include, libctf, ld: extend variable section to contain functions too

The CTF variable section is an optional (usually-not-present) section in
the CTF dict which contains name -> type mappings corresponding to data
symbols that are present in the linker input but not in the output
symbol table: the idea is that programs that use their own symbol-
resolution mechanisms can use this section to look up the types of
symbols they have found using their own mechanism.

Because these removed symbols (mostly static variables, functions, etc)
all have names that are unlikely to appear in the ELF symtab and because
very few programs have their own symbol-resolution mechanisms, a special
linker flag (--ctf-variables) is needed to emit this section.

Historically, we emitted only removed data symbols into the variable
section.  This seemed to make sense at the time, but in hindsight it
really doesn't: functions are symbols too, and a C program can look them
up just like any other type.  So extend the variable section so that it
contains all static function symbols too (if it is emitted at all), with
types of kind CTF_K_FUNCTION.

This is a little fiddly.  We relied on compiler assistance for data
symbols: the compiler simply emits all data symbols twice, once into the
symtypetab as an indexed symbol and once into the variable section.

Rather than wait for a suitably adjusted compiler that does the same for
function symbols, we can pluck unreported function symbols out of the
symtab and add them to the variable section ourselves.  While we're at
it, we do the same with data symbols: this is redundant right now
because the compiler does it, but it costs very little time and lets the
compiler drop this kludge and save a little space in .o files.

include/
	* ctf.h: Mention the new things we can see in the variable
	section.

ld/
	* testsuite/ld-ctf/data-func-conflicted-vars.d: New test.

libctf/
	* ctf-link.c (ctf_link_deduplicating_variables): Duplicate
	symbols into the variable section too.
	* ctf-serialize.c (symtypetab_delete_nonstatic_vars): Rename
	to...
	(symtypetab_delete_nonstatics): ... this.  Check the funchash
	when pruning redundant variables.
	(ctf_symtypetab_sect_sizes): Adjust accordingly.
	* NEWS: Describe this change.

3 files changed, 57 insertions, 12 deletions

diff --git a/libctf/NEWS b/libctf/NEWS
index 956cca8473e..f4e59734639 100644
--- a/libctf/NEWS
+++ b/libctf/NEWS
@@ -1,5 +1,14 @@
 -*- text -*-
 
+Changes in 2.39:
+
+* New features
+
+** The CTF variable section (if generated via ld --ctf-variables) now contains
+   entries for static functions, hidden functions, and other functions with
+   no associated symbol.  The associated type is of kind CTF_K_FUNCTION.
+   (No change if --ctf-variables is not specified, which is the default.)
+
 Changes in 2.37:
 
 * New features
diff --git a/libctf/ctf-link.c b/libctf/ctf-link.c
index ee836054463..d92a6930dd0 100644
--- a/libctf/ctf-link.c
+++ b/libctf/ctf-link.c
@@ -807,7 +807,12 @@ ctf_link_deduplicating_close_inputs (ctf_dict_t *fp, ctf_dynhash_t *cu_names,
   return 0;
 }
 
-/* Do a deduplicating link of all variables in the inputs.  */
+/* Do a deduplicating link of all variables in the inputs.
+
+   Also, if we are not omitting the variable section, integrate all symbols from
+   the symtypetabs into the variable section too.  (Duplication with the
+   symtypetab section in the output will be eliminated at serialization time.)  */
+
 static int
 ctf_link_deduplicating_variables (ctf_dict_t *fp, ctf_dict_t **inputs,
 				  size_t ninputs, int cu_mapped)
@@ -820,6 +825,8 @@ ctf_link_deduplicating_variables (ctf_dict_t *fp, ctf_dict_t **inputs,
       ctf_id_t type;
       const char *name;
 
