PR 21847, Don't default PowerPC64 to --plt-localentry

The big comment in ppc64_elf_tls_setup says why.  I've also added some
code to the bfd linker that catches the -lpthread -lc symbol
differences and disable generation of optimized call stubs even when
--plt-localentry is activated.  Gold doesn't yet have that.

	PR 21847
bfd/
	* elf64-ppc.c (struct ppc_link_hash_entry): Add non_zero_localentry.
	(ppc64_elf_merge_symbol): Set non_zero_localentry.
	(is_elfv2_localentry0): Test non_zero_localentry.
	(ppc64_elf_tls_setup): Default to --no-plt-localentry.
gold/
	* powerpc.cc (Target_powerpc::scan_relocs): Default to
	--no-plt-localentry.
ld/
	* ld.texinfo (plt-localentry): Document.

6 files changed, 56 insertions, 6 deletions

diff --git a/bfd/ChangeLog b/bfd/ChangeLog
index 0f7135861bb..41c935dd0d8 100644
--- a/bfd/ChangeLog
+++ b/bfd/ChangeLog
@@ -1,3 +1,11 @@
+2017-07-29  Alan Modra  <amodra@gmail.com>
+
+	PR 21847
+	* elf64-ppc.c (struct ppc_link_hash_entry): Add non_zero_localentry.
+	(ppc64_elf_merge_symbol): Set non_zero_localentry.
+	(is_elfv2_localentry0): Test non_zero_localentry.
+	(ppc64_elf_tls_setup): Default to --no-plt-localentry.
+
 2017-07-28  Andreas Krebbel  <krebbel@linux.vnet.ibm.com>
 
         * elf32-s390.c (elf_s390_finish_dynamic_sections): Add NULL
diff --git a/bfd/elf64-ppc.c b/bfd/elf64-ppc.c
index cc0e8ee996c..5f3c79f8111 100644
--- a/bfd/elf64-ppc.c
+++ b/bfd/elf64-ppc.c
@@ -4013,6 +4013,10 @@ struct ppc_link_hash_entry
      with non-standard calling convention.  */
   unsigned int save_res:1;
 
+  /* Set if a duplicate symbol with non-zero localentry is detected,
+     even when the duplicate symbol does not provide a definition.  */
+  unsigned int non_zero_localentry:1;
+
   /* Contexts in which symbol is used in the GOT (or TOC).
      TLS_GD .. TLS_EXPLICIT bits are or'd into the mask as the
      corresponding relocs are encountered during check_relocs.
@@ -5021,7 +5025,7 @@ ppc64_elf_merge_symbol_attribute (struct elf_link_hash_entry *h,
 
 static bfd_boolean
 ppc64_elf_merge_symbol (struct elf_link_hash_entry *h,
-			const Elf_Internal_Sym *isym ATTRIBUTE_UNUSED,
+			const Elf_Internal_Sym *isym,
 			asection **psec ATTRIBUTE_UNUSED,
 			bfd_boolean newdef ATTRIBUTE_UNUSED,
 			bfd_boolean olddef ATTRIBUTE_UNUSED,
@@ -5029,6 +5033,8 @@ ppc64_elf_merge_symbol (struct elf_link_hash_entry *h,
 			const asection *oldsec ATTRIBUTE_UNUSED)
 {
   ((struct ppc_link_hash_entry *) h)->fake = 0;
+  if ((STO_PPC64_LOCAL_MASK & isym->st_other) != 0)
+    ((struct ppc_link_hash_entry *) h)->non_zero_localentry = 1;
   return TRUE;
 }
 
@@ -6335,6 +6341,7 @@ is_elfv2_localentry0 (struct elf_link_hash_entry *h)
 	  && h->type == STT_FUNC
 	  && h->root.type == bfd_link_hash_defined
 	  && (STO_PPC64_LOCAL_MASK & h->other) == 0
+	  && !((struct ppc_link_hash_entry *) h)->non_zero_localentry
 	  && is_ppc64_elf (h->root.u.def.section->owner)
 	  && abiversion (h->root.u.def.section->owner) >= 2);
 }
@@ -8349,10 +8356,22 @@ ppc64_elf_tls_setup (struct bfd_link_info *info)
   else if (!htab->do_multi_toc)
     htab->params->no_multi_toc = 1;
 
