[llvm] [llvm-objdump][ELF] Enhancing llvm-objdump stability and error handling(#86612) (PR #125679)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

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

Author: Cabbaken (cabbaken)

<details>
<summary>Changes</summary>

This change introduces a check for the strtab offset to prevent llvm-objdump from crashing when processing malformed ELF files.
It provide a minimal reproduce test for https://github.com/llvm/llvm-project/issues/86612#issuecomment-2035694455.
Additionally, it modifies how llvm-objdump handles and outputs malformed ELF files with invalid string offsets.(More info: https://discourse.llvm.org/t/should-llvm-objdump-objdump-display-actual-corrupted-values-in-malformed-elf-files/84391)

---
Full diff: https://github.com/llvm/llvm-project/pull/125679.diff


2 Files Affected:

- (modified) llvm/test/tools/llvm-objdump/ELF/dynamic-section.test (+34) 
- (modified) llvm/tools/llvm-objdump/ELFDump.cpp (+23) 


``````````diff
diff --git a/llvm/test/tools/llvm-objdump/ELF/dynamic-section.test b/llvm/test/tools/llvm-objdump/ELF/dynamic-section.test
index 5205c5a3876d5f..33ca7e5b40c262 100644
--- a/llvm/test/tools/llvm-objdump/ELF/dynamic-section.test
+++ b/llvm/test/tools/llvm-objdump/ELF/dynamic-section.test
@@ -438,6 +438,9 @@ ProgramHeaders:
 # RUN: yaml2obj --docnum=4 %s -o %t4
 # RUN: llvm-objdump -p %t4 | FileCheck %s --strict-whitespace --check-prefix=INDENT
 
+# RUN: yaml2obj --docnum=5 %s -o %t5
+# RUN: llvm-objdump -p %t5 | FileCheck %s --strict-whitespace --check-prefix=INDENT
+
 # INDENT: {{^}}Dynamic Section:
 # INDENT: {{^}}  NEEDED 0x
 
@@ -470,3 +473,34 @@ Sections:
        Value: 0x1
      - Tag:   DT_NULL
        Value: 0x0
+
+--- !ELF
+FileHeader:
+  Class:   ELFCLASS64
+  Data:    ELFDATA2LSB
+  Type:    ET_EXEC
+  Machine: EM_X86_64
+Sections:
+  - Name:    .dynstr
+    Type:    SHT_STRTAB
+    Address: 0x1000
+    Size:    0x10
+    Content: "004400550066007700"
+  - Name: .dynamic
+    Type: SHT_DYNAMIC
+    Entries:
+     - Tag:   DT_NEEDED
+       Value: 0x1245657656
+     - Tag:   DT_STRTAB
+       Value: 0x1000
+     - Tag:   DT_NULL
+       Value: 0x0
+ProgramHeaders:
+  - Type:     PT_LOAD
+    VAddr:    0x1000
+    FirstSec: .dynstr
+    LastSec:  .dynamic
+  - Type:     PT_DYNAMIC
+    VAddr:    0x101D
+    FirstSec: .dynamic
+    LastSec:  .dynamic
\ No newline at end of file
diff --git a/llvm/tools/llvm-objdump/ELFDump.cpp b/llvm/tools/llvm-objdump/ELFDump.cpp
index e9e5b059f1786e..949bf1c6faacb8 100644
--- a/llvm/tools/llvm-objdump/ELFDump.cpp
+++ b/llvm/tools/llvm-objdump/ELFDump.cpp
@@ -14,8 +14,11 @@
 #include "ELFDump.h"
 
 #include "llvm-objdump.h"
+#include "llvm/BinaryFormat/ELF.h"
 #include "llvm/Demangle/Demangle.h"
+#include "llvm/Object/ELF.h"
 #include "llvm/Object/ELFObjectFile.h"
+#include "llvm/Object/ELFTypes.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/raw_ostream.h"
 
@@ -221,6 +224,20 @@ template <class ELFT> void ELFDumper<ELFT>::printDynamicSection() {
   std::string TagFmt = "  %-" + std::to_string(MaxLen) + "s ";
 
   outs() << "\nDynamic Section:\n";
+  auto StringTableSize = (typename ELFT::Xword)0;
+  for (const auto &Sec : cantFail(Elf.sections())) {
+    if (Sec.sh_type == ELF::SHT_STRTAB)
+      StringTableSize =
+          StringTableSize < Sec.sh_size ? Sec.sh_size : StringTableSize;
+  }
+  for (const typename ELFT::Dyn &Dyn : DynamicEntries) {
+    if (Dyn.d_tag == ELF::DT_STRSZ) {
+      StringTableSize =
+          StringTableSize < Dyn.getVal() ? Dyn.getVal() : StringTableSize;
+      break;
+    }
+  }
+
   for (const typename ELFT::Dyn &Dyn : DynamicEntries) {
     if (Dyn.d_tag == ELF::DT_NULL)
       continue;
@@ -235,6 +252,12 @@ template <class ELFT> void ELFDumper<ELFT>::printDynamicSection() {
       Expected<StringRef> StrTabOrErr = getDynamicStrTab(Elf);
       if (StrTabOrErr) {
         const char *Data = StrTabOrErr->data();
+        if (Dyn.getVal() > StringTableSize) {
+          reportWarning("Invalid string table offset", Obj.getFileName());
+          outs() << format(TagFmt.c_str(), Str.c_str())
+                 << format(Fmt, (uint64_t)Dyn.getVal());
+          continue;
+        }
         outs() << format(TagFmt.c_str(), Str.c_str()) << Data + Dyn.getVal()
                << "\n";
         continue;

``````````

</details>


https://github.com/llvm/llvm-project/pull/125679