Re: [PATCH bpf v2 2/2] selftests/bpf: cover UTF-8 trace_printk output

[Paul Chaignon]

On Wed, Apr 15, 2026 at 11:21:26AM +0800, Yihan Ding wrote:
> Extend trace_printk coverage to verify that UTF-8 literal text is
> emitted successfully and that non-ASCII bytes are still rejected once
> parsing is inside a '%' format sequence.
> 
> Suggested-by: Alan Maguire <alan.maguire@xxxxxxxxxx>
> Signed-off-by: Yihan Ding <dingyihan@xxxxxxxxxxxxx>
> ---
>  .../selftests/bpf/prog_tests/trace_printk.c   | 26 +++++++++++++++----
>  .../selftests/bpf/progs/trace_printk.c        |  9 +++++++
>  2 files changed, 30 insertions(+), 5 deletions(-)
> 
> diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
> index e56e88596d64..40499f01d228 100644
> --- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
> +++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
> @@ -6,18 +6,21 @@
>  #include "trace_printk.lskel.h"
>  
>  #define SEARCHMSG	"testing,testing"
> +#define SEARCHMSG_UTF8	"中文,测试"
>  
>  static void trace_pipe_cb(const char *str, void *data)
>  {
>  	if (strstr(str, SEARCHMSG) != NULL)
> -		(*(int *)data)++;
> +		((int *)data)[0]++;
> +	if (strstr(str, SEARCHMSG_UTF8) != NULL)
> +		((int *)data)[1]++;
>  }
>  
>  void serial_test_trace_printk(void)
>  {
>  	struct trace_printk_lskel__bss *bss;
>  	struct trace_printk_lskel *skel;
> -	int err = 0, found = 0;
> +	int err = 0, found[2] = {};
>  
>  	skel = trace_printk_lskel__open();
>  	if (!ASSERT_OK_PTR(skel, "trace_printk__open"))
> @@ -46,11 +49,24 @@ void serial_test_trace_printk(void)
>  	if (!ASSERT_GT(bss->trace_printk_ret, 0, "bss->trace_printk_ret"))
>  		goto cleanup;
>  
> -	/* verify our search string is in the trace buffer */
> -	ASSERT_OK(read_trace_pipe_iter(trace_pipe_cb, &found, 1000),
> +	if (!ASSERT_GT(bss->trace_printk_utf8_ran, 0, "bss->trace_printk_utf8_ran"))
> +		goto cleanup;
> +
> +	if (!ASSERT_GT(bss->trace_printk_utf8_ret, 0, "bss->trace_printk_utf8_ret"))
> +		goto cleanup;
> +
> +	if (!ASSERT_LT(bss->trace_printk_utf8_spec_ret, 0,
> +		       "bss->trace_printk_utf8_spec_ret"))
> +		goto cleanup;
> +
> +	/* verify our search strings are in the trace buffer */
> +	ASSERT_OK(read_trace_pipe_iter(trace_pipe_cb, found, 1000),
>  		 "read_trace_pipe_iter");
>  
> -	if (!ASSERT_EQ(found, bss->trace_printk_ran, "found"))
> +	if (!ASSERT_EQ(found[0], bss->trace_printk_ran, "found"))
> +		goto cleanup;
> +
> +	if (!ASSERT_EQ(found[1], bss->trace_printk_utf8_ran, "found_utf8"))
>  		goto cleanup;
>  
>  cleanup:
> diff --git a/tools/testing/selftests/bpf/progs/trace_printk.c b/tools/testing/selftests/bpf/progs/trace_printk.c
> index 6695478c2b25..62153d8c5eba 100644
> --- a/tools/testing/selftests/bpf/progs/trace_printk.c
> +++ b/tools/testing/selftests/bpf/progs/trace_printk.c
> @@ -10,13 +10,22 @@ char _license[] SEC("license") = "GPL";
>  
>  int trace_printk_ret = 0;
>  int trace_printk_ran = 0;
> +int trace_printk_utf8_spec_ret = 0;
> +int trace_printk_utf8_ret = 0;
> +int trace_printk_utf8_ran = 0;
>  
>  const char fmt[] = "Testing,testing %d\n";
> +static const char utf8_fmt[] = "中文,测试 %d\n";
> +static const char utf8_spec_fmt[] = "%中文\n";

What's the purpose of the second string here?

>  
>  SEC("fentry/" SYS_PREFIX "sys_nanosleep")
>  int sys_enter(void *ctx)
>  {
>  	trace_printk_ret = bpf_trace_printk(fmt, sizeof(fmt),
>  					    ++trace_printk_ran);
> +	trace_printk_utf8_ret = bpf_trace_printk(utf8_fmt, sizeof(utf8_fmt),
> +						 ++trace_printk_utf8_ran);
> +	trace_printk_utf8_spec_ret = bpf_trace_printk(utf8_spec_fmt,
> +						      sizeof(utf8_spec_fmt));
>  	return 0;
>  }
> -- 
> 2.20.1
>