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.

2 files changed, 13 insertions, 4 deletions

diff --git a/elf/dynamic-link.h b/elf/dynamic-link.h
index 6f4a773d5a..8d428e20d3 100644
--- a/elf/dynamic-link.h
+++ b/elf/dynamic-link.h
@@ -25,11 +25,14 @@
    an attempt to allocate it in surplus space on the fly.  If that
    can't be done, we fall back to the error that DF_STATIC_TLS is
    intended to produce.  */
+#define HAVE_STATIC_TLS(map, sym_map)					\
+    (__builtin_expect ((sym_map)->l_tls_offset != NO_TLS_OFFSET		\
+		       && ((sym_map)->l_tls_offset			\
+			   != FORCED_DYNAMIC_TLS_OFFSET), 1))
+
 #define CHECK_STATIC_TLS(map, sym_map)					\
     do {								\
-      if (__builtin_expect ((sym_map)->l_tls_offset == NO_TLS_OFFSET	\
-			    || ((sym_map)->l_tls_offset			\
-				== FORCED_DYNAMIC_TLS_OFFSET), 0))	\
+      if (!HAVE_STATIC_TLS (map, sym_map))				\
 	_dl_allocate_static_tls (sym_map);				\
     } while (0)
 
diff --git a/elf/elf.h b/elf/elf.h
index 496f08d515..71492a24d6 100644
--- a/elf/elf.h
+++ b/elf/elf.h
@@ -2194,6 +2194,8 @@ enum
 #define R_PPC_GOT_DTPREL16_LO	92 /* half16*	(sym+add)@got@dtprel@l */
 #define R_PPC_GOT_DTPREL16_HI	93 /* half16*	(sym+add)@got@dtprel@h */
 #define R_PPC_GOT_DTPREL16_HA	94 /* half16*	(sym+add)@got@dtprel@ha */
+#define R_PPC_TLSGD		95 /* none	(sym+add)@tlsgd */
+#define R_PPC_TLSLD		96 /* none	(sym+add)@tlsld */
 
 /* The remaining relocs are from the Embedded ELF ABI, and are not
    in the SVR4 ELF ABI.  */
@@ -2237,7 +2239,11 @@ enum
 
 /* PowerPC specific values for the Dyn d_tag field.  */
 #define DT_PPC_GOT		(DT_LOPROC + 0)
-#define DT_PPC_NUM		1
+#define DT_PPC_OPT		(DT_LOPROC + 1)
+#define DT_PPC_NUM		2
+
+/* PowerPC specific values for the DT_PPC_OPT Dyn entry.  */
+#define PPC_OPT_TLS		1
 
 /* PowerPC64 relocations defined by the ABIs */
 #define R_PPC64_NONE		R_PPC_NONE