libctf: symbol type linking support

This adds facilities to write out the function info and data object
sections, which efficiently map from entries in the symbol table to
types.  The write-side code is entirely new: the read-side code was
merely significantly changed and support for indexed tables added
(pointed to by the no-longer-unused cth_objtidxoff and cth_funcidxoff
header fields).

With this in place, you can use ctf_lookup_by_symbol to look up the
types of symbols of function and object type (and, as before, you can
use ctf_lookup_variable to look up types of file-scope variables not
present in the symbol table, as long as you know their name: but
variables that are also data objects are now found in the data object
section instead.)

(Compatible) file format change:

The CTF spec has always said that the function info section looks much
like the CTF_K_FUNCTIONs in the type section: an info word (including an
argument count) followed by a return type and N argument types. This
format is suboptimal: it means function symbols cannot be deduplicated
and it causes a lot of ugly code duplication in libctf.  But
conveniently the compiler has never emitted this!  Because it has always
emitted a rather different format that libctf has never accepted, we can
be sure that there are no instances of this function info section in the
wild, and can freely change its format without compatibility concerns or
a file format version bump.  (And since it has never been emitted in any
code that generated any older file format version, either, we need keep
no code to read the format as specified at all!)

So the function info section is now specified as an array of uint32_t,
exactly like the object data section: each entry is a type ID in the
type section which must be of kind CTF_K_FUNCTION, the prototype of
this function.

This allows function types to be deduplicated and also correctly encodes
the fact that all functions declared in C really are types available to
the program: so they should be stored in the type section like all other
types.  (In format v4, we will be able to represent the types of static
functions as well, but that really does require a file format change.)

We introduce a new header flag, CTF_F_NEWFUNCINFO, which is set if the
new function info format is in use.  A sufficiently new compiler will
always set this flag.  New libctf will always set this flag: old libctf
will refuse to open any CTF dicts that have this flag set.  If the flag
is not set on a dict being read in, new libctf will disregard the
function info section.  Format v4 will remove this flag (or, rather, the
flag has no meaning there and the bit position may be recycled for some
other purpose).

New API:

Symbol addition:
  ctf_add_func_sym: Add a symbol with a given name and type.  The
                    type must be of kind CTF_K_FUNCTION (a function
                    pointer).  Internally this adds a name -> type
                    mapping to the ctf_funchash in the ctf_dict.
  ctf_add_objt_sym: Add a symbol with a given name and type.  The type
                    kind can be anything, including function pointers.
		    This adds to ctf_objthash.

These both treat symbols as name -> type mappings: the linker associates
symbol names with symbol indexes via the ctf_link_shuffle_syms callback,
which sets up the ctf_dynsyms/ctf_dynsymidx/ctf_dynsymmax fields in the
ctf_dict.  Repeated relinks can add more symbols.

Variables that are also exposed as symbols are removed from the variable
section at serialization time.

CTF symbol type sections which have enough pads, defined by
CTF_INDEX_PAD_THRESHOLD (whether because they are in dicts with symbols
where most types are unknown, or in archive where most types are defined
in some child or parent dict, not in this specific dict) are sorted by
name rather than symidx and accompanied by an index which associates
each symbol type entry with a name: the existing ctf_lookup_by_symbol
will map symbol indexes to symbol names and look the names up in the
index automatically.  (This is currently ELF-symbol-table-dependent, but
there is almost nothing specific to ELF in here and we can add support
for other symbol table formats easily).

The compiler also uses index sections to communicate the contents of
object file symbol tables without relying on any specific ordering of
symbols: it doesn't need to sort them, and libctf will detect an
unsorted index section via the absence of the new CTF_F_IDXSORTED header
flag, and sort it if needed.

Iteration:
  ctf_symbol_next: Iterator which returns the types and names of symbols
                   one by one, either for function or data symbols.

This does not require any sorting: the ctf_link machinery uses it to
pull in all the compiler-provided symbols cheaply, but it is not
restricted to that use.

(Compatible) changes in API:
  ctf_lookup_by_symbol: can now be called for object and function
                        symbols: never returns ECTF_NOTDATA (which is
			now not thrown by anything, but is kept for
                        compatibility and because it is a plausible
                        error that we might start throwing again at some
                        later date).

