elf/x86-64: Subtract __ImageBase for R_AMD64_IMAGEBASE

When linking Windows x86-64 relocatable object files to generate x86-64
ELF executable, we need to subtract __ImageBase, aka __executable_start,
for R_AMD64_IMAGEBASE relocation:

1. Add link_info to struct output_elf_obj_tdata to store linker info and
_bfd_get_link_info() to retrieve it.
2. Add ldelf_set_output_arch to set up link_info.
3. Add pex64_link_add_symbols to create an indirect reference to
__executable_start for __ImageBase to support R_AMD64_IMAGEBASE relocation
when adding symbols from Windows x86-64 relocatable object files to
generate x86-64 ELF executable.
4. Also subtract __ImageBase for R_AMD64_IMAGEBASE when generating x86-64
ELF executable.

bfd/

	PR ld/27425
	PR ld/27432
	* bfd.c (_bfd_get_link_info): New function.
	* elf-bfd.h (output_elf_obj_tdata): Add link_info.
	(elf_link_info): New.
	* libbfd-in.h (_bfd_get_link_info): New prototype.
	* coff-x86_64.c (coff_amd64_reloc): Also subtract __ImageBase for
	R_AMD64_IMAGEBASE when generating x86-64 ELF executable.
	* pe-x86_64.c: Include "coff/internal.h" and "libcoff.h".
	(pex64_link_add_symbols): New function.
	(coff_bfd_link_add_symbols): New macro.
	* libbfd.h: Regenerated.

ld/

	PR ld/27425
	PR ld/27432
	* ldelf.c (ldelf_set_output_arch): New function.
	* ldelf.h (ldelf_set_output_arch): New prototype.
	* emultempl/elf.em (LDEMUL_SET_OUTPUT_ARCH): Default to
	ldelf_set_output_arch.
	* ld-x86-64/pe-x86-64-1.od: Expect __executable_start.
	* testsuite/ld-x86-64/pe-x86-64-2.od: Likewise.
	* testsuite/ld-x86-64/pe-x86-64-3.od: Likewise.
	* testsuite/ld-x86-64/pe-x86-64-4.od: Likewise.
	* testsuite/ld-x86-64/pe-x86-64-5.od: Likewise.
	* testsuite/ld-x86-64/pe-x86-64-5.rd: Likewise.
	* testsuite/ld-x86-64/pe-x86-64-6.obj.bz2: New file.
	* testsuite/ld-x86-64/pe-x86-64-6.od: Likewise.
	* testsuite/ld-x86-64/pe-x86-64.exp: Run ld/27425 test.

bfd/ChangeLog

@@ -1,3 +1,18 @@
+2021-03-05  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR ld/27425
+	PR ld/27432
+	* bfd.c (_bfd_get_link_info): New function.
+	* elf-bfd.h (output_elf_obj_tdata): Add link_info.
+	(elf_link_info): New.
+	* libbfd-in.h (_bfd_get_link_info): New prototype.
+	* coff-x86_64.c (coff_amd64_reloc): Also subtract __ImageBase for
+	R_AMD64_IMAGEBASE when generating x86-64 ELF executable.
+	* pe-x86_64.c: Include "coff/internal.h" and "libcoff.h".
+	(pex64_link_add_symbols): New function.
+	(coff_bfd_link_add_symbols): New macro.
+	* libbfd.h: Regenerated.
+
 2021-03-05  Craig Blackmore  <craig.blackmore@embecosm.com>
 	    Andrew Burgess  <andrew.burgess@embecosm.com>
 

bfd/bfd.c

@@ -2808,3 +2808,14 @@ bfd_convert_section_contents (bfd *ibfd, sec_ptr isec, bfd *obfd,
   *ptr_size = size;
   return TRUE;
 }
+
+/* Get the linker information.  */
+
+struct bfd_link_info *
+_bfd_get_link_info (bfd *abfd)
+{
+  if (bfd_get_flavour (abfd) != bfd_target_elf_flavour)
+    return NULL;
+
+  return elf_link_info (abfd);
+}

bfd/coff-x86_64.c

@@ -131,11 +131,38 @@ coff_amd64_reloc (bfd *abfd,
 	diff -= reloc_entry->howto->type - R_AMD64_PCRLONG;
     }
 
