Merge tag 'trace-v6.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing fixes from Steven Rostedt:
 "Replace trace_check_vprintf() with test_event_printk() and
  ignore_event()

  The function test_event_printk() checks on boot up if the trace event
  printf() formats dereference any pointers, and if they do, it then
  looks at the arguments to make sure that the pointers they dereference
  will exist in the event on the ring buffer. If they do not, it issues
  a WARN_ON() as it is a likely bug.

  But this isn't the case for the strings that can be dereferenced with
  "%s", as some trace events (notably RCU and some IPI events) save a
  pointer to a static string in the ring buffer. As the string it points
  to lives as long as the kernel is running, it is not a bug to
  reference it, as it is guaranteed to be there when the event is read.
  But it is also possible (and a common bug) to point to some allocated
  string that could be freed before the trace event is read and the
  dereference is to bad memory. This case requires a run time check.

  The previous way to handle this was with trace_check_vprintf() that
  would process the printf format piece by piece and send what it didn't
  care about to vsnprintf() to handle arguments that were not strings.
  This kept it from having to reimplement vsnprintf(). But it relied on
  va_list implementation and for architectures that copied the va_list
  and did not pass it by reference, it wasn't even possible to do this
  check and it would be skipped. As 64bit x86 passed va_list by
  reference, most events were tested and this kept out bugs where
  strings would have been dereferenced after being freed.

  Instead of relying on the implementation of va_list, extend the boot
  up test_event_printk() function to validate all the "%s" strings that
  can be validated at boot, and for the few events that point to strings
  outside the ring buffer, flag both the event and the field that is
  dereferenced as "needs_test". Then before the event is printed, a call
  to ignore_event() is made, and if the event has the flag set, it
  iterates all its fields and for every field that is to be tested, it
  will read the pointer directly from the event in the ring buffer and
  make sure that it is valid. If the pointer is not valid, it will print
  a WARN_ON(), print out to the trace that the event has unsafe memory
  and ignore the print format.

  With this new update, the trace_check_vprintf() can be safely removed
  and now all events can be verified regardless of architecture"

* tag 'trace-v6.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Check "%s" dereference via the field and not the TP_printk format
  tracing: Add "%s" check in test_event_printk()
  tracing: Add missing helper functions in event pointer dereference check
  tracing: Fix test_event_printk() to process entire print argument

Author: torvalds

include/linux/trace_events.h

@@ -273,7 +273,8 @@ struct trace_event_fields {
 			const char *name;
 			const int  size;
 			const int  align;
-			const int  is_signed;
+			const unsigned int is_signed:1;
+			unsigned int needs_test:1;
 			const int  filter_type;
 			const int  len;
 		};
@@ -324,6 +325,7 @@ enum {
 	TRACE_EVENT_FL_EPROBE_BIT,
 	TRACE_EVENT_FL_FPROBE_BIT,
 	TRACE_EVENT_FL_CUSTOM_BIT,
+	TRACE_EVENT_FL_TEST_STR_BIT,
 };
 
 /*
@@ -340,6 +342,7 @@ enum {
  *  CUSTOM        - Event is a custom event (to be attached to an exsiting tracepoint)
  *                   This is set when the custom event has not been attached
  *                   to a tracepoint yet, then it is cleared when it is.
+ *  TEST_STR      - The event has a "%s" that points to a string outside the event
  */
 enum {
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
@@ -352,6 +355,7 @@ enum {
 	TRACE_EVENT_FL_EPROBE		= (1 << TRACE_EVENT_FL_EPROBE_BIT),
 	TRACE_EVENT_FL_FPROBE		= (1 << TRACE_EVENT_FL_FPROBE_BIT),
 	TRACE_EVENT_FL_CUSTOM		= (1 << TRACE_EVENT_FL_CUSTOM_BIT),
+	TRACE_EVENT_FL_TEST_STR		= (1 << TRACE_EVENT_FL_TEST_STR_BIT),
 };
 
 #define TRACE_EVENT_FL_UKPROBE (TRACE_EVENT_FL_KPROBE | TRACE_EVENT_FL_UPROBE)

kernel/trace/trace.c

@@ -3611,17 +3611,12 @@ char *trace_iter_expand_format(struct trace_iterator *iter)
 }
 
 /* Returns true if the string is safe to dereference from an event */
-static bool trace_safe_str(struct trace_iterator *iter, const char *str,
-			   bool star, int len)
+static bool trace_safe_str(struct trace_iterator *iter, const char *str)
 {
 	unsigned long addr = (unsigned long)str;
 	struct trace_event *trace_event;
 	struct trace_event_call *event;
 
-	/* Ignore strings with no length */
-	if (star && !len)
-		return true;
-
 	/* OK if part of the event data */
 	if ((addr >= (unsigned long)iter->ent) &&
 	    (addr < (unsigned long)iter->ent + iter->ent_size))
@@ -3661,181 +3656,69 @@ static bool trace_safe_str(struct trace_iterator *iter, const char *str,
 	return false;
 }
 