Internally we also have changes to the ctf-string functionality so that
"external" strings (those where we track a string -> offset mapping, but
only write out an offset) can be consulted via the usual means
(ctf_strptr) before the strtab is written out.  This is important
because ctf_link_add_linker_symbol can now be handed symbols named via
strtab offsets, and ctf_link_shuffle_syms must figure out their actual
names by looking in the external symtab we have just been fed by the
ctf_link_add_strtab callback, long before that strtab is written out.

include/ChangeLog
2020-11-20  Nick Alcock  <nick.alcock@oracle.com>

	* ctf-api.h (ctf_symbol_next): New.
	(ctf_add_objt_sym): Likewise.
	(ctf_add_func_sym): Likewise.
	* ctf.h: Document new function info section format.
	(CTF_F_NEWFUNCINFO): New.
	(CTF_F_IDXSORTED): New.
	(CTF_F_MAX): Adjust accordingly.

libctf/ChangeLog
2020-11-20  Nick Alcock  <nick.alcock@oracle.com>

	* ctf-impl.h (CTF_INDEX_PAD_THRESHOLD): New.
	(_libctf_nonnull_): Likewise.
	(ctf_in_flight_dynsym_t): New.
	(ctf_dict_t) <ctf_funcidx_names>: Likewise.
	<ctf_objtidx_names>: Likewise.
	<ctf_nfuncidx>: Likewise.
	<ctf_nobjtidx>: Likewise.
	<ctf_funcidx_sxlate>: Likewise.
	<ctf_objtidx_sxlate>: Likewise.
	<ctf_objthash>: Likewise.
	<ctf_funchash>: Likewise.
	<ctf_dynsyms>: Likewise.
	<ctf_dynsymidx>: Likewise.
	<ctf_dynsymmax>: Likewise.
	<ctf_in_flight_dynsym>: Likewise.
	(struct ctf_next) <u.ctn_next>: Likewise.
	(ctf_symtab_skippable): New prototype.
	(ctf_add_funcobjt_sym): Likewise.
	(ctf_dynhash_sort_by_name): Likewise.
	(ctf_sym_to_elf64): Rename to...
	(ctf_elf32_to_link_sym): ... this, and...
	(ctf_elf64_to_link_sym): ... this.
	* ctf-open.c (init_symtab): Check for lack of CTF_F_NEWFUNCINFO
	flag, and presence of index sections.  Refactor out
	ctf_symtab_skippable and ctf_elf*_to_link_sym, and use them.  Use
	ctf_link_sym_t, not Elf64_Sym.  Skip initializing objt or func
	sxlate sections if corresponding index section is present.  Adjust
	for new func info section format.
	(ctf_bufopen_internal): Add ctf_err_warn to corrupt-file error
	handling.  Report incorrect-length index sections.  Always do an
	init_symtab, even if there is no symtab section (there may be index
	sections still).
	(flip_objts): Adjust comment: func and objt sections are actually
	identical in structure now, no need to caveat.
	(ctf_dict_close):  Free newly-added data structures.
	* ctf-create.c (ctf_create): Initialize them.
	(ctf_symtab_skippable): New, refactored out of
	init_symtab, with st_nameidx_set check added.
	(ctf_add_funcobjt_sym): New, add a function or object symbol to the
	ctf_objthash or ctf_funchash, by name.
	(ctf_add_objt_sym): Call it.
	(ctf_add_func_sym): Likewise.
	(symtypetab_delete_nonstatic_vars): New, delete vars also present as
	data objects.
	(CTF_SYMTYPETAB_EMIT_FUNCTION): New flag to symtypetab emitters:
	this is a function emission, not a data object emission.
	(CTF_SYMTYPETAB_EMIT_PAD): New flag to symtypetab emitters: emit
	pads for symbols with no type (only set for unindexed sections).
