diff --git a/bolt/include/bolt/Core/BinaryFunction.h b/bolt/include/bolt/Core/BinaryFunction.h --- a/bolt/include/bolt/Core/BinaryFunction.h +++ b/bolt/include/bolt/Core/BinaryFunction.h @@ -172,6 +172,9 @@ mutable MCSymbol *FunctionConstantIslandLabel{nullptr}; mutable MCSymbol *FunctionColdConstantIslandLabel{nullptr}; + + // Returns constant island alignment + uint16_t getAlignment() const { return sizeof(uint64_t); } }; static constexpr uint64_t COUNT_NO_PROFILE = @@ -2047,6 +2050,10 @@ return *std::prev(CodeIter) <= *DataIter; } + uint16_t getConstantIslandAlignment() const { + return Islands ? Islands->getAlignment() : 1; + } + uint64_t estimateConstantIslandSize(const BinaryFunction *OnBehalfOf = nullptr) const { if (!Islands) @@ -2074,9 +2081,13 @@ Size += NextMarker - *DataIter; } - if (!OnBehalfOf) - for (BinaryFunction *ExternalFunc : Islands->Dependency) + if (!OnBehalfOf) { + for (BinaryFunction *ExternalFunc : Islands->Dependency) { + Size = alignTo(Size, ExternalFunc->getConstantIslandAlignment()); Size += ExternalFunc->estimateConstantIslandSize(this); + } + } + return Size; } diff --git a/bolt/lib/Core/BinaryEmitter.cpp b/bolt/lib/Core/BinaryEmitter.cpp --- a/bolt/lib/Core/BinaryEmitter.cpp +++ b/bolt/lib/Core/BinaryEmitter.cpp @@ -500,6 +500,13 @@ if (Islands.DataOffsets.empty() && Islands.Dependency.empty()) return; + // AArch64 requires CI to be aligned to 8 bytes due to access instructions + // restrictions. E.g. the ldr with imm, where imm must be aligned to 8 bytes. + const uint16_t Alignment = OnBehalfOf + ? OnBehalfOf->getConstantIslandAlignment() + : BF.getConstantIslandAlignment(); + Streamer.emitCodeAlignment(Alignment, &*BC.STI); + if (!OnBehalfOf) { if (!EmitColdPart) Streamer.emitLabel(BF.getFunctionConstantIslandLabel()); diff --git a/bolt/lib/Passes/LongJmp.cpp b/bolt/lib/Passes/LongJmp.cpp --- a/bolt/lib/Passes/LongJmp.cpp +++ b/bolt/lib/Passes/LongJmp.cpp @@ -308,6 +308,7 @@ LLVM_DEBUG(dbgs() << Func->getPrintName() << " cold tentative: " << Twine::utohexstr(DotAddress) << "\n"); DotAddress += Func->estimateColdSize(); + DotAddress = alignTo(DotAddress, Func->getConstantIslandAlignment()); DotAddress += Func->estimateConstantIslandSize(); } return DotAddress; @@ -364,6 +365,8 @@ DotAddress += Func->estimateSize(); else DotAddress += Func->estimateHotSize(); + + DotAddress = alignTo(DotAddress, Func->getConstantIslandAlignment()); DotAddress += Func->estimateConstantIslandSize(); ++CurrentIndex; } diff --git a/bolt/test/AArch64/constant-island-alignment.s b/bolt/test/AArch64/constant-island-alignment.s new file mode 100644 --- /dev/null +++ b/bolt/test/AArch64/constant-island-alignment.s @@ -0,0 +1,38 @@ +// This test checks that the constant island is aligned after BOLT tool. +// In case the nop before .Lci will be removed the pointer to exit function +// won't be alinged and the test will fail. + +# RUN: llvm-mc -filetype=obj -triple aarch64-unknown-unknown \ +# RUN: %s -o %t.o +# RUN: %clang %cflags -fPIC -pie %t.o -o %t.exe -Wl,-q \ +# RUN: -nostartfiles -nodefaultlibs -lc +# RUN: llvm-bolt %t.exe -o %t.bolt -use-old-text=0 -lite=0 -trap-old-code +# RUN: llvm-objdump -d --disassemble-symbols='$d' %t.bolt | FileCheck %s + +.text +.align 4 +.global +.type dummy, %function +dummy: + add x0, x0, #1 + ret + +.global +.type exitOk, %function +exitOk: + mov x0, #0 + bl exit + +.global _start +.type _start, %function +_start: + adrp x0, .Lci + ldr x0, [x0, #:lo12:.Lci] + blr x0 + mov x1, #1 + bl exit + nop +# CHECK: {{0|8}} <$d>: +.Lci: + .xword exitOk + .xword 0 diff --git a/bolt/test/runtime/AArch64/adrrelaxationpass.s b/bolt/test/runtime/AArch64/adrrelaxationpass.s --- a/bolt/test/runtime/AArch64/adrrelaxationpass.s +++ b/bolt/test/runtime/AArch64/adrrelaxationpass.s @@ -41,9 +41,9 @@ .word 0xff # CHECK:
: -# CHECK-NEXT: adr x0, #28 +# CHECK-NEXT: adr x0, #{{[0-9][0-9]*}} # CHECK-NEXT: adrp x1, 0x{{[1-8a-f][0-9a-f]*}} # CHECK-NEXT: add x1, x1, #{{[1-8a-f][0-9a-f]*}} # CHECK-NEXT: adrp x2, 0x{{[1-8a-f][0-9a-f]*}} # CHECK-NEXT: add x2, x2, #{{[1-8a-f][0-9a-f]*}} -# CHECK-NEXT: adr x3, #4 +# CHECK-NEXT: adr x3, #{{[0-9][0-9]*}}