+      /* First the variables on the inputs.  */
+
       while ((type = ctf_variable_next (inputs[i], &it, &name)) != CTF_ERR)
 	{
 	  if (ctf_link_one_variable (fp, inputs[i], name, type, cu_mapped) < 0)
@@ -830,6 +837,34 @@ ctf_link_deduplicating_variables (ctf_dict_t *fp, ctf_dict_t **inputs,
 	}
       if (ctf_errno (inputs[i]) != ECTF_NEXT_END)
 	return ctf_set_errno (fp, ctf_errno (inputs[i]));
+
+      /* Next the symbols.  We integrate data symbols even though the compiler
+	 is currently doing the same, to allow the compiler to stop in
+	 future.  */
+
+      while ((type = ctf_symbol_next (inputs[i], &it, &name, 0)) != CTF_ERR)
+	{
+	  if (ctf_link_one_variable (fp, inputs[i], name, type, 1) < 0)
+	    {
+	      ctf_next_destroy (it);
+	      return -1;			/* errno is set for us.  */
+	    }
+	}
+      if (ctf_errno (inputs[i]) != ECTF_NEXT_END)
+	return ctf_set_errno (fp, ctf_errno (inputs[i]));
+
+      /* Finally the function symbols.  */
+
+      while ((type = ctf_symbol_next (inputs[i], &it, &name, 1)) != CTF_ERR)
+	{
+	  if (ctf_link_one_variable (fp, inputs[i], name, type, 1) < 0)
+	    {
+	      ctf_next_destroy (it);
+	      return -1;			/* errno is set for us.  */
+	    }
+	}
+      if (ctf_errno (inputs[i]) != ECTF_NEXT_END)
+	return ctf_set_errno (fp, ctf_errno (inputs[i]));
     }
   return 0;
 }
diff --git a/libctf/ctf-serialize.c b/libctf/ctf-serialize.c
index 89f1ac01aa1..cc9e59d4836 100644
--- a/libctf/ctf-serialize.c
+++ b/libctf/ctf-serialize.c
@@ -431,12 +431,12 @@ emit_symtypetab_index (ctf_dict_t *fp, ctf_dict_t *symfp, uint32_t *dp,
   return 0;
 }
 
-/* Delete data symbols that have been assigned names from the variable section.
-   Must be called from within ctf_serialize, because that is the only place
-   you can safely delete variables without messing up ctf_rollback.  */
+/* Delete symbols that have been assigned names from the variable section.  Must
+   be called from within ctf_serialize, because that is the only place you can
+   safely delete variables without messing up ctf_rollback.  */
 
 static int
-symtypetab_delete_nonstatic_vars (ctf_dict_t *fp, ctf_dict_t *symfp)
+symtypetab_delete_nonstatics (ctf_dict_t *fp, ctf_dict_t *symfp)
 {
   ctf_dvdef_t *dvd, *nvd;
   ctf_id_t type;
@@ -445,8 +445,10 @@ symtypetab_delete_nonstatic_vars (ctf_dict_t *fp, ctf_dict_t *symfp)
     {
       nvd = ctf_list_next (dvd);
 
-      if (((type = (ctf_id_t) (uintptr_t)
-	    ctf_dynhash_lookup (fp->ctf_objthash, dvd->dvd_name)) > 0)
+      if ((((type = (ctf_id_t) (uintptr_t)
+	     ctf_dynhash_lookup (fp->ctf_objthash, dvd->dvd_name)) > 0)
+	   || (type = (ctf_id_t) (uintptr_t)
+	       ctf_dynhash_lookup (fp->ctf_funchash, dvd->dvd_name)) > 0)
 	  && ctf_dynhash_lookup (symfp->ctf_dynsyms, dvd->dvd_name) != NULL
 	  && type == dvd->dvd_type)
 	ctf_dvd_delete (fp, dvd);
@@ -560,13 +562,12 @@ ctf_symtypetab_sect_sizes (ctf_dict_t *fp, emit_symtypetab_state_t *s,
 
   /* If we are filtering symbols out, those symbols that the linker has not
      reported have now been removed from the ctf_objthash and ctf_funchash.
-     Delete entries from the variable section that duplicate newly-added data
-     symbols.  There's no need to migrate new ones in, because the compiler
-     always emits both a variable and a data symbol simultaneously, and
-     filtering only happens at final link time.  */
+     Delete entries from the variable section that duplicate newly-added
+     symbols.  There's no need to migrate new ones in: we do that (if necessary)
+     in ctf_link_deduplicating_variables.  */
 
   if (s->filter_syms && s->symfp->ctf_dynsyms &&
-      symtypetab_delete_nonstatic_vars (fp, s->symfp) < 0)
+      symtypetab_delete_nonstatics (fp, s->symfp) < 0)
     return -1;
 
   return 0;