x86-64: Generate branch with PLT32 relocation

Since there is no need to prepare for PLT branch on x86-64, generate
R_X86_64_PLT32, instead of R_X86_64_PC32, if possible, which can be
used as a marker for 32-bit PC-relative branches.

To compile Linux kernel, this patch:

From: "H.J. Lu" <hjl.tools@gmail.com>
Subject: [PATCH] x86: Treat R_X86_64_PLT32 as R_X86_64_PC32

On i386, there are 2 types of PLTs, PIC and non-PIC.  PIE and shared
objects must use PIC PLT.  To use PIC PLT, you need to load
_GLOBAL_OFFSET_TABLE_ into EBX first.  There is no need for that on
x86-64 since x86-64 uses PC-relative PLT.

On x86-64, for 32-bit PC-relative branches, we can generate PLT32
relocation, instead of PC32 relocation, which can also be used as
a marker for 32-bit PC-relative branches.  Linker can always reduce
PLT32 relocation to PC32 if function is defined locally.   Local
functions should use PC32 relocation.  As far as Linux kernel is
concerned, R_X86_64_PLT32 can be treated the same as R_X86_64_PC32
since Linux kernel doesn't use PLT.

is needed.  It is available on hjl/plt32/master branch at

https://github.com/hjl-tools/linux

bfd/

	PR gas/22791
	* elf64-x86-64.c (is_32bit_relative_branch): Removed.
	(elf_x86_64_relocate_section): Check PIC relocations in PIE.
	Remove is_32bit_relative_branch usage.  Disallow PC32 reloc
	against protected function in shared object.

gas/

	PR gas/22791
	* config/tc-i386.c (need_plt32_p): New function.
	(output_jump): Generate BFD_RELOC_X86_64_PLT32 if possible.
	(md_estimate_size_before_relax): Likewise.
	* testsuite/gas/i386/reloc64.d: Updated.
	* testsuite/gas/i386/x86-64-jump.d: Likewise.
	* testsuite/gas/i386/x86-64-mpx-branch-1.d: Likewise.
	* testsuite/gas/i386/x86-64-mpx-branch-2.d: Likewise.
	* testsuite/gas/i386/x86-64-relax-2.d: Likewise.
	* testsuite/gas/i386/x86-64-relax-3.d: Likewise.
	* testsuite/gas/i386/ilp32/reloc64.d: Likewise.
	* testsuite/gas/i386/ilp32/x86-64-branch.d: Likewise.

ld/

	PR gas/22791
	* testsuite/ld-x86-64/mpx1c.rd: Updated.
	* testsuite/ld-x86-64/pr22791-1.err: New file.
	* testsuite/ld-x86-64/pr22791-1a.c: Likewise.
	* testsuite/ld-x86-64/pr22791-1b.s: Likewise.
	* testsuite/ld-x86-64/pr22791-2.rd: Likewise.
	* testsuite/ld-x86-64/pr22791-2a.s: Likewise.
	* testsuite/ld-x86-64/pr22791-2b.c: Likewise.
	* testsuite/ld-x86-64/pr22791-2c.s: Likewise.
	* testsuite/ld-x86-64/x86-64.exp: Run PR ld/22791 tests.

10 files changed, 85 insertions, 23 deletions

diff --git a/gas/ChangeLog b/gas/ChangeLog
index 97b3581..e66e8ce 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,3 +1,18 @@
+2018-02-13  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR gas/22791
+	* config/tc-i386.c (need_plt32_p): New function.
+	(output_jump): Generate BFD_RELOC_X86_64_PLT32 if possible.
+	(md_estimate_size_before_relax): Likewise.
+	* testsuite/gas/i386/reloc64.d: Updated.
+	* testsuite/gas/i386/x86-64-jump.d: Likewise.
+	* testsuite/gas/i386/x86-64-mpx-branch-1.d: Likewise.
+	* testsuite/gas/i386/x86-64-mpx-branch-2.d: Likewise.
+	* testsuite/gas/i386/x86-64-relax-2.d: Likewise.
+	* testsuite/gas/i386/x86-64-relax-3.d: Likewise.
+	* testsuite/gas/i386/ilp32/reloc64.d: Likewise.
+	* testsuite/gas/i386/ilp32/x86-64-branch.d: Likewise.
+
 2018-02-13  Maciej W. Rozycki  <macro@mips.com>
 
 	* testsuite/gas/mips/loongson-3a-2.d: Rename test.
diff --git a/gas/config/tc-i386.c b/gas/config/tc-i386.c
index 552c1b8..1a5be1b 100644
--- a/gas/config/tc-i386.c
+++ b/gas/config/tc-i386.c
@@ -7023,12 +7023,46 @@ output_branch (void)
   frag_var (rs_machine_dependent, 5, i.reloc[0], subtype, sym, off, p);
 }
 