	(CTF_SYMTYPETAB_FORCE_INDEXED): New flag to symtypetab emitters:
	always emit indexed.
	(symtypetab_density): New, figure out section sizes.
	(emit_symtypetab): New, emit a symtypetab.
	(emit_symtypetab_index): New, emit a symtypetab index.
	(ctf_serialize): Call them, emitting suitably sorted symtypetab
	sections and indexes.  Set suitable header flags.  Copy over new
	fields.
	* ctf-hash.c (ctf_dynhash_sort_by_name): New, used to impose an
	order on symtypetab index sections.
	* ctf-link.c (ctf_add_type_mapping): Delete erroneous comment
	relating to code that was never committed.
	(ctf_link_one_variable): Improve variable name.
	(check_sym): New, symtypetab analogue of check_variable.
	(ctf_link_deduplicating_one_symtypetab): New.
	(ctf_link_deduplicating_syms): Likewise.
	(ctf_link_deduplicating): Call them.
	(ctf_link_deduplicating_per_cu): Note that we don't call them in
	this case (yet).
	(ctf_link_add_strtab): Set the error on the fp correctly.
	(ctf_link_add_linker_symbol): New (no longer a do-nothing stub), add
	a linker symbol to the in-flight list.
	(ctf_link_shuffle_syms): New (no longer a do-nothing stub), turn the
	in-flight list into a mapping we can use, now its names are
	resolvable in the external strtab.
	* ctf-string.c (ctf_str_rollback_atom): Don't roll back atoms with
	external strtab offsets.
	(ctf_str_rollback): Adjust comment.
	(ctf_str_write_strtab): Migrate ctf_syn_ext_strtab population from
	writeout time...
	(ctf_str_add_external): ... to string addition time.
	* ctf-lookup.c (ctf_lookup_var_key_t): Rename to...
	(ctf_lookup_idx_key_t): ... this, now we use it for syms too.
	<clik_names>: New member, a name table.
	(ctf_lookup_var): Adjust accordingly.
	(ctf_lookup_variable): Likewise.
	(ctf_lookup_by_id): Shuffle further up in the file.
	(ctf_symidx_sort_arg_cb): New, callback for...
	(sort_symidx_by_name): ... this new function to sort a symidx
	found to be unsorted (likely originating from the compiler).
	(ctf_symidx_sort): New, sort a symidx.
	(ctf_lookup_symbol_name): Support dynamic symbols with indexes
	provided by the linker.  Use ctf_link_sym_t, not Elf64_Sym.
	Check the parent if a child lookup fails.
	(ctf_lookup_by_symbol): Likewise.  Work for function symbols too.
	(ctf_symbol_next): New, iterate over symbols with types (without
	sorting).
	(ctf_lookup_idx_name): New, bsearch for symbol names in indexes.
	(ctf_try_lookup_indexed): New, attempt an indexed lookup.
	(ctf_func_info): Reimplement in terms of ctf_lookup_by_symbol.
	(ctf_func_args): Likewise.
	(ctf_get_dict): Move...
	* ctf-types.c (ctf_get_dict): ... here.
	* ctf-util.c (ctf_sym_to_elf64): Re-express as...
	(ctf_elf64_to_link_sym): ... this.  Add new st_symidx field, and
	st_nameidx_set (always 0, so st_nameidx can be ignored).  Look in
	the ELF strtab for names.
	(ctf_elf32_to_link_sym): Likewise, for Elf32_Sym.
	(ctf_next_destroy): Destroy ctf_next_t.u.ctn_next if need be.
	* libctf.ver: Add ctf_symbol_next, ctf_add_objt_sym and
	ctf_add_func_sym.

