[BOLT] Handle broken .dynsym in stripped binaries

[nhuhuan]

Summary

Strip tools cause a few symbols in .dynsym to have bad section index.
This update safely keeps such broken symbols intact.

Test Plan:

ninja check-bolt

[maksfb]

Looks good, but please add a test case.

[Amir]

We need a test case for this fix: yaml2obj test with a dynamic symbol table with wrong (out of bounds) index. We should check that BOLT keeps this index intact.

[nhuhuan]

Update test case.

[nhuhuan]

Simplified test.

[Amir]

Note for other reviewers: we were unable to get yaml input with a broken symbol section index (yaml2obj refuses to produce an object file). So this approach (yaml2obj + llvm-strip) is the closest we were able to get.

bolt/lib/Rewrite/RewriteInstance.cpp

if (Itr != IslandSizes.end())
       return Itr->second;
     return IslandSizes[&BF] = BF.estimateConstantIslandSize();
   };
 
   // Symbols for the new symbol table.
   std::vector<ELFSymTy> Symbols;
 
   auto getNewSectionIndex = [&](uint32_t OldIndex) {
+    // For dynamic symbol table, the section index could be wrong on the input,
+    // and its value is ignored by the runtime if it's different from
+    // SHN_UNDEF and SHN_ABS.
+    // However, we still need to update dynamic symbol table, so return a
+    // section index, even though the index is broken.
+    if (IsDynSym && OldIndex >= NewSectionIndex.size())
+      return OldIndex;
+
     assert(OldIndex < NewSectionIndex.size() && "section index out of bounds");
     const uint32_t NewIndex = NewSectionIndex[OldIndex];
 
     // We may have stripped the section that dynsym was referencing due to
     // the linker bug. In that case return the old index avoiding marking
     // the symbol as undefined.
     if (IsDynSym && NewIndex != OldIndex && NewIndex == ELF::SHN_UNDEF)
       return OldIndex;