+#if defined (OBJ_ELF) || defined (OBJ_MAYBE_ELF)
+/* Return TRUE iff PLT32 relocation should be used for branching to
+   symbol S.  */
+
+static bfd_boolean
+need_plt32_p (symbolS *s)
+{
+  /* PLT32 relocation is ELF only.  */
+  if (!IS_ELF)
+    return FALSE;
+
+  /* Since there is no need to prepare for PLT branch on x86-64, we
+     can generate R_X86_64_PLT32, instead of R_X86_64_PC32, which can
+     be used as a marker for 32-bit PC-relative branches.  */
+  if (!object_64bit)
+    return FALSE;
+
+  /* Weak or undefined symbol need PLT32 relocation.  */
+  if (S_IS_WEAK (s) || !S_IS_DEFINED (s))
+    return TRUE;
+
+  /* Non-global symbol doesn't need PLT32 relocation.  */
+  if (! S_IS_EXTERNAL (s))
+    return FALSE;
+
+  /* Other global symbols need PLT32 relocation.  NB: Symbol with
+     non-default visibilities are treated as normal global symbol
+     so that PLT32 relocation can be used as a marker for 32-bit
+     PC-relative branches.  It is useful for linker relaxation.  */
+  return TRUE;
+}
+#endif
+
 static void
 output_jump (void)
 {
   char *p;
   int size;
   fixS *fixP;
+  bfd_reloc_code_real_type jump_reloc = i.reloc[0];
 
   if (i.tm.opcode_modifier.jumpbyte)
     {
@@ -7096,8 +7130,17 @@ output_jump (void)
       abort ();
     }
 
+#if defined (OBJ_ELF) || defined (OBJ_MAYBE_ELF)
+  if (size == 4
+      && jump_reloc == NO_RELOC
+      && need_plt32_p (i.op[0].disps->X_add_symbol))
+    jump_reloc = BFD_RELOC_X86_64_PLT32;
+#endif
+
+  jump_reloc = reloc (size, 1, 1, jump_reloc);
+
   fixP = fix_new_exp (frag_now, p - frag_now->fr_literal, size,
-		      i.op[0].disps, 1, reloc (size, 1, 1, i.reloc[0]));
+		      i.op[0].disps, 1, jump_reloc);
 
   /* All jumps handled here are signed, but don't use a signed limit
      check for 32 and 16 bit jumps as we want to allow wrap around at
@@ -9315,6 +9358,10 @@ md_estimate_size_before_relax (fragS *fragP, segT segment)
 	reloc_type = (enum bfd_reloc_code_real) fragP->fr_var;
       else if (size == 2)
 	reloc_type = BFD_RELOC_16_PCREL;
+#if defined (OBJ_ELF) || defined (OBJ_MAYBE_ELF)
+      else if (need_plt32_p (fragP->fr_symbol))
+	reloc_type = BFD_RELOC_X86_64_PLT32;
+#endif
       else
 	reloc_type = BFD_RELOC_32_PCREL;
 
