libctf: support getting strings from the ELF strtab

The CTF file format has always supported "external strtabs", which
internally are strtab offsets with their MSB on: such refs
get their strings from the strtab passed in at CTF file open time:
this is usually intended to be the ELF strtab, and that's what this
implementation is meant to support, though in theory the external
strtab could come from anywhere.

This commit adds support for these external strings in the ctf-string.c
strtab tracking layer.  It's quite easy: we just add a field csa_offset
to the atoms table that tracks all strings: this field tracks the offset
of the string in the ELF strtab (with its MSB already on, courtesy of a
new macro CTF_SET_STID), and adds a new function that sets the
csa_offset to the specified offset (plus MSB).  Then we just need to
avoid writing out strings to the internal strtab if they have csa_offset
set, and note that the internal strtab is shorter than it might
otherwise be.

(We could in theory save a little more time here by eschewing sorting
such strings, since we never actually write the strings out anywhere,
but that would mean storing them separately and it's just not worth the
complexity cost until profiling shows it's worth doing.)

We also have to go through a bit of extra effort at variable-sorting
time.  This was previously using direct references to the internal
strtab: it couldn't use ctf_strptr or ctf_strraw because the new strtab
is not yet ready to put in its usual field (in a ctf_file_t that hasn't
even been allocated yet at this stage): but now we're using the external
strtab, this will no longer do because it'll be looking things up in the
wrong strtab, with disastrous results.  Instead, pass the new internal
strtab in to a new ctf_strraw_explicit function which is just like
ctf_strraw except you can specify a ne winternal strtab to use.

But even now that it is using a new internal strtab, this is not quite
enough: it can't look up strings in the external strtab because ld
hasn't written it out yet, and when it does will write it straight to
disk.  Instead, when we write the internal strtab, note all the offset
-> string mappings that we have noted belong in the *external* strtab to
a new "synthetic external strtab" dynhash, ctf_syn_ext_strtab, and look
in there at ctf_strraw time if it is set.  This uses minimal extra
memory (because only strings in the external strtab that we actually use
are stored, and even those come straight out of the atoms table), but
let both variable sorting and name interning when ctf_bufopen is next
called work fine.  (This also means that we don't need to filter out
spurious ECTF_STRTAB warnings from ctf_bufopen but can pass them back to
the caller, once we wrap ctf_bufopen so that we have a new internal
variant of ctf_bufopen etc that we can pass the synthetic external
strtab to. That error has been filtered out since the days of Solaris
libctf, which didn't try to handle the problem of getting external
strtabs right at construction time at all.)

v3: add the synthetic strtab and all associated machinery.
v5: fix tabdamage.

include/
	* ctf.h (CTF_SET_STID): New.

libctf/
	* ctf-impl.h (ctf_str_atom_t) <csa_offset>: New field.
	(ctf_file_t) <ctf_syn_ext_strtab>: Likewise.
	(ctf_str_add_ref): Name the last arg.
	(ctf_str_add_external) New.
	(ctf_str_add_strraw_explicit): Likewise.
	(ctf_simple_open_internal): Likewise.
	(ctf_bufopen_internal): Likewise.

	* ctf-string.c (ctf_strraw_explicit): Split from...
	(ctf_strraw): ... here, with new support for ctf_syn_ext_strtab.
	(ctf_str_add_ref_internal): Return the atom, not the
	string.
	(ctf_str_add): Adjust accordingly.
	(ctf_str_add_ref): Likewise.  Move up in the file.
	(ctf_str_add_external): New: update the csa_offset.
	(ctf_str_count_strtab): Only account for strings with no csa_offset
	in the internal strtab length.
	(ctf_str_write_strtab): If the csa_offset is set, update the
	string's refs without writing the string out, and update the
	ctf_syn_ext_strtab.  Make OOM handling less ugly.
	* ctf-create.c (struct ctf_sort_var_arg_cb): New.
	(ctf_update): Handle failure to populate the strtab.  Pass in the
	new ctf_sort_var arg.  Adjust for ctf_syn_ext_strtab addition.
	Call ctf_simple_open_internal, not ctf_simple_open.
	(ctf_sort_var): Call ctf_strraw_explicit rather than looking up
	strings by hand.
	* ctf-hash.c (ctf_hash_insert_type): Likewise (but using
	ctf_strraw).  Adjust to diagnose ECTF_STRTAB nonetheless.
	* ctf-open.c (init_types): No longer filter out ECTF_STRTAB.
	(ctf_file_close): Destroy the ctf_syn_ext_strtab.
	(ctf_simple_open): Rename to, and reimplement as a wrapper around...
	(ctf_simple_open_internal): ... this new function, which calls
	ctf_bufopen_internal.
	(ctf_bufopen): Rename to, and reimplement as a wrapper around...
	(ctf_bufopen_internal): ... this new function, which sets
	ctf_syn_ext_strtab.

