[PATCH bpf v3 1/2] bpf: allow UTF-8 literals in bpf_bprintf_prepare()

[Yihan Ding]

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 <dingyihan@xxxxxxxxxxxxx>
---
 kernel/bpf/helpers.c                            | 17 ++++++++++++++++-
 .../testing/selftests/bpf/prog_tests/snprintf.c |  3 ++-
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 6eb6c82ed2ee..d51f1b612f1d 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] == '-' ||
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
index 594441acb707..4e4a82d54f79 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -114,7 +114,8 @@ static void test_snprintf_negative(void)
 	ASSERT_ERR(load_single_snprintf("%--------"), "invalid specifier 5");
 	ASSERT_ERR(load_single_snprintf("%lc"), "invalid specifier 6");
 	ASSERT_ERR(load_single_snprintf("%llc"), "invalid specifier 7");
-	ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
+	ASSERT_OK(load_single_snprintf("\x80"), "non ascii plain text");
+	ASSERT_ERR(load_single_snprintf("%\x80"), "non ascii in specifier");
 	ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
 	ASSERT_ERR(load_single_snprintf("%p%"), "invalid specifier 8");
 	ASSERT_ERR(load_single_snprintf("%s%"), "invalid specifier 9");
-- 
2.20.1