tracing: Check "%s" dereference via the field and not the TP_printk format

The TP_printk() portion of a trace event is executed at the time a event
is read from the trace. This can happen seconds, minutes, hours, days,
months, years possibly later since the event was recorded. If the print
format contains a dereference to a string via "%s", and that string was
allocated, there's a chance that string could be freed before it is read
by the trace file.

To protect against such bugs, there are two functions that verify the
event. The first one is test_event_printk(), which is called when the
event is created. It reads the TP_printk() format as well as its arguments
to make sure nothing may be dereferencing a pointer that was not copied
into the ring buffer along with the event. If it is, it will trigger a
WARN_ON().

For strings that use "%s", it is not so easy. The string may not reside in
the ring buffer but may still be valid. Strings that are static and part
of the kernel proper which will not be freed for the life of the running
system, are safe to dereference. But to know if it is a pointer to a
static string or to something on the heap can not be determined until the
event is triggered.

This brings us to the second function that tests for the bad dereferencing
of strings, trace_check_vprintf(). It would walk through the printf format
looking for "%s", and when it finds it, it would validate that the pointer
is safe to read. If not, it would produces a WARN_ON() as well and write
into the ring buffer "[UNSAFE-MEMORY]".

The problem with this is how it used va_list to have vsnprintf() handle
all the cases that it didn't need to check. Instead of re-implementing
vsnprintf(), it would make a copy of the format up to the %s part, and
call vsnprintf() with the current va_list ap variable, where the ap would
then be ready to point at the string in question.

For architectures that passed va_list by reference this was possible. For
architectures that passed it by copy it was not. A test_can_verify()
function was used to differentiate between the two, and if it wasn't
possible, it would disable it.

Even for architectures where this was feasible, it was a stretch to rely
on such a method that is undocumented, and could cause issues later on
with new optimizations of the compiler.

Instead, the first function test_event_printk() was updated to look at
"%s" as well. If the "%s" argument is a pointer outside the event in the
ring buffer, it would find the field type of the event that is the problem
and mark the structure with a new flag called "needs_test". The event
itself will be marked by TRACE_EVENT_FL_TEST_STR to let it be known that
this event has a field that needs to be verified before the event can be
printed using the printf format.

When the event fields are created from the field type structure, the
fields would copy the field type's "needs_test" value.

Finally, before being printed, a new function ignore_event() is called
which will check if the event has the TEST_STR flag set (if not, it
returns false). If the flag is set, it then iterates through the events
fields looking for the ones that have the "needs_test" flag set.

Then it uses the offset field from the field structure to find the pointer
in the ring buffer event. It runs the tests to make sure that pointer is
safe to print and if not, it triggers the WARN_ON() and also adds to the
trace output that the event in question has an unsafe memory access.

The ignore_event() makes the trace_check_vprintf() obsolete so it is
removed.

Link: https://lore.kernel.org/all/CAHk-=wh3uOnqnZPpR0PeLZZtyWbZLboZ7cHLCKRWsocvs9Y7hQ@mail.gmail.com/

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/20241217024720.848621576@goodmis.org
Fixes: 5013f454a352c ("tracing: Add check of trace event print fmts for dereferencing pointers")
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

1 files changed, 22 insertions, 10 deletions

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 521ad2fd1fe7..1545cc8b49d0 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -82,7 +82,7 @@ static int system_refcount_dec(struct event_subsystem *system)
 	}
 
 static struct ftrace_event_field *
-__find_event_field(struct list_head *head, char *name)
+__find_event_field(struct list_head *head, const char *name)
 {
 	struct ftrace_event_field *field;
 
@@ -114,7 +114,8 @@ trace_find_event_field(struct trace_event_call *call, char *name)
 
 static int __trace_define_field(struct list_head *head, const char *type,
 				const char *name, int offset, int size,
-				int is_signed, int filter_type, int len)
+				int is_signed, int filter_type, int len,
+				int need_test)
 {
 	struct ftrace_event_field *field;
 
@@ -133,6 +134,7 @@ static int __trace_define_field(struct list_head *head, const char *type,
 	field->offset = offset;
 	field->size = size;
 	field->is_signed = is_signed;
+	field->needs_test = need_test;
 	field->len = len;
 
 	list_add(&field->link, head);
@@ -151,13 +153,13 @@ int trace_define_field(struct trace_event_call *call, const char *type,
 
 	head = trace_get_fields(call);
 	return __trace_define_field(head, type, name, offset, size,
-				    is_signed, filter_type, 0);
+				    is_signed, filter_type, 0, 0);
 }
 EXPORT_SYMBOL_GPL(trace_define_field);
 
 static int trace_define_field_ext(struct trace_event_call *call, const char *type,
 		       const char *name, int offset, int size, int is_signed,
-		       int filter_type, int len)
+		       int filter_type, int len, int need_test)
 {
 	struct list_head *head;
 
@@ -166,13 +168,13 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
 
 	head = trace_get_fields(call);
 	return __trace_define_field(head, type, name, offset, size,
-				    is_signed, filter_type, len);
+				    is_signed, filter_type, len, need_test);
 }
 
 #define __generic_field(type, item, filter_type)			\
 	ret = __trace_define_field(&ftrace_generic_fields, #type,	\
 				   #item, 0, 0, is_signed_type(type),	\
-				   filter_type, 0);			\
+				   filter_type, 0, 0);			\
 	if (ret)							\
 		return ret;
 
@@ -181,7 +183,8 @@ static int trace_define_field_ext(struct trace_event_call *call, const char *typ
 				   "common_" #item,			\
 				   offsetof(typeof(ent), item),		\
 				   sizeof(ent.item),			\
-				   is_signed_type(type), FILTER_OTHER, 0);	\
+				   is_signed_type(type), FILTER_OTHER,	\
+				   0, 0);				\
 	if (ret)							\
 		return ret;
 
@@ -332,6 +335,7 @@ static bool process_pointer(const char *fmt, int len, struct trace_event_call *c
 /* Return true if the string is safe */
 static bool process_string(const char *fmt, int len, struct trace_event_call *call)
 {
+	struct trace_event_fields *field;
 	const char *r, *e, *s;
 
 	e = fmt + len;
@@ -372,8 +376,16 @@ static bool process_string(const char *fmt, int len, struct trace_event_call *ca
 	if (process_pointer(fmt, len, call))
 		return true;
 
-	/* Make sure the field is found, and consider it OK for now if it is */
-	return find_event_field(fmt, call) != NULL;
+	/* Make sure the field is found */
+	field = find_event_field(fmt, call);
+	if (!field)
+		return false;
+
+	/* Test this field's string before printing the event */
+	call->flags |= TRACE_EVENT_FL_TEST_STR;
+	field->needs_test = 1;
+
+	return true;
 }
 
 /*
@@ -2586,7 +2598,7 @@ event_define_fields(struct trace_event_call *call)
 			ret = trace_define_field_ext(call, field->type, field->name,
 						 offset, field->size,
 						 field->is_signed, field->filter_type,
-						 field->len);
+						 field->len, field->needs_test);
 			if (WARN_ON_ONCE(ret)) {
 				pr_err("error code is %d\n", ret);
 				break;