[PATCH v2] perf trace: Format fields with hex specifiers in print_fmt as hexadecimal

[PATCH v2] perf trace: Format fields with hex specifiers in print_fmt as hexadecimal

[Aaron Tomlin]

Currently, when a probe event is added using perf probe --add with a
hexadecimal type cast (e.g., var:x64 and var:x32), the kernel traceprobe
subsystem sets the field type to "u64" in the event's format file, yet
generates a print format specifier of "var=0x%Lx" or "0x%x".

By default, perf trace uses its internal beautifiers which only inspect
field->type and field->flags. Because traceprobe events declare
primitive integer field types ("u64") without a C pointer asterisk
(i.e., "*"), perf trace defaults to printing the field's value as a
decimal unsigned long ("%ld"), ignoring the hexadecimal intent.

Introduce field_has_hex_fmt() to inspect the tracepoint's print_fmt
format string. If a field's print format assignment uses hexadecimal
specifiers (i.e., "=0x", "=%#", or "=%p"), assign SCA_PTR formatting so
perf trace displays the value in hexadecimal by default without
requiring --libtraceevent. For example:

    ❯ sudo ./perf probe --add 'enqueue_task_fair rq=rq:x64 p=p:x64 flags=flags:x32'
    Added new event:
      probe:enqueue_task_fair (on enqueue_task_fair with rq=rq:x64 p=p:x64 flags=flags:x32)

    You can now use it in all perf tools, such as:

            perf record -e probe:enqueue_task_fair -aR sleep 1

    ❯ sudo ./perf trace --show-cpu --event probe:enqueue_task_fair --max-event 3
         0.000 [000] :0/0 probe:enqueue_task_fair(rq: 0xffff8ac632233180, p: 0xffff8ac2c1240000, flags: 0x100009)
         0.006 [004] :0/0 probe:enqueue_task_fair(rq: 0xffff8ac632433180, p: 0xffff8ac624cf8000, flags: 0x9)
         0.069 [001] :0/0 probe:enqueue_task_fair(rq: 0xffff8ac6322b3180, p: 0xffff8ac4c4212c40, flags: 0x9)

Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
---
Changes since v1:

 - Fixed field_has_hex_fmt() to properly handle escaped quotes (\") in
   format strings

 - Link to v1: https://lore.kernel.org/lkml/20260731215909.125335-1-atomlin@atomlin.com/
---
 tools/perf/builtin-trace.c | 46 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index ba0f8749fc7d..5a3e043b5b72 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2098,6 +2098,49 @@ static bool is_internal_field(struct tep_format_field *field)
 	return !strcmp(field->type, "__data_loc char[]");
 }
 
+static bool field_has_hex_fmt(struct tep_format_field *field, int len)
+{
+	const char *fmt, *pos, *end = NULL;
+
+	if (!field || !field->event || !field->event->print_fmt.format)
+		return false;
+
+	fmt = field->event->print_fmt.format;
+
+	/* NB: Limit scanning strictly to the quoted printf format string */
+	if (*fmt == '"') {
+		const char *p = ++fmt;
+
+		while (*p) {
+			if (*p == '\\' && p[1] != '\0') {
+				/* NB: Skip escaped character */
+				p += 2;
+			} else if (*p == '"') {
+				end = p;
+				break;
+			} else {
+				p++;
+			}
+		}
+	} else {
+		end = strchr(fmt, ',');
+	}
+
+	for (pos = strstr(fmt, field->name); pos && (!end || pos < end);
+	     pos = strstr(pos + 1, field->name)) {
+		if (pos == fmt || !(isalnum(pos[-1]) || pos[-1] == '_')) {
+			const char *after = pos + len;
+
+			if (*after == '=' && (strstarts(after + 1, "0x") ||
+					      strstarts(after + 1, "%#") ||
+					      strstarts(after + 1, "%p")))
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static struct tep_format_field *
 syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field *field,
 			    bool *use_btf)
@@ -2125,7 +2168,8 @@ syscall_arg_fmt__init_array(struct syscall_arg_fmt *arg, struct tep_format_field
 		    ((len >= 4 && strcmp(field->name + len - 4, "name") == 0) ||
 		     strstr(field->name, "path") != NULL)) {
 			arg->scnprintf = SCA_FILENAME;
-		} else if ((field->flags & TEP_FIELD_IS_POINTER) || strstr(field->name, "addr"))
+		} else if ((field->flags & TEP_FIELD_IS_POINTER) || strstr(field->name, "addr") ||
+			   field_has_hex_fmt(field, len))
 			arg->scnprintf = SCA_PTR;
 		else if (strcmp(field->type, "pid_t") == 0)
 			arg->scnprintf = SCA_PID;
-- 
2.55.0