Open ELF core dumps with more than 64K sections

Summary:
Problem:

There are three filelds in the ELF header - e_phnum, e_shnum, and e_shstrndx -
that could be bigger than 64K and therefore do not fit in 16 bits reserved for
them in the header. If this happens, pretty often there is a special section at
index 0 which contains their real values for these fields in the section header
in the fields sh_info, sh_size, and sh_link respectively.

Fix:

- Rename original fields in the header declaration. We want to have them around
just in case.

- Reintroduce these fields as 32-bit members at the end of the header. By default
they are initialized from the header in Parse() method.

- In Parse(), detect the situation when the header might have been extended into
section info #0 and try to read it from the same data source.

- ObjectFileELF::GetModuleSpecifications accesses some of these fields but the
original parse uses too small data source. Re-parse the header if necessary
using bigger data source.

- ProcessElfCore::CreateInstance uses header with potentially sentinel values,
but it does not access these fields, so a comment here is enough.

Reviewers: labath

Reviewed By: labath

Subscribers: davidb, lldb-commits, mgorny

Differential Revision: https://reviews.llvm.org/D29095
Author: Eugene Birukov <eugenebi@hotmail.com>

llvm-svn: 293714

lldb/source/Plugins/ObjectFile/ELF/ELFHeader.cpp

@@ -81,6 +81,39 @@ ByteOrder ELFHeader::GetByteOrder() const {
   return eByteOrderInvalid;
 }
 
+bool ELFHeader::HasHeaderExtension() const {
+  bool result = false;
+
+  // Check if any of these values looks like sentinel.
+  result |= e_phnum_hdr == 0xFFFF; // PN_XNUM
+  result |= e_shnum_hdr == SHN_UNDEF;
+  result |= e_shstrndx_hdr == SHN_XINDEX;
+
+  // If header extension is present, the section offset cannot be null.
+  result &= e_shoff != 0;
+
+  // Done.
+  return result;
+}
+
+void ELFHeader::ParseHeaderExtension(lldb_private::DataExtractor &data) {
+  // Extract section #0 header.
+  ELFSectionHeader section_zero;
+  lldb::offset_t offset = 0;
+  lldb_private::DataExtractor sh_data(data, e_shoff, e_shentsize);
+  bool ok = section_zero.Parse(sh_data, &offset);
+
+  // If we succeeded, fix the header.
+  if (ok) {
+    if (e_phnum_hdr == 0xFFFF) // PN_XNUM
+      e_phnum = section_zero.sh_info;
+    if (e_shnum_hdr == SHN_UNDEF)
+      e_shnum = section_zero.sh_size;
+    if (e_shstrndx_hdr == SHN_XINDEX)
+      e_shstrndx = section_zero.sh_link;
+  }
+}
+
 bool ELFHeader::Parse(lldb_private::DataExtractor &data,
                       lldb::offset_t *offset) {
   // Read e_ident.  This provides byte order and address size info.
@@ -112,6 +145,16 @@ bool ELFHeader::Parse(lldb_private::DataExtractor &data,
   if (data.GetU16(offset, &e_ehsize, 6) == NULL)
     return false;
 
+  // Initialize e_phnum, e_shnum, and e_shstrndx with the values
+  // read from the header.
+  e_phnum = e_phnum_hdr;
+  e_shnum = e_shnum_hdr;
+  e_shstrndx = e_shstrndx_hdr;
+
+  // See if we have extended header in section #0.
+  if (HasHeaderExtension())
+    ParseHeaderExtension(data);
+
   return true;
 }
 

lldb/source/Plugins/ObjectFile/ELF/ELFHeader.h

@@ -24,6 +24,7 @@
 #include "llvm/Support/ELF.h"
 
