[PATCH v3 bpf-next 1/4] tracing/probe: Add PERF_EVENT_IOC_QUERY_PROBE ioctl
From: Daniel Xu
Date: Fri Aug 16 2019 - 18:32:31 EST
It's useful to know [uk]probe's nmissed and nhit stats. For example with
tracing tools, it's important to know when events may have been lost.
debugfs currently exposes a control file to get this information, but
it is not compatible with probes registered with the perf API.
While bpf programs may be able to manually count nhit, there is no way
to gather nmissed. In other words, it is currently not possible to
retrieve information about FD-based probes.
This patch adds a new ioctl that lets users query nmissed (as well as
nhit for completeness). We currently only add support for [uk]probes
but leave the possibility open for other probes like tracepoint.
Signed-off-by: Daniel Xu <dxu@xxxxxxxxx>
---
include/linux/trace_events.h | 12 ++++++++++++
include/uapi/linux/perf_event.h | 23 +++++++++++++++++++++++
kernel/events/core.c | 20 ++++++++++++++++++++
kernel/trace/trace_kprobe.c | 24 ++++++++++++++++++++++++
kernel/trace/trace_uprobe.c | 24 ++++++++++++++++++++++++
5 files changed, 103 insertions(+)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 5150436783e8..61558f19696a 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -586,6 +586,12 @@ extern int bpf_get_kprobe_info(const struct perf_event *event,
u32 *fd_type, const char **symbol,
u64 *probe_offset, u64 *probe_addr,
bool perf_type_tracepoint);
+extern int perf_kprobe_event_query(struct perf_event *event, void __user *info);
+#else
+int perf_kprobe_event_query(struct perf_event *event, void __user *info)
+{
+ return -EOPNOTSUPP;
+}
#endif
#ifdef CONFIG_UPROBE_EVENTS
extern int perf_uprobe_init(struct perf_event *event,
@@ -594,6 +600,12 @@ extern void perf_uprobe_destroy(struct perf_event *event);
extern int bpf_get_uprobe_info(const struct perf_event *event,
u32 *fd_type, const char **filename,
u64 *probe_offset, bool perf_type_tracepoint);
+extern int perf_uprobe_event_query(struct perf_event *event, void __user *info);
+#else
+int perf_uprobe_event_query(struct perf_event *event, void __user *info)
+{
+ return -EOPNOTSUPP;
+}
#endif
extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
char *filter_str);
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7198ddd0c6b1..8783d29a807a 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -447,6 +447,28 @@ struct perf_event_query_bpf {
__u32 ids[0];
};
+/*
+ * Structure used by below PERF_EVENT_IOC_QUERY_PROBE command
+ * to query information about the probe attached to the perf
+ * event. Currently only supports [uk]probes.
+ */
+struct perf_event_query_probe {
+ /*
+ * Size of structure for forward/backward compatibility
+ */
+ __u64 size;
+ /*
+ * Set by the kernel to indicate number of times this probe
+ * was temporarily disabled
+ */
+ __u64 nmissed;
+ /*
+ * Set by the kernel to indicate number of times this probe
+ * was hit
+ */
+ __u64 nhit;
+};
+
/*
* Ioctls that can be done on a perf event fd:
*/
@@ -462,6 +484,7 @@ struct perf_event_query_bpf {
#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32)
#define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *)
#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW('$', 11, struct perf_event_attr *)
+#define PERF_EVENT_IOC_QUERY_PROBE _IOR('$', 12, struct perf_event_query_probe *)
enum perf_event_ioc_flags {
PERF_IOC_FLAG_GROUP = 1U << 0,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0463c1151bae..ed33d50511a3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5060,6 +5060,8 @@ static int perf_event_set_filter(struct perf_event *event, void __user *arg);
static int perf_event_set_bpf_prog(struct perf_event *event, u32 prog_fd);
static int perf_copy_attr(struct perf_event_attr __user *uattr,
struct perf_event_attr *attr);
+static int perf_probe_event_query(struct perf_event *event,
+ void __user *info);
static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
{
@@ -5143,6 +5145,10 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
return perf_event_modify_attr(event, &new_attr);
}
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
+ case PERF_EVENT_IOC_QUERY_PROBE:
+ return perf_probe_event_query(event, (void __user *)arg);
+#endif
default:
return -ENOTTY;
}
@@ -8833,6 +8839,20 @@ static inline void perf_tp_register(void)
#endif
}
+static int perf_probe_event_query(struct perf_event *event,
+ void __user *info)
+{
+#ifdef CONFIG_KPROBE_EVENTS
+ if (event->attr.type == perf_kprobe.type)
+ return perf_kprobe_event_query(event, (void __user *)info);
+#endif
+#ifdef CONFIG_UPROBE_EVENTS
+ if (event->attr.type == perf_uprobe.type)
+ return perf_uprobe_event_query(event, (void __user *)info);
+#endif
+ return -EINVAL;
+}
+
static void perf_event_free_filter(struct perf_event *event)
{
ftrace_profile_free_filter(event);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 9d483ad9bb6c..89fbe3e97562 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -196,6 +196,30 @@ bool trace_kprobe_error_injectable(struct trace_event_call *call)
return within_error_injection_list(trace_kprobe_address(tk));
}
+int perf_kprobe_event_query(struct perf_event *event, void __user *info)
+{
+ struct perf_event_query_probe __user *uquery = info;
+ struct perf_event_query_probe query = {};
+ struct trace_event_call *call = event->tp_event;
+ struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
+ u64 ncopy;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (copy_from_user(&query, uquery,
+ offsetofend(struct perf_event_query_probe, size)))
+ return -EFAULT;
+
+ ncopy = min_t(u64, query.size, sizeof(query));
+ query.nhit = trace_kprobe_nhit(tk);
+ query.nmissed = tk->rp.kp.nmissed;
+
+ if (copy_to_user(uquery, &query, ncopy))
+ return -EFAULT;
+
+ return 0;
+}
+
static int register_kprobe_event(struct trace_kprobe *tk);
static int unregister_kprobe_event(struct trace_kprobe *tk);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 1ceedb9146b1..ecdf2bdb91a7 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -1333,6 +1333,30 @@ static inline void init_trace_event_call(struct trace_uprobe *tu)
call->data = tu;
}
+int perf_uprobe_event_query(struct perf_event *event, void __user *info)
+{
+ struct perf_event_query_probe __user *uquery = info;
+ struct perf_event_query_probe query = {};
+ struct trace_event_call *call = event->tp_event;
+ struct trace_uprobe *tu = (struct trace_uprobe *)call->data;
+ u64 ncopy;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ if (copy_from_user(&query, uquery,
+ offsetofend(struct perf_event_query_probe, size)))
+ return -EFAULT;
+
+ ncopy = min_t(u64, query.size, sizeof(query));
+ query.nhit = tu->nhit;
+ query.nmissed = 0;
+
+ if (copy_to_user(uquery, &query, ncopy))
+ return -EFAULT;
+
+ return 0;
+}
+
static int register_uprobe_event(struct trace_uprobe *tu)
{
init_trace_event_call(tu);
--
2.20.1