diff --git a/gas/testsuite/gas/i386/ilp32/reloc64.d b/gas/testsuite/gas/i386/ilp32/reloc64.d
index 53083f3..f6bc628 100644
--- a/gas/testsuite/gas/i386/ilp32/reloc64.d
+++ b/gas/testsuite/gas/i386/ilp32/reloc64.d
@@ -16,7 +16,7 @@ Disassembly of section \.text:
 .*[ 	]+R_X86_64_PC8[ 	]+xtrn\+0x0*1
 .*[ 	]+R_X86_64_PC32[ 	]+xtrn-0x0*4
 .*[ 	]+R_X86_64_PC32[ 	]+xtrn-0x0*4
-.*[ 	]+R_X86_64_PC32[ 	]+xtrn-0x0*4
+.*[ 	]+R_X86_64_PLT32[ 	]+xtrn-0x0*4
 .*[ 	]+R_X86_64_PC8[ 	]+xtrn-0x0*1
 .*[ 	]+R_X86_64_GOT32[ 	]+xtrn
 .*[ 	]+R_X86_64_GOT32[ 	]+xtrn
diff --git a/gas/testsuite/gas/i386/ilp32/x86-64-branch.d b/gas/testsuite/gas/i386/ilp32/x86-64-branch.d
index 915dbf3..45ab617 100644
--- a/gas/testsuite/gas/i386/ilp32/x86-64-branch.d
+++ b/gas/testsuite/gas/i386/ilp32/x86-64-branch.d
@@ -20,9 +20,9 @@ Disassembly of section .text:
 [ 	]*[a-f0-9]+:	66 ff 20             	data16 jmpq \*\(%rax\)
 [ 	]*[a-f0-9]+:	e8 00 00 00 00       	callq  0x1f	1b: R_X86_64_PC32	\*ABS\*\+0x10003c
 [ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   0x24	20: R_X86_64_PC32	\*ABS\*\+0x10003c
-[ 	]*[a-f0-9]+:	66 e8 00 00 00 00    	data16 callq 0x2a	26: R_X86_64_PC32	foo-0x4
-[ 	]*[a-f0-9]+:	66 e9 00 00 00 00    	data16 jmpq 0x30	2c: R_X86_64_PC32	foo-0x4
-[ 	]*[a-f0-9]+:	66 0f 82 00 00 00 00 	data16 jb 0x37	33: R_X86_64_PC32	foo-0x4
+[ 	]*[a-f0-9]+:	66 e8 00 00 00 00    	data16 callq 0x2a	26: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	66 e9 00 00 00 00    	data16 jmpq 0x30	2c: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	66 0f 82 00 00 00 00 	data16 jb 0x37	33: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	ff d0                	callq  \*%rax
 [ 	]*[a-f0-9]+:	ff d0                	callq  \*%rax
 [ 	]*[a-f0-9]+:	66 ff d0             	data16 callq \*%rax
diff --git a/gas/testsuite/gas/i386/reloc64.d b/gas/testsuite/gas/i386/reloc64.d
index a7fd3d6..4cf884d 100644
--- a/gas/testsuite/gas/i386/reloc64.d
+++ b/gas/testsuite/gas/i386/reloc64.d
@@ -18,7 +18,7 @@ Disassembly of section \.text:
 .*[ 	]+R_X86_64_PC8[ 	]+xtrn\+0x0*1
 .*[ 	]+R_X86_64_PC32[ 	]+xtrn-0x0*4
 .*[ 	]+R_X86_64_PC32[ 	]+xtrn-0x0*4
-.*[ 	]+R_X86_64_PC32[ 	]+xtrn-0x0*4
+.*[ 	]+R_X86_64_PLT32[ 	]+xtrn-0x0*4
 .*[ 	]+R_X86_64_PC8[ 	]+xtrn-0x0*1
 .*[ 	]+R_X86_64_GOT64[ 	]+xtrn
 .*[ 	]+R_X86_64_GOT32[ 	]+xtrn
diff --git a/gas/testsuite/gas/i386/x86-64-jump.d b/gas/testsuite/gas/i386/x86-64-jump.d
index edb34e6..9f7b4b4 100644
--- a/gas/testsuite/gas/i386/x86-64-jump.d
+++ b/gas/testsuite/gas/i386/x86-64-jump.d
@@ -8,7 +8,7 @@ Disassembly of section .text:
 
 0+ <.text>:
 [ 	]*[a-f0-9]+:	eb fe                	jmp    (0x0|0 <.text>)
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   0x7	3: R_X86_64_PC32	xxx-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   0x7	3: R_X86_64_PLT32	xxx-0x4
 [ 	]*[a-f0-9]+:	ff 24 25 00 00 00 00 	jmpq   \*0x0	a: R_X86_64_32S	xxx
 [ 	]*[a-f0-9]+:	ff e7                	jmpq   \*%rdi
 [ 	]*[a-f0-9]+:	ff 27                	jmpq   \*\(%rdi\)
@@ -17,7 +17,7 @@ Disassembly of section .text:
 [ 	]*[a-f0-9]+:	ff 2c 25 00 00 00 00 	ljmp   \*0x0	24: R_X86_64_32S	xxx
 [ 	]*[a-f0-9]+:	66 ff 2c 25 00 00 00 00 	ljmpw  \*0x0	2c: R_X86_64_32S	xxx
 [ 	]*[a-f0-9]+:	e8 cb ff ff ff       	callq  0x0
-[ 	]*[a-f0-9]+:	e8 00 00 00 00       	callq  0x3a	36: R_X86_64_PC32	xxx-0x4
+[ 	]*[a-f0-9]+:	e8 00 00 00 00       	callq  0x3a	36: R_X86_64_PLT32	xxx-0x4
 [ 	]*[a-f0-9]+:	ff 14 25 00 00 00 00 	callq  \*0x0	3d: R_X86_64_32S	xxx
 [ 	]*[a-f0-9]+:	ff d7                	callq  \*%rdi
 [ 	]*[a-f0-9]+:	ff 17                	callq  \*\(%rdi\)
diff --git a/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d b/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d
index c070029..d44841e 100644
--- a/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d
+++ b/gas/testsuite/gas/i386/x86-64-mpx-branch-1.d
@@ -20,9 +20,9 @@ Disassembly of section .text:
 [ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 24 <foo2>
 