 #include "lldb/lldb-enumerations.h"
+#include "lldb/lldb-types.h"
 
 namespace lldb_private {
 class DataExtractor;
@@ -65,10 +66,17 @@ struct ELFHeader {
   elf_half e_machine;   ///< Target architecture.
   elf_half e_ehsize;    ///< Byte size of the ELF header.
   elf_half e_phentsize; ///< Size of a program header table entry.
-  elf_half e_phnum;     ///< Number of program header entries.
+  elf_half e_phnum_hdr; ///< Number of program header entries.
   elf_half e_shentsize; ///< Size of a section header table entry.
-  elf_half e_shnum;     ///< Number of section header entries.
-  elf_half e_shstrndx;  ///< String table section index.
+  elf_half e_shnum_hdr; ///< Number of section header entries.
+  elf_half e_shstrndx_hdr; ///< String table section index.
+
+  // In some cases these numbers do not fit in 16 bits and they are
+  // stored outside of the header in section #0. Here are the actual
+  // values.
+  elf_word e_phnum;     ///< Number of program header entries.
+  elf_word e_shnum;     ///< Number of section header entries.
+  elf_word e_shstrndx;  ///< String table section index.
 
   ELFHeader();
 
@@ -101,6 +109,14 @@ struct ELFHeader {
   /// The jump slot relocation type of this ELF.
   unsigned GetRelocationJumpSlotType() const;
 
+  //--------------------------------------------------------------------------
+  /// Check if there should be header extension in section header #0
+  ///
+  /// @return
+  ///    True if parsing the ELFHeader requires reading header extension
+  ///    and false otherwise.
+  bool HasHeaderExtension() const;
+
   //--------------------------------------------------------------------------
   /// Parse an ELFHeader entry starting at position \p offset and
   /// update the data extractor with the address size and byte order
@@ -137,6 +153,16 @@ struct ELFHeader {
   ///    The number of bytes forming an address in the ELF file (either 4 or
   ///    8), else zero if the address size could not be determined.
   static unsigned AddressSizeInBytes(const uint8_t *magic);
+
+private:
+
+  //--------------------------------------------------------------------------
+  /// Parse an ELFHeader header extension entry.  This method is called
+  /// by Parse().
+  ///
+  /// @param[in] data
+  ///    The DataExtractor to read from.
+  void ParseHeaderExtension(lldb_private::DataExtractor &data);
 };
 
 //------------------------------------------------------------------------------

lldb/source/Plugins/ObjectFile/ELF/ObjectFileELF.cpp

@@ -610,7 +610,8 @@ size_t ObjectFileELF::GetModuleSpecifications(
     DataExtractor data;
     data.SetData(data_sp);
     elf::ELFHeader header;
-    if (header.Parse(data, &data_offset)) {
+    lldb::offset_t header_offset = data_offset;
+    if (header.Parse(data, &header_offset)) {
       if (data_sp) {
         ModuleSpec spec(file);
 
@@ -645,10 +646,24 @@ size_t ObjectFileELF::GetModuleSpecifications(
                           __FUNCTION__, file.GetPath().c_str());
           }
 
+          // In case there is header extension in the section #0, the header
+          // we parsed above could have sentinel values for e_phnum, e_shnum,
+          // and e_shstrndx.  In this case we need to reparse the header
+          // with a bigger data source to get the actual values.
+          size_t section_header_end = header.e_shoff + header.e_shentsize;
+          if (header.HasHeaderExtension() &&
+            section_header_end > data_sp->GetByteSize()) {
+            data_sp = file.MemoryMapFileContentsIfLocal (file_offset,
+                                                         section_header_end);
+            data.SetData(data_sp);
+            lldb::offset_t header_offset = data_offset;
+            header.Parse(data, &header_offset);
+          }
+
           // Try to get the UUID from the section list. Usually that's at the
           // end, so
           // map the file in if we don't have it already.
-          size_t section_header_end =
+          section_header_end =
               header.e_shoff + header.e_shnum * header.e_shentsize;
           if (section_header_end > data_sp->GetByteSize()) {
             data_sp = file.MemoryMapFileContentsIfLocal(file_offset,
@@ -3067,10 +3082,10 @@ void ObjectFileELF::DumpELFHeader(Stream *s, const ELFHeader &header) {
   s->Printf("e_flags     = 0x%8.8x\n", header.e_flags);
   s->Printf("e_ehsize    = 0x%4.4x\n", header.e_ehsize);
   s->Printf("e_phentsize = 0x%4.4x\n", header.e_phentsize);
-  s->Printf("e_phnum     = 0x%4.4x\n", header.e_phnum);
+  s->Printf("e_phnum     = 0x%8.8x\n", header.e_phnum);
   s->Printf("e_shentsize = 0x%4.4x\n", header.e_shentsize);
-  s->Printf("e_shnum     = 0x%4.4x\n", header.e_shnum);
-  s->Printf("e_shstrndx  = 0x%4.4x\n", header.e_shstrndx);
+  s->Printf("e_shnum     = 0x%8.8x\n", header.e_shnum);
+  s->Printf("e_shstrndx  = 0x%8.8x\n", header.e_shstrndx);
 }
 
