bfd, ld, libctf: skip zero-refcount strings in CTF string reporting

This is a tricky one.  BFD, on the linker's behalf, reports symbols to
libctf via the ctf_new_symbol and ctf_new_dynsym callbacks, which
ultimately call ctf_link_add_linker_symbol.  But while this happens
after strtab offsets are finalized, it happens before the .dynstr is
actually laid out, so we can't iterate over it at this stage and
it is not clear what the reported symbols are actually called.  So
a second callback, examine_strtab, is called after the .dynstr is
finalized, which calls ctf_link_add_strtab and ultimately leads
to ldelf_ctf_strtab_iter_cb being called back repeatedly until the
offsets of every string in the .dynstr is passed to libctf.

libctf can then use this to get symbol names out of the input (which
usually stores symbol types in the form of a name -> type mapping at
this stage) and extract the types of those symbols, feeding them back
into their final form as a 1:1 association with the real symtab's
STT_OBJ and STT_FUNC symbols (with a few skipped, see
ctf_symtab_skippable).

This representation is compact, but has one problem: if libctf somehow
gets confused about the st_type of a symbol, it'll stick an entry into
the function symtypetab when it should put it into the object
symtypetab, or vice versa, and *every symbol from that one on* will have
the wrong CTF type because it's actually looking up the type for a
different symbol.

And we have just such a bug.  ctf_link_add_strtab was not taking the
refcounts of strings into consideration, so even strings that had been
eliminated from the strtab by virtue of being in objects eliminated via
--as-needed etc were being reported.  This is harmful because it can
lead to multiple strings with the same apparent offset, and if the last
duplicate to be reported relates to an eliminated symbol, we look up the
wrong symbol from the input and gets its type wrong: if it's unlucky and
the eliminated symbol is also of the wrong st_type, we will end up with
a corrupted symtypetab.

Thankfully the wrong-st_type case is already diagnosed by a
this-can-never-happen paranoid warning:

  CTF warning: Symbol 61a added to CTF as a function but is of type 1

or the converse

 * CTF warning: Symbol a3 added to CTF as a data object but is of type 2

so at least we can tell when the corruption has spread to more than one
symbol's type.

Skipping zero-refcounted strings is easy: teach _bfd_elf_strtab_str to
skip them, and ldelf_ctf_strtab_iter_cb to loop over skipped strings
until it falls off the end or finds one that isn't skipped.

bfd/ChangeLog
2021-03-02  Nick Alcock  <nick.alcock@oracle.com>

	* elf-strtab.c (_bfd_elf_strtab_str): Skip strings with zero refcount.

ld/ChangeLog
2021-03-02  Nick Alcock  <nick.alcock@oracle.com>

	* ldelfgen.c (ldelf_ctf_strtab_iter_cb): Skip zero-refcount strings.

libctf/ChangeLog
2021-03-02  Nick Alcock  <nick.alcock@oracle.com>

	* ctf-create.c (symtypetab_density): Report the symbol name as
	well as index in the name != object error; note the likely
	consequences.
	* ctf-link.c (ctf_link_shuffle_syms): Report the symbol index
	as well as name.

diff --git a/bfd/ChangeLog b/bfd/ChangeLog
index c4c4fa2647aaf692e0b0706a31130a99a0fedb45..c56cfc493839e999f8d55a6906be2258212a340f 100644 (file)
--- a/bfd/ChangeLog
+++ b/bfd/ChangeLog
@@ -1,3 +1,7 @@
+2021-03-02  Nick Alcock  <nick.alcock@oracle.com>
+
+       * elf-strtab.c (_bfd_elf_strtab_str): Skip strings with zero refcount.
+
 2021-03-02  Alan Modra  <amodra@gmail.com>
 
        PR 27451

diff --git a/bfd/elf-strtab.c b/bfd/elf-strtab.c
index 3e5e16221092b9c5fd2d5fe32a0f31c3d82e0c85..a3cb4ef7b4a3df03f1fafe16d3ff995ea020df26 100644 (file)
--- a/bfd/elf-strtab.c
+++ b/bfd/elf-strtab.c
@@ -299,9 +299,11 @@ _bfd_elf_strtab_str (struct elf_strtab_hash *tab, size_t idx,
                     bfd_size_type *offset)
 {
   if (idx == 0)
-    return 0;
+    return NULL;
   BFD_ASSERT (idx < tab->size);
   BFD_ASSERT (tab->sec_size);
+  if (tab->array[idx]->refcount == 0)
+    return NULL;
   if (offset)
     *offset = tab->array[idx]->u.index;
   return tab->array[idx]->root.string;

diff --git a/ld/ChangeLog b/ld/ChangeLog
index d12e537791a8b6144c7983af9f487a05df13122d..9116ee01170f18c0ab6335f584b42fcd49ef850a 100644 (file)
--- a/ld/ChangeLog
+++ b/ld/ChangeLog
@@ -1,3 +1,7 @@
+2021-03-02  Nick Alcock  <nick.alcock@oracle.com>
+
+       * ldelfgen.c (ldelf_ctf_strtab_iter_cb): Skip zero-refcount strings.
+
 2021-03-02  Alan Modra  <amodra@gmail.com>
 
