Index: lld/MachO/ConcatOutputSection.cpp =================================================================== --- lld/MachO/ConcatOutputSection.cpp +++ lld/MachO/ConcatOutputSection.cpp @@ -57,14 +57,14 @@ // implement thunks. TODO: Adding support for branch islands! // // Internally -- as expressed in LLD's data structures -- a -// branch-range-extension thunk comprises ... +// branch-range-extension thunk consists of: // -// (1) new Defined privateExtern symbol for the thunk named +// (1) new Defined symbol for the thunk named // .thunk., which references ... // (2) new InputSection, which contains ... // (3.1) new data for the instructions to load & branch to the far address + // (3.2) new Relocs on instructions to load the far address, which reference ... -// (4.1) existing Defined extern symbol for the real function in __text, or +// (4.1) existing Defined symbol for the real function in __text, or // (4.2) existing DylibSymbol for the real function in a dylib // // Nearly-optimal thunk-placement algorithm features: @@ -89,8 +89,8 @@ // goes out of range, we increment the sequence number and create a new // thunk named .thunk.. // -// * A thunk incarnation comprises (a) private-extern Defined symbol pointing -// to (b) an InputSection holding machine instructions (similar to a MachO +// * A thunk consists of (a) a Defined symbol pointing to +// (b) an InputSection holding machine instructions (similar to a MachO // stub), and (c) Reloc(s) that reference the real function for fixing-up // the stub code. // @@ -323,11 +323,20 @@ StringRef thunkName = saver().save(funcSym->getName() + ".thunk." + std::to_string(thunkInfo.sequence++)); - r.referent = thunkInfo.sym = symtab->addDefined( - thunkName, /*file=*/nullptr, thunkInfo.isec, /*value=*/0, - /*size=*/thunkSize, /*isWeakDef=*/false, /*isPrivateExtern=*/true, - /*isThumb=*/false, /*isReferencedDynamically=*/false, - /*noDeadStrip=*/false, /*isWeakDefCanBeHidden=*/false); + if (!isa(funcSym) || cast(funcSym)->isExternal()) { + r.referent = thunkInfo.sym = symtab->addDefined( + thunkName, /*file=*/nullptr, thunkInfo.isec, /*value=*/0, + thunkSize, /*isWeakDef=*/false, /*isPrivateExtern=*/true, + /*isThumb=*/false, /*isReferencedDynamically=*/false, + /*noDeadStrip=*/false, /*isWeakDefCanBeHidden=*/false); + } else { + r.referent = thunkInfo.sym = make( + thunkName, /*file=*/nullptr, thunkInfo.isec, /*value=*/0, + thunkSize, /*isWeakDef=*/false, /*isExternal=*/false, + /*isPrivateExtern=*/true, /*isThumb=*/false, + /*isReferencedDynamically=*/false, /*noDeadStrip=*/false, + /*isWeakDefCanBeHidden=*/false); + } thunkInfo.sym->used = true; target->populateThunk(thunkInfo.isec, funcSym); finalizeOne(thunkInfo.isec); Index: lld/test/MachO/arm64-thunk-starvation.s =================================================================== --- lld/test/MachO/arm64-thunk-starvation.s +++ lld/test/MachO/arm64-thunk-starvation.s @@ -18,7 +18,7 @@ ## Currently leaves 12 bytes for one thunk, so 36 bytes. ## Uses < instead of <=, so 40 bytes. -.global _spacer1, _spacer1 +.global _spacer1, _spacer2 ## 0x8000000 is 128 MiB, one more than the forward branch limit, ## distributed over two functions since our thunk insertion algorithm ## can't deal with a single function that's 128 MiB. Index: lld/test/MachO/arm64-thunk-visibility.s =================================================================== --- /dev/null +++ lld/test/MachO/arm64-thunk-visibility.s @@ -0,0 +1,83 @@ +# REQUIRES: aarch64 + +# foo.s and bar.s both contain TU-local symbols (think static function) +# with the same name, and both need a thunk.. This tests that ld64.lld doesn't +# create a duplicate symbol for the two functions. + +# Test this both when the TU-local symbol is the branch source or target, +# and for both forward and backwards jumps. + +# RUN: rm -rf %t; split-file %s %t +# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %t/foo.s -o %t/foo.o +# RUN: llvm-mc -filetype=obj -triple=arm64-apple-darwin %t/bar.s -o %t/bar.o +# RUN: %lld -arch arm64 -lSystem -o %t.out %t/foo.o %t/bar.o + +#--- foo.s + +.subsections_via_symbols + +# Note: No .globl, since these are TU-local symbols. +.p2align 2 +_early_jumping_local_fn: b _some_late_external +.p2align 2 +_early_landing_local_fn: ret + +.globl _some_early_external +.p2align 2 +_some_early_external: b _late_landing_local_fn + +## 0x8000000 is 128 MiB, one more than the forward branch limit. +## Distribute that over two functions since our thunk insertion algorithm +## can't deal with a single function that's 128 MiB. +.global _spacer1, _spacer2 +_spacer1: +.space 0x4000000 +_spacer2: +.space 0x4000000 + +# Note: No .globl, since these are TU-local symbols. +.p2align 2 +_late_jumping_local_fn: b _some_early_external +.p2align 2 +_late_landing_local_fn: ret + +.globl _some_late_external +.p2align 2 +_some_late_external: b _early_landing_local_fn + +#--- bar.s + +.subsections_via_symbols + +# Note: No .globl, since these are TU-local symbols. +.p2align 2 +_early_jumping_local_fn: b _some_other_late_external +.p2align 2 +_early_landing_local_fn: ret + +.globl _some_other_early_external +.p2align 2 +_some_other_early_external: b _late_landing_local_fn + +## 0x8000000 is 128 MiB, one more than the forward branch limit. +## Distribute that over two functions since our thunk insertion algorithm +## can't deal with a single function that's 128 MiB. +.global _other_spacer1, _other_spacer1 +_spacer1: +.space 0x4000000 +_spacer2: +.space 0x4000000 + +# Note: No .globl, since these are TU-local symbols. +.p2align 2 +_late_jumping_local_fn: b _some_other_early_external +.p2align 2 +_late_landing_local_fn: ret + +.globl _some_other_late_external +.p2align 2 +_some_other_late_external: b _early_landing_local_fn + +.globl _main +_main: + ret