old-cross-binutils/ld/testsuite/ld-x86-64/bnd-ifunc-1.d

#as: --64 -madd-bnd-prefix
#ld: -shared -melf_x86_64 -z bndplt
#objdump: -dw

#...
[ 	]*[a-f0-9]+:	f2 e8 f0 ff ff ff    	bnd callq 220 <\*ABS\*\+0x228@plt>
#pass
Create the second PLT for BND relocations Intel MPX introduces 4 bound registers, which will be used for parameter passing in x86-64. Bound registers are cleared by branch instructions. Branch instructions with BND prefix will keep bound register contents. This leads to 2 requirements to 64-bit MPX run-time: 1. Dynamic linker (ld.so) should save and restore bound registers during symbol lookup. 2. Change the current 16-byte PLT0: ff 35 08 00 00 00 pushq GOT+8(%rip) ff 25 00 10 00 jmpq GOT+16(%rip) 0f 1f 40 00 nopl 0x0(%rax) and 16-byte PLT1: ff 25 00 00 00 00 jmpq name@GOTPCREL(%rip) 68 00 00 00 00 pushq $index e9 00 00 00 00 jmpq PLT0 which clear bound registers, to preserve bound registers. We use 2 new relocations: to mark branch instructions with BND prefix. When linker sees any R_X86_64_PC32_BND or R_X86_64_PLT32_BND relocations, it switches to a different PLT0: ff 35 08 00 00 00 pushq GOT+8(%rip) f2 ff 25 00 10 00 bnd jmpq GOT+16(%rip) 0f 1f 00 nopl (%rax) to preserve bound registers for symbol lookup and it also creates an external PLT section, .pl.bnd. Linker will create a BND PLT1 entry in .plt: 68 00 00 00 00 pushq $index f2 e9 00 00 00 00 bnd jmpq PLT0 0f 1f 44 00 00 nopl 0(%rax,%rax,1) and a 8-byte BND PLT entry in .plt.bnd: f2 ff 25 00 00 00 00 bnd jmpq name@GOTPCREL(%rip) 90 nop Otherwise, linker will create a legacy PLT1 entry in .plt: 68 00 00 00 00 pushq $index e9 00 00 00 00 jmpq PLT0 66 0f 1f 44 00 00 nopw 0(%rax,%rax,1) and a 8-byte legacy PLT in .plt.bnd: ff 25 00 00 00 00 jmpq name@GOTPCREL(%rip) 66 90 xchg %ax,%ax The initial value of the GOT entry for "name" will be set to the the "pushq" instruction in the corresponding entry in .plt. Linker will resolve reference of symbol "name" to the entry in the second PLT, .plt.bnd. Prelink stores the offset of pushq of PLT1 (plt_base + 0x10) in GOT[1] and GOT[1] is stored in GOT[3]. We can undo prelink in GOT by computing the corresponding the pushq offset with GOT[1] + (GOT offset - &GOT[3]) 2 Since for each entry in .plt except for PLT0 we create a 8-byte entry in .plt.bnd, there is extra 8-byte per PLT symbol. We also investigated the 16-byte entry for .plt.bnd. We compared the 8-byte entry vs the the 16-byte entry for .plt.bnd on Sandy Bridge. There are no performance differences in SPEC CPU 2000/2006 as well as micro benchmarks. Pros: No change to undo prelink in dynamic linker. Only 8-byte memory overhead for each PLT symbol. Cons: Extra .plt.bnd section is needed. Extra 8 byte for legacy branches to PLT. GDB is unware of the new layout of .plt and .plt.bnd. bfd/ * elf64-x86-64.c (elf_x86_64_bnd_plt0_entry): New. (elf_x86_64_legacy_plt_entry): Likewise. (elf_x86_64_bnd_plt_entry): Likewise. (elf_x86_64_legacy_plt2_entry): Likewise. (elf_x86_64_bnd_plt2_entry): Likewise. (elf_x86_64_bnd_arch_bed): Likewise. (elf_x86_64_link_hash_entry): Add has_bnd_reloc and plt_bnd. (elf_x86_64_link_hash_table): Add plt_bnd. (elf_x86_64_link_hash_newfunc): Initialize has_bnd_reloc and plt_bnd. (elf_x86_64_copy_indirect_symbol): Also copy has_bnd_reloc. (elf_x86_64_check_relocs): Create the second PLT for Intel MPX in 64-bit mode. (elf_x86_64_allocate_dynrelocs): Handle the second PLT for IFUNC symbols. Resolve call to the second PLT if it is created. (elf_x86_64_size_dynamic_sections): Keep the second PLT section. (elf_x86_64_relocate_section): Resolve