-  /* FIXME: How should this case be handled?  */
   if (reloc_entry->howto->type == R_AMD64_IMAGEBASE
-      && output_bfd != NULL
+      && output_bfd == NULL)
-      && bfd_get_flavour (output_bfd) == bfd_target_coff_flavour)
+    {
-    diff -= pe_data (output_bfd)->pe_opthdr.ImageBase;
+      bfd *obfd = input_section->output_section->owner;
+      struct bfd_link_info *link_info;
+      struct bfd_link_hash_entry *h;
+      switch (bfd_get_flavour (obfd))
+	{
+	case bfd_target_coff_flavour:
+	  diff -= pe_data (obfd)->pe_opthdr.ImageBase;
+	  break;
+	case bfd_target_elf_flavour:
+	  /* Subtract __ImageBase.  */
+	  link_info = _bfd_get_link_info (obfd);
+	  if (link_info == NULL)
+	    return bfd_reloc_dangerous;
+	  h = bfd_link_hash_lookup (link_info->hash, "__ImageBase",
+				    FALSE, FALSE, FALSE);
+	  if (h == NULL)
+	    return bfd_reloc_dangerous;
+	  while (h->type == bfd_link_hash_indirect)
+	    h = h->u.i.link;
+	  /* ELF symbols in relocatable files are section relative,
+	     but in nonrelocatable files they are virtual addresses.  */
+	  diff -= (h->u.def.value
+		   + h->u.def.section->output_offset
+		   + h->u.def.section->output_section->vma);
+	  break;
+	default:
+	  break;
+	}
+    }
 #endif
 
 #define DOIT(x) \

bfd/elf-bfd.h

@@ -1887,6 +1887,9 @@ struct output_elf_obj_tdata
   /* Used when laying out sections.  */
   file_ptr next_file_pos;
 
+  /* Linker information.  */
+  struct bfd_link_info *link_info;
+
   int num_section_syms;
   unsigned int shstrtab_section, strtab_section;
 
@@ -2064,6 +2067,7 @@ struct elf_obj_tdata
 #define elf_elfsections(bfd)	(elf_tdata(bfd) -> elf_sect_ptr)
 #define elf_numsections(bfd)	(elf_tdata(bfd) -> num_elf_sections)
 #define elf_seg_map(bfd)	(elf_tdata(bfd) -> o->seg_map)
+#define elf_link_info(bfd)	(elf_tdata(bfd) -> o->link_info)
 #define elf_next_file_pos(bfd)	(elf_tdata(bfd) -> o->next_file_pos)
 #define elf_eh_frame_hdr(bfd)	(elf_tdata(bfd) -> o->eh_frame_hdr)
 #define elf_stack_flags(bfd)	(elf_tdata(bfd) -> o->stack_flags)

bfd/libbfd-in.h

@@ -899,6 +899,8 @@ extern bfd_vma _bfd_safe_read_leb128
 extern bfd_byte * _bfd_write_unsigned_leb128
   (bfd_byte *, bfd_byte *, bfd_vma) ATTRIBUTE_HIDDEN;
 
+extern struct bfd_link_info *_bfd_get_link_info (bfd *);
+
 #if GCC_VERSION >= 7000
 #define _bfd_mul_overflow(a, b, res) __builtin_mul_overflow (a, b, res)
 #else

bfd/libbfd.h

@@ -904,6 +904,8 @@ extern bfd_vma _bfd_safe_read_leb128
 extern bfd_byte * _bfd_write_unsigned_leb128
   (bfd_byte *, bfd_byte *, bfd_vma) ATTRIBUTE_HIDDEN;
 
