On 7/5/19 9:35 PM, Andrii Nakryiko wrote:
> BPF_MAP_TYPE_PERF_EVENT_ARRAY map is often used to send data from BPF program
> to user space for additional processing. libbpf already has very low-level API
> to read single CPU perf buffer, bpf_perf_event_read_simple(), but it's hard to
> use and requires a lot of code to set everything up. This patch adds
> perf_buffer abstraction on top of it, abstracting setting up and polling
> per-CPU logic into simple and convenient API, similar to what BCC provides.
>
> perf_buffer__new() sets up per-CPU ring buffers and updates corresponding BPF
> map entries. It accepts two user-provided callbacks: one for handling raw
> samples and one for get notifications of lost samples due to buffer overflow.
>
> perf_buffer__new_raw() is similar, but provides more control over how
> perf events are set up (by accepting user-provided perf_event_attr), how
> they are handled (perf_event_header pointer is passed directly to
> user-provided callback), and on which CPUs ring buffers are created
> (it's possible to provide a list of CPUs and corresponding map keys to
> update). This API allows advanced users fuller control.
>
> perf_buffer__poll() is used to fetch ring buffer data across all CPUs,
> utilizing epoll instance.
>
> perf_buffer__free() does corresponding clean up and unsets FDs from BPF map.
>
> All APIs are not thread-safe. User should ensure proper locking/coordination if
> used in multi-threaded set up.
>
> Signed-off-by: Andrii Nakryiko <andriin@xxxxxx>
> ---
> tools/lib/bpf/libbpf.c | 366 +++++++++++++++++++++++++++++++++++++++
> tools/lib/bpf/libbpf.h | 49 ++++++
> tools/lib/bpf/libbpf.map | 4 +
> 3 files changed, 419 insertions(+)
>
> diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
> index 2a08eb106221..72149d68b8c1 100644
> --- a/tools/lib/bpf/libbpf.c
> +++ b/tools/lib/bpf/libbpf.c
> @@ -32,7 +32,9 @@
> #include <linux/limits.h>
> #include <linux/perf_event.h>
> #include <linux/ring_buffer.h>
> +#include <sys/epoll.h>
> #include <sys/ioctl.h>
> +#include <sys/mman.h>
> #include <sys/stat.h>
> #include <sys/types.h>
> #include <sys/vfs.h>
> @@ -4354,6 +4356,370 @@ bpf_perf_event_read_simple(void *mmap_mem, size_t mmap_size, size_t page_size,
> return ret;
> }
>
> +struct perf_buffer;
> +
> +struct perf_buffer_params {
> + struct perf_event_attr *attr;
> + /* if event_cb is specified, it takes precendence */
> + perf_buffer_event_fn event_cb;
> + /* sample_cb and lost_cb are higher-level common-case callbacks */
> + perf_buffer_sample_fn sample_cb;
> + perf_buffer_lost_fn lost_cb;
> + void *ctx;
> + int cpu_cnt;
> + int *cpus;
[...]
> +
> +int perf_buffer__poll(struct perf_buffer *pb, int timeout_ms)
> +{
> + int cnt, err;
> +
> + cnt = epoll_wait(pb->epoll_fd, pb->events, pb->cpu_cnt, timeout_ms);
> + for (int i = 0; i < cnt; i++) {
Find one compilation error here.
libbpf.c: In function ‘perf_buffer__poll’:
libbpf.c:4728:2: error: ‘for’ loop initial declarations are only allowed
in C99 mode
for (int i = 0; i < cnt; i++) {
^
> + struct perf_cpu_buf *cpu_buf = pb->events[i].data.ptr;
> +
> + err = perf_buffer__process_records(pb, cpu_buf);
> + if (err) {
> + pr_warning("error while processing records: %d\n", err);
> + return err;
> + }
> + }
> + return cnt < 0 ? -errno : cnt;
> +}
> +
> struct bpf_prog_info_array_desc {
> int array_offset; /* e.g. offset of jited_prog_insns */
> int count_offset; /* e.g. offset of jited_prog_len */
[...]
