From afcd9480feca651eef436d8438b783dde5c3bbb2 Mon Sep 17 00:00:00 2001
From: Alan Modra <amodra@gmail.com>
Date: Wed, 25 Mar 2015 15:53:47 +1030
Subject: powerpc __tls_get_addr call optimization

This patch is glibc support for a PowerPC TLS optimization, inspired
by Alexandre Oliva's TLS optimization for other processors,
http://www.lsd.ic.unicamp.br/~oliva/writeups/TLS/RFC-TLSDESC-x86.txt

In essence, this optimization uses a zero module id in the tls_index
GOT entry to indicate that a TLS variable is allocated space in the
static TLS area.  A special plt call linker stub for __tls_get_addr
checks for such a tls_index and if found, returns the offset
immediately.  The linker communicates the fact that the special
__tls_get_addr stub is used by setting a bit in the dynamic tag
DT_PPC64_OPT/DT_PPC_OPT.  glibc communicates to the linker that this
optimization is available by the presence of __tls_get_addr_opt.

tst-tlsmod2.so is built with -Wl,--no-tls-get-addr-optimize for
tst-tls-dlinfo, which otherwise would fail since it tests that no
static tls is allocated.  The ld option --no-tls-get-addr-optimize has
been available since binutils-2.20 so doesn't need a configure test.

	* NEWS: Advertise TLS optimization.
	* elf/elf.h (R_PPC_TLSGD, R_PPC_TLSLD, DT_PPC_OPT, PPC_OPT_TLS): Define.
	(DT_PPC_NUM): Increment.
	* elf/dynamic-link.h (HAVE_STATIC_TLS): Define.
	(CHECK_STATIC_TLS): Use here.
	* sysdeps/powerpc/powerpc32/dl-machine.h (elf_machine_rela): Optimize
	TLS descriptors.
	* sysdeps/powerpc/powerpc64/dl-machine.h (elf_machine_rela): Likewise.
	* sysdeps/powerpc/dl-tls.c: New file.
	* sysdeps/powerpc/Versions: Add __tls_get_addr_opt.
	* sysdeps/powerpc/tst-tlsopt-powerpc.c: New tls test.
	* sysdeps/unix/sysv/linux/powerpc/Makefile: Add new test.
	Build tst-tlsmod2.so with --no-tls-get-addr-optimize.
	* sysdeps/unix/sysv/linux/powerpc/powerpc32/ld.abilist: Update.
	* sysdeps/unix/sysv/linux/powerpc/powerpc64/ld.abilist: Likewise.
	* sysdeps/unix/sysv/linux/powerpc/powerpc64/ld-le.abilist: Likewise.
---
 sysdeps/powerpc/powerpc32/dl-machine.h | 48 ++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

(limited to 'sysdeps/powerpc/powerpc32')

diff --git a/sysdeps/powerpc/powerpc32/dl-machine.h b/sysdeps/powerpc/powerpc32/dl-machine.h
index c94674f..8b0c067 100644
--- a/sysdeps/powerpc/powerpc32/dl-machine.h
+++ b/sysdeps/powerpc/powerpc32/dl-machine.h
@@ -333,6 +333,32 @@ elf_machine_rela (struct link_map *map, const Elf32_Rela *reloc,
 # endif
 
     case R_PPC_DTPMOD32:
+      if (map->l_info[DT_PPC(OPT)]
+	  && (map->l_info[DT_PPC(OPT)]->d_un.d_val & PPC_OPT_TLS))
+	{
+	  if (!NOT_BOOTSTRAP)
+	    {
+	      reloc_addr[0] = 0;
+	      reloc_addr[1] = (sym_map->l_tls_offset - TLS_TP_OFFSET
+			       + TLS_DTV_OFFSET);
+	      break;
+	    }
+	  else if (sym_map != NULL)
+	    {
+# ifndef SHARED
+	      CHECK_STATIC_TLS (map, sym_map);
+# else
+	      if (TRY_STATIC_TLS (map, sym_map))
+# endif
+		{
+		  reloc_addr[0] = 0;
+		  /* Set up for local dynamic.  */
+		  reloc_addr[1] = (sym_map->l_tls_offset - TLS_TP_OFFSET
+				   + TLS_DTV_OFFSET);
+		  break;
+		}
+	    }
+	}
       if (!NOT_BOOTSTRAP)
 	/* During startup the dynamic linker is always index 1.  */
 	*reloc_addr = 1;
@@ -342,6 +368,28 @@ elf_machine_rela (struct link_map *map, const Elf32_Rela *reloc,
 	*reloc_addr = sym_map->l_tls_modid;
       break;
     case R_PPC_DTPREL32:
+      if (map->l_info[DT_PPC(OPT)]
+	  && (map->l_info[DT_PPC(OPT)]->d_un.d_val & PPC_OPT_TLS))
+	{
+	  if (!NOT_BOOTSTRAP)
+	    {
+	      *reloc_addr = TLS_TPREL_VALUE (sym_map, sym, reloc);
+	      break;
+	    }
+	  else if (sym_map != NULL)
+	    {
+	      /* This reloc is always preceded by R_PPC_DTPMOD32.  */
+# ifndef SHARED
+	      assert (HAVE_STATIC_TLS (map, sym_map));
+# else
+	      if (HAVE_STATIC_TLS (map, sym_map))
+# endif
+		{
+		  *reloc_addr = TLS_TPREL_VALUE (sym_map, sym, reloc);
+		  break;
+		}
+	    }
+	}
       /* During relocation all TLS symbols are defined and used.
 	 Therefore the offset is already correct.  */
       if (NOT_BOOTSTRAP && sym_map != NULL)
-- 
cgit v1.1