        * testsuite/ld-powerpc/startstop.d,

diff --git a/ld/ldelfgen.c b/ld/ldelfgen.c
index df3dae0abe8c45b08086257531a48f582df8705a..c49b85494ee1679b75cccbd32946cc536c353774 100644 (file)
--- a/ld/ldelfgen.c
+++ b/ld/ldelfgen.c
@@ -375,13 +375,20 @@ ldelf_ctf_strtab_iter_cb (uint32_t *offset, void *arg_)
   if (arg->next_i == 0)
     arg->next_i = 1;
 
-  if (arg->next_i >= _bfd_elf_strtab_len (arg->strtab))
+  /* Hunt through strings until we fall off the end or find one with
+     a nonzero refcount.  */
+  do
     {
-      arg->next_i = 0;
-      return NULL;
+      if (arg->next_i >= _bfd_elf_strtab_len (arg->strtab))
+       {
+         arg->next_i = 0;
+         return NULL;
+       }
+
+      ret = _bfd_elf_strtab_str (arg->strtab, arg->next_i++, &off);
     }
+  while (ret == NULL);
 
-  ret = _bfd_elf_strtab_str (arg->strtab, arg->next_i++, &off);
   *offset = off;
 
   /* If we've overflowed, we cannot share any further strings: the CTF

diff --git a/libctf/ChangeLog b/libctf/ChangeLog
index 8fa98c68a82c6d20e189532b3a095730ee0c09c3..f095c3e1e30ace882fec5942052d7128d9030075 100644 (file)
--- a/libctf/ChangeLog
+++ b/libctf/ChangeLog
@@ -1,3 +1,11 @@
+2021-03-02  Nick Alcock  <nick.alcock@oracle.com>
+
+       * ctf-create.c (symtypetab_density): Report the symbol name as
+       well as index in the name != object error; note the likely
+       consequences.
+       * ctf-link.c (ctf_link_shuffle_syms): Report the symbol index
+       as well as name.
+
 2021-03-02  Nick Alcock  <nick.alcock@oracle.com>
 
        * ctf-link.c (ctf_link_shuffle_syms): Free ctf_dynsyms properly.

diff --git a/libctf/ctf-create.c b/libctf/ctf-create.c
index d417922e7fde5f6db8fd950f51d2d215b58bad38..3f2c5dacb03da89ef1ca059b4985eca3699d3875 100644 (file)
--- a/libctf/ctf-create.c
+++ b/libctf/ctf-create.c
@@ -318,18 +318,22 @@ symtypetab_density (ctf_dict_t *fp, ctf_dict_t *symfp, ctf_dynhash_t *symhash,
          if ((flags & CTF_SYMTYPETAB_EMIT_FUNCTION)
              && sym->st_type != STT_FUNC)
            {
-             ctf_err_warn (fp, 1, 0, _("Symbol %x added to CTF as a function "
-                                       "but is of type %x\n"),
-                           sym->st_symidx, sym->st_type);
+             ctf_err_warn (fp, 1, 0, _("symbol %s (%x) added to CTF as a "
+                                       "function but is of type %x.  "
+                                       "The symbol type lookup tables "
+                                       "are probably corrupted"),
+                           sym->st_name, sym->st_symidx, sym->st_type);
              ctf_dynhash_remove (symhash, name);
              continue;
            }
          else if (!(flags & CTF_SYMTYPETAB_EMIT_FUNCTION)
                   && sym->st_type != STT_OBJECT)
            {
-             ctf_err_warn (fp, 1, 0, _("Symbol %x added to CTF as a data "
-                                       "object but is of type %x\n"),
-                           sym->st_symidx, sym->st_type);
+             ctf_err_warn (fp, 1, 0, _("symbol %s (%x) added to CTF as a "
+                                       "data object but is of type %x.  "
+                                       "The symbol type lookup tables "
+                                       "are probably corrupted"),
+                           sym->st_name, sym->st_symidx, sym->st_type);
              ctf_dynhash_remove (symhash, name);
              continue;
            }

diff --git a/libctf/ctf-link.c b/libctf/ctf-link.c
index 882d4297e4fc8b75e8744b25803b9df6bd5d6bb7..5471fccd0f7eb814b834562ad6dd9649e0964cc6 100644 (file)
--- a/libctf/ctf-link.c
+++ b/libctf/ctf-link.c
@@ -1552,7 +1552,8 @@ ctf_link_shuffle_syms (ctf_dict_t *fp)
         for skippability here.  */
       if (!ctf_symtab_skippable (&did->cid_sym))
        {
-         ctf_dprintf ("symbol name from linker: %s\n", did->cid_sym.st_name);
+         ctf_dprintf ("symbol from linker: %s (%x)\n", did->cid_sym.st_name,
+                      did->cid_sym.st_symidx);
 
          if ((new_sym = malloc (sizeof (ctf_link_sym_t))) == NULL)
            goto local_oom;