1 files changed, 15 insertions, 2 deletions

diff --git a/libctf/ctf-impl.h b/libctf/ctf-impl.h
index 5b331cb..03c48cf 100644
--- a/libctf/ctf-impl.h
+++ b/libctf/ctf-impl.h
@@ -192,6 +192,7 @@ typedef struct ctf_str_atom
 {
   const char *csa_str;		/* Backpointer to string (hash key).  */
   ctf_list_t csa_refs;		/* This string's refs.  */
+  uint32_t csa_offset;		/* External strtab offset, if any.  */
   unsigned long csa_snapshot_id; /* Snapshot ID at time of creation.  */
 } ctf_str_atom_t;
 
@@ -222,6 +223,7 @@ struct ctf_file
   ctf_sect_t ctf_data;		    /* CTF data from object file.  */
   ctf_sect_t ctf_symtab;	    /* Symbol table from object file.  */
   ctf_sect_t ctf_strtab;	    /* String table from object file.  */
+  ctf_dynhash_t *ctf_syn_ext_strtab; /* Maps ext-strtab offsets to names.  */
   void *ctf_data_mmapped;	    /* CTF data we mmapped, to free later.  */
   size_t ctf_data_mmapped_len;	    /* Length of CTF data we mmapped.  */
   ctf_hash_t *ctf_structs;	    /* Hash table of struct types.  */
@@ -375,12 +377,15 @@ _libctf_printflike_ (2, 3)
 extern void ctf_decl_sprintf (ctf_decl_t *, const char *, ...);
 extern char *ctf_decl_buf (ctf_decl_t *cd);
 
-extern const char *ctf_strraw (ctf_file_t *, uint32_t);
 extern const char *ctf_strptr (ctf_file_t *, uint32_t);
+extern const char *ctf_strraw (ctf_file_t *, uint32_t);
+extern const char *ctf_strraw_explicit (ctf_file_t *, uint32_t,
+					ctf_strs_t *);
 extern int ctf_str_create_atoms (ctf_file_t *);
 extern void ctf_str_free_atoms (ctf_file_t *);
 extern const char *ctf_str_add (ctf_file_t *, const char *);
-extern const char *ctf_str_add_ref (ctf_file_t *, const char *, uint32_t *);
+extern const char *ctf_str_add_ref (ctf_file_t *, const char *, uint32_t *ref);
+extern const char *ctf_str_add_external (ctf_file_t *, const char *, uint32_t offset);
 extern void ctf_str_rollback (ctf_file_t *, ctf_snapshot_id_t);
 extern void ctf_str_purge_refs (ctf_file_t *);
 extern ctf_strs_writable_t ctf_str_write_strtab (ctf_file_t *);
@@ -391,6 +396,14 @@ extern void ctf_arc_close_internal (struct ctf_archive *);
 extern void *ctf_set_open_errno (int *, int);
 extern unsigned long ctf_set_errno (ctf_file_t *, int);
 
+extern ctf_file_t *ctf_simple_open_internal (const char *, size_t, const char *,
+					     size_t, size_t,
+					     const char *, size_t,
+					     ctf_dynhash_t *, int *);
+extern ctf_file_t *ctf_bufopen_internal (const ctf_sect_t *, const ctf_sect_t *,
+					 const ctf_sect_t *, ctf_dynhash_t *,
+					 int *);
+
 _libctf_malloc_
 extern void *ctf_mmap (size_t length, size_t offset, int fd);
 extern void ctf_munmap (void *, size_t);