tcp: support variable-length tcp_dissect_pdus

Originally suggested by Bill Meier for the MQTT protocol[1], but the
Websocket protocol can also benefit from this. Since
DESEGMENT_ONE_MORE_SEGMENT is a valid packet length, use the zero length
instead as an indicator that the length is not yet known.

Updated documentation too and remove the function documentation from
packet-tcp.c since it is duplicated in packet-tcp.h.

A noteworthy WSDG change is that the get_pdu_len parameter of
tcp_dissect_pdus gained another void pointer since
v1.99.2rc0-890-gceb8d95 ("Lua: Expose tcp_dissect_pdus() to Lua").

 [1]: https://www.wireshark.org/lists/wireshark-dev/201405/msg00044.html

Change-Id: I4eba380e00cd757635eb5639c2857356dae3171e
Reviewed-on: https://code.wireshark.org/review/7279
Reviewed-by: Guy Harris <guy@alum.mit.edu>
Reviewed-by: Michael Mann <mmann78@netscape.net>
Petri-Dish: Michael Mann <mmann78@netscape.net>
Tested-by: Petri Dish Buildbot <buildbot-no-reply@wireshark.org>
Reviewed-by: Evan Huus <eapache@gmail.com>

doc/README.dissector

@@ -2972,16 +2972,17 @@ The arguments to tcp_dissect_pdus are:
     a routine that takes as arguments a packet_info pointer, a tvbuff
     pointer and an offset value representing the offset into the tvbuff
     at which a PDU begins, and a void pointer for user data, and should
-    return - *without* throwing an exception (it is guaranteed that the
+    return the total length of the PDU in bytes (or 0 if more bytes are
+    needed to determine the message length).
+    The routine must not throw exceptions (it is guaranteed that the
     number of bytes specified by the previous argument to
     tcp_dissect_pdus is available, but more data might not be available,
-    so don't refer to any data past that) - the total length of the PDU,
-    in bytes;
+    so don't refer to any data past that);
 
     a new_dissector_t routine to dissect the pdu that's passed a tvbuff
     pointer, packet_info pointer, proto_tree pointer and a void pointer for
     user data, with the tvbuff containing a possibly-reassembled PDU. (The
-    "reported_length" of the tvbuff will be the length of the PDU).
+    "reported_length" of the tvbuff will be the length of the PDU);
 
     a void pointer to user data that is passed to the length-determining
     routine, and the dissector routine referenced in the previous parameter.

docbook/wsdg_src/WSDG_chapter_dissection.asciidoc

@@ -594,7 +594,7 @@ effect.
         guchar *decompressed_buffer = (guchar*)g_malloc(orig_size);
         offset += 2;
         decompress_packet(tvb_get_ptr(tvb, offset, -1),
-                tvb_length_remaining(tvb, offset),
+                tvb_captured_length_remaining(tvb, offset),
                 decompressed_buffer, orig_size);
         /* Now re-setup the tvb buffer to have the new data */
         next_tvb = tvb_new_child_real_data(tvb, decompressed_buffer, orig_size, orig_size);
@@ -618,7 +618,7 @@ So armed with the size, a buffer is allocated to receive the uncompressed data
 using +g_malloc()+, and the packet is decompressed into it. The +tvb_get_ptr()+
 function is useful to get a pointer to the raw data of the packet from the
 offset onwards. In this case the decompression routine also needs to know the
-length, which is given by the +tvb_length_remaining()+ function.
+length, which is given by the +tvb_captured_length_remaining()+ function.
 
 Next we build a new tvb buffer from this data, using the
 +tvb_new_child_real_data()+ call. This data is a child of our original data, so
@@ -700,7 +700,7 @@ if (flags & FL_FRAGMENT) { /* fragmented */
         msg_fragment_table, /* list of message fragments */
         msg_reassembled_table, /* list of reassembled messages */
         msg_num, /* fragment sequence number */
-        tvb_length_remaining(tvb, offset), /* fragment length - to the end */
+        tvb_captured_length_remaining(tvb, offset), /* fragment length - to the end */
         flags & FL_FRAG_LAST); /* More fragments? */
 ----
 ====
@@ -922,25 +922,28 @@ This function is implemented in 'epan/dissectors/packet-tcp.h'.
 #define FRAME_HEADER_LEN 8
 
