libctf: add the object index and function index sections

No code handles these yet, but our latest GCC patches are generating
them, so we have to be ready for them or erroneously conclude that we
have file corruption.

(This simultaneously fixes a longstanding bug, concealed because nothing
was generating anything in the object or function info sections, where
the end of the section was being tested against the wrong thing: it
would have walked over the entire contents of the variable section and
treated them as part of the function info section.  This had to change
now anyway because the new sections have landed in between.)

include/
	* ctf.h: Add object index and function index sections.  Describe
	them. Improve the description of the variable section and clarify
	the constraints on backward-pointing type nodes.
	(ctf_header): Add cth_objtidxoff, cth_funcidxoff.

libctf/
	* ctf-open.c (init_symtab): Check for overflow against the right
	section.
	(upgrade_header): Set cth_objtidxoff, cth_funcidxoff to zero-length.
	(upgrade_types_v1): Note that these sections are not checked.
	(flip_header): Endian-swap the header fields.
	(flip_ctf): Endian-swap the sections.
	(flip_objts): Update comment.
	(ctf_bufopen): Check header offsets and alignment for validity.

4 files changed, 66 insertions, 15 deletions

diff --git a/include/ChangeLog b/include/ChangeLog
index de93394..c2e8031 100644
--- a/include/ChangeLog
+++ b/include/ChangeLog
@@ -1,3 +1,10 @@
+2019-07-11  Nick Alcock  <nick.alcock@oracle.com>
+
+	* ctf.h: Add object index and function index sections.  Describe
+	them. Improve the description of the variable section and clarify
+	the constraints on backward-pointing type nodes.
+	(ctf_header): Add cth_objtidxoff, cth_funcidxoff.
+
 2019-07-06  Nick Alcock  <nick.alcock@oracle.com>
 
 	* ctf-api.h (ctf_cuname): New function.
diff --git a/include/ctf.h b/include/ctf.h
index 7e00005..f371cd7 100644
--- a/include/ctf.h
+++ b/include/ctf.h
@@ -52,10 +52,15 @@ extern "C"
 
    The CTF file or section itself has the following structure:
 
-   +--------+--------+---------+----------+----------+-------+--------+
-   |  file  |  type  |  data   | function | variable | data  | string |
-   | header | labels | objects |   info   |   info   | types | table  |
-   +--------+--------+---------+----------+----------+-------+--------+
+   +--------+--------+---------+----------+--------+----------+...
+   |  file  |  type  |  data   | function | object | function |...
+   | header | labels | objects |   info   | index  |  index   |...
+   +--------+--------+---------+----------+--------+----------+...
+
+   ...+----------+-------+--------+
+   ...| variable | data  | string |
+   ...|   info   | types | table  |
+      +----------+-------+--------+
 
    The file header stores a magic number and version information, encoding
    flags, and the byte offset of each of the sections relative to the end of the
@@ -74,14 +79,27 @@ extern "C"
    For each data object, the type ID (a small integer) is recorded.  For each
    function, the type ID of the return type and argument types is recorded.
 
+   For situations in which the order of the symbols in the symtab is not known,
+   a pair of optional indexes follow the data object and function info sections:
+   each of these is an array of strtab indexes, mapped 1:1 to the corresponding
+   data object / function info section, giving each entry in those sections a
+   name so that the linker can correlate them with final symtab entries and
+   reorder them accordingly (dropping the indexes in the process).
+
    Variable records (as distinct from data objects) provide a modicum of support
    for non-ELF systems, mapping a variable name to a CTF type ID.  The variable
-   names are sorted into ASCIIbetical order, permitting binary searching.
+   names are sorted into ASCIIbetical order, permitting binary searching.  We do
+   not define how the consumer maps these variable names to addresses or
+   anything else, or indeed what these names represent: they might be names
+   looked up at runtime via dlsym() or names extracted at runtime by a debugger
+   or anything else the consumer likes.
 