+extern struct bfd_link_info *_bfd_get_link_info (bfd *);
+
 #if GCC_VERSION >= 7000
 #define _bfd_mul_overflow(a, b, res) __builtin_mul_overflow (a, b, res)
 #else

bfd/pe-x86_64.c

@@ -22,6 +22,8 @@
 
 #include "sysdep.h"
 #include "bfd.h"
+#include "coff/internal.h"
+#include "libcoff.h"
 
 #define TARGET_SYM		x86_64_pe_vec
 #define TARGET_NAME		"pe-x86-64"
@@ -66,5 +68,33 @@ extern bfd_boolean pex64_bfd_print_pdata (bfd *, void *);
 
 #define bfd_pe_print_pdata   pex64_bfd_print_pdata
 
-#include "coff-x86_64.c"
+static bfd_boolean
+pex64_link_add_symbols (bfd *abfd, struct bfd_link_info *info)
+{
+  if (bfd_link_pde (info)
+      && bfd_get_flavour (info->output_bfd) == bfd_target_elf_flavour)
+    {
+      /* NB: When linking Windows x86-64 relocatable object files to
+	 generate ELF executable, create an indirect reference to
+	 __executable_start for __ImageBase to support R_AMD64_IMAGEBASE
+	 relocation which is relative to __ImageBase.  */
+      struct bfd_link_hash_entry *h, *hi;
+      hi = bfd_link_hash_lookup (info->hash, "__ImageBase", TRUE, FALSE,
+				 FALSE);
+      if (hi->type == bfd_link_hash_new
+	  || hi->type == bfd_link_hash_undefined
+	  || hi->type == bfd_link_hash_undefweak)
+	{
+	  h = bfd_link_hash_lookup (info->hash, "__executable_start",
+				    TRUE, FALSE, TRUE);
+	  hi->type = bfd_link_hash_indirect;
+	  hi->u.i.link = h;
+	}
+    }
 
+  return _bfd_coff_link_add_symbols (abfd, info);
+}
+
+#define coff_bfd_link_add_symbols pex64_link_add_symbols
+
+#include "coff-x86_64.c"

ld/ChangeLog

@@ -1,3 +1,21 @@
+2021-03-05  H.J. Lu  <hongjiu.lu@intel.com>
+
+	PR ld/27425
+	PR ld/27432
+	* ldelf.c (ldelf_set_output_arch): New function.
+	* ldelf.h (ldelf_set_output_arch): New prototype.
+	* emultempl/elf.em (LDEMUL_SET_OUTPUT_ARCH): Default to
+	ldelf_set_output_arch.
+	* ld-x86-64/pe-x86-64-1.od: Expect __executable_start.
+	* testsuite/ld-x86-64/pe-x86-64-2.od: Likewise.
+	* testsuite/ld-x86-64/pe-x86-64-3.od: Likewise.
+	* testsuite/ld-x86-64/pe-x86-64-4.od: Likewise.
+	* testsuite/ld-x86-64/pe-x86-64-5.od: Likewise.
+	* testsuite/ld-x86-64/pe-x86-64-5.rd: Likewise.
+	* testsuite/ld-x86-64/pe-x86-64-6.obj.bz2: New file.
+	* testsuite/ld-x86-64/pe-x86-64-6.od: Likewise.
+	* testsuite/ld-x86-64/pe-x86-64.exp: Run ld/27425 test.
+
 2021-03-04  Jan Beulich  <jbeulich@suse.com>
 
 	* testsuite/ld-scripts/map-address.exp: Set image base to zero

ld/emultempl/elf.em

@@ -919,7 +919,7 @@ struct ld_emulation_xfer_struct ld_${EMULATION_NAME}_emulation =
   ${LDEMUL_AFTER_CHECK_RELOCS-after_check_relocs_default},
   ${LDEMUL_BEFORE_PLACE_ORPHANS-ldelf_before_place_orphans},
   ${LDEMUL_AFTER_ALLOCATION-gld${EMULATION_NAME}_after_allocation},
-  ${LDEMUL_SET_OUTPUT_ARCH-set_output_arch_default},
+  ${LDEMUL_SET_OUTPUT_ARCH-ldelf_set_output_arch},
   ${LDEMUL_CHOOSE_TARGET-ldemul_default_target},
   ${LDEMUL_BEFORE_ALLOCATION-gld${EMULATION_NAME}_before_allocation},
   ${LDEMUL_GET_SCRIPT-gld${EMULATION_NAME}_get_script},

