From 58e2dde45f775328b71b532e65762a9696ccccbd Mon Sep 17 00:00:00 2001 From: Joshua Haberman Date: Fri, 21 Nov 2025 17:03:40 -0800 Subject: [lld:MachO] Allow independent override of weak symbols aliased via .set (#167825) Currently, if multiple external weak symbols are defined at the same address in an object file (e.g., by using the .set assembler directive to alias them to a single weak variable), ld64.lld treats them as a single unit. When any one of these symbols is overridden by a strong definition, all of the original weak symbols resolve to the strong definition. This patch changes the behavior in `transplantSymbolsAtOffset`. When a weak symbol is being replaced by a strong one, only non-external (local) symbols at the same offset are moved to the new symbol's section. Other *external* symbols are no longer transplanted. This allows each external weak symbol to be overridden independently. This behavior is consistent with Apple's ld-classic, but diverges from ld-prime in one case, as noted on https://github.com/llvm/llvm-project/issues/167262 (this discrepancy has recently been reported to Apple). ### Backward Compatibility This change alters linker behavior for a specific scenario. The creation of multiple external weak symbols aliased to the same address via assembler directives is primarily an advanced technique. It's unlikely that existing builds rely on the current behavior of all aliases being overridden together. If there are concerns, this could be put behind a linker option, but the new default seems more correct, less surprising, and is consistent with ld-classic. ### Testing The new lit test `test/MachO/weak-alias-override.s` verifies this behavior using llvm-nm. Fixes #167262 --- lld/MachO/SymbolTable.cpp | 35 ++++++------- lld/test/MachO/weak-alias-override.s | 97 ++++++++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+), 17 deletions(-) create mode 100644 lld/test/MachO/weak-alias-override.s diff --git a/lld/MachO/SymbolTable.cpp b/lld/MachO/SymbolTable.cpp index baddddcb76fb..a7db5a3ac96e 100644 --- a/lld/MachO/SymbolTable.cpp +++ b/lld/MachO/SymbolTable.cpp @@ -61,8 +61,8 @@ struct DuplicateSymbolDiag { SmallVector dupSymDiags; } // namespace -// Move symbols at \p fromOff in \p fromIsec into \p toIsec, unless that symbol -// is \p skip. +// Move local symbols at \p fromOff in \p fromIsec into \p toIsec, unless that +// symbol is \p skip, in which case we just remove it. static void transplantSymbolsAtOffset(InputSection *fromIsec, InputSection *toIsec, Defined *skip, uint64_t fromOff, uint64_t toOff) { @@ -78,22 +78,23 @@ static void transplantSymbolsAtOffset(InputSection *fromIsec, auto insertIt = llvm::upper_bound(toIsec->symbols, toOff, symSucceedsOff); llvm::erase_if(fromIsec->symbols, [&](Symbol *s) { auto *d = cast(s); - if (d->value != fromOff) + if (d == skip) + return true; + if (d->value != fromOff || d->isExternal()) return false; - if (d != skip) { - // This repeated insertion will be quadratic unless insertIt is the end - // iterator. However, that is typically the case for files that have - // .subsections_via_symbols set. - insertIt = toIsec->symbols.insert(insertIt, d); - d->originalIsec = toIsec; - d->value = toOff; - // We don't want to have more than one unwindEntry at a given address, so - // drop the redundant ones. We We can safely drop the unwindEntries of - // the symbols in fromIsec since we will be adding another unwindEntry as - // we finish parsing toIsec's file. (We can assume that toIsec has its - // own unwindEntry because of the ODR.) - d->originalUnwindEntry = nullptr; - } + + // This repeated insertion will be quadratic unless insertIt is the end + // iterator. However, that is typically the case for files that have + // .subsections_via_symbols set. + insertIt = toIsec->symbols.insert(insertIt, d); + d->originalIsec = toIsec; + d->value = toOff; + // We don't want to have more than one unwindEntry at a given address, so + // drop the redundant ones. We can safely drop the unwindEntries of the + // symbols in