    The data types section is a list of variable size records that represent each
    type, in order by their ID.  The types themselves form a directed graph,
    where each node may contain one or more outgoing edges to other type nodes,
-   denoted by their ID.
+   denoted by their ID.  Most type nodes are standalone or point backwards to
+   earlier nodes, but this is not required: nodes can point to later nodes,
+   particularly structure and union members.
 
    Strings are recorded as a string table ID (0 or 1) and a byte offset into the
    string table.  String table 0 is the internal CTF string table.  String table
@@ -149,6 +167,8 @@ typedef struct ctf_header
   uint32_t cth_lbloff;		/* Offset of label section.  */
   uint32_t cth_objtoff;		/* Offset of object section.  */
   uint32_t cth_funcoff;		/* Offset of function section.  */
+  uint32_t cth_objtidxoff;	/* Offset of object index section.  */
+  uint32_t cth_funcidxoff;	/* Offset of function index section.  */
   uint32_t cth_varoff;		/* Offset of variable section.  */
   uint32_t cth_typeoff;		/* Offset of type section.  */
   uint32_t cth_stroff;		/* Offset of string section.  */
diff --git a/libctf/ChangeLog b/libctf/ChangeLog
index 7fa9fc0..64d644f 100644
--- a/libctf/ChangeLog
+++ b/libctf/ChangeLog
@@ -1,5 +1,16 @@
 2019-07-13  Nick Alcock  <nick.alcock@oracle.com>
 
+	* ctf-open.c (init_symtab): Check for overflow against the right
+	section.
+	(upgrade_header): Set cth_objtidxoff, cth_funcidxoff to zero-length.
+	(upgrade_types_v1): Note that these sections are not checked.
+	(flip_header): Endian-swap the header fields.
+	(flip_ctf): Endian-swap the sections.
+	(flip_objts): Update comment.
+	(ctf_bufopen): Check header offsets and alignment for validity.
+
+2019-07-13  Nick Alcock  <nick.alcock@oracle.com>
+
 	* ctf-open-bfd.c: Add <assert.h>.
 	(ctf_bfdopen_ctfsect): Open string and symbol tables using
 	techniques borrowed from bfd_elf_sym_name.
diff --git a/libctf/ctf-open.c b/libctf/ctf-open.c
index 51f9edc..c96bad7 100644
--- a/libctf/ctf-open.c
+++ b/libctf/ctf-open.c
@@ -278,7 +278,7 @@ init_symtab (ctf_file_t *fp, const ctf_header_t *hp,
 	  break;
 
 	case STT_FUNC:
-	  if (funcoff >= hp->cth_typeoff)
+	  if (funcoff >= hp->cth_objtidxoff)
 	    {
 	      *xp = -1u;
 	      break;
@@ -376,6 +376,8 @@ upgrade_header (ctf_header_t *hp)
   hp->cth_stroff = oldhp->cth_stroff;
   hp->cth_typeoff = oldhp->cth_typeoff;
   hp->cth_varoff = oldhp->cth_varoff;
+  hp->cth_funcidxoff = hp->cth_varoff;		/* No index sections.  */
+  hp->cth_objtidxoff = hp->cth_funcidxoff;
   hp->cth_funcoff = oldhp->cth_funcoff;
   hp->cth_objtoff = oldhp->cth_objtoff;
   hp->cth_lbloff = oldhp->cth_lbloff;
@@ -388,6 +390,9 @@ upgrade_header (ctf_header_t *hp)
    The upgrade is not done in-place: the ctf_base is moved.  ctf_strptr() must
    not be called before reallocation is complete.
 
