gold: Support x86-64 TLS code sequences without PLT

There are extensions to x86-64 psABI:

https://groups.google.com/forum/#!topic/x86-64-abi/de5_KnLHxtI

to call tls_get_addr via GOT:

call *__tls_get_addr@GOTPCREL(%rip)

Since direct call is 4-byte long and indirect call, is 5-byte long, the
extra one byte must be handled properly.

For general dynamic model, one 0x66 prefix before call instruction is
removed to make room for indirect call.  For local dynamic model, we
simply use 5-byte indirect call.

TLS linker optimization is updated to recognize new instruction
patterns.  For local dynamic model to local exec model transition, we
generate 4 0x66 prefixes, instead of 3, before mov instruction in 64-bit
and generate a 5-byte nop, instead of 4-byte, before mov instruction in
32-bit.

	PR gold/20216
	* configure.ac (DEFAULT_TARGET_X86_64_OR_X32): New
	AM_CONDITIONAL.
	* configure: Regenerated.
	* x86_64.cc (Target_x86_64<size>::Relocate::relocate): Allow
	R_X86_64_GOTPCRELX relocation against __tls_get_addr.
	(Target_x86_64<size>::Relocate::tls_gd_to_ie): Support indirect
	call to __tls_get_addr.
	(Target_x86_64<size>::Relocate::tls_gd_to_le): Likewise.
	(Target_x86_64<size>::Relocate::tls_ld_to_le): Likewise.
	* testsuite/Makefile.am (check_PROGRAMS): Add pr20216a_test,
	pr20216b_test, pr20216c_test, pr20216d_test, pr20216e_test.
	(pr20216a_test_SOURCES): New.
	(pr20216a_test_DEPENDENCIES): Likewise.
	(pr20216a_test_CFLAGS): Likewise.
	(pr20216a_test_LDFLAGS): Likewise.
	(pr20216a_test_LDADD): Likewise.
	(pr20216b_test_SOURCES): Likewise.
	(pr20216b_test_DEPENDENCIES): Likewise.
	(pr20216b_test_CFLAGS): Likewise.
	(pr20216b_test_LDFLAGS): Likewise.
	(pr20216b_test_LDADD): Likewise.
	(pr20216c_test_SOURCES): Likewise.
	(pr20216c_test_DEPENDENCIES): Likewise.
	(pr20216c_test_CFLAGS): Likewise.
	(pr20216c_test_LDFLAGS): Likewise.
	(pr20216c_test_LDADD): Likewise.
	(pr20216d_test_SOURCES): Likewise.
	(pr20216d_test_DEPENDENCIES): Likewise.
	(pr20216d_test_CFLAGS): Likewise.
	(pr20216d_test_LDFLAGS): Likewise.
	(pr20216d_test_LDADD): Likewise.
	(pr20216e_test_SOURCES): Likewise.
	(pr20216e_test_DEPENDENCIES): Likewise.
	(pr20216e_test_CFLAGS): Likewise.
	(pr20216e_test_LDFLAGS): Likewise.
	(pr20216e_test_LDADD): Likewise.
	(pr20216a.so): Likewise.
	(pr20216b.so): Likewise.
	(pr20216_gd.o): Likewise.
	(pr20216_ld.o): Likewise.
	(MOSTLYCLEANFILES): Add pr20216a.so pr20216b.so.
	* testsuite/Makefile.in: Regenerated.
	* testsuite/pr20216_def.c: New file.
	* testsuite/pr20216_gd.S: Likewise.
	* testsuite/pr20216_ld.S: Likewise.
	* testsuite/pr20216_main.c: Likewise.

1 files changed, 45 insertions, 10 deletions

diff --git a/gold/x86_64.cc b/gold/x86_64.cc
index 6c511e2..6aa489a 100644
--- a/gold/x86_64.cc
+++ b/gold/x86_64.cc
@@ -3505,6 +3505,7 @@ Target_x86_64<size>::Relocate::relocate(
   if (this->skip_call_tls_get_addr_)
     {
       if ((r_type != elfcpp::R_X86_64_PLT32
+	   && r_type != elfcpp::R_X86_64_GOTPCRELX
 	   && r_type != elfcpp::R_X86_64_PLT32_BND
 	   && r_type != elfcpp::R_X86_64_PC32_BND
 	   && r_type != elfcpp::R_X86_64_PC32)
@@ -4169,16 +4170,23 @@ Target_x86_64<size>::Relocate::tls_gd_to_ie(
 {
   // For SIZE == 64:
   //	.byte 0x66; leaq foo@tlsgd(%rip),%rdi;
-  //	.word 0x6666; rex64; call __tls_get_addr
+  //	.word 0x6666; rex64; call __tls_get_addr@PLT
+  //	==> movq %fs:0,%rax; addq x@gottpoff(%rip),%rax
+  //	.byte 0x66; leaq foo@tlsgd(%rip),%rdi;
+  //	.word 0x66; rex64; call *__tls_get_addr@GOTPCREL(%rip)
   //	==> movq %fs:0,%rax; addq x@gottpoff(%rip),%rax
   // For SIZE == 32:
   //	leaq foo@tlsgd(%rip),%rdi;
-  //	.word 0x6666; rex64; call __tls_get_addr
+  //	.word 0x6666; rex64; call __tls_get_addr@PLT
+  //	==> movl %fs:0,%eax; addq x@gottpoff(%rip),%rax
+  //	leaq foo@tlsgd(%rip),%rdi;
+  //	.word 0x66; rex64; call *__tls_get_addr@GOTPCREL(%rip)
   //	==> movl %fs:0,%eax; addq x@gottpoff(%rip),%rax
 
