") introduced bpf_send_signal() helper. If the context is nmi, the sending signal work needs to be deferred to irq_work. If the signal is invalid, the error will appear in irq_work and it won't be propagated to user. This patch did an early check in the helper itself to notify user invalid signal, as suggested by Daniel. Suggested-by: Daniel Borkmann Signed-off-by: Yonghong Song Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 70029eafc71f..fe73926a07cd 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -600,6 +600,12 @@ BPF_CALL_1(bpf_send_signal, u32, sig) return -EPERM; if (in_nmi()) { + /* Do an early check on signal validity. Otherwise, + * the error is lost in deferred irq_work. + */ + if (unlikely(!valid_signal(sig))) + return -EINVAL; + work = this_cpu_ptr(&send_signal_work); if (work->irq_work.flags & IRQ_WORK_BUSY) return -EBUSY; -- cgit v1.2.3 From e672db03ab0e43e41ab6f8b2156a10d6e40f243d Mon Sep 17 00:00:00 2001 From: Stanislav Fomichev Date: Tue, 28 May 2019 14:14:44 -0700 Subject: bpf: tracing: properly use bpf_prog_array api Now that we don't have __rcu markers on the bpf_prog_array helpers, let's use proper rcu_dereference_protected to obtain array pointer under mutex. Cc: Steven Rostedt Cc: Ingo Molnar Signed-off-by: Stanislav Fomichev Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'kernel/trace') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index fe73926a07cd..3994a231eb92 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -19,6 +19,9 @@ #include "trace_probe.h" #include "trace.h" +#define bpf_event_rcu_dereference(p) \ + rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex)) + #ifdef CONFIG_MODULES struct bpf_trace_module { struct module *module; @@ -1099,7 +1102,7 @@ static DEFINE_MUTEX(bpf_event_mutex); int perf_event_attach_bpf_prog(struct perf_event *event, struct bpf_prog *prog) { - struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret = -EEXIST; @@ -1117,7 +1120,7 @@ int perf_event_attach_bpf_prog(struct perf_event *event, if (event->prog) goto unlock; - old_array = event->tp_event->prog_array; + old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); if (old_array && bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) { ret = -E2BIG; @@ -1140,7 +1143,7 @@ unlock: void perf_event_detach_bpf_prog(struct perf_event *event) { - struct bpf_prog_array __rcu *old_array; + struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; int ret; @@ -1149,7 +1152,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event) if (!event->prog) goto unlock; - old_array = event->tp_event->prog_array; + old_array = bpf_event_rcu_dereference(event->tp_event->prog_array); ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array); if (ret == -ENOENT) goto unlock; @@ -1171,6 +1174,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) { struct perf_event_query_bpf __user *uquery = info; struct perf_event_query_bpf query = {}; + struct bpf_prog_array *progs; u32 *ids, prog_cnt, ids_len; int ret; @@ -1195,10 +1199,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info) */ mutex_lock(&bpf_event_mutex); - ret = bpf_prog_array_copy_info(event->tp_event->prog_array, - ids, - ids_len, - &prog_cnt); + progs = bpf_event_rcu_dereference(event->tp_event->prog_array); + ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt); mutex_unlock(&bpf_event_mutex); if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) || -- cgit v1.2.3