+   Sections not checked here due to nonexistence or nonpopulated state in older
+   formats: objtidx, funcidx.
+
    Type kinds not checked here due to nonexistence in older formats:
       CTF_K_SLICE.  */
 static int
@@ -967,6 +972,8 @@ flip_header (ctf_header_t *cth)
   swap_thing (cth->cth_cuname);
   swap_thing (cth->cth_objtoff);
   swap_thing (cth->cth_funcoff);
+  swap_thing (cth->cth_objtidxoff);
+  swap_thing (cth->cth_funcidxoff);
   swap_thing (cth->cth_varoff);
   swap_thing (cth->cth_typeoff);
   swap_thing (cth->cth_stroff);
@@ -987,10 +994,10 @@ flip_lbls (void *start, size_t len)
     }
 }
 
-/* Flip the endianness of the data-object or function sections, an array of
-   uint32_t.  (The function section has more internal structure, but that
-   structure is an array of uint32_t, so can be treated as one big array for
-   byte-swapping.)  */
+/* Flip the endianness of the data-object or function sections or their indexes,
+   all arrays of uint32_t.  (The function section has more internal structure,
+   but that structure is an array of uint32_t, so can be treated as one big
+   array for byte-swapping.)  */
 
 static void
 flip_objts (void *start, size_t len)
@@ -1176,7 +1183,9 @@ flip_ctf (ctf_header_t *cth, unsigned char *buf)
 {
   flip_lbls (buf + cth->cth_lbloff, cth->cth_objtoff - cth->cth_lbloff);
   flip_objts (buf + cth->cth_objtoff, cth->cth_funcoff - cth->cth_objtoff);
-  flip_objts (buf + cth->cth_funcoff, cth->cth_varoff - cth->cth_funcoff);
+  flip_objts (buf + cth->cth_funcoff, cth->cth_objtidxoff - cth->cth_funcoff);
+  flip_objts (buf + cth->cth_objtidxoff, cth->cth_funcidxoff - cth->cth_objtidxoff);
+  flip_objts (buf + cth->cth_funcidxoff, cth->cth_varoff - cth->cth_funcidxoff);
   flip_vars (buf + cth->cth_varoff, cth->cth_typeoff - cth->cth_varoff);
   return flip_types (buf + cth->cth_typeoff, cth->cth_stroff - cth->cth_typeoff);
 }
@@ -1330,19 +1339,23 @@ ctf_bufopen (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
 	       (unsigned long) fp->ctf_size);
 
   if (hp->cth_lbloff > fp->ctf_size || hp->cth_objtoff > fp->ctf_size
-      || hp->cth_funcoff > fp->ctf_size || hp->cth_typeoff > fp->ctf_size
+      || hp->cth_funcoff > fp->ctf_size || hp->cth_objtidxoff > fp->ctf_size
+      || hp->cth_funcidxoff > fp->ctf_size || hp->cth_typeoff > fp->ctf_size
       || hp->cth_stroff > fp->ctf_size)
     return (ctf_set_open_errno (errp, ECTF_CORRUPT));
 
   if (hp->cth_lbloff > hp->cth_objtoff
       || hp->cth_objtoff > hp->cth_funcoff
       || hp->cth_funcoff > hp->cth_typeoff
-      || hp->cth_funcoff > hp->cth_varoff
+      || hp->cth_funcoff > hp->cth_objtidxoff
+      || hp->cth_objtidxoff > hp->cth_funcidxoff
+      || hp->cth_funcidxoff > hp->cth_varoff
       || hp->cth_varoff > hp->cth_typeoff || hp->cth_typeoff > hp->cth_stroff)
     return (ctf_set_open_errno (errp, ECTF_CORRUPT));
 
   if ((hp->cth_lbloff & 3) || (hp->cth_objtoff & 2)
-      || (hp->cth_funcoff & 2) || (hp->cth_varoff & 3)
+      || (hp->cth_funcoff & 2) || (hp->cth_objtidxoff & 2)
+      || (hp->cth_funcidxoff & 2) || (hp->cth_varoff & 3)
       || (hp->cth_typeoff & 3))
     return (ctf_set_open_errno (errp, ECTF_CORRUPT));