   tls::check_range(relinfo, relnum, rela.get_r_offset(), view_size, 12);
   tls::check_tls(relinfo, relnum, rela.get_r_offset(),
-		 (memcmp(view + 4, "\x66\x66\x48\xe8", 4) == 0));
+		 (memcmp(view + 4, "\x66\x66\x48\xe8", 4) == 0
+		  || memcmp(view + 4, "\x66\x48\xff", 3) == 0));
 
   if (size == 64)
     {
@@ -4225,16 +4233,23 @@ Target_x86_64<size>::Relocate::tls_gd_to_le(
 {
   // For SIZE == 64:
   //	.byte 0x66; leaq foo@tlsgd(%rip),%rdi;
-  //	.word 0x6666; rex64; call __tls_get_addr
+  //	.word 0x6666; rex64; call __tls_get_addr@PLT
+  //	==> movq %fs:0,%rax; leaq x@tpoff(%rax),%rax
+  //	.byte 0x66; leaq foo@tlsgd(%rip),%rdi;
+  //	.word 0x66; rex64; call *__tls_get_addr@GOTPCREL(%rip)
   //	==> movq %fs:0,%rax; leaq x@tpoff(%rax),%rax
   // For SIZE == 32:
   //	leaq foo@tlsgd(%rip),%rdi;
-  //	.word 0x6666; rex64; call __tls_get_addr
+  //	.word 0x6666; rex64; call __tls_get_addr@PLT
+  //	==> movl %fs:0,%eax; leaq x@tpoff(%rax),%rax
+  //	leaq foo@tlsgd(%rip),%rdi;
+  //	.word 0x66; rex64; call *__tls_get_addr@GOTPCREL(%rip)
   //	==> movl %fs:0,%eax; leaq x@tpoff(%rax),%rax
 
   tls::check_range(relinfo, relnum, rela.get_r_offset(), view_size, 12);
   tls::check_tls(relinfo, relnum, rela.get_r_offset(),
-		 (memcmp(view + 4, "\x66\x66\x48\xe8", 4) == 0));
+		 (memcmp(view + 4, "\x66\x66\x48\xe8", 4) == 0
+		  || memcmp(view + 4, "\x66\x48\xff", 3) == 0));
 
   if (size == 64)
     {
@@ -4362,6 +4377,13 @@ Target_x86_64<size>::Relocate::tls_ld_to_le(
   // For SIZE == 32:
   // ... leq foo@dtpoff(%rax),%reg
   // ==> nopl 0x0(%rax); movl %fs:0,%eax ... leaq x@tpoff(%rax),%rdx
+  // leaq foo@tlsld(%rip),%rdi; call *__tls_get_addr@GOTPCREL(%rip)
+  // For SIZE == 64:
+  // ... leq foo@dtpoff(%rax),%reg
+  // ==> .word 0x6666; .byte 0x6666; movq %fs:0,%rax ... leaq x@tpoff(%rax),%rdx
+  // For SIZE == 32:
+  // ... leq foo@dtpoff(%rax),%reg
+  // ==> nopw 0x0(%rax); movl %fs:0,%eax ... leaq x@tpoff(%rax),%rdx
 
   tls::check_range(relinfo, relnum, rela.get_r_offset(), view_size, -3);
   tls::check_range(relinfo, relnum, rela.get_r_offset(), view_size, 9);
@@ -4369,12 +4391,25 @@ Target_x86_64<size>::Relocate::tls_ld_to_le(
   tls::check_tls(relinfo, relnum, rela.get_r_offset(),
 		 view[-3] == 0x48 && view[-2] == 0x8d && view[-1] == 0x3d);
 
-  tls::check_tls(relinfo, relnum, rela.get_r_offset(), view[4] == 0xe8);
+  tls::check_tls(relinfo, relnum, rela.get_r_offset(),
+		 view[4] == 0xe8 || view[4] == 0xff);
 
-  if (size == 64)
-    memcpy(view - 3, "\x66\x66\x66\x64\x48\x8b\x04\x25\0\0\0\0", 12);
+  if (view[4] == 0xe8)
+    {
+      if (size == 64)
+	memcpy(view - 3, "\x66\x66\x66\x64\x48\x8b\x04\x25\0\0\0\0", 12);
+      else
+	memcpy(view - 3, "\x0f\x1f\x40\x00\x64\x8b\x04\x25\0\0\0\0", 12);
+    }
   else
-    memcpy(view - 3, "\x0f\x1f\x40\x00\x64\x8b\x04\x25\0\0\0\0", 12);
+    {
+      if (size == 64)
+	memcpy(view - 3, "\x66\x66\x66\x66\x64\x48\x8b\x04\x25\0\0\0\0",
+	       13);
+      else
+	memcpy(view - 3, "\x66\x0f\x1f\x40\x00\x64\x8b\x04\x25\0\0\0\0",
+	       13);
+    }
 
   // The next reloc should be a PLT32 reloc against __tls_get_addr.
   // We can skip it.