fromIsec since we will be adding another unwindEntry as we + // finish parsing toIsec's file. (We can assume that toIsec has its own + // unwindEntry because of the ODR.) + d->originalUnwindEntry = nullptr; return true; }); } diff --git a/lld/test/MachO/weak-alias-override.s b/lld/test/MachO/weak-alias-override.s new file mode 100644 index 000000000000..224ddc4ec38d --- /dev/null +++ b/lld/test/MachO/weak-alias-override.s @@ -0,0 +1,97 @@ +# REQUIRES: x86 +# RUN: rm -rf %t; split-file %s %t +# RUN: mkdir -p %t/bin + +# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-macos -o %t/weak.o %t/weak.s +# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-macos -o %t/strong_a.o %t/strong_a.s +# RUN: llvm-mc -filetype=obj -triple=x86_64-apple-macos -o %t/strong_b.o %t/strong_b.s + +# --- Test Case 1: No overrides +# RUN: %lld %t/weak.o -o %t/bin/alone -e _s +# RUN: llvm-nm -am %t/bin/alone | FileCheck --check-prefix=NM_ALONE %s + +# NM_ALONE: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_ALONE: [[#P_ADDR]] (__TEXT,__const) weak external _weak_a +# NM_ALONE: [[#P_ADDR]] (__TEXT,__const) weak external _weak_b + +# --- Test Case 2: Override weak_a +# RUN: %lld %t/weak.o %t/strong_a.o -o %t/bin/with_a -e _s +# RUN: llvm-nm -am %t/bin/with_a | FileCheck --check-prefix=NM_WITH_A %s +# RUN: llvm-nm -am %t/bin/with_a | FileCheck --check-prefix=NM_WITH_A_BAD %s + +# NM_WITH_A: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_WITH_A: [[#%x, A_ADDR:]] (__TEXT,__const) external _strong_a +# NM_WITH_A: [[#A_ADDR]] (__TEXT,__const) external _weak_a +# NM_WITH_A: [[#P_ADDR]] (__TEXT,__const) weak external _weak_b + +# --- Addresses of _placeholder_int and _strong_a must not match. +# NM_WITH_A_BAD: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_WITH_A_BAD-NOT: [[#P_ADDR]] (__TEXT,__const) external _strong_a + +# --- Test Case 3: Override weak_b +# RUN: %lld %t/weak.o %t/strong_b.o -o %t/bin/with_b -e _s +# RUN: llvm-nm -am %t/bin/with_b | FileCheck --check-prefix=NM_WITH_B %s +# RUN: llvm-nm -am %t/bin/with_b | FileCheck --check-prefix=NM_WITH_B_BAD %s + +# NM_WITH_B: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_WITH_B: [[#%x, B_ADDR:]] (__TEXT,__const) external _strong_b +# NM_WITH_B: [[#P_ADDR]] (__TEXT,__const) weak external _weak_a +# NM_WITH_B: [[#B_ADDR]] (__TEXT,__const) external _weak_b + +# --- Addresses of _placeholder_int and _strong_a must not match. +# NM_WITH_B_BAD: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_WITH_B_BAD-NOT: [[#P_ADDR]] (__TEXT,__const) external _strong_b + +# --- Test Case 4: Override weak_a and weak_b +# RUN: %lld %t/weak.o %t/strong_a.o %t/strong_b.o -o %t/bin/with_ab -e _s +# RUN: llvm-nm -am %t/bin/with_ab | FileCheck --check-prefix=NM_WITH_AB %s +# RUN: llvm-nm -am %t/bin/with_ab | FileCheck --check-prefix=NM_WITH_AB_BAD %s + +# NM_WITH_AB: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_WITH_AB: [[#%x, A_ADDR:]] (__TEXT,__const) external _strong_a +# NM_WITH_AB: [[#%x, B_ADDR:]] (__TEXT,__const) external _strong_b +# NM_WITH_AB: [[#A_ADDR]] (__TEXT,__const) external _weak_a +# NM_WITH_AB: [[#B_ADDR]] (__TEXT,__const) external _weak_b + +# --- Addresses of _placeholder_int, _strong_a, and _strong_b must all be distinct +# NM_WITH_AB_BAD: [[#%x, P_ADDR:]] (__TEXT,__const) weak external _placeholder_int +# NM_WITH_AB_BAD-NOT: [[#P_ADDR]] (__TEXT,__const) external _strong_a +# NM_WITH_AB_BAD-NOT: [[#P_ADDR]] (__TEXT,__const) external _strong_b + +#--- weak.s +.section __TEXT,__const +.globl _placeholder_int +.weak_definition _placeholder_int +_placeholder_int: + .long 0 + +.globl _weak_a +.set _weak_a, _placeholder_int +.weak_definition _weak_a + +.globl _weak_b +.set _weak_b, _placeholder_int +.weak_definition _weak_b + +.globl _s +_s: + .quad _weak_a + .quad _weak_b + +#--- strong_a.s +.section __TEXT,__const +.globl _strong_a +_strong_a: + .long 1 + +.globl _weak_a +_weak_a = _strong_a + +#--- strong_b.s +.section __TEXT,__const +.globl _strong_b +_strong_b: + .long 2 + +.globl _weak_b +_weak_b = _strong_b -- cgit v1.2.3