[lld-macho] Don't emit rebase opcodes for subtractor minuend relocs
Also add a few asserts to verify that we are indeed handling an
UNSIGNED relocation as the minued. I haven't made it an actual
user-facing error since I don't think llvm-mc is capable of generating
SUBTRACTOR relocations without an associated UNSIGNED.
Reviewed By: #lld-macho, smeenai
Differential Revision: https://reviews.llvm.org/D97103
GitOrigin-RevId: 541390131ef72a8dad93c936d816279c8b76374e
diff --git a/MachO/Arch/ARM64.cpp b/MachO/Arch/ARM64.cpp
index d70574c..8428ef4 100644
--- a/MachO/Arch/ARM64.cpp
+++ b/MachO/Arch/ARM64.cpp
@@ -47,7 +47,6 @@
// Random notes on reloc types:
// ADDEND always pairs with BRANCH26, PAGE21, or PAGEOFF12
-// SUBTRACTOR always pairs with UNSIGNED (a delta between two sections)
// POINTER_TO_GOT: ld64 supports a 4-byte pc-relative form as well as an 8-byte
// absolute version of this relocation. The semantics of the absolute relocation
// are weird -- it results in the value of the GOT slot being written, instead
diff --git a/MachO/InputFiles.cpp b/MachO/InputFiles.cpp
index 249cde3..9203022 100644
--- a/MachO/InputFiles.cpp
+++ b/MachO/InputFiles.cpp
@@ -287,6 +287,10 @@
p.type = relInfo.r_type;
p.referent = symbols[relInfo.r_symbolnum];
relInfo = relInfos[++i];
+ // SUBTRACTOR relocations should always be followed by an UNSIGNED one
+ // indicating the minuend symbol.
+ assert(target->hasAttr(relInfo.r_type, RelocAttrBits::UNSIGNED) &&
+ relInfo.r_extern);
}
Reloc r;
r.type = relInfo.r_type;
@@ -317,8 +321,7 @@
}
InputSection *subsec = findContainingSubsection(subsecMap, &r.offset);
- if (p.type != GENERIC_RELOC_INVALID &&
- target->hasAttr(p.type, RelocAttrBits::SUBTRAHEND))
+ if (p.type != GENERIC_RELOC_INVALID)
subsec->relocs.push_back(p);
subsec->relocs.push_back(r);
}
diff --git a/MachO/InputSection.cpp b/MachO/InputSection.cpp
index 971ca64..33f79dd 100644
--- a/MachO/InputSection.cpp
+++ b/MachO/InputSection.cpp
@@ -59,13 +59,13 @@
for (size_t i = 0; i < relocs.size(); i++) {
auto *fromSym = target->hasAttr(relocs[i].type, RelocAttrBits::SUBTRAHEND)
- ? relocs[i++].referent.dyn_cast<Symbol *>()
+ ? relocs[i++].referent.get<Symbol *>()
: nullptr;
const Reloc &r = relocs[i];
uint8_t *loc = buf + r.offset;
uint64_t referentVA = 0;
if (fromSym) {
- auto *toSym = r.referent.dyn_cast<Symbol *>();
+ auto *toSym = r.referent.get<Symbol *>();
referentVA = toSym->getVA() - fromSym->getVA();
} else if (auto *referentSym = r.referent.dyn_cast<Symbol *>()) {
if (target->hasAttr(r.type, RelocAttrBits::LOAD) &&
diff --git a/MachO/Target.h b/MachO/Target.h
index f07a69e..4ad833f 100644
--- a/MachO/Target.h
+++ b/MachO/Target.h
@@ -52,6 +52,7 @@
UNSIGNED = 1 << 14, // *_UNSIGNED relocs
LLVM_MARK_AS_BITMASK_ENUM(/*LargestValue*/ (1 << 15) - 1),
};
+// Note: SUBTRACTOR always pairs with UNSIGNED (a delta between two symbols).
class TargetInfo {
public:
diff --git a/MachO/Writer.cpp b/MachO/Writer.cpp
index a0b3ac4..56da22c 100644
--- a/MachO/Writer.cpp
+++ b/MachO/Writer.cpp
@@ -449,9 +449,16 @@
continue;
}
- for (Reloc &r : isec->relocs) {
- if (target->hasAttr(r.type, RelocAttrBits::SUBTRAHEND))
+ for (auto it = isec->relocs.begin(); it != isec->relocs.end(); ++it) {
+ Reloc &r = *it;
+ 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 = std::next(it);
+ assert(isa<Defined>(it->referent.dyn_cast<lld::macho::Symbol *>()));
continue;
+ }
if (auto *sym = r.referent.dyn_cast<lld::macho::Symbol *>()) {
if (auto *undefined = dyn_cast<Undefined>(sym))
treatUndefinedSymbol(*undefined);
diff --git a/test/MachO/reloc-subtractor.s b/test/MachO/reloc-subtractor.s
index 14355f3..e445184 100644
--- a/test/MachO/reloc-subtractor.s
+++ b/test/MachO/reloc-subtractor.s
@@ -3,9 +3,9 @@
# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-darwin %s -o %t/x86_64.o
# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %s -o %t/arm64.o
# RUN: %lld -lSystem %t/x86_64.o -o %t/x86_64
-# RUN: llvm-objdump --syms --full-contents %t/x86_64 | FileCheck %s
+# RUN: llvm-objdump --syms --full-contents --rebase %t/x86_64 | FileCheck %s
# RUN: %lld -arch arm64 -lSystem %t/arm64.o -o %t/arm64
-# RUN: llvm-objdump --syms --full-contents %t/arm64 | FileCheck %s
+# RUN: llvm-objdump --syms --full-contents --rebase %t/arm64 | FileCheck %s
# CHECK-LABEL: SYMBOL TABLE:
# CHECK: {{0*}}[[#%x, SUB1ADDR:]] l {{.*}} __DATA,__data _sub1
@@ -17,6 +17,9 @@
# CHECK-NEXT: [[#SUB2ADDR]] f0ffffff
# CHECK-NEXT: [[#SUB3ADDR]] 10000000 00000000
# CHECK-NEXT: [[#SUB4ADDR]] f0ffffff ffffffff
+# CHECK: Rebase table:
+# CHECK-NEXT: segment section address type
+# CHECK-EMPTY:
.globl _main, _subtrahend_1, _subtrahend_2, _minued1, _minued2