 /* This method dissects fully reassembled messages */
-static int dissect_foo_message(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree, void* data _U_)
+static int
+dissect_foo_message(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree, void *data _U_)
 {
     /* TODO: implement your dissecting code */
-    return tvb_length(tvb);
+    return tvb_captured_length(tvb);
 }
 
 /* determine PDU length of protocol foo */
-static guint get_foo_message_len(packet_info *pinfo, tvbuff_t *tvb, int offset)
+static guint
+get_foo_message_len(packet_info *pinfo _U_, tvbuff_t *tvb, int offset, void *data _U_)
 {
     /* TODO: change this to your needs */
     return (guint)tvb_get_ntohl(tvb, offset+4); /* e.g. length is at offset 4 */
 }
 
 /* The main dissecting routine */
-static int dissect_foo(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree, void* data)
+static int
+dissect_foo(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree, void *data)
 {
     tcp_dissect_pdus(tvb, pinfo, tree, TRUE, FRAME_HEADER_LEN,
                      get_foo_message_len, dissect_foo_message, data);
-    return tvb_length(tvb);
+    return tvb_captured_length(tvb);
 }
 
 ...
@@ -951,16 +954,20 @@ As you can see this is really simple. Just call +tcp_dissect_pdus()+ in your
 main dissection routine and move you message parsing code into another function.
 This function gets called whenever a message has been reassembled.
 
-The parameters tvb, pinfo, treeand dataare just handed over to
+The parameters tvb, pinfo, tree and data are just handed over to
 +tcp_dissect_pdus()+. The 4th parameter is a flag to indicate if the data should
 be reassembled or not. This could be set according to a dissector preference as
 well. Parameter 5 indicates how much data has at least to be available to be
 able to determine the length of the foo message. Parameter 6 is a function
 pointer to a method that returns this length. It gets called when at least the
 number of bytes given in the previous parameter is available. Parameter 7 is a
-function pointer to your real message dissector. Parameter 8 is a the data
+function pointer to your real message dissector. Parameter 8 is the data
 passed in from parent dissector.
 
+Protocols which need more data before the message length can be determined can
+return zero. Other values smaller than the fixed length will result in an
+exception.
+
 [[ChDissectTap]]
 
 === How to tap protocols

epan/dissectors/packet-tcp.c

@@ -2306,24 +2306,6 @@ again:
     }
 }
 
-/*
- * Loop for dissecting PDUs within a TCP stream; assumes that a PDU
- * consists of a fixed-length chunk of data that contains enough information
- * to determine the length of the PDU, followed by rest of the PDU.
- *
- * The first three arguments are the arguments passed to the dissector
- * that calls this routine.
- *
- * "proto_desegment" is the dissector's flag controlling whether it should
- * desegment PDUs that cross TCP segment boundaries.
- *
- * "fixed_len" is the length of the fixed-length part of the PDU.
- *
- * "get_pdu_len()" is a routine called to get the length of the PDU from
- * the fixed-length part of the PDU; it's passed "pinfo", "tvb" and "offset".
- *
- * "dissect_pdu()" is the routine to dissect a PDU.
- */
 void
 tcp_dissect_pdus(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree,
                  gboolean proto_desegment, guint fixed_len,
@@ -2379,6 +2361,16 @@ tcp_dissect_pdus(tvbuff_t *tvb, packet_info *pinfo, proto_tree *tree,
          * Get the length of the PDU.
          */
         plen = (*get_pdu_len)(pinfo, tvb, offset, dissector_data);
+        if (plen == 0) {
+            /*
+             * Support protocols which have a variable length which cannot
+             * always be determined within the given fixed_len.
+             */
+            DISSECTOR_ASSERT(proto_desegment && pinfo->can_desegment);
+            pinfo->desegment_offset = offset;
+            pinfo->desegment_len = DESEGMENT_ONE_MORE_SEGMENT;
+            return;
+        }
         if (plen < fixed_len) {
             /*
              * Either:

epan/dissectors/packet-tcp.h

@@ -99,7 +99,8 @@ struct tcpinfo {
  * "fixed_len" is the length of the fixed-length part of the PDU.
  *
  * "get_pdu_len()" is a routine called to get the length of the PDU from
- * the fixed-length part of the PDU; it's passed "pinfo", "tvb" and "offset".
+ * the fixed-length part of the PDU; it's passed "pinfo", "tvb", "offset" and
+ * "dissector_data".
  *
  * "dissect_pdu()" is the routine to dissect a PDU.
  */