[llvm] [Object][ELF] Support extended header for Object Parser in ELF (PR #162288)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Oct 9 05:30:06 PDT 2025
https://github.com/aokblast updated https://github.com/llvm/llvm-project/pull/162288
>From d2740bcf5c84d4f5d71e4058b25169034ec8f5e5 Mon Sep 17 00:00:00 2001
From: ShengYi Hung <aokblast at FreeBSD.org>
Date: Tue, 7 Oct 2025 21:46:52 +0800
Subject: [PATCH] [Object, ELF] Implement PN_XNUM extension for program headers
In ELF file, there is a possible extended header for those phnum, shnum,
and shstrndx larger than the maximum of 16 bits. This extended header
use section 0 to record these fields in 32 bits. We implment this
feature so that programs rely on ELFFile::program_headers() can get the
correct number of segments. Also, the consumers don't have to check the
section 0 themselve, insteead, they can use the getPhNum() as an
alternative.
---
llvm/include/llvm/BinaryFormat/ELF.h | 2 +
llvm/include/llvm/Object/ELF.h | 60 +++++++++++++++++++---------
llvm/include/llvm/Object/ELFTypes.h | 5 +++
3 files changed, 48 insertions(+), 19 deletions(-)
diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index e619b186dfe3d..136f8cfbde818 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -1123,6 +1123,8 @@ struct Elf64_Shdr {
Elf64_Xword sh_entsize;
};
+enum { PN_XNUM = 0xffff };
+
// Special section indices.
enum {
SHN_UNDEF = 0, // Undefined, missing, irrelevant, or meaningless
diff --git a/llvm/include/llvm/Object/ELF.h b/llvm/include/llvm/Object/ELF.h
index 59f63eb6b5bb6..3b96c0e2b9d1f 100644
--- a/llvm/include/llvm/Object/ELF.h
+++ b/llvm/include/llvm/Object/ELF.h
@@ -278,9 +278,16 @@ class ELFFile {
std::vector<Elf_Shdr> FakeSections;
SmallString<0> FakeSectionStrings;
+ Elf_Word RealPhNum;
+ Elf_Word RealShNum;
+ Elf_Word RealShStrNdx;
+
ELFFile(StringRef Object);
public:
+ Elf_Word getPhNum() const { return RealPhNum; }
+ Elf_Word getShNum() const { return RealShNum; }
+ Elf_Word getShStrNdx() const { return RealShStrNdx; }
const Elf_Ehdr &getHeader() const {
return *reinterpret_cast<const Elf_Ehdr *>(base());
}
@@ -379,22 +386,21 @@ class ELFFile {
/// Iterate over program header table.
Expected<Elf_Phdr_Range> program_headers() const {
- if (getHeader().e_phnum && getHeader().e_phentsize != sizeof(Elf_Phdr))
+ if (RealPhNum && getHeader().e_phentsize != sizeof(Elf_Phdr))
return createError("invalid e_phentsize: " +
Twine(getHeader().e_phentsize));
- uint64_t HeadersSize =
- (uint64_t)getHeader().e_phnum * getHeader().e_phentsize;
+ uint64_t HeadersSize = (uint64_t)RealPhNum * getHeader().e_phentsize;
uint64_t PhOff = getHeader().e_phoff;
if (PhOff + HeadersSize < PhOff || PhOff + HeadersSize > getBufSize())
return createError("program headers are longer than binary of size " +
Twine(getBufSize()) + ": e_phoff = 0x" +
Twine::utohexstr(getHeader().e_phoff) +
- ", e_phnum = " + Twine(getHeader().e_phnum) +
+ ", e_phnum = " + Twine(RealPhNum) +
", e_phentsize = " + Twine(getHeader().e_phentsize));
auto *Begin = reinterpret_cast<const Elf_Phdr *>(base() + PhOff);
- return ArrayRef(Begin, Begin + getHeader().e_phnum);
+ return ArrayRef(Begin, Begin + RealPhNum);
}
/// Get an iterator over notes in a program header.
