/* * Force it to be aligned to unsigned long to avoid misaligned accesses * surprises
*/ typedef typeof(unsignedlong [PERF_MAX_TRACE_SIZE / sizeof(unsignedlong)])
perf_trace_t;
/* Count the events in use (per event id, not per instance) */ staticint total_ref_count;
staticint perf_trace_event_perm(struct trace_event_call *tp_event, struct perf_event *p_event)
{ int ret;
if (tp_event->perf_perm) {
ret = tp_event->perf_perm(tp_event, p_event); if (ret) return ret;
}
/* * We checked and allowed to create parent, * allow children without checking.
*/ if (p_event->parent) return 0;
/* * It's ok to check current process (owner) permissions in here, * because code below is called only via perf_event_open syscall.
*/
/* The ftrace function trace is allowed only for root. */ if (ftrace_event_is_function(tp_event)) {
ret = perf_allow_tracepoint(); if (ret) return ret;
if (!is_sampling_event(p_event)) return 0;
/* * We don't allow user space callchains for function trace * event, due to issues with page faults while tracing page * fault handler and its overall trickiness nature.
*/ if (!p_event->attr.exclude_callchain_user) return -EINVAL;
/* * Same reason to disable user stack dump as for user space * callchains above.
*/ if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER) return -EINVAL;
}
/* No tracing, just counting, so no obvious leak */ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW)) return 0;
/* Some events are ok to be traced by non-root users... */ if (p_event->attach_state == PERF_ATTACH_TASK) { if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY) return 0;
}
/* * ...otherwise raw tracepoint data can be a severe data leak, * only allow root to have these.
*/
ret = perf_allow_tracepoint(); if (ret) return ret;
return 0;
}
staticint perf_trace_event_reg(struct trace_event_call *tp_event, struct perf_event *p_event)
{ struct hlist_head __percpu *list; int ret = -ENOMEM; int cpu;
p_event->tp_event = tp_event; if (tp_event->perf_refcount++ > 0) return 0;
list = alloc_percpu(struct hlist_head); if (!list) goto fail;
#ifdef CONFIG_UPROBE_EVENTS int perf_uprobe_init(struct perf_event *p_event, unsignedlong ref_ctr_offset, bool is_retprobe)
{ int ret; char *path = NULL; struct trace_event_call *tp_event;
if (!p_event->attr.uprobe_path) return -EINVAL;
path = strndup_user(u64_to_user_ptr(p_event->attr.uprobe_path),
PATH_MAX); if (IS_ERR(path)) {
ret = PTR_ERR(path); return (ret == -EINVAL) ? -E2BIG : ret;
} if (path[0] == '\0') {
ret = -EINVAL; goto out;
}
tp_event = create_local_trace_uprobe(path, p_event->attr.probe_offset,
ref_ctr_offset, is_retprobe); if (IS_ERR(tp_event)) {
ret = PTR_ERR(tp_event); goto out;
}
/* * local trace_uprobe need to hold event_mutex to call * uprobe_buffer_enable() and uprobe_buffer_disable(). * event_mutex is not required for local trace_kprobes.
*/
mutex_lock(&event_mutex);
ret = perf_trace_event_init(tp_event, p_event); if (ret)
destroy_local_trace_uprobe(tp_event);
mutex_unlock(&event_mutex);
out:
kfree(path); return ret;
}
int perf_trace_add(struct perf_event *p_event, int flags)
{ struct trace_event_call *tp_event = p_event->tp_event; struct hw_perf_event *hwc = &p_event->hw;
if (!(flags & PERF_EF_START))
p_event->hw.state = PERF_HES_STOPPED;
if (is_sampling_event(p_event)) {
hwc->last_period = hwc->sample_period;
perf_swevent_set_period(p_event);
}
/* * If TRACE_REG_PERF_ADD returns false; no custom action was performed * and we need to take the default action of enqueueing our event on * the right per-cpu hlist.
*/ if (!tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event)) { struct hlist_head __percpu *pcpu_list; struct hlist_head *list;
pcpu_list = tp_event->perf_events; if (WARN_ON_ONCE(!pcpu_list)) return -EINVAL;
list = this_cpu_ptr(pcpu_list);
hlist_add_head_rcu(&p_event->hlist_entry, list);
}
/* * If TRACE_REG_PERF_DEL returns false; no custom action was performed * and we need to take the default action of dequeueing our event from * the right per-cpu hlist.
*/ if (!tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event))
hlist_del_rcu(&p_event->hlist_entry);
}
void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
{ char *raw_data; int rctx;
if (regs)
*regs = this_cpu_ptr(&__perf_regs[rctx]);
raw_data = this_cpu_ptr(perf_trace_buf[rctx]);
/* zero the dead bytes from align to not leak stack to user */
memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64)); return raw_data;
}
EXPORT_SYMBOL_GPL(perf_trace_buf_alloc);
NOKPROBE_SYMBOL(perf_trace_buf_alloc);
/* * @event->hlist entry is NULL (per INIT_HLIST_NODE), and all * the perf code does is hlist_for_each_entry_rcu(), so we can * get away with simply setting the @head.first pointer in order * to create a singular list.
*/
head.first = &event->hlist_entry;
switch (type) { case TRACE_REG_REGISTER: case TRACE_REG_UNREGISTER: break; case TRACE_REG_PERF_REGISTER: case TRACE_REG_PERF_UNREGISTER: return 0; case TRACE_REG_PERF_OPEN: return perf_ftrace_function_register(data); case TRACE_REG_PERF_CLOSE: return perf_ftrace_function_unregister(data); case TRACE_REG_PERF_ADD:
event->ftrace_ops.private = (void *)(unsignedlong)smp_processor_id(); return 1; case TRACE_REG_PERF_DEL:
event->ftrace_ops.private = (void *)(unsignedlong)nr_cpu_ids; return 1;
}
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.