1 files changed, 139 insertions, 61 deletions

diff --git a/libctf/ctf-open.c b/libctf/ctf-open.c
index 456efa65469..3281c678ac4 100644
--- a/libctf/ctf-open.c
+++ b/libctf/ctf-open.c
@@ -27,8 +27,6 @@
 #include <bfd.h>
 #include <zlib.h>
 
-#include "elf-bfd.h"
-
 static const ctf_dmodel_t _libctf_models[] = {
   {"ILP32", CTF_MODEL_ILP32, 4, 1, 2, 4, 4},
   {"LP64", CTF_MODEL_LP64, 8, 1, 2, 4, 8},
@@ -220,55 +218,88 @@ static const ctf_dictops_t ctf_dictops[] = {
   {get_kind_v2, get_root_v2, get_vlen_v2, get_ctt_size_v2, get_vbytes_v2},
 };
 
-/* Initialize the symtab translation table by filling each entry with the
-  offset of the CTF type or function data corresponding to each STT_FUNC or
-  STT_OBJECT entry in the symbol table.  */
+/* Initialize the symtab translation table as appropriate for its indexing
+   state.  For unindexed symtypetabs, fill each entry with the offset of the CTF
+   type or function data corresponding to each STT_FUNC or STT_OBJECT entry in
+   the symbol table.  For indexed symtypetabs, do nothing: the needed
+   initialization for indexed lookups may be quite expensive, so it is done only
+   as needed, when lookups happen.  (In particular, the majority of indexed
+   symtypetabs come from the compiler, and all the linker does is iteration over
+   all entries, which doesn't need this initialization.)
+
+   The SP symbol table section may be NULL if there is no symtab.  */
 
 static int
-init_symtab (ctf_dict_t *fp, const ctf_header_t *hp,
-	     const ctf_sect_t *sp, const ctf_sect_t *strp)
+init_symtab (ctf_dict_t *fp, const ctf_header_t *hp, const ctf_sect_t *sp)
 {
-  const unsigned char *symp = sp->cts_data;
+  const unsigned char *symp;
+  int skip_func_info = 0;
+  int i;
   uint32_t *xp = fp->ctf_sxlate;
   uint32_t *xend = xp + fp->ctf_nsyms;
 
   uint32_t objtoff = hp->cth_objtoff;
   uint32_t funcoff = hp->cth_funcoff;
 
-  uint32_t info, vlen;
-  Elf64_Sym sym, *gsp;
-  const char *name;
-
-  /* The CTF data object and function type sections are ordered to match
-     the relative order of the respective symbol types in the symtab.
-     If no type information is available for a symbol table entry, a
-     pad is inserted in the CTF section.  As a further optimization,
-     anonymous or undefined symbols are omitted from the CTF data.  */
-
-  for (; xp < xend; xp++, symp += sp->cts_entsize)
+  /* If the CTF_F_NEWFUNCINFO flag is not set, pretend the func info section
+     is empty: this compiler is too old to emit a function info section we
+     understand.  */
+
+  if (!(hp->cth_flags & CTF_F_NEWFUNCINFO))
+    skip_func_info = 1;
+
+  if (hp->cth_objtidxoff < hp->cth_funcidxoff)
+    fp->ctf_objtidx_names = (uint32_t *) (fp->ctf_buf + hp->cth_objtidxoff);
+  if (hp->cth_funcidxoff < hp->cth_varoff && !skip_func_info)
+    fp->ctf_funcidx_names = (uint32_t *) (fp->ctf_buf + hp->cth_funcidxoff);
+
+  /* Don't bother doing the rest if everything is indexed, or if we don't have a
+     symbol table: we will never use it.  */
+  if ((fp->ctf_objtidx_names && fp->ctf_funcidx_names) || !sp || !sp->cts_data)
+    return 0;
+
+  /* The CTF data object and function type sections are ordered to match the
+     relative order of the respective symbol types in the symtab, unless there
+     is an index section, in which case the order is arbitrary and the index
+     gives the mapping.  If no type information is available for a symbol table
+     entry, a pad is inserted in the CTF section.  As a further optimization,
+     anonymous or undefined symbols are omitted from the CTF data.  If an
+     index is available for function symbols but not object symbols, or vice
+     versa, we populate the xslate table for the unindexed symbols only.  */
+
+  for (i = 0, symp = sp->cts_data; xp < xend; xp++, symp += sp->cts_entsize,
+	 i++)
     {
-      if (sp->cts_entsize == sizeof (Elf32_Sym))
-	gsp = ctf_sym_to_elf64 ((Elf32_Sym *) (uintptr_t) symp, &sym);
-      else
-	gsp = (Elf64_Sym *) (uintptr_t) symp;
+      ctf_link_sym_t sym;
 
-      if (gsp->st_name < strp->cts_size)
-	name = (const char *) strp->cts_data + gsp->st_name;
-      else
-	name = _CTF_NULLSTR;
+      switch (sp->cts_entsize)
+	{
+	case sizeof (Elf64_Sym):
+	  {
+	    const Elf64_Sym *symp64 = (Elf64_Sym *) (uintptr_t) symp;
+	    ctf_elf64_to_link_sym (fp, &sym, symp64, i);
+	  }
+	  break;
+	case sizeof (Elf32_Sym):
+	  {
+	    const Elf32_Sym *symp32 = (Elf32_Sym *) (uintptr_t) symp;
+	    ctf_elf32_to_link_sym (fp, &sym, symp32, i);
+	  }
+	  break;
+	default:
+	  return ECTF_SYMTAB;
+	}
 