-static DEFINE_STATIC_KEY_FALSE(trace_no_verify);
-
-static int test_can_verify_check(const char *fmt, ...)
-{
-	char buf[16];
-	va_list ap;
-	int ret;
-
-	/*
-	 * The verifier is dependent on vsnprintf() modifies the va_list
-	 * passed to it, where it is sent as a reference. Some architectures
-	 * (like x86_32) passes it by value, which means that vsnprintf()
-	 * does not modify the va_list passed to it, and the verifier
-	 * would then need to be able to understand all the values that
-	 * vsnprintf can use. If it is passed by value, then the verifier
-	 * is disabled.
-	 */
-	va_start(ap, fmt);
-	vsnprintf(buf, 16, "%d", ap);
-	ret = va_arg(ap, int);
-	va_end(ap);
-
-	return ret;
-}
-
-static void test_can_verify(void)
-{
-	if (!test_can_verify_check("%d %d", 0, 1)) {
-		pr_info("trace event string verifier disabled\n");
-		static_branch_inc(&trace_no_verify);
-	}
-}
-
 /**
- * trace_check_vprintf - Check dereferenced strings while writing to the seq buffer
+ * ignore_event - Check dereferenced fields while writing to the seq buffer
  * @iter: The iterator that holds the seq buffer and the event being printed
- * @fmt: The format used to print the event
- * @ap: The va_list holding the data to print from @fmt.
  *
- * This writes the data into the @iter->seq buffer using the data from
- * @fmt and @ap. If the format has a %s, then the source of the string
- * is examined to make sure it is safe to print, otherwise it will
- * warn and print "[UNSAFE MEMORY]" in place of the dereferenced string
- * pointer.
+ * At boot up, test_event_printk() will flag any event that dereferences
+ * a string with "%s" that does exist in the ring buffer. It may still
+ * be valid, as the string may point to a static string in the kernel
+ * rodata that never gets freed. But if the string pointer is pointing
+ * to something that was allocated, there's a chance that it can be freed
+ * by the time the user reads the trace. This would cause a bad memory
+ * access by the kernel and possibly crash the system.
+ *
+ * This function will check if the event has any fields flagged as needing
+ * to be checked at runtime and perform those checks.
+ *
+ * If it is found that a field is unsafe, it will write into the @iter->seq
+ * a message stating what was found to be unsafe.
+ *
+ * @return: true if the event is unsafe and should be ignored,
+ *          false otherwise.
  */
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
-			 va_list ap)
+bool ignore_event(struct trace_iterator *iter)
 {
-	long text_delta = 0;
-	long data_delta = 0;
-	const char *p = fmt;
-	const char *str;
-	bool good;
-	int i, j;
+	struct ftrace_event_field *field;
+	struct trace_event *trace_event;
+	struct trace_event_call *event;
+	struct list_head *head;
+	struct trace_seq *seq;
+	const void *ptr;
 
-	if (WARN_ON_ONCE(!fmt))
-		return;
+	trace_event = ftrace_find_event(iter->ent->type);
 
-	if (static_branch_unlikely(&trace_no_verify))
-		goto print;
+	seq = &iter->seq;
 
-	/*
-	 * When the kernel is booted with the tp_printk command line
-	 * parameter, trace events go directly through to printk().
-	 * It also is checked by this function, but it does not
-	 * have an associated trace_array (tr) for it.
-	 */
-	if (iter->tr) {
-		text_delta = iter->tr->text_delta;
-		data_delta = iter->tr->data_delta;
+	if (!trace_event) {
+		trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type);
+		return true;
 	}
 
-	/* Don't bother checking when doing a ftrace_dump() */
-	if (iter->fmt == static_fmt_buf)
-		goto print;
-
-	while (*p) {
-		bool star = false;
-		int len = 0;
-
-		j = 0;
-
-		/*
-		 * We only care about %s and variants
-		 * as well as %p[sS] if delta is non-zero
-		 */
-		for (i = 0; p[i]; i++) {
-			if (i + 1 >= iter->fmt_size) {
-				/*
-				 * If we can't expand the copy buffer,
-				 * just print it.
-				 */
-				if (!trace_iter_expand_format(iter))
-					goto print;
-			}
-
-			if (p[i] == '\\' && p[i+1]) {
-				i++;
-				continue;
-			}
-			if (p[i] == '%') {
-				/* Need to test cases like %08.*s */
-				for (j = 1; p[i+j]; j++) {
-					if (isdigit(p[i+j]) ||
-					    p[i+j] == '.')
-						continue;
-					if (p[i+j] == '*') {
-						star = true;
-						continue;
-					}
-					break;
-				}
-				if (p[i+j] == 's')
-					break;
-
-				if (text_delta && p[i+1] == 'p' &&
-				    ((p[i+2] == 's' || p[i+2] == 'S')))
-					break;
-
-				star = false;
-			}
-			j = 0;
-		}
-		/* If no %s found then just print normally */
-		if (!p[i])
-			break;
-
-		/* Copy up to the %s, and print that */
-		strncpy(iter->fmt, p, i);
-		iter->fmt[i] = '\0';
-		trace_seq_vprintf(&iter->seq, iter->fmt, ap);
+	event = container_of(trace_event, struct trace_event_call, event);
+	if (!(event->flags & TRACE_EVENT_FL_TEST_STR))
+		return false;
 
