[lld] 7e5f4ed - [lld-macho]Ensure canonicalization happen even for "skipped" referent sections.

[Vy Nguyen via llvm-commits]

Author: Vy Nguyen
Date: 2023-06-06T12:53:03-04:00
New Revision: 7e5f4ed5565892e33d7f2a504e8345459d5235e5

URL: https://github.com/llvm/llvm-project/commit/7e5f4ed5565892e33d7f2a504e8345459d5235e5
DIFF: https://github.com/llvm/llvm-project/commit/7e5f4ed5565892e33d7f2a504e8345459d5235e5.diff

LOG: [lld-macho]Ensure canonicalization happen even for "skipped" referent sections.

Details:

See bug report:  https://github.com/llvm/llvm-project/issues/63039

Differential Revision: https://reviews.llvm.org/D151824

Added: 
    lld/test/MachO/fold-dwarf-lsda.s

Modified: 
    lld/MachO/Writer.cpp

Removed: 
    


################################################################################
diff  --git a/lld/MachO/Writer.cpp b/lld/MachO/Writer.cpp
index d2d4adf6a2bbc..8c457ff692b87 100644
--- a/lld/MachO/Writer.cpp
+++ b/lld/MachO/Writer.cpp
@@ -674,11 +674,21 @@ void Writer::scanRelocations() {
 
     for (auto it = isec->relocs.begin(); it != isec->relocs.end(); ++it) {
       lld::macho::Reloc &r = *it;
+
+      // Canonicalize the referent so that later accesses in Writer won't
+      // have to worry about it.
+      if (auto *referentIsec = r.referent.dyn_cast<InputSection *>())
+        r.referent = referentIsec->canonical();
+
       if (target->hasAttr(r.type, RelocAttrBits::SUBTRAHEND)) {
         // Skip over the following UNSIGNED relocation -- it's just there as the
         // minuend, and doesn't have the usual UNSIGNED semantics. We don't want
         // to emit rebase opcodes for it.
-        it++;
+        ++it;
+        // Canonicalize the referent so that later accesses in Writer won't
+        // have to worry about it.
+        if (auto *referentIsec = it->referent.dyn_cast<InputSection *>())
+          it->referent = referentIsec->canonical();
         continue;
       }
       if (auto *sym = r.referent.dyn_cast<Symbol *>()) {
@@ -688,11 +698,6 @@ void Writer::scanRelocations() {
         if (!isa<Undefined>(sym) && validateSymbolRelocation(sym, isec, r))
           prepareSymbolRelocation(sym, isec, r);
       } else {
-        // Canonicalize the referent so that later accesses in Writer won't
-        // have to worry about it. Perhaps we should do this for Defined::isec
-        // too...
-        auto *referentIsec = r.referent.get<InputSection *>();
-        r.referent = referentIsec->canonical();
         if (!r.pcrel) {
           if (config->emitChainedFixups)
             in.chainedFixups->addRebase(isec, r.offset);

diff  --git a/lld/test/MachO/fold-dwarf-lsda.s b/lld/test/MachO/fold-dwarf-lsda.s
new file mode 100644
index 0000000000000..e651fa81b8b7a
--- /dev/null
+++ b/lld/test/MachO/fold-dwarf-lsda.s
@@ -0,0 +1,86 @@
+# REQUIRES: x86
+## Regression test for https://github.com/llvm/llvm-project/issues/63039
+
+## Use an old version to ensure we do *not* have any compact-unwind.
+# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-macos9 %s -o %t.o
+
+## Pre-cond: smoke-check that there is really no compact-unwind entries - only dwarfs.
+# RUN: llvm-objdump --macho --unwind-info --dwarf=frames %t.o | FileCheck %s --check-prefix=PRE
+# PRE-NOT: Contents of __compact_unwind section:
+# PRE-NOT: Entry at offset
+# PRE: .eh_frame contents:
+# PRE: {{[0-9a-f]+}} {{.*}} CIE
+# PRE:   Format:                DWARF32
+# PRE:   Version:               1
+
+## Link should succeed (ie., not crashed due to bug in icf code).
+# RUN: %lld -lSystem -lc++ --icf=all -arch x86_64 -arch x86_64 -platform_version macos 11.0 11.0 %t.o -o %t.out
+
+## Post-cond: verify that the final binary has expected eh-frame contents.
+# RUN: llvm-objdump --macho --syms --dwarf=frames %t.out | FileCheck %s --check-prefix=POST
+# POST-LABEL: SYMBOL TABLE:
+# POST: [[#%x,EXCEPT_ADDR:]] l   O __TEXT,__gcc_except_tab GCC_except_table0
+# POST: [[#%x,EXCEPT_ADDR]]  l   O __TEXT,__gcc_except_tab GCC_except_table1
+# POST: [[#%.16x,F0_ADDR:]]  g   F __TEXT,__text _f0
+# POST: [[#%.16x,F1_ADDR:]]  g   F __TEXT,__text _f1
+# POST: [[#%.16x,G_ADDR:]]   g   F __TEXT,__text _g
+
+# POST-LABEL: .eh_frame contents:
+# POST: {{.*}} FDE cie={{.+}} pc=[[#%x,G_ADDR]]...{{.+}}
+
+# POST: {{.*}} FDE cie={{.+}} pc=[[#%x,F0_ADDR]]...{{.+}}
+# POST: Format:       DWARF32 
+# POST: LSDA Address: [[#%.16x,EXCEPT_ADDR]]
+
+# POST: {{.*}} FDE cie={{.+}} pc=[[#%x,F1_ADDR]]...{{.+}}
+# POST Format:       DWARF32 
+# POST LSDA Address: [[#%.16x,EXCEPT_ADDR]]
+
+	.section        __TEXT,__text,regular,pure_instructions
+	.globl	_f0
+_f0:
+	.cfi_startproc
+	.cfi_lsda 16, Lexception0
+	.cfi_def_cfa_offset 16
+	.cfi_offset %rbp, -16
+	callq	_g
+	retq
+	.cfi_endproc
+	
+	.section	__TEXT,__gcc_except_tab
+GCC_except_table0:
+Lexception0:
+	.byte	255
+                                
+	.section	__TEXT,__text,regular,pure_instructions
+	.globl	_f1
+_f1:
+	.cfi_startproc
+	.cfi_lsda 16, Lexception1
+	.cfi_def_cfa_offset 16
+	.cfi_offset %rbp, -16
+	callq	_g
+	retq
+	.cfi_endproc
+	
+	.section	__TEXT,__gcc_except_tab
+GCC_except_table1:
+Lexception1:
+	.byte	255
+
+	.section	__TEXT,__text,regular,pure_instructions
+	.globl	_g
+_g:               
+	.cfi_startproc
+	.cfi_def_cfa_offset 16
+	.cfi_offset %rbp, -16
+	.cfi_def_cfa_register %rbp	
+	retq
+	.cfi_endproc
+	
+	.section	__TEXT,__text,regular,pure_instructions
+	.globl	_main             
+_main:                            
+	retq
+
+.subsections_via_symbols