-      if (gsp->st_name == 0 || gsp->st_shndx == SHN_UNDEF
-	  || strcmp (name, "_START_") == 0 || strcmp (name, "_END_") == 0)
+      if (ctf_symtab_skippable (&sym))
 	{
 	  *xp = -1u;
 	  continue;
 	}
 
-      switch (ELF64_ST_TYPE (gsp->st_info))
+      switch (sym.st_type)
 	{
 	case STT_OBJECT:
-	  if (objtoff >= hp->cth_funcoff
-	      || (gsp->st_shndx == SHN_EXTABS && gsp->st_value == 0))
+	  if (fp->ctf_objtidx_names || objtoff >= hp->cth_funcoff)
 	    {
 	      *xp = -1u;
 	      break;
@@ -279,25 +310,15 @@ init_symtab (ctf_dict_t *fp, const ctf_header_t *hp,
 	  break;
 
 	case STT_FUNC:
-	  if (funcoff >= hp->cth_objtidxoff)
+	  if (fp->ctf_funcidx_names || funcoff >= hp->cth_objtidxoff
+	      || skip_func_info)
 	    {
 	      *xp = -1u;
 	      break;
 	    }
 
 	  *xp = funcoff;
-
-	  info = *(uint32_t *) ((uintptr_t) fp->ctf_buf + funcoff);
-	  vlen = LCTF_INFO_VLEN (fp, info);
-
-	  /* If we encounter a zero pad at the end, just skip it.  Otherwise
-	     skip over the function and its return type (+2) and the argument
-	     list (vlen).
-	   */
-	  if (LCTF_INFO_KIND (fp, info) == CTF_K_UNKNOWN && vlen == 0)
-	    funcoff += sizeof (uint32_t);	/* Skip pad.  */
-	  else
-	    funcoff += sizeof (uint32_t) * (vlen + 2);
+	  funcoff += sizeof (uint32_t);
 	  break;
 
 	default:
@@ -1012,9 +1033,7 @@ flip_lbls (void *start, size_t len)
 }
 
 /* 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.)  */
+   all arrays of uint32_t.  */
 
 static void
 flip_objts (void *start, size_t len)
@@ -1379,8 +1398,9 @@ ctf_bufopen_internal (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
 	 info.  We do not support dynamically upgrading such entries (none
 	 should exist in any case, since dwarf2ctf does not create them).  */
 
-      ctf_err_warn (NULL, 0, 0, _("ctf_bufopen: CTF version %d symsect not "
-				  "supported"), pp->ctp_version);
+      ctf_err_warn (NULL, 0, ECTF_NOTSUP, _("ctf_bufopen: CTF version %d "
+					    "symsect not supported"),
+		    pp->ctp_version);
       return (ctf_set_open_errno (errp, ECTF_NOTSUP));
     }
 
@@ -1388,7 +1408,12 @@ ctf_bufopen_internal (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
     hdrsz = sizeof (ctf_header_v2_t);
 
   if (_libctf_unlikely_ (pp->ctp_flags > CTF_F_MAX))
-    return (ctf_set_open_errno (errp, ECTF_FLAGS));
+    {
+      ctf_err_warn (NULL, 0, ECTF_FLAGS, _("ctf_bufopen: invalid header "
+					   "flags: %x"),
+		    (unsigned int) pp->ctp_flags);
+      return (ctf_set_open_errno (errp, ECTF_FLAGS));
+    }
 
   if (ctfsect->cts_size < hdrsz)
     return (ctf_set_open_errno (errp, ECTF_NOCTFBUF));
@@ -1423,7 +1448,10 @@ ctf_bufopen_internal (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
       || 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));
+    {
+      ctf_err_warn (NULL, 0, ECTF_CORRUPT, _("header offset exceeds CTF size"));
+      return (ctf_set_open_errno (errp, ECTF_CORRUPT));
+    }
 
   if (hp->cth_lbloff > hp->cth_objtoff
       || hp->cth_objtoff > hp->cth_funcoff
@@ -1432,13 +1460,46 @@ ctf_bufopen_internal (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
       || 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));
+    {
+      ctf_err_warn (NULL, 0, ECTF_CORRUPT, _("overlapping CTF sections"));
+      return (ctf_set_open_errno (errp, ECTF_CORRUPT));
+    }
 