+  /* Default to --no-plt-localentry, as this option can cause problems
+     with symbol interposition.  For example, glibc libpthread.so and
+     libc.so duplicate many pthread symbols, with a fallback
+     implementation in libc.so.  In some cases the fallback does more
+     work than the pthread implementation.  __pthread_condattr_destroy
+     is one such symbol: the libpthread.so implementation is
+     localentry:0 while the libc.so implementation is localentry:8.
+     An app that "cleverly" uses dlopen to only load necessary
+     libraries at runtime may omit loading libpthread.so when not
+     running multi-threaded, which then results in the libc.so
+     fallback symbols being used and ld.so complaining.  Now there
+     are workarounds in ld (see non_zero_localentry) to detect the
+     pthread situation, but that may not be the only case where
+     --plt-localentry can cause trouble.  */
   if (htab->params->plt_localentry0 < 0)
-    htab->params->plt_localentry0
-      = elf_link_hash_lookup (&htab->elf, "GLIBC_2.26",
-			      FALSE, FALSE, FALSE) != NULL;
+    htab->params->plt_localentry0 = 0;
 
   htab->tls_get_addr = ((struct ppc_link_hash_entry *)
 			elf_link_hash_lookup (&htab->elf, ".__tls_get_addr",
diff --git a/gold/ChangeLog b/gold/ChangeLog
index fdac9313c3c..a0193937001 100644
--- a/gold/ChangeLog
+++ b/gold/ChangeLog
@@ -1,3 +1,9 @@
+2017-07-29  Alan Modra  <amodra@gmail.com>
+
+	PR 21847
+	* powerpc.cc (Target_powerpc::scan_relocs): Default to
+	--no-plt-localentry.
+
 2017-07-28  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR gold/21857
diff --git a/gold/powerpc.cc b/gold/powerpc.cc
index a4966b8b3cf..e322d6f8836 100644
--- a/gold/powerpc.cc
+++ b/gold/powerpc.cc
@@ -7660,8 +7660,6 @@ Target_powerpc<size, big_endian>::scan_relocs(
 	{
 	  if (parameters->options().user_set_plt_localentry())
 	    plt_localentry0 = parameters->options().plt_localentry();
-	  else
-	    plt_localentry0 = symtab->lookup("GLIBC_2.26", NULL) != NULL;
 	}
       this->plt_localentry0_ = plt_localentry0;
       this->plt_localentry0_init_ = true;
diff --git a/ld/ChangeLog b/ld/ChangeLog
index 93457854a72..2a371b9c250 100644
--- a/ld/ChangeLog
+++ b/ld/ChangeLog
@@ -1,3 +1,7 @@
+2017-07-29  Alan Modra  <amodra@gmail.com>
+
+	* ld.texinfo (plt-localentry): Document.
+
 2017-07-28  Andrew Burgess  <andrew.burgess@embecosm.com>
 
 	* ldgram.y (ldgram_had_keep): Make static.
diff --git a/ld/ld.texinfo b/ld/ld.texinfo
index 987816f33cf..172c1ddd9fa 100644
--- a/ld/ld.texinfo
+++ b/ld/ld.texinfo
@@ -7600,6 +7600,21 @@ barrier in the call stub, or use LD_BIND_NOW=1.  By default, @code{ld}
 looks for calls to commonly used functions that create threads, and if
 seen, adds the necessary barriers.  Use these options to change the
 default behaviour.
+
+@cindex PowerPC64 ELFv2 PLT localentry optimization
+@kindex --plt-localentry
+@kindex --no-plt-localentry
+@item --plt-localentry
+@itemx --no-localentry
+ELFv2 functions with localentry:0 are those with a single entry point,
+ie. global entry == local entry, and that have no requirement on r2
+(the TOC/GOT pointer) or r12, and guarantee r2 is unchanged on return.
+Such an external function can be called via the PLT without saving r2
+or restoring it on return, avoiding a common load-hit-store for small
+functions.   The optimization is attractive, with up to 40% reduction
+in execution time for a small function, but can result in symbol
+interposition failures.  Use with care.  @option{--no-plt-localentry}
+is the default.
 @end table
 
 @ifclear GENERIC