 0+24 <foo2>:
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 2a <foo2\+0x6>	26: R_X86_64_PC32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 31 <foo2\+0xd>	2d: R_X86_64_PC32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 37 <foo2\+0x13>	33: R_X86_64_PC32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 2a <foo2\+0x6>	26: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 31 <foo2\+0xd>	2d: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 37 <foo2\+0x13>	33: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 3d <foo2\+0x19>	39: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 44 <foo2\+0x20>	40: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 4a <foo2\+0x26>	46: R_X86_64_PLT32	foo-0x4
diff --git a/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d b/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d
index 5bb6a57..514c343 100644
--- a/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d
+++ b/gas/testsuite/gas/i386/x86-64-mpx-branch-2.d
@@ -20,9 +20,9 @@ Disassembly of section .text:
 [ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 24 <foo2>
 
 0+24 <foo2>:
-[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 2a <foo2\+0x6>	26: R_X86_64_PC32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 31 <foo2\+0xd>	2d: R_X86_64_PC32	foo-0x4
-[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 37 <foo2\+0x13>	33: R_X86_64_PC32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 2a <foo2\+0x6>	26: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 31 <foo2\+0xd>	2d: R_X86_64_PLT32	foo-0x4
+[ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 37 <foo2\+0x13>	33: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	f2 e9 00 00 00 00    	bnd jmpq 3d <foo2\+0x19>	39: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	f2 0f 82 00 00 00 00 	bnd jb 44 <foo2\+0x20>	40: R_X86_64_PLT32	foo-0x4
 [ 	]*[a-f0-9]+:	f2 e8 00 00 00 00    	bnd callq 4a <foo2\+0x26>	46: R_X86_64_PLT32	foo-0x4
diff --git a/gas/testsuite/gas/i386/x86-64-relax-2.d b/gas/testsuite/gas/i386/x86-64-relax-2.d
index c124102..c9eba84 100644
--- a/gas/testsuite/gas/i386/x86-64-relax-2.d
+++ b/gas/testsuite/gas/i386/x86-64-relax-2.d
@@ -10,12 +10,12 @@ Disassembly of section .text:
 0+ <foo>:
 [ 	]*[a-f0-9]+:	eb 24                	jmp    26 <local>
 [ 	]*[a-f0-9]+:	eb 1e                	jmp    22 <hidden_def>
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   9 <foo\+0x9>	5: R_X86_64_PC32	global_def-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   9 <foo\+0x9>	5: R_X86_64_PLT32	global_def-0x4
 [ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   e <foo\+0xe>	a: R_X86_64_PLT32	global_def-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   13 <foo\+0x13>	f: R_X86_64_PC32	weak_def-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   18 <foo\+0x18>	14: R_X86_64_PC32	weak_hidden_undef-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   1d <foo\+0x1d>	19: R_X86_64_PC32	weak_hidden_def-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   22 <hidden_def>	1e: R_X86_64_PC32	hidden_undef-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   13 <foo\+0x13>	f: R_X86_64_PLT32	weak_def-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   18 <foo\+0x18>	14: R_X86_64_PLT32	weak_hidden_undef-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   1d <foo\+0x1d>	19: R_X86_64_PLT32	weak_hidden_def-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   22 <hidden_def>	1e: R_X86_64_PLT32	hidden_undef-0x4
 
 0+22 <hidden_def>:
 [ 	]*[a-f0-9]+:	c3                   	retq   
diff --git a/gas/testsuite/gas/i386/x86-64-relax-3.d b/gas/testsuite/gas/i386/x86-64-relax-3.d
index 98fd28d..28ab5dd 100644
--- a/gas/testsuite/gas/i386/x86-64-relax-3.d
+++ b/gas/testsuite/gas/i386/x86-64-relax-3.d
@@ -11,10 +11,10 @@ Disassembly of section .text:
 [ 	]*[a-f0-9]+:	eb 1b                	jmp    1f <hidden_def>
 [ 	]*[a-f0-9]+:	eb 1b                	jmp    21 <global_def>
 [ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   b <foo\+0xb>	7: R_X86_64_PLT32	global_def-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   10 <foo\+0x10>	c: R_X86_64_PC32	weak_def-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   15 <foo\+0x15>	11: R_X86_64_PC32	weak_hidden_undef-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   1a <foo\+0x1a>	16: R_X86_64_PC32	weak_hidden_def-0x4
-[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   1f <hidden_def>	1b: R_X86_64_PC32	hidden_undef-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   10 <foo\+0x10>	c: R_X86_64_PLT32	weak_def-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   15 <foo\+0x15>	11: R_X86_64_PLT32	weak_hidden_undef-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   1a <foo\+0x1a>	16: R_X86_64_PLT32	weak_hidden_def-0x4
+[ 	]*[a-f0-9]+:	e9 00 00 00 00       	jmpq   1f <hidden_def>	1b: R_X86_64_PLT32	hidden_undef-0x4
 
 0+1f <hidden_def>:
 [ 	]*[a-f0-9]+:	c3                   	retq