ld/ldelf.c

@@ -2206,3 +2206,11 @@ ldelf_before_place_orphans (void)
 	  }
       }
 }
+
+void
+ldelf_set_output_arch (void)
+{
+  set_output_arch_default ();
+  if (link_info.output_bfd->xvec->flavour == bfd_target_elf_flavour)
+    elf_link_info (link_info.output_bfd) = &link_info;
+}

ld/ldelf.h

@@ -31,3 +31,4 @@ extern bfd_boolean ldelf_open_dynamic_archive
 extern lang_output_section_statement_type *ldelf_place_orphan
   (asection *, const char *, int);
 extern void ldelf_before_place_orphans (void);
+extern void ldelf_set_output_arch (void);

ld/testsuite/ld-x86-64/pe-x86-64-1.od

@@ -2,6 +2,7 @@
 .*: +file format .*
 
 SYMBOL TABLE:
+0+400000 g       .text\$mn	0000000000000000 __executable_start
 0+401000 g       .text\$mn	0000000000000000 getaddr1
 0+401020 g       .text\$mn	0000000000000000 begin
 0+403014 g       .bss	0000000000000000 __bss_start

ld/testsuite/ld-x86-64/pe-x86-64-2.od

@@ -2,6 +2,7 @@
 .*: +file format .*
 
 SYMBOL TABLE:
+0+400000 g       .text\$mn	0000000000000000 __executable_start
 0+401000 g       .text\$mn	0000000000000000 getaddr1
 0+401020 g       .text\$mn	0000000000000000 begin
 0+403014 g       .bss	0000000000000000 __bss_start

ld/testsuite/ld-x86-64/pe-x86-64-3.od

@@ -2,6 +2,7 @@
 .*: +file format .*
 
 SYMBOL TABLE:
+0+400000 g       .text\$mn	0000000000000000 __executable_start
 0+401000 g       .text\$mn	0000000000000000 getaddr1
 0+401020 g       .text\$mn	0000000000000000 begin
 0+403014 g       .bss	0000000000000000 __bss_start

ld/testsuite/ld-x86-64/pe-x86-64-4.od

@@ -2,6 +2,7 @@
 .*: +file format .*
 
 SYMBOL TABLE:
+0+400000 g       .text\$mn	0000000000000000 __executable_start
 0+403038 g       .bss	0000000000000000 c
 0+401000 g       .text\$mn	0000000000000000 begin
 0+403038 g       .bss	0000000000000000 __bss_start

ld/testsuite/ld-x86-64/pe-x86-64-5.od

@@ -4,6 +4,7 @@
 SYMBOL TABLE:
 0+402014 g       .bss	0000000000000000 non_initdummy
 0+402010 g       .data	0000000000000000 initdummy
+0+400000 g       .text\$mn	0000000000000000 __executable_start
 0+401000 g       .text\$mn	0000000000000000 begin
 0+402012 g       .bss	0000000000000000 __bss_start
 0+402000 g       .data	0000000000000000 Struct

ld/testsuite/ld-x86-64/pe-x86-64-5.rd

@@ -1,9 +1,10 @@
 
-Symbol table '.symtab' contains 10 entries:
+Symbol table '.symtab' contains 11 entries:
    Num:    Value          Size Type    Bind   Vis      Ndx Name
  +[a-f0-9]+: 0000000000000000     0 NOTYPE  LOCAL  DEFAULT  UND 
  +[a-f0-9]+: 0000000000402014     0 NOTYPE  GLOBAL DEFAULT    3 non_initdummy
  +[a-f0-9]+: 0000000000402010     0 NOTYPE  GLOBAL DEFAULT    2 initdummy
+ +[a-f0-9]+: 0000000000400000     0 NOTYPE  GLOBAL DEFAULT    1 __executable_start
  +[a-f0-9]+: 0000000000401000     0 NOTYPE  GLOBAL DEFAULT    1 begin
  +[a-f0-9]+: 0000000000402012     0 NOTYPE  GLOBAL DEFAULT    3 __bss_start
  +[a-f0-9]+: 0000000000402000     0 NOTYPE  GLOBAL DEFAULT    2 Struct

