[Object,ELF] Implement PN_XNUM extension for program headers

[aokblast]

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.

[aokblast]

This change nothing but just creating a user branch so we can rebase easily.

[llvmbot]

@llvm/pr-subscribers-llvm-binary-utilities

Author: None (aokblast)

Changes

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.

---

Full diff: https://github.com/llvm/llvm-project/pull/165284.diff

2 Files Affected:

• (modified) llvm/include/llvm/BinaryFormat/ELF.h (+2)
• (modified) llvm/include/llvm/Object/ELF.h (+87-19)

diff --git a/llvm/include/llvm/BinaryFormat/ELF.h b/llvm/include/llvm/BinaryFormat/ELF.h
index 6ee6b666c1735..39e9611c7190e 100644
--- a/llvm/include/llvm/BinaryFormat/ELF.h
+++ b/llvm/include/llvm/BinaryFormat/ELF.h
@@ -1125,6 +1125,8 @@ 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..03d5ee21a71b4 100644
--- a/llvm/include/llvm/Object/ELF.h
+++ b/llvm/include/llvm/Object/ELF.h
@@ -278,9 +278,46 @@ class ELFFile {
   std::vector<Elf_Shdr> FakeSections;
   SmallString<0> FakeSectionStrings;
 
+  // When the number of program headers is >= PN_XNUM, the actual number is
+  // contained in the sh_info field of the section header at index 0.
+  std::optional<uint32_t> RealPhNum;
+  // When the number of section headers is >= SHN_LORESERVE, the actual number
+  // is contained in the sh_size field of the section header at index 0.
+  std::optional<uint64_t> RealShNum;
+  // When the section index of the section name table is >= SHN_LORESERVE, the
+  // actual number is contained in the sh_link field of the section header at
+  // index 0.
+  std::optional<uint32_t> RealShStrNdx;
+
   ELFFile(StringRef Object);
 
+  Error readShdrZero();
+
 public:
+  Expected<uint32_t> getPhNum() const {
+    if (!RealPhNum) {
+      if (Error E = const_cast<ELFFile<ELFT> *>(this)->readShdrZero())
+        return std::move(E);
+    }
+    return *RealPhNum;
+  }
+
+  Expected<uint64_t> getShNum() const {
+    if (!RealShNum) {
+      if (Error E = const_cast<ELFFile<ELFT> *>(this)->readShdrZero())
+        return std::move(E);
+    }
+    return *RealShNum;
+  }
+
+  Expected<uint32_t> getShStrNdx() const {
+    if (!RealShStrNdx) {
+      if (Error E = const_cast<ELFFile<ELFT> *>(this)->readShdrZero())
+        return std::move(E);
+    }
+    return *RealShStrNdx;
+  }
+
   const Elf_Ehdr &getHeader() const {
     return *reinterpret_cast<const Elf_Ehdr *>(base());
   }
@@ -379,22 +416,26 @@ class ELFFile {
 
   /// Iterate over program header table.
   Expected<Elf_Phdr_Range> program_headers() const {
-    if (getHeader().e_phnum && getHeader().e_phentsize != sizeof(Elf_Phdr))
+    uint32_t NumPh;
+    if (Expected<uint32_t> PhNumOrErr = getPhNum())
+      NumPh = *PhNumOrErr;
+    else
+      return PhNumOrErr.takeError();
+    if (NumPh && 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)NumPh * 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(NumPh) +
                          ", 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 + NumPh);
   }
 
   /// Get an iterator over notes in a program header.
@@ -772,19 +813,15 @@ 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");
+  Expected<uint32_t> ShStrNdxOrErr = getShStrNdx();
+  if (!ShStrNdxOrErr)
+    return ShStrNdxOrErr.takeError();
 
-    Index = Sections[0].sh_link;
-  }
+  if (*ShStrNdxOrErr == ELF::SHN_XINDEX && Sections.empty())
+    return createError(
+        "e_shstrndx == SHN_XINDEX, but the section header table is empty");
 
+  uint32_t Index = *ShStrNdxOrErr;
   // There is no section name string table. Return FakeSectionStrings which
   // is non-empty if we have created fake sections.
   if (!Index)
@@ -891,6 +928,35 @@ Expected<uint64_t> ELFFile<ELFT>::getDynSymtabSize() const {
 
 template <class ELFT> ELFFile<ELFT>::ELFFile(StringRef Object) : Buf(Object) {}
 
+template <class ELFT> Error ELFFile<ELFT>::readShdrZero() {
+  const Elf_Ehdr &Header = getHeader();
+
+  if ((Header.e_phnum == ELF::PN_XNUM || Header.e_shnum == 0 ||
+       Header.e_shstrndx == ELF::SHN_XINDEX) &&
+      Header.e_shoff != 0) {
+    // Pretend we have section 0 or sections() would call getShNum and thus
+    // become an infinite recursion.
+    RealShNum = 1;
+    auto SecOrErr = getSection(0);
+    if (!SecOrErr) {
+      RealShNum = std::nullopt;
+      return SecOrErr.takeError();
+    }
+
+    RealPhNum =
+        Header.e_phnum == ELF::PN_XNUM ? (*SecOrErr)->sh_info : Header.e_phnum;
+    RealShNum = Header.e_shnum == 0 ? (*SecOrErr)->sh_size : Header.e_shnum;
+    RealShStrNdx = Header.e_shstrndx == ELF::SHN_XINDEX ? (*SecOrErr)->sh_link
+                                                        : Header.e_shstrndx;
+  } else {
+    RealPhNum = Header.e_phnum;
+    RealShNum = Header.e_shnum;
+    RealShStrNdx = Header.e_shstrndx;
+  }
+
+  return Error::success();
+}
+
 template <class ELFT>
 Expected<ELFFile<ELFT>> ELFFile<ELFT>::create(StringRef Object) {
   if (sizeof(Elf_Ehdr) > Object.size())
@@ -956,9 +1022,11 @@ 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;
-  if (NumSections == 0)
-    NumSections = First->sh_size;
+  uintX_t NumSections = 0;
+  if (Expected<uint64_t> ShNumOrErr = getShNum())
+    NumSections = *ShNumOrErr;
+  else
+    return ShNumOrErr.takeError();
 
   if (NumSections > UINT64_MAX / sizeof(Elf_Shdr))
     return createError("invalid number of sections specified in the NULL "

[jh7370]

For the record, if something like this happens again and your original PR has been approved, you don't need to (currently) wait for re-approval of a new, identical PR.

Please however add a link to the original PR in your description, for traceability purposes.