From ec786906f5feb4dceba1b5338927079e63e78095 Mon Sep 17 00:00:00 2001 From: Fangrui Song Date: Thu, 30 Apr 2020 22:15:05 -0700 Subject: [PATCH] [llvm-objcopy] -O binary: skip empty sections After SHF_ALLOC sections are ordered by LMA: * If initial sections are empty, GNU objcopy skips their contents while we emit leading zeros. (binary-paddr.test %t4) * If trailing sections are empty, GNU objcopy skips their contents while we emit trailing zeros. (binary-paddr.test %t5) This patch matches GNU objcopy's behavior. Linkers don't keep p_memsz PT_LOAD segments. Such empty sections would not have a containing PT_LOAD and `Section::ParentSegment` might be null if linkers fail to optimize the file offsets (lld D79254). In particular, without D79254, the arm Linux kernel's multi_v5_defconfig depends on this behavior: in `vmlinux`, an empty .text_itcm is mapped at a very high address (0xfffe0000) but the kernel does not expect `objcopy -O binary` to create a very large `arch/arm/boot/Image` (0xfffe0000-0xc0000000 ~= 1GiB). See https://bugs.llvm.org/show_bug.cgi?id=45632 Reviewed By: jhenderson Differential Revision: https://reviews.llvm.org/D79229 --- .../tools/llvm-objcopy/ELF/binary-paddr.test | 59 ++++++++++++++++++- llvm/tools/llvm-objcopy/ELF/Object.cpp | 13 ++-- 2 files changed, 64 insertions(+), 8 deletions(-) diff --git a/llvm/test/tools/llvm-objcopy/ELF/binary-paddr.test b/llvm/test/tools/llvm-objcopy/ELF/binary-paddr.test index fd78d436930d..f7974a60ffd6 100644 --- a/llvm/test/tools/llvm-objcopy/ELF/binary-paddr.test +++ b/llvm/test/tools/llvm-objcopy/ELF/binary-paddr.test @@ -48,7 +48,7 @@ ProgramHeaders: # RUN: od -A x -t x2 %t2.out | FileCheck %s --check-prefix=CHECK2 --ignore-case # RUN: wc -c %t2.out | FileCheck %s --check-prefix=SIZE2 -## The computed LMA of .data is 0x4000. The minimum LMA of all sections is 0x1000. +## The computed LMA of .data is 0x4000. The minimum LMA of all non-empty sections is 0x1000. ## The content of .data will be written at 0x4000-0x1000 = 0x3000. # CHECK2: 000000 c3c3 c3c3 0000 0000 0000 0000 0000 0000 # CHECK2-NEXT: 000010 0000 0000 0000 0000 0000 0000 0000 0000 @@ -93,7 +93,7 @@ ProgramHeaders: # RUN: od -A x -t x2 %t3.out | FileCheck %s --check-prefix=CHECK3 --ignore-case # RUN: wc -c %t3.out | FileCheck %s --check-prefix=SIZE3 -## The minimum LMA of all sections is 0x1000. +## The minimum LMA of all non-empty sections is 0x1000. ## The content of .data will be written at 0x3000-0x1000 = 0x2000. # CHECK3: 000000 c3c3 c3c3 0000 0000 0000 0000 0000 0000 # CHECK3-NEXT: 000010 0000 0000 0000 0000 0000 0000 0000 0000 @@ -129,3 +129,58 @@ ProgramHeaders: VAddr: 0x3000 Sections: - Section: .data + +## The first section (.text) is empty. Test that we skip its LMA until the first +## non-empty section, otherwise we would leave a large number of leading zeroes. +# RUN: yaml2obj --docnum=4 %s -o %t4 +# RUN: llvm-objcopy -O binary %t4 %t4.out +# RUN: od -A x -t x2 %t4.out | FileCheck %s --check-prefix=SKIPEMPTY + +# SKIPEMPTY: 000000 3232 +# SKIPEMPTY-NEXT: 000002 + +--- !ELF +FileHeader: + Class: ELFCLASS64 + Data: ELFDATA2LSB + Type: ET_EXEC + Machine: EM_X86_64 +Sections: + - Name: .text + Type: SHT_PROGBITS + Flags: [ SHF_ALLOC, SHF_EXECINSTR ] + Address: 0x1000 + AddressAlign: 0x1000 + - Name: gap + Type: Fill + Size: 0x1000 + - Name: .data + Type: SHT_PROGBITS + Flags: [ SHF_ALLOC, SHF_WRITE ] + Content: "3232" + +## The last section (.data) is empty. Test that we stop dumping after the last +## non-empty section, otherwise we would leave a large number of trailing zeroes. +# RUN: yaml2obj --docnum=5 %s -o %t5 +# RUN: llvm-objcopy -O binary %t5 %t5.out +# RUN: od -A x -t x2 %t5.out | FileCheck %s --check-prefix=SKIPEMPTY + +--- !ELF +FileHeader: + Class: ELFCLASS64 + Data: ELFDATA2LSB + Type: ET_EXEC + Machine: EM_X86_64 +Sections: + - Name: .text + Type: SHT_PROGBITS + Flags: [ SHF_ALLOC, SHF_EXECINSTR ] + Address: 0x1000 + AddressAlign: 0x1000 + Content: "3232" + - Name: gap + Type: Fill + Size: 0xffd + - Name: .data + Type: SHT_PROGBITS + Flags: [ SHF_ALLOC, SHF_WRITE ] diff --git a/llvm/tools/llvm-objcopy/ELF/Object.cpp b/llvm/tools/llvm-objcopy/ELF/Object.cpp index 3808e92d0b42..f5ae3be5c516 100644 --- a/llvm/tools/llvm-objcopy/ELF/Object.cpp +++ b/llvm/tools/llvm-objcopy/ELF/Object.cpp @@ -2217,25 +2217,26 @@ Error BinaryWriter::write() { Error BinaryWriter::finalize() { // Compute the section LMA based on its sh_offset and the containing segment's - // p_offset and p_paddr. Also compute the minimum LMA of all sections as - // MinAddr. In the output, the contents between address 0 and MinAddr will be - // skipped. + // p_offset and p_paddr. Also compute the minimum LMA of all non-empty + // sections as MinAddr. In the output, the contents between address 0 and + // MinAddr will be skipped. uint64_t MinAddr = UINT64_MAX; for (SectionBase &Sec : Obj.allocSections()) { if (Sec.ParentSegment != nullptr) Sec.Addr = Sec.Offset - Sec.ParentSegment->Offset + Sec.ParentSegment->PAddr; - MinAddr = std::min(MinAddr, Sec.Addr); + if (Sec.Size > 0) + MinAddr = std::min(MinAddr, Sec.Addr); } // Now that every section has been laid out we just need to compute the total // file size. This might not be the same as the offset returned by // layoutSections, because we want to truncate the last segment to the end of - // its last section, to match GNU objcopy's behaviour. + // its last non-empty section, to match GNU objcopy's behaviour. TotalSize = 0; for (SectionBase &Sec : Obj.allocSections()) { Sec.Offset = Sec.Addr - MinAddr; - if (Sec.Type != SHT_NOBITS) + if (Sec.Type != SHT_NOBITS && Sec.Size > 0) TotalSize = std::max(TotalSize, Sec.Offset + Sec.Size); }