[binutils-gdb] PowerPC64 thread-safe stubs not needed for iplt

[Alan Modra <amodra at sourceware dot org>]

https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=bd4d2eaad0f624bc47b2e27222480a44d1a48108

commit bd4d2eaad0f624bc47b2e27222480a44d1a48108
Author: Alan Modra <amodra@gmail.com>
Date:   Thu Feb 26 21:26:42 2015 +1030

    PowerPC64 thread-safe stubs not needed for iplt
    
    I was looking at a current glibc using objdump today and saw an odd
    plt call stub.
    
    0000000000044d80 <00000033.plt_call.__strchrnul>:
       44d80:       f8 41 00 28     std     r2,40(r1)
       44d84:       e9 82 8c f8     ld      r12,-29448(r2)
       44d88:       7d 89 03 a6     mtctr   r12
       44d8c:       e8 42 8d 00     ld      r2,-29440(r2)
       44d90:       28 22 00 00     cmpldi  r2,0
       44d94:       4c e2 04 20     bnectr+
       44d98:       48 13 84 f0     b       17d288 <realloc@plt>
    
    What?  It doesn't branch to __strchrnul@plt on finding a zero r2?
    
    Turns out this isn't a real problem since the stub is for loading an
    ifunc, so will not be lazily resolved and thus r2 will never be zero.
    Of course, that means the thread-safety check is unnecessary.
    
    I also tweak the special __tls_get_addr_opt call stub here, to
    restore r2 immediately after the call.  Not doing that might affect
    eh_frame unwinding.
    
    	* elf64-ppc.c (plt_stub_size, build_plt_stub): Don't build
    	thread-safe stubs for iplt.
    	(build_tls_get_addr_stub): Restore r2 immediately after call.

Diff:
---
 bfd/ChangeLog   |  6 ++++++
 bfd/elf64-ppc.c | 17 +++++++++++------
 2 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/bfd/ChangeLog b/bfd/ChangeLog
index 01b2d68..c2f114a 100644
--- a/bfd/ChangeLog
+++ b/bfd/ChangeLog
@@ -1,3 +1,9 @@
+2015-02-26  Alan Modra  <amodra@gmail.com>
+
+	* elf64-ppc.c (plt_stub_size, build_plt_stub): Don't build
+	thread-safe stubs for iplt.
+	(build_tls_get_addr_stub): Restore r2 immediately after call.
+
 2015-02-26  Terry Guo  <terry.guo@arm.com>
 
 	* elf32-arm.c (elf32_arm_merge_eabi_attributes): Update how we
diff --git a/bfd/elf64-ppc.c b/bfd/elf64-ppc.c
index 1573e30..90c2cc0 100644
--- a/bfd/elf64-ppc.c
+++ b/bfd/elf64-ppc.c
@@ -10220,7 +10220,10 @@ plt_stub_size (struct ppc_link_hash_table *htab,
       size += 4;
       if (htab->params->plt_static_chain)
 	size += 4;
-      if (htab->params->plt_thread_safe)
+      if (htab->params->plt_thread_safe
+	  && htab->elf.dynamic_sections_created
+	  && stub_entry->h != NULL
+	  && stub_entry->h->elf.dynindx != -1)
 	size += 8;
       if (PPC_HA (off + 8 + 8 * htab->params->plt_static_chain) != PPC_HA (off))
 	size += 4;
@@ -10260,16 +10263,18 @@ build_plt_stub (struct ppc_link_hash_table *htab,
   bfd *obfd = htab->params->stub_bfd;
   bfd_boolean plt_load_toc = htab->opd_abi;
   bfd_boolean plt_static_chain = htab->params->plt_static_chain;
-  bfd_boolean plt_thread_safe = htab->params->plt_thread_safe;
+  bfd_boolean plt_thread_safe = (htab->params->plt_thread_safe
+				 && htab->elf.dynamic_sections_created
+				 && stub_entry->h != NULL
+				 && stub_entry->h->elf.dynindx != -1);
   bfd_boolean use_fake_dep = plt_thread_safe;
   bfd_vma cmp_branch_off = 0;
 
   if (!ALWAYS_USE_FAKE_DEP
       && plt_load_toc
       && plt_thread_safe
-      && !(stub_entry->h != NULL
-	   && (stub_entry->h == htab->tls_get_addr_fd
-	       || stub_entry->h == htab->tls_get_addr)
+      && !((stub_entry->h == htab->tls_get_addr_fd
+	    || stub_entry->h == htab->tls_get_addr)
 	   && !htab->params->no_tls_get_addr_opt))
     {
       bfd_vma pltoff = stub_entry->plt_ent->plt.offset & ~1;
@@ -10462,8 +10467,8 @@ build_tls_get_addr_stub (struct ppc_link_hash_table *htab,
   p = build_plt_stub (htab, stub_entry, p, offset, r);
   bfd_put_32 (obfd, BCTRL, p - 4);
 
-  bfd_put_32 (obfd, LD_R11_0R1 + STK_LINKER (htab), p),	p += 4;
   bfd_put_32 (obfd, LD_R2_0R1 + STK_TOC (htab), p),	p += 4;
+  bfd_put_32 (obfd, LD_R11_0R1 + STK_LINKER (htab), p),	p += 4;
   bfd_put_32 (obfd, MTLR_R11, p),		p += 4;
   bfd_put_32 (obfd, BLR, p),			p += 4;