ld/testsuite/ld-x86-64/pe-x86-64-6.od

@@ -0,0 +1,91 @@
+
+.*: +file format .*
+
+SYMBOL TABLE:
+0+4010a8 g       .text\$mn	0000000000000000 xfunc
+0+402000 g       .rdata	0000000000000000 \?\?_C@_02LDKJOMJN@AB@
+0+400000 g       .text\$mn	0000000000000000 __executable_start
+0+403058 g       .data	0000000000000000 __bss_start
+0+401000 g       .text\$mn	0000000000000000 main
+0+403038 g       .data	0000000000000000 deadloopvar
+0+4010ac g       .text\$mn	0000000000000000 xstring
+0+403058 g       .data	0000000000000000 _edata
+0+403058 g       .data	0000000000000000 _end
+
+
+
+Disassembly of section .text\$mn:
+
+0+401000 <main>:
+ +[a-f0-9]+:	48 89 5c 24 08       	mov    %rbx,0x8\(%rsp\)
+ +[a-f0-9]+:	48 89 6c 24 10       	mov    %rbp,0x10\(%rsp\)
+ +[a-f0-9]+:	48 89 74 24 20       	mov    %rsi,0x20\(%rsp\)
+ +[a-f0-9]+:	57                   	push   %rdi
+ +[a-f0-9]+:	48 83 ec 20          	sub    \$0x20,%rsp
+ +[a-f0-9]+:	cc                   	int3   
+ +[a-f0-9]+:	8b 05 1d 20 00 00    	mov    0x201d\(%rip\),%eax        # 403038 <deadloopvar>
+ +[a-f0-9]+:	83 f8 01             	cmp    \$0x1,%eax
+ +[a-f0-9]+:	74 f5                	je     401015 <main\+0x15>
+ +[a-f0-9]+:	0f 31                	rdtsc  
+ +[a-f0-9]+:	48 c1 e2 20          	shl    \$0x20,%rdx
+ +[a-f0-9]+:	48 0b c2             	or     %rdx,%rax
+ +[a-f0-9]+:	74 5d                	je     401088 <main\+0x88>
+ +[a-f0-9]+:	33 ff                	xor    %edi,%edi
+ +[a-f0-9]+:	48 8d 2d cc ef ff ff 	lea    -0x1034\(%rip\),%rbp        # 400000 <__executable_start>
+ +[a-f0-9]+:	33 db                	xor    %ebx,%ebx
+ +[a-f0-9]+:	48 8d 35 ff 1f 00 00 	lea    0x1fff\(%rip\),%rsi        # 40303c <deadloopvar\+0x4>
+ +[a-f0-9]+:	48 8b 8c 2b 50 30 00 00 	mov    0x3050\(%rbx,%rbp,1\),%rcx
+ +[a-f0-9]+:	44 8a 01             	mov    \(%rcx\),%r8b
+ +[a-f0-9]+:	45 84 c0             	test   %r8b,%r8b
+ +[a-f0-9]+:	74 28                	je     401075 <main\+0x75>
+ +[a-f0-9]+:	b8 05 00 00 00       	mov    \$0x5,%eax
+ +[a-f0-9]+:	2b 84 2b 48 30 00 00 	sub    0x3048\(%rbx,%rbp,1\),%eax
+ +[a-f0-9]+:	99                   	cltd   
+ +[a-f0-9]+:	2b c2                	sub    %edx,%eax
+ +[a-f0-9]+:	d1 f8                	sar    %eax
+ +[a-f0-9]+:	48 63 d0             	movslq %eax,%rdx
+ +[a-f0-9]+:	48 03 d6             	add    %rsi,%rdx
+ +[a-f0-9]+:	48 ff c1             	inc    %rcx
+ +[a-f0-9]+:	44 88 02             	mov    %r8b,\(%rdx\)