bolt/test/X86/broken_dynsym.s

+# This test checks if BOLT can process stripped binaries, where symbol's section
+# header index is corrupted due to strip tool.
+
+# RUN: %clang++ %s -o %t -Wl,-q
+# RUN: llvm-strip -s %t
+# RUN: llvm-bolt %t -o %t.bolt
+
+  .text
+  .section  .text.startup,"ax",@progbits
+  .p2align  4, 0x90                         # -- Begin function __cxx_global_var_init
+  .type __cxx_global_var_init,@function
+__cxx_global_var_init:                  # @__cxx_global_var_init
+  .cfi_startproc
+# %bb.0:                                # %entry
+  pushq %rbp
+  .cfi_def_cfa_offset 16
+  .cfi_offset %rbp, -16
+  movq  %rsp, %rbp
+  .cfi_def_cfa_register %rbp
+  movabsq $_ZStL8__ioinit, %rdi
+  callq _ZNSt8ios_base4InitC1Ev
+  movabsq $_ZNSt8ios_base4InitD1Ev, %rdi
+  movabsq $_ZStL8__ioinit, %rsi
+  movabsq $__dso_handle, %rdx
+  callq __cxa_atexit
+  popq  %rbp
+  .cfi_def_cfa %rsp, 8
+  retq
+.Lfunc_end0:
+  .size __cxx_global_var_init, .Lfunc_end0-__cxx_global_var_init
+  .cfi_endproc
+                                        # -- End function
+  .text
+  .globl  main                            # -- Begin function main
+  .p2align  4, 0x90
+  .type main,@function
+main:                                   # @main
+  .cfi_startproc
+# %bb.0:                                # %entry
+  pushq %rbp
+  .cfi_def_cfa_offset 16
+  .cfi_offset %rbp, -16
+  movq  %rsp, %rbp
+  .cfi_def_cfa_register %rbp
+  subq  $32, %rsp
+  movl  $0, -4(%rbp)
+  movabsq $_ZSt4cout, %rdi
+  movabsq $.L.str, %rsi
+  callq _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
+  movabsq $_ZSt3cin, %rdi
+  leaq  -8(%rbp), %rsi
+  callq _ZNSirsERi
+  movq  %rax, %rdi
+  leaq  -12(%rbp), %rsi
+  callq _ZNSirsERi
+  movl  -12(%rbp), %eax
+  cmpl  -8(%rbp), %eax
+  jle .LBB1_2
+# %bb.1:                                # %if.then
+  movl  -12(%rbp), %eax
+  movl  %eax, -20(%rbp)
+  movl  -8(%rbp), %eax
+  movl  %eax, -12(%rbp)
+  movl  -20(%rbp), %eax
+  movl  %eax, -8(%rbp)
+.LBB1_2:                                # %if.end
+  movl  $1, -24(%rbp)
+.LBB1_3:                                # %for.cond
+                                        # =>This Inner Loop Header: Depth=1
+  movl  -24(%rbp), %eax
+  cmpl  -12(%rbp), %eax
+  jg  .LBB1_9
+# %bb.4:                                # %for.body
+                                        #   in Loop: Header=BB1_3 Depth=1
+  movl  -8(%rbp), %eax
+  cltd
+  idivl -24(%rbp)
+  cmpl  $0, %edx
+  jne .LBB1_7
+# %bb.5:                                # %land.lhs.true
+                                        #   in Loop: Header=BB1_3 Depth=1
+  movl  -12(%rbp), %eax
+  cltd
+  idivl -24(%rbp)
+  cmpl  $0, %edx
+  jne .LBB1_7
+# %bb.6:                                # %if.then7
+                                        #   in Loop: Header=BB1_3 Depth=1
+  movl  -24(%rbp), %eax
+  movl  %eax, -16(%rbp)
+.LBB1_7:                                # %if.end8
+                                        #   in Loop: Header=BB1_3 Depth=1
+  jmp .LBB1_8
+.LBB1_8:                                # %for.inc
+                                        #   in Loop: Header=BB1_3 Depth=1
+  movl  -24(%rbp), %eax
+  addl  $1, %eax
+  movl  %eax, -24(%rbp)
+  jmp .LBB1_3
+.LBB1_9:                                # %for.end
+  movabsq $_ZSt4cout, %rdi
+  movabsq $.L.str.1, %rsi
+  callq _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
+  movq  %rax, %rdi
+  movl  -16(%rbp), %esi
+  callq _ZNSolsEi
+  movq  %rax, %rdi
+  movabsq $.L.str.2, %rsi
+  callq _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
+  xorl  %eax, %eax
+  addq  $32, %rsp
+  popq  %rbp
+  .cfi_def_cfa %rsp, 8
+  retq
+.Lfunc_end1:
+  .size main, .Lfunc_end1-main
+  .cfi_endproc
+                                        # -- End function
+  .section  .text.startup,"ax",@progbits
+  .p2align  4, 0x90                         # -- Begin function _GLOBAL__sub_I_gcd.cpp
+  .type _GLOBAL__sub_I_gcd.cpp,@function
+_GLOBAL__sub_I_gcd.cpp:                 # @_GLOBAL__sub_I_gcd.cpp
+  .cfi_startproc
+# %bb.0:                                # %entry
+  pushq %rbp
+  .cfi_def_cfa_offset 16
+  .cfi_offset %rbp, -16
+  movq  %rsp, %rbp
+  .cfi_def_cfa_register %rbp
+  callq __cxx_global_var_init
+  popq  %rbp
+  .cfi_def_cfa %rsp, 8
+  retq
+.Lfunc_end2:
+  .size _GLOBAL__sub_I_gcd.cpp, .Lfunc_end2-_GLOBAL__sub_I_gcd.cpp
+  .cfi_endproc
+                                        # -- End function
+  .type _ZStL8__ioinit,@object          # @_ZStL8__ioinit
+  .local  _ZStL8__ioinit
+  .comm _ZStL8__ioinit,1,1
+  .hidden __dso_handle
+  .type .L.str,@object                  # @.str
+  .section  .rodata.str1.1,"aMS",@progbits,1
+.L.str:
+  .asciz  "Enter two numbers: "
+  .size .L.str, 20
+
+  .type .L.str.1,@object                # @.str.1
+.L.str.1:
+  .asciz  "Greatest common divisor = "
+  .size .L.str.1, 27
+
+  .type .L.str.2,@object                # @.str.2
+.L.str.2:
+  .asciz  "\n"
+  .size .L.str.2, 2
+
+  .section  .init_array,"aw",@init_array
+  .p2align  3
+  .quad _GLOBAL__sub_I_gcd.cpp
+  .ident  "clang version 15.0.0 (ssh://git.vip.facebook.com/data/gitrepos/osmeta/external/llvm-project 91ed9bd853620e163fda21b2f65a8ec2a3d8c867)"
+  .section  ".note.GNU-stack","",@progbits
+  .addrsig
+  .addrsig_sym __cxx_global_var_init
+  .addrsig_sym __cxa_atexit
+  .addrsig_sym _ZStlsISt11char_traitsIcEERSt13basic_ostreamIcT_ES5_PKc
+  .addrsig_sym _ZNSirsERi
+  .addrsig_sym _ZNSolsEi
+  .addrsig_sym _GLOBAL__sub_I_gcd.cpp
+  .addrsig_sym _ZStL8__ioinit
+  .addrsig_sym __dso_handle
+  .addrsig_sym _ZSt4cout
+  .addrsig_sym _ZSt3cin