@@ -772,18 +778,10 @@ template <class ELFT>
Expected<StringRef>
ELFFile<ELFT>::getSectionStringTable(Elf_Shdr_Range Sections,
WarningHandler WarnHandler) const {
- uint32_t Index = getHeader().e_shstrndx;
- if (Index == ELF::SHN_XINDEX) {
- // If the section name string table section index is greater than
- // or equal to SHN_LORESERVE, then the actual index of the section name
- // string table section is contained in the sh_link field of the section
- // header at index 0.
- if (Sections.empty())
- return createError(
- "e_shstrndx == SHN_XINDEX, but the section header table is empty");
-
- Index = Sections[0].sh_link;
- }
+ uint32_t Index = RealShStrNdx;
+ if (Index == ELF::SHN_XINDEX)
+ return createError(
+ "e_shstrndx == SHN_XINDEX, but the section header table is empty");
// There is no section name string table. Return FakeSectionStrings which
// is non-empty if we have created fake sections.
@@ -889,7 +887,31 @@ Expected<uint64_t> ELFFile<ELFT>::getDynSymtabSize() const {
return 0;
}
-template <class ELFT> ELFFile<ELFT>::ELFFile(StringRef Object) : Buf(Object) {}
+template <class ELFT> ELFFile<ELFT>::ELFFile(StringRef Object) : Buf(Object) {
+ const Elf_Ehdr &Header = getHeader();
+ RealPhNum = Header.e_phnum;
+ RealShNum = Header.e_shnum;
+ RealShStrNdx = Header.e_shstrndx;
+ if (!Header.hasPhdrNumExtension())
+ return;
+
+ // An ELF binary may report `hasExtendedHeader` as true but not actually
+ // include an extended header. For example, a core dump can contain 65,535
+ // segments but no sections at all. We defer reporting an error until section
+ // 0 is accessed. Consumers should handle and emit the error themselves when
+ // they attempt to access it.
+ auto SecOrErr = getSection(0);
+ if (!SecOrErr) {
+ consumeError(SecOrErr.takeError());
+ return;
+ }
+ if (RealPhNum == 0xFFFF)
+ RealPhNum = (*SecOrErr)->sh_info;
+ if (RealShNum == ELF::SHN_UNDEF)
+ RealShNum = (*SecOrErr)->sh_size;
+ if (RealShStrNdx == ELF::SHN_XINDEX)
+ RealShStrNdx = (*SecOrErr)->sh_link;
+}
template <class ELFT>
Expected<ELFFile<ELFT>> ELFFile<ELFT>::create(StringRef Object) {
@@ -956,7 +978,7 @@ Expected<typename ELFT::ShdrRange> ELFFile<ELFT>::sections() const {
const Elf_Shdr *First =
reinterpret_cast<const Elf_Shdr *>(base() + SectionTableOffset);
- uintX_t NumSections = getHeader().e_shnum;
+ uintX_t NumSections = RealShNum;
if (NumSections == 0)
NumSections = First->sh_size;
diff --git a/llvm/include/llvm/Object/ELFTypes.h b/llvm/include/llvm/Object/ELFTypes.h
index 5a26e2fc31458..b791f7486fe97 100644
--- a/llvm/include/llvm/Object/ELFTypes.h
+++ b/llvm/include/llvm/Object/ELFTypes.h
@@ -529,6 +529,11 @@ struct Elf_Ehdr_Impl {
unsigned char getFileClass() const { return e_ident[ELF::EI_CLASS]; }
unsigned char getDataEncoding() const { return e_ident[ELF::EI_DATA]; }
+ bool hasPhdrNumExtension() const {
+ return (e_phnum == ELF::PN_XNUM || e_shnum == ELF::SHN_UNDEF ||
+ e_shstrndx == ELF::SHN_XINDEX) &&
+ e_shoff != 0;
+ }
};
template <endianness Endianness>
More information about the llvm-commits
mailing list