[lld] [lld-macho] Add support for category names in ConcatInputSection's (PR #90850)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-lld-macho

Author: None (alx32)

<details>
<summary>Changes</summary>

In some cases we see strings from categories being part of "data" sections (Ex:`__objc_const`), not part of of sections marked as `cstring_literals`. Since lld treats these sections differently we need to explicitly implement support for reading strings from the non-`cstring_literals` sections.

Adding a test that previously would result in an assert.

---
Full diff: https://github.com/llvm/llvm-project/pull/90850.diff


2 Files Affected:

- (modified) lld/MachO/ObjC.cpp (+14-3) 
- (modified) lld/test/MachO/objc-category-merging-extern-class-minimal.s (+1-1) 


``````````diff
diff --git a/lld/MachO/ObjC.cpp b/lld/MachO/ObjC.cpp
index 95fe0c9374f150..68a8645532dff6 100644
--- a/lld/MachO/ObjC.cpp
+++ b/lld/MachO/ObjC.cpp
@@ -186,13 +186,24 @@ ObjcCategoryChecker::ObjcCategoryChecker()
       roClassLayout(target->wordSize), listHeaderLayout(target->wordSize),
       methodLayout(target->wordSize) {}
 
-// \p r must point to an offset within a cstring section.
+// \p r must point to an offset within a CStringInputSection or a
+// ConcatInputSection
 static StringRef getReferentString(const Reloc &r) {
   if (auto *isec = r.referent.dyn_cast<InputSection *>())
     return cast<CStringInputSection>(isec)->getStringRefAtOffset(r.addend);
   auto *sym = cast<Defined>(r.referent.get<Symbol *>());
-  return cast<CStringInputSection>(sym->isec())
-      ->getStringRefAtOffset(sym->value + r.addend);
+  if (isa<CStringInputSection>(sym->isec()))
+    return cast<CStringInputSection>(sym->isec())
+        ->getStringRefAtOffset(sym->value + r.addend);
+
+  if (isa<ConcatInputSection>(sym->isec())) {
+    auto &data = sym->isec()->data;
+    const char *pDataStart = reinterpret_cast<const char *>(data.data());
+    uint32_t len = strnlen(pDataStart + sym->value, data.size() - sym->value);
+    return StringRef(pDataStart + sym->value, len);
+  }
+
+  llvm_unreachable("unknown reference section in getReferentString");
 }
 
 void ObjcCategoryChecker::parseMethods(const ConcatInputSection *methodsIsec,
diff --git a/lld/test/MachO/objc-category-merging-extern-class-minimal.s b/lld/test/MachO/objc-category-merging-extern-class-minimal.s
index ede7ef5d9c32d4..3e220ef372ca0d 100644
--- a/lld/test/MachO/objc-category-merging-extern-class-minimal.s
+++ b/lld/test/MachO/objc-category-merging-extern-class-minimal.s
@@ -118,7 +118,7 @@ __OBJC_$_CATEGORY_MyBaseClass_$_Category01:
 	.quad	0
 	.long	64                              ; 0x40
 	.space	4
-	.section	__TEXT,__objc_classname,cstring_literals
+	.section	__DATA,__objc_const
 l_OBJC_CLASS_NAME_.1:                   ; @OBJC_CLASS_NAME_.1
 	.asciz	"Category02"
 	.section	__TEXT,__objc_methname,cstring_literals

``````````

</details>


https://github.com/llvm/llvm-project/pull/90850