On 8/6/19 4:41 PM, Daniel Xu wrote:
> It's useful to know kprobe's nmissed and nhit stats. For example with
> tracing tools, it's important to know when events may have been lost.
> There is currently no way to get that information from the perf API.
> This patch adds a new ioctl that lets users query this information.
> ---
> include/linux/trace_events.h | 6 ++++++
> include/uapi/linux/perf_event.h | 23 +++++++++++++++++++++++
> kernel/events/core.c | 11 +++++++++++
> kernel/trace/trace_kprobe.c | 25 +++++++++++++++++++++++++
> 4 files changed, 65 insertions(+)
>
> diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
> index 5150436783e8..28faf115e0b8 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_event_query_kprobe(struct perf_event *event, void __user *info);
> +#else
> +int perf_event_query_kprobe(struct perf_event *event, void __user *info)
> +{
> + return -EOPNOTSUPP;
> +}
> #endif
> #ifdef CONFIG_UPROBE_EVENTS
> extern int perf_uprobe_init(struct perf_event *event,
> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
> index 7198ddd0c6b1..4a5e18606baf 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_KPROE command
> + * to query information about the kprobe attached to the perf
> + * event.
> + */
> +struct perf_event_query_kprobe {
> + /*
> + * Size of structure for forward/backward compatibility
> + */
> + __u32 size;
> + /*
> + * Set by the kernel to indicate number of times this kprobe
> + * was temporarily disabled
> + */
> + __u64 nmissed;
> + /*
> + * Set by the kernel to indicate number of times this kprobe
> + * 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('$', 11, struct perf_event_attr *)
> +#define PERF_EVENT_IOC_QUERY_KPROBE _IOWR('$', 12, struct perf_event_query_kprobe *)
>
> enum perf_event_ioc_flags {
> PERF_IOC_FLAG_GROUP = 1U << 0,
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index 026a14541a38..d61c3ac5da4f 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -5061,6 +5061,10 @@ 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);
>
> +#ifdef CONFIG_KPROBE_EVENTS
> +static struct pmu perf_kprobe;
> +#endif /* CONFIG_KPROBE_EVENTS */
> +
> static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned long arg)
> {
> void (*func)(struct perf_event *);
> @@ -5143,6 +5147,13 @@ static long _perf_ioctl(struct perf_event *event, unsigned int cmd, unsigned lon
>
> return perf_event_modify_attr(event, &new_attr);
> }
> +#ifdef CONFIG_KPROBE_EVENTS
> + case PERF_EVENT_IOC_QUERY_KPROBE:
> + if (event->attr.type != perf_kprobe.type)
> + return -EINVAL;
> +
> + return perf_event_query_kprobe(event, (void __user *)arg);
> +#endif /* CONFIG_KPROBE_EVENTS */
> default:
> return -ENOTTY;
> }
> diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
> index 9d483ad9bb6c..5449182f3056 100644
> --- a/kernel/trace/trace_kprobe.c
> +++ b/kernel/trace/trace_kprobe.c
> @@ -196,6 +196,31 @@ bool trace_kprobe_error_injectable(struct trace_event_call *call)
> return within_error_injection_list(trace_kprobe_address(tk));
> }
>
> +int perf_event_query_kprobe(struct perf_event *event, void __user *info)
> +{
> + struct perf_event_query_kprobe __user *uquery = info;
> + struct perf_event_query_kprobe query = {};
> + struct trace_event_call *call = event->tp_event;
> + struct trace_kprobe *tk = (struct trace_kprobe *)call->data;
> + u64 nmissed, nhit;
> +
> + if (!capable(CAP_SYS_ADMIN))
> + return -EPERM;
> + if (copy_from_user(&query, uquery, sizeof(query)))
> + return -EFAULT;
> + if (query.size != sizeof(query))
> + return -EINVAL;
Note that here we did not handle any backward or forward compatibility.
> +
> + nhit = trace_kprobe_nhit(tk);
> + nmissed = tk->rp.kp.nmissed;
> +
> + if (copy_to_user(&uquery->nmissed, &nmissed, sizeof(nmissed)) ||
> + copy_to_user(&uquery->nhit, &nhit, sizeof(nhit)))
> + return -EFAULT;
> +
> + return 0;
> +}
> +
> static int register_kprobe_event(struct trace_kprobe *tk);
> static int unregister_kprobe_event(struct trace_kprobe *tk);
>
>