 //----------------------------------------------------------------------

lldb/source/Plugins/Process/elf-core/ProcessElfCore.cpp

@@ -56,6 +56,8 @@ lldb::ProcessSP ProcessElfCore::CreateInstance(lldb::TargetSP target_sp,
   lldb::ProcessSP process_sp;
   if (crash_file) {
     // Read enough data for a ELF32 header or ELF64 header
+    // Note: Here we care about e_type field only, so it is safe
+    // to ignore possible presence of the header extension.
     const size_t header_size = sizeof(llvm::ELF::Elf64_Ehdr);
 
     lldb::DataBufferSP data_sp(crash_file->ReadFileContents(0, header_size));

lldb/unittests/CMakeLists.txt

@@ -53,6 +53,7 @@ add_subdirectory(Expression)
 add_subdirectory(Host)
 add_subdirectory(Interpreter)
 add_subdirectory(Language)
+add_subdirectory(ObjectFile)
 add_subdirectory(Platform)
 add_subdirectory(Process)
 add_subdirectory(ScriptInterpreter)

lldb/unittests/ObjectFile/CMakeLists.txt

@@ -0,0 +1 @@
+add_subdirectory(ELF)

lldb/unittests/ObjectFile/ELF/CMakeLists.txt

@@ -0,0 +1,3 @@
+add_lldb_unittest(ObjectFileELFTests
+  TestELFHeader.cpp
+  )

lldb/unittests/ObjectFile/ELF/TestELFHeader.cpp

@@ -0,0 +1,62 @@
+//===-- TestELFHeader.cpp ---------------------------------------*- C++ -*-===//
+//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "Plugins/ObjectFile/ELF/ELFHeader.h"
+#include "lldb/Core/DataExtractor.h"
+#include "gtest/gtest.h"
+
+using namespace lldb;
+using namespace lldb_private;
+
+
+TEST(ELFHeader, ParseHeaderExtension) {
+  uint8_t data[] = {
+      // e_ident
+      0x7f, 0x45, 0x4c, 0x46, 0x02, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00,
+
+      // e_type, e_machine, e_version, e_entry
+      0x03, 0x00, 0x3e, 0x00, 0x01, 0x00, 0x00, 0x00, 0x90, 0x48, 0x40, 0x00,
+      0x00, 0x00, 0x00, 0x00,
+
+      // e_phoff, e_shoff
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00,
+
+      // e_flags, e_ehsize, e_phentsize, e_phnum, e_shentsize, e_shnum,
+      // e_shstrndx
+      0x00, 0x00, 0x00, 0x00, 0x40, 0x00, 0x38, 0x00, 0xff, 0xff, 0x40, 0x00,
+      0x00, 0x00, 0xff, 0xff,
+
+      // sh_name, sh_type, sh_flags
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00,
+
+      // sh_addr, sh_offset
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00,
+
+      // sh_size, sh_link, sh_info
+      0x23, 0x45, 0x67, 0x00, 0x00, 0x00, 0x00, 0x00, 0x34, 0x56, 0x78, 0x00,
+      0x12, 0x34, 0x56, 0x00,
+
+      // sh_addralign, sh_entsize
+      0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+      0x00, 0x00, 0x00, 0x00,
+  };
+
+  DataExtractor extractor(data, sizeof data, eByteOrderLittle, 8);
+  elf::ELFHeader header;
+  offset_t offset = 0;
+  ASSERT_TRUE(header.Parse(extractor, &offset));
+  EXPECT_EQ(0x563412u, header.e_phnum);
+  EXPECT_EQ(0x785634u, header.e_shstrndx);
+  EXPECT_EQ(0x674523u, header.e_shnum);
+}