+ +[a-f0-9]+:	48 ff c2             	inc    %rdx
+ +[a-f0-9]+:	44 8a 01             	mov    \(%rcx\),%r8b
+ +[a-f0-9]+:	45 84 c0             	test   %r8b,%r8b
+ +[a-f0-9]+:	75 ef                	jne    401064 <main\+0x64>
+ +[a-f0-9]+:	48 8b ce             	mov    %rsi,%rcx
+ +[a-f0-9]+:	e8 2f 00 00 00       	call   4010ac <xstring>
+ +[a-f0-9]+:	ff c7                	inc    %edi
+ +[a-f0-9]+:	48 83 c3 08          	add    \$0x8,%rbx
+ +[a-f0-9]+:	83 ff 01             	cmp    \$0x1,%edi
+ +[a-f0-9]+:	72 b5                	jb     40103d <main\+0x3d>
+ +[a-f0-9]+:	b1 aa                	mov    \$0xaa,%cl
+ +[a-f0-9]+:	e8 19 00 00 00       	call   4010a8 <xfunc>
+ +[a-f0-9]+:	48 8b 5c 24 30       	mov    0x30\(%rsp\),%rbx
+ +[a-f0-9]+:	33 c0                	xor    %eax,%eax
+ +[a-f0-9]+:	48 8b 6c 24 38       	mov    0x38\(%rsp\),%rbp
+ +[a-f0-9]+:	48 8b 74 24 48       	mov    0x48\(%rsp\),%rsi
+ +[a-f0-9]+:	48 83 c4 20          	add    \$0x20,%rsp
+ +[a-f0-9]+:	5f                   	pop    %rdi
+ +[a-f0-9]+:	c3                   	ret    
+ +[a-f0-9]+:	66 90                	xchg   %ax,%ax
+
+0+4010a8 <xfunc>:
+ +[a-f0-9]+:	66 90                	xchg   %ax,%ax
+ +[a-f0-9]+:	cc                   	int3   
+ +[a-f0-9]+:	c3                   	ret    
+
+0+4010ac <xstring>:
+ +[a-f0-9]+:	40 53                	rex push %rbx
+ +[a-f0-9]+:	48 83 ec 20          	sub    \$0x20,%rsp
+ +[a-f0-9]+:	8a 01                	mov    \(%rcx\),%al
+ +[a-f0-9]+:	48 8b d9             	mov    %rcx,%rbx
+ +[a-f0-9]+:	eb 0c                	jmp    4010c5 <xstring\+0x19>
+ +[a-f0-9]+:	8a c8                	mov    %al,%cl
+ +[a-f0-9]+:	e8 e8 ff ff ff       	call   4010a8 <xfunc>
+ +[a-f0-9]+:	48 ff c3             	inc    %rbx
+ +[a-f0-9]+:	8a 03                	mov    \(%rbx\),%al
+ +[a-f0-9]+:	84 c0                	test   %al,%al
+ +[a-f0-9]+:	75 f0                	jne    4010b9 <xstring\+0xd>
+ +[a-f0-9]+:	48 83 c4 20          	add    \$0x20,%rsp
+ +[a-f0-9]+:	5b                   	pop    %rbx
+ +[a-f0-9]+:	c3                   	ret    
+#pass

ld/testsuite/ld-x86-64/pe-x86-64.exp

@@ -73,4 +73,13 @@ run_ld_link_tests [list \
 	 {readelf {-s -x .data} pe-x86-64-5.rd}} \
 	"pe-x86-64-5" \
     ] \
+    [list \
+	"Build pe-x86-64-6" \
+	"-m elf_x86_64 --entry=main" \
+	"" \
+	"" \
+	{pe-x86-64-6.obj.bz2 } \
+	{{objdump {-dw --sym} pe-x86-64-6.od}} \
+	"pe-x86-64-6" \
+    ] \
 ]