PLT references to the second PLT if it is created. (elf_x86_64_finish_dynamic_symbol): Use BND PLT0 and fill the second PLT entry for BND relocation. (elf_x86_64_finish_dynamic_sections): Use MPX backend data if the second PLT is created. (elf_x86_64_get_synthetic_symtab): New. (bfd_elf64_get_synthetic_symtab): Likewise. Undefine for NaCl. ld/ * emulparams/elf_x86_64.sh (TINY_READONLY_SECTION): New. ld/testsuite/ * ld-x86-64/mpx.exp: Run bnd-ifunc-1 and bnd-plt-1. * ld-x86-64/bnd-ifunc-1.d: New file. * ld-x86-64/bnd-ifunc-1.s: Likewise. * ld-x86-64/bnd-plt-1.d: Likewise. 2013-11-20 17:01:04 +00:00			`#as: --64 -madd-bnd-prefix`
Add -z bndplt to generate BND prefix in PLT entries This patch adds "-z bndplt" option Linux/x86-64 linker to generate BND prefix in PLT entries. It also updated Linux/x86-64 assembler not to generate R_X86_64_PLT32_BND nor R_X86_64_PC32_BND relocations. bfd/ 2014-11-18 Igor Zamyatin <igor.zamyatin@intel.com> * elf64-x86-64.c (elf_x86_64_check_relocs): Enable MPX PLT only for -z bndplt. gas/ 2014-11-18 Igor Zamyatin <igor.zamyatin@intel.com> * config/tc-i386-intel.c (i386_operator): Remove last argument from lex_got call. * config/tc-i386.c (reloc): Remove bnd_prefix from parameters' list. Return always BFD_RELOC_32_PCREL. * (output_branch): Remove condition for BFD_RELOC_X86_64_PC32_BND. * (output_jump): Update call to reloc accordingly. * (output_interseg_jump): Likewise. * (output_disp): Likewise. * (output_imm): Likewise. * (x86_cons_fix_new): Likewise. * (lex_got): Remove bnd_prefix from parameters' list in macro and declarations. Don't use BFD_RELOC_X86_64_PLT32_BND. * (x86_cons): Update call to lex_got accordingly. * (i386_immediate): Likewise. * (i386_displacement): Likewise. * (md_apply_fix): Don't use BFD_RELOC_X86_64_PLT32_BND nor BFD_RELOC_X86_64_PC32_BND. * (tc_gen_reloc): Likewise. include/ 2014-11-18 Igor Zamyatin <igor.zamyatin@intel.com> * bfdlink.h (struct bfd_link_info): Add bndplt. ld/ 2014-11-18 Igor Zamyatin <igor.zamyatin@intel.com> * emulparams/elf_x86_64.sh (BNDPLT): Set to yes for x86_64. * emultempl/elf32.em (gld${EMULATION_NAME}_handle_option): Handle "-z bndplt" if BNDPLT is yes. (gld${EMULATION_NAME}_list_options): Add "-z bndplt" entry. * ld.texinfo: Add description for bndplt. ld/testsuite/ 2014-11-18 Igor Zamyatin <igor.zamyatin@intel.com> * testsuite/ld-x86-64/bnd-ifunc-1.d: Add bndplt option. * testsuite/ld-x86-64/bnd-ifunc-2.d: Likewise. * testsuite/ld-x86-64/bnd-plt-1.d: Likewise. Update dissassembly sections. * testsuite/ld-x86-64/mpx.exp: Handle mpx3 and mpx4 tests. * testsuite/ld-x86-64/mpx1a.rd: Remove _BND from relocation name. * testsuite/ld-x86-64/mpx1c.rd: Likewise. * testsuite/ld-x86-64/mpx2a.rd: Likewise. * testsuite/ld-x86-64/mpx2c.rd: Likewise. * testsuite/ld-x86-64/mpx3.dd: New file. * testsuite/ld-x86-64/mpx3a.s: Likewise. * testsuite/ld-x86-64/mpx3b.s: Likewise. * testsuite/ld-x86-64/mpx4.dd: Likewise. * testsuite/ld-x86-64/mpx4a.s: Likewise. * testsuite/ld-x86-64/mpx4b.s: Likewise. 2014-11-18 07:52:36 +00:00			`#ld: -shared -melf_x86_64 -z bndplt`