   if ((hp->cth_lbloff & 3) || (hp->cth_objtoff & 2)
       || (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));
+    {
+      ctf_err_warn (NULL, 0, ECTF_CORRUPT,
+		    _("CTF sections not properly aligned"));
+      return (ctf_set_open_errno (errp, ECTF_CORRUPT));
+    }
+
+  /* This invariant will be lifted in v4, but for now it is true.  */
+
+  if ((hp->cth_funcidxoff - hp->cth_objtidxoff != 0) &&
+      (hp->cth_funcidxoff - hp->cth_objtidxoff
+       != hp->cth_funcoff - hp->cth_objtoff))
+    {
+      ctf_err_warn (NULL, 0, ECTF_CORRUPT,
+		    _("Object index section exists is neither empty nor the "
+		      "same length as the object section: %u versus %u "
+		      "bytes"), hp->cth_funcoff - hp->cth_objtoff,
+		    hp->cth_funcidxoff - hp->cth_objtidxoff);
+      return (ctf_set_open_errno (errp, ECTF_CORRUPT));
+    }
+
+  if ((hp->cth_varoff - hp->cth_funcidxoff != 0) &&
+      (hp->cth_varoff - hp->cth_funcidxoff
+       != hp->cth_objtidxoff - hp->cth_funcoff))
+    {
+      ctf_err_warn (NULL, 0, ECTF_CORRUPT,
+		    _("Function index section exists is neither empty nor the "
+		      "same length as the function section: %u versus %u "
+		      "bytes"), hp->cth_objtidxoff - hp->cth_funcoff,
+		    hp->cth_varoff - hp->cth_funcidxoff);
+      return (ctf_set_open_errno (errp, ECTF_CORRUPT));
+    }
 
   /* Once everything is determined to be valid, attempt to decompress the CTF
      data buffer if it is compressed, or copy it into new storage if it is not
@@ -1586,10 +1647,12 @@ ctf_bufopen_internal (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
   if ((err = init_types (fp, hp)) != 0)
     goto bad;
 
-  /* If we have a symbol table section, allocate and initialize
-     the symtab translation table, pointed to by ctf_sxlate.  This table may be
-     too large for the actual size of the object and function info sections: if
-     so, ctf_nsyms will be adjusted and the excess will never be used.  */
+  /* Allocate and initialize the symtab translation table, pointed to by
+     ctf_sxlate, and the corresponding index sections.  This table may be too
+     large for the actual size of the object and function info sections: if so,
+     ctf_nsyms will be adjusted and the excess will never be used.  It's
+     possible to do indexed symbol lookups even without a symbol table, so check
+     even in that case.  */
 
   if (symsect != NULL)
     {
@@ -1601,11 +1664,11 @@ ctf_bufopen_internal (const ctf_sect_t *ctfsect, const ctf_sect_t *symsect,
 	  err = ENOMEM;
 	  goto bad;
 	}
-
-      if ((err = init_symtab (fp, hp, symsect, strsect)) != 0)
-	goto bad;
     }
 
+  if ((err = init_symtab (fp, hp, symsect)) != 0)
+    goto bad;
+
   ctf_set_ctl_hashes (fp);
 
   if (symsect != NULL)
@@ -1649,6 +1712,7 @@ ctf_dict_close (ctf_dict_t *fp)
 {
   ctf_dtdef_t *dtd, *ntd;
   ctf_dvdef_t *dvd, *nvd;
+  ctf_in_flight_dynsym_t *did, *nid;
   ctf_err_warning_t *err, *nerr;
 
   if (fp == NULL)
@@ -1701,6 +1765,20 @@ ctf_dict_close (ctf_dict_t *fp)
       ctf_dvd_delete (fp, dvd);
     }
   ctf_dynhash_destroy (fp->ctf_dvhash);
+
+  free (fp->ctf_funcidx_sxlate);
+  free (fp->ctf_objtidx_sxlate);
+  ctf_dynhash_destroy (fp->ctf_objthash);
+  ctf_dynhash_destroy (fp->ctf_funchash);
+  free (fp->ctf_dynsymidx);
+  ctf_dynhash_destroy (fp->ctf_dynsyms);
+  for (did = ctf_list_next (&fp->ctf_in_flight_dynsyms); did != NULL; did = nid)
+    {
+      nid = ctf_list_next (did);
+      ctf_list_delete (&fp->ctf_in_flight_dynsyms, did);
+      free (did);
+    }
+
   ctf_str_free_atoms (fp);
   free (fp->ctf_tmp_typeslice);