From b960430ea8862ef37ce53c8bf74a8dc79d3f2404 Mon Sep 17 00:00:00 2001 From: Yihan Ding Date: Thu, 16 Apr 2026 20:01:41 +0800 Subject: bpf: allow UTF-8 literals in bpf_bprintf_prepare() bpf_bprintf_prepare() only needs ASCII parsing for conversion specifiers. Plain text can safely carry bytes >= 0x80, so allow UTF-8 literals outside '%' sequences while keeping ASCII control bytes rejected and format specifiers ASCII-only. This keeps existing parsing rules for format directives unchanged, while allowing helpers such as bpf_trace_printk() to emit UTF-8 literal text. Update test_snprintf_negative() in the same commit so selftests keep matching the new plain-text vs format-specifier split during bisection. Fixes: 48cac3f4a96d ("bpf: Implement formatted output helpers with bstr_printf") Signed-off-by: Yihan Ding Acked-by: Paul Chaignon Link: https://lore.kernel.org/r/20260416120142.1420646-2-dingyihan@uniontech.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/helpers.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index bb95e287b0dc..2bb60200c266 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -845,7 +845,13 @@ int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, data->buf = buffers->buf; for (i = 0; i < fmt_size; i++) { - if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) { + unsigned char c = fmt[i]; + + /* + * Permit bytes >= 0x80 in plain text so UTF-8 literals can pass + * through unchanged, while still rejecting ASCII control bytes. + */ + if (isascii(c) && !isprint(c) && !isspace(c)) { err = -EINVAL; goto out; } @@ -867,6 +873,15 @@ int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args, * always access fmt[i + 1], in the worst case it will be a 0 */ i++; + c = fmt[i]; + /* + * The format parser below only understands ASCII conversion + * specifiers and modifiers, so reject non-ASCII after '%'. + */ + if (!isascii(c)) { + err = -EINVAL; + goto out; + } /* skip optional "[0 +-][num]" width formatting field */ while (fmt[i] == '0' || fmt[i] == '+' || fmt[i] == '-' || -- cgit v1.2.3