Create the second PLT for BND relocations Intel MPX introduces 4 bound registers, which will be used for parameter passing in x86-64. Bound registers are cleared by branch instructions. Branch instructions with BND prefix will keep bound register contents. This leads to 2 requirements to 64-bit MPX run-time: 1. Dynamic linker (ld.so) should save and restore bound registers during symbol lookup. 2. Change the current 16-byte PLT0: ff 35 08 00 00 00 pushq GOT+8(%rip) ff 25 00 10 00 jmpq GOT+16(%rip) 0f 1f 40 00 nopl 0x0(%rax) and 16-byte PLT1: ff 25 00 00 00 00 jmpq name@GOTPCREL(%rip) 68 00 00 00 00 pushq $index e9 00 00 00 00 jmpq PLT0 which clear bound registers, to preserve bound registers. We use 2 new relocations: to mark branch instructions with BND prefix. When linker sees any R_X86_64_PC32_BND or R_X86_64_PLT32_BND relocations, it switches to a different PLT0: ff 35 08 00 00 00 pushq GOT+8(%rip) f2 ff 25 00 10 00 bnd jmpq GOT+16(%rip) 0f 1f 00 nopl (%rax) to preserve bound registers for symbol lookup and it also creates an external PLT section, .pl.bnd. Linker will create a BND PLT1 entry in .plt: 68 00 00 00 00 pushq $index f2 e9 00 00 00 00 bnd jmpq PLT0 0f 1f 44 00 00 nopl 0(%rax,%rax,1) and a 8-byte BND PLT entry in .plt.bnd: f2 ff 25 00 00 00 00 bnd jmpq name@GOTPCREL(%rip) 90 nop Otherwise, linker will create a legacy PLT1 entry in .plt: 68 00 00 00 00 pushq $index e9 00 00 00 00 jmpq PLT0 66 0f 1f 44 00 00 nopw 0(%rax,%rax,1) and a 8-byte legacy PLT in .plt.bnd: ff 25 00 00 00 00 jmpq name@GOTPCREL(%rip) 66 90 xchg %ax,%ax The initial value of the GOT entry for "name" will be set to the the "pushq" instruction in the corresponding entry in .plt. Linker will resolve reference of symbol "name" to the entry in the second PLT, .plt.bnd. Prelink stores the offset of pushq of PLT1 (plt_base + 0x10) in GOT[1] and GOT[1] is stored in GOT[3]. We can undo prelink in GOT by computing the corresponding the pushq offset with GOT[1] + (GOT offset - &GOT[3]) 2 Since for each entry in .plt except for PLT0 we create a 8-byte entry in .plt.bnd, there is extra 8-byte per PLT symbol. We also investigated the 16-byte entry for .plt.bnd. We compared the 8-byte entry vs the the 16-byte entry for .plt.bnd on Sandy Bridge. There are no performance differences in SPEC CPU 2000/2006 as well as micro benchmarks. Pros: No change to undo prelink in dynamic linker. Only 8-byte memory overhead for each PLT symbol. Cons: Extra .plt.bnd section is needed. Extra 8 byte for legacy branches to PLT. GDB is unware of the new layout of .plt and .plt.bnd. bfd/ * elf64-x86-64.c (elf_x86_64_bnd_plt0_entry): New. (elf_x86_64_legacy_plt_entry): Likewise. (elf_x86_64_bnd_plt_entry): Likewise. (elf_x86_64_legacy_plt2_entry): Likewise. (elf_x86_64_bnd_plt2_entry): Likewise. (elf_x86_64_bnd_arch_bed): Likewise. (elf_x86_64_link_hash_entry): Add has_bnd_reloc and plt_bnd. (elf_x86_64_link_hash_table): Add plt_bnd. (elf_x86_64_link_hash_newfunc): Initialize has_bnd_reloc and plt_bnd. (elf_x86_64_copy_indirect_symbol): Also copy has_bnd_reloc. (elf_x86_64_check_relocs): Create the second PLT for Intel MPX in 64-bit mode. (elf_x86_64_allocate_dynrelocs): Handle the second PLT for IFUNC symbols. Resolve call to the second PLT if it is created. (elf_x86_64_size_dynamic_sections): Keep the second PLT section. (elf_x86_64_relocate_section): Resolve PLT references to the second PLT if it is created. (elf_x86_64_finish_dynamic_symbol): Use BND PLT0 and fill the second PLT entry for BND relocation. (elf_x86_64_finish_dynamic_sections): Use MPX backend data if the second PLT is created. (elf_x86_64_get_synthetic_symtab): New. (bfd_elf64_get_synthetic_symtab): Likewise. Undefine for NaCl. ld/ * emulparams/elf_x86_64.sh (TINY_READONLY_SECTION): New. ld/testsuite/ * ld-x86-64/mpx.exp: Run bnd-ifunc-1 and bnd-plt-1. * ld-x86-64/bnd-ifunc-1.d: New file. * ld-x86-64/bnd-ifunc-1.s: Likewise. * ld-x86-64/bnd-plt-1.d: Likewise. 2013-11-20 17:01:04 +00:00			`#objdump: -dw`

			`#...`
			`[ ][a-f0-9]+: f2 e8 f0 ff ff ff bnd callq 220 <\ABS\*\+0x228@plt>`
			`#pass`