diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index cf24dfdeb6b2..0081190201a7 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -100,8 +100,9 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str)
 			copy = iterator->remain;
 
 		/* Copy out the bit of the string that we need */
-		memcpy(iterator->data,
-			str + (iterator->start - iterator->offset), copy);
+		if (iterator->data)
+			memcpy(iterator->data,
+			       str + (iterator->start - iterator->offset), copy);
 
 		iterator->offset = iterator->start + copy;
 		iterator->remain -= copy;
@@ -110,7 +111,8 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str)
 
 		len = min_t(ssize_t, strlen(str), iterator->remain);
 
-		memcpy(iterator->data + pos, str, len);
+		if (iterator->data)
+			memcpy(iterator->data + pos, str, len);
 
 		iterator->offset += len;
 		iterator->remain -= len;
@@ -140,8 +142,9 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
 	if ((iterator->offset >= iterator->start) && (len < iterator->remain)) {
 		ssize_t pos = iterator->offset - iterator->start;
 
-		snprintf(((char *) iterator->data) + pos,
-			iterator->remain, "%pV", vaf);
+		if (iterator->data)
+			snprintf(((char *) iterator->data) + pos,
+				 iterator->remain, "%pV", vaf);
 
 		iterator->offset += len;
 		iterator->remain -= len;
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index 5d9dff5149c9..d2676831d765 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -221,7 +221,8 @@ drm_vprintf(struct drm_printer *p, const char *fmt, va_list *va)
 
 /**
  * struct drm_print_iterator - local struct used with drm_printer_coredump
- * @data: Pointer to the devcoredump output buffer
+ * @data: Pointer to the devcoredump output buffer, can be NULL if using
+ * drm_printer_coredump to determine size of devcoredump
  * @start: The offset within the buffer to start writing
  * @remain: The number of bytes to write for this iteration
  */
@@ -266,6 +267,57 @@ struct drm_print_iterator {
  *			coredump_read, ...)
  *	}
  *
+ * The above example has a time complexity of O(N^2), where N is the size of the
+ * devcoredump. This is acceptable for small devcoredumps but scales poorly for
+ * larger ones.
+ *
+ * Another use case for drm_coredump_printer is to capture the devcoredump into
+ * a saved buffer before the dev_coredump() callback. This involves two passes:
+ * one to determine the size of the devcoredump and another to print it to a
+ * buffer. Then, in dev_coredump(), copy from the saved buffer into the
+ * devcoredump read buffer.
+ *
+ * For example::
+ *
+ *	char *devcoredump_saved_buffer;
+ *
+ *	ssize_t __coredump_print(char *buffer, ssize_t count, ...)
+ *	{
+ *		struct drm_print_iterator iter;
+ *		struct drm_printer p;
+ *
+ *		iter.data = buffer;
+ *		iter.start = 0;
+ *		iter.remain = count;
+ *
+ *		p = drm_coredump_printer(&iter);
+ *
+ *		drm_printf(p, "foo=%d\n", foo);
+ *		...
+ *		return count - iter.remain;
+ *	}
+ *
+ *	void coredump_print(...)
+ *	{
+ *		ssize_t count;
+ *
+ *		count = __coredump_print(NULL, INT_MAX, ...);
+ *		devcoredump_saved_buffer = kvmalloc(count, GFP_KERNEL);
+ *		__coredump_print(devcoredump_saved_buffer, count, ...);
+ *	}
+ *
+ *	void coredump_read(char *buffer, loff_t offset, size_t count,
+ *			   void *data, size_t datalen)
+ *	{
+ *		...
+ *		memcpy(buffer, devcoredump_saved_buffer + offset, count);
+ *		...
+ *	}
+ *
+ * The above example has a time complexity of O(N*2), where N is the size of the
+ * devcoredump. This scales better than the previous example for larger
+ * devcoredumps.
+ *
  * RETURNS:
  * The &drm_printer object
  */