This patch is mainly considered based on the Android Perfetto (A powerful trace collection and analysis tool, support ftrace data source).
The output of bpf_trace_printk and bpf_vtrace_printk in ftrace is like:
app-12345 [001] d... 654321.1970001: bpf_trace_printk: blabla..
FUNCTION field of this kind of message is 'bpf_trace_printk', and there's no standard syntax format for it.
Currently, Perfetto doesn't collect 'bpf_trace/bpf_trace_printk' trace event by default, but does support
'tracing_mark_write' function style by default, such as:
app-3151 [000] d.h1. 6059.904239: tracing_mark_write: B|2491|BPRF-3151|TracingFunc
app-3151 [000] d.h1. 6059.904239: tracing_mark_write: E|2491
Therefore, it's considered to add this kfunc to output formatted BPF messages to ftrace like trace_marker,
allowing perfetto to collect and parse 'tracing_mark_write' events by default and eventually visualize them in the perfetto UI.
-----邮件原件-----
发件人: Alexei Starovoitov <alexei.starovoitov@xxxxxxxxx>
发送时间: 2024年9月30日 1:10
收件人: 燕青洲(Eric Yan) <eric.yan@xxxxxxxx>
抄送: kbuild test robot <lkp@xxxxxxxxx>; Andrii Nakryiko <andrii@xxxxxxxxxx>; Alexei Starovoitov <ast@xxxxxxxxxx>; bpf <bpf@xxxxxxxxxxxxxxx>; Daniel Borkmann <daniel@xxxxxxxxxxxxx>; Hao Luo <haoluo@xxxxxxxxxx>; John Fastabend <john.fastabend@xxxxxxxxx>; Jiri Olsa <jolsa@xxxxxxxxxx>; KP Singh <kpsingh@xxxxxxxxxx>; LKML <linux-kernel@xxxxxxxxxxxxxxx>; Martin KaFai Lau <martin.lau@xxxxxxxxx>; oe-kbuild-all@xxxxxxxxxxxxxxx; Stanislav Fomichev <sdf@xxxxxxxxxxx>; Song Liu <song@xxxxxxxxxx>; Yonghong Song <yonghong.song@xxxxxxxxx>
主题: Re: [PATCH v2] Add BPF Kernel Function bpf_ptrace_vprintk
On Thu, Sep 26, 2024 at 12:28 AM Eric Yan <eric.yan@xxxxxxxx> wrote:
>
> add a kfunc 'bpf_ptrace_vprintk' printing bpf msg with trace_marker
> format requirement so that these msgs can be retrieved by android
> perfetto by default and well represented in perfetto UI.
>
> [testing prog]
> const volatile bool ptrace_enabled = true; extern int
> bpf_ptrace_vprintk(char *fmt, u32 fmt_size, const void *args, u32
> args__sz) __ksym;
>
> ({ \
> if (!ptrace_enabled) { \
> bpf_printk(fmt, __VA_ARGS__); \
> } else { \
> char __fmt[] = fmt; \
> _Pragma("GCC diagnostic push") \
> _Pragma("GCC diagnostic ignored \"-Wint-conversion\"") \
> u64 __params[] = { __VA_ARGS__ }; \
> _Pragma("GCC diagnostic pop") \
> bpf_ptrace_vprintk(__fmt, sizeof(__fmt), __params, sizeof(__params)); \
> } \
> })
>
> SEC("perf_event")
> int do_sample(struct bpf_perf_event_data *ctx) {
> u64 ip = PT_REGS_IP(&ctx->regs);
> u64 id = bpf_get_current_pid_tgid();
> s32 pid = id >> 32;
> s32 tid = id;
> debug_printk("N|%d|BPRF-%d|BPRF:%llx", pid, tid, ip);
> return 0;
> }
>
> [output]:
> app-3151 [000] d.h1. 6059.904239: tracing_mark_write: N|2491|BPRF-3151|BPRF:58750d0eec
>
> Signed-off-by: Eric Yan <eric.yan@xxxxxxxx>
> ---
> kernel/bpf/helpers.c | 34 ++++++++++++++++++++++++++++++++++
> 1 file changed, 34 insertions(+)
>
> diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index
> 1a43d06eab28..1e37dae74ca6 100644
> --- a/kernel/bpf/helpers.c
> +++ b/kernel/bpf/helpers.c
> @@ -2521,6 +2521,39 @@ __bpf_kfunc struct task_struct *bpf_task_from_pid(s32 pid)
> return p;
> }
>
> +static noinline void tracing_mark_write(char *buf) {
> + trace_printk(buf);
> +}
> +
> +/* same as bpf_trace_vprintk, only with a trace_marker format
> +requirement
> + * @fmt: Format string, e.g. <B|E|C|N>|<%d:pid>|<%s:TAG>...
> + */
> +__bpf_kfunc int bpf_ptrace_vprintk(char *fmt, u32 fmt_size, const
> +void *args, u32 args__sz) {
> + struct bpf_bprintf_data data = {
> + .get_bin_args = true,
> + .get_buf = true,
> + };
> + int ret, num_args;
> +
> + if (args__sz & 7 || args__sz > MAX_BPRINTF_VARARGS * 8 || (args__sz && !args))
> + return -EINVAL;
> + num_args = args__sz / 8;
> +
> + ret = bpf_bprintf_prepare(fmt, fmt_size, args, num_args, &data);
> + if (ret < 0)
> + return ret;
> +
> + ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt,
> + data.bin_args);
> +
> + tracing_mark_write(data.buf);
> +
> + bpf_bprintf_cleanup(&data);
> +
> + return ret;
> +}
> +
> /**
> * bpf_dynptr_slice() - Obtain a read-only pointer to the dynptr data.
> * @p: The dynptr whose data slice to retrieve @@ -3090,6 +3123,7 @@
> BTF_ID_FLAGS(func, bpf_iter_bits_new, KF_ITER_NEW) BTF_ID_FLAGS(func,
> bpf_iter_bits_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func,
> bpf_iter_bits_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func,
> bpf_copy_from_user_str, KF_SLEEPABLE)
> +BTF_ID_FLAGS(func, bpf_ptrace_vprintk)
> BTF_KFUNCS_END(common_btf_ids)
Why new kfunc?
Use bpf_snprintf() and follow with bpf_trace_printk() ?