-		/* Add delta to %pS pointers */
-		if (p[i+1] == 'p') {
-			unsigned long addr;
-			char fmt[4];
+	head = trace_get_fields(event);
+	if (!head) {
+		trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n",
+				 trace_event_name(event));
+		return true;
+	}
 
-			fmt[0] = '%';
-			fmt[1] = 'p';
-			fmt[2] = p[i+2]; /* Either %ps or %pS */
-			fmt[3] = '\0';
+	/* Offsets are from the iter->ent that points to the raw event */
+	ptr = iter->ent;
 
-			addr = va_arg(ap, unsigned long);
-			addr += text_delta;
-			trace_seq_printf(&iter->seq, fmt, (void *)addr);
+	list_for_each_entry(field, head, link) {
+		const char *str;
+		bool good;
 
-			p += i + 3;
+		if (!field->needs_test)
 			continue;
-		}
 
-		/*
-		 * If iter->seq is full, the above call no longer guarantees
-		 * that ap is in sync with fmt processing, and further calls
-		 * to va_arg() can return wrong positional arguments.
-		 *
-		 * Ensure that ap is no longer used in this case.
-		 */
-		if (iter->seq.full) {
-			p = "";
-			break;
-		}
-
-		if (star)
-			len = va_arg(ap, int);
-
-		/* The ap now points to the string data of the %s */
-		str = va_arg(ap, const char *);
+		str = *(const char **)(ptr + field->offset);
 
-		good = trace_safe_str(iter, str, star, len);
-
-		/* Could be from the last boot */
-		if (data_delta && !good) {
-			str += data_delta;
-			good = trace_safe_str(iter, str, star, len);
-		}
+		good = trace_safe_str(iter, str);
 
 		/*
 		 * If you hit this warning, it is likely that the
@@ -3846,44 +3729,14 @@ void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
 		 * instead. See samples/trace_events/trace-events-sample.h
 		 * for reference.
 		 */
-		if (WARN_ONCE(!good, "fmt: '%s' current_buffer: '%s'",
-			      fmt, seq_buf_str(&iter->seq.seq))) {
-			int ret;
-
-			/* Try to safely read the string */
-			if (star) {
-				if (len + 1 > iter->fmt_size)
-					len = iter->fmt_size - 1;
-				if (len < 0)
-					len = 0;
-				ret = copy_from_kernel_nofault(iter->fmt, str, len);
-				iter->fmt[len] = 0;
-				star = false;
-			} else {
-				ret = strncpy_from_kernel_nofault(iter->fmt, str,
-								  iter->fmt_size);
-			}
-			if (ret < 0)
-				trace_seq_printf(&iter->seq, "(0x%px)", str);
-			else
-				trace_seq_printf(&iter->seq, "(0x%px:%s)",
-						 str, iter->fmt);
-			str = "[UNSAFE-MEMORY]";
-			strcpy(iter->fmt, "%s");
-		} else {
-			strncpy(iter->fmt, p + i, j + 1);
-			iter->fmt[j+1] = '\0';
+		if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'",
+			      trace_event_name(event), field->name)) {
+			trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n",
+					 trace_event_name(event), field->name);
+			return true;
 		}
-		if (star)
-			trace_seq_printf(&iter->seq, iter->fmt, len, str);
-		else
-			trace_seq_printf(&iter->seq, iter->fmt, str);
-
-		p += i + j + 1;
 	}
- print:
-	if (*p)
-		trace_seq_vprintf(&iter->seq, p, ap);
+	return false;
 }
 
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
@@ -10777,8 +10630,6 @@ __init static int tracer_alloc_buffers(void)
 
 	register_snapshot_cmd();
 
-	test_can_verify();
-
 	return 0;
 
 out_free_pipe_cpumask:

kernel/trace/trace.h

@@ -667,9 +667,8 @@ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer,
 
 bool trace_is_tracepoint_string(const char *str);
 const char *trace_event_format(struct trace_iterator *iter, const char *fmt);
-void trace_check_vprintf(struct trace_iterator *iter, const char *fmt,
-			 va_list ap) __printf(2, 0);
 char *trace_iter_expand_format(struct trace_iterator *iter);
+bool ignore_event(struct trace_iterator *iter);
 
 int trace_empty(struct trace_iterator *iter);
 
@@ -1413,7 +1412,8 @@ struct ftrace_event_field {
 	int			filter_type;
 	int			offset;
 	int			size;
-	int			is_signed;
+	unsigned int		is_signed:1;
+	unsigned int